{ "schema": "ddc-token-boundary-ledger/1", "runner_id": "THINK_B_2EP_SIX_ARMS_RUNNER_V3", "bindings": { "config_sha256": "5c5965a584fe72804b4752efb2e27b010079eb50e0357eb288923d913e458fa4", "runner_code_sha256": "fd6d1c6403810acc4460e2ce0fb5f4418881387b11f4bd21f7cd21067faa3a0a", "config_schema_sha256": "d6d13eeee42bf04cf34fc68b2fa7a61b316c4543b77d7d779815b8eddf10c099", "python_binary_sha256": "5700a6a7804feb44da6c963ebd1323982478b7ca57478e4e81981c47818453bd", "environment_lock_sha256": "627d4fe088b8f64841b0520ae5bd9dc5c81e9dcd5969b4bd45c9a9910b2f3c01", "base_composite_sha256": "526963d72561cb6244f60f751312673d2671111d214636ae571de0d62c762760", "base_lock_sha256": "6791648e4030008388f2e9241b23771cb07eb0416fbd7bc3c6777c7c36bda3be", "frozen_rows_sha256": "8221ff30de8fa345441e6002c111c948a3fdd20413e5c09e3a8f76cf26b12ef1", "ordered_ids_sha256": "dde87a60437027a3e19566382b4ac25381f2888e45507bef0ddc3d6d284c412b", "update_plan_sha256": "24e1f6fecc9e9e5b5c371c7041cbe0bf79dec48741caf8a60d50310984e59ef1", "data_receipt_sha256": "e66346fb413557929ab53648bc656fb3102557cf3460abb49c7b1c6e7281420d", "decontamination_receipt_sha256": "66c360871b06208ed20e473e57ad0f09c79e4dac1b3124a9461a5b729b487153", "render_receipt_sha256": "e66346fb413557929ab53648bc656fb3102557cf3460abb49c7b1c6e7281420d", "token_bake_sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b", "continuation_sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b" }, "completed_optimizer_updates": 987, "next_update_index": 987, "next_ordered_position": 11750, "cumulative_planned_active_tokens": 64632872, "cumulative_realized_active_tokens": 64632872, "optimizer_step_count": 987, "scheduler_step_count": 987, "token_bake": { "enabled": false, "positive_lr_active_tokens": null, "frozen": null, "freeze_digest": null }, "updates": [ { "update_id": 0, "row_count": 8, "row_ids_sha256": "d5763a62eaf6a704a14d1097ffd0bc4381e822ae1c8bce09373927779f44deb6", "input_ids_vector_sha256": "846d36a8baba452b04f4e44264a228962099c25b9b2eaab35b4e7aadaa23932a", "labels_vector_sha256": "382131cf846debb67db8b00737b0ddf6031455ea7b7c3963eacd099db73630a9", "planned_active_tokens": 68937, "realized_active_tokens": 68937, "cumulative_start": 0, "cumulative_end": 68937, "loss_sum": 60675.1103515625, "token_normalized_loss": 0.8801530433810943, "grad_norm_before_clip": 0.5549384355545044, "learning_rates_at_step": { "lora": 1.7776559500687473e-06, "row_tokens": 1.7776559500687473e-06 }, "learning_rates_after_step": { "lora": 3.48148465228733e-06, "row_tokens": 3.48148465228733e-06 } }, { "update_id": 1, "row_count": 8, "row_ids_sha256": "e0acaa8beab24825738a93251d7280c8abcc80075ff06b959034be3158eaaf9f", "input_ids_vector_sha256": "70bd5d21582479816d6a6be17068c3f0ceba986fdd33623916144bead56fd3be", "labels_vector_sha256": "0811b38936728889540c8cefe1b07dc5b20ce785b9fecfdb3d45bf91147ac108", "planned_active_tokens": 66074, "realized_active_tokens": 66074, "cumulative_start": 68937, "cumulative_end": 135011, "loss_sum": 58900.9013671875, "token_normalized_loss": 0.8914384079545282, "grad_norm_before_clip": 0.5734447240829468, "learning_rates_at_step": { "lora": 3.48148465228733e-06, "row_tokens": 3.48148465228733e-06 }, "learning_rates_after_step": { "lora": 5.184462394261743e-06, "row_tokens": 5.184462394261743e-06 } }, { "update_id": 2, "row_count": 9, "row_ids_sha256": "2b93307d9d714ad7fb910b4b525f3bebbf078fd2d22fbb9bfa2d9c2272b47363", "input_ids_vector_sha256": "96ae8ee497eff6b47e53c7de791ada14b8dbc1f70c796b56b226ab1c20e60bd6", "labels_vector_sha256": "19d998155dda618714e4e8fdc757685ed2f14f45d1d9ee8a15dce29e24110bfd", "planned_active_tokens": 66041, "realized_active_tokens": 66041, "cumulative_start": 135011, "cumulative_end": 201052, "loss_sum": 58834.69006347656, "token_normalized_loss": 0.8908812716869303, "grad_norm_before_clip": 0.5673310160636902, "learning_rates_at_step": { "lora": 5.184462394261743e-06, "row_tokens": 5.184462394261743e-06 }, "learning_rates_after_step": { "lora": 6.819982196880226e-06, "row_tokens": 6.819982196880226e-06 } }, { "update_id": 3, "row_count": 9, "row_ids_sha256": "a22f5901e649af7b1b10896d050facd879d312247981af1606114484dc8df468", "input_ids_vector_sha256": "1b3d63c6dc715daf00c0274538c2d77a8ebc104a8e9b811cecbea0d783f740dc", "labels_vector_sha256": "87a62b5fb842ecb5b616bed4952335c6e185deeb759a5616c363d9ef3b611718", "planned_active_tokens": 63425, "realized_active_tokens": 63425, "cumulative_start": 201052, "cumulative_end": 264477, "loss_sum": 51212.281982421875, "token_normalized_loss": 0.807446306384263, "grad_norm_before_clip": 0.6600819826126099, "learning_rates_at_step": { "lora": 6.819982196880226e-06, "row_tokens": 6.819982196880226e-06 }, "learning_rates_after_step": { "lora": 8.590572598254965e-06, "row_tokens": 8.590572598254965e-06 } }, { "update_id": 4, "row_count": 8, "row_ids_sha256": "b404921d613b8cb9e12a84ea0908b34a0d3832ea25bd97c1822963fc16fd31e8", "input_ids_vector_sha256": "f68cf52b841fc710158deda9cd13f56ab47d1327ff9fb69abde1321899484c3c", "labels_vector_sha256": "cf191dcb243a7037db6fedd7708e3b377afd9bc67edd05554e2c038d515983d4", "planned_active_tokens": 68663, "realized_active_tokens": 68663, "cumulative_start": 264477, "cumulative_end": 333140, "loss_sum": 51592.89501953125, "token_normalized_loss": 0.7513929630154705, "grad_norm_before_clip": 0.6244915723800659, "learning_rates_at_step": { "lora": 8.590572598254965e-06, "row_tokens": 8.590572598254965e-06 }, "learning_rates_after_step": { "lora": 1.0230011975331437e-05, "row_tokens": 1.0230011975331437e-05 } }, { "update_id": 5, "row_count": 9, "row_ids_sha256": "bd98b09339ab342c82bb95d7c3c5932e851ee75addf7b4a11a38062beaef61ea", "input_ids_vector_sha256": "9a881785bbef8f2284c33c68da7f57ddce99b6f008c52fca9501a5f2948ad2f5", "labels_vector_sha256": "94d91944e13e12e95ddcca21b28fbbb4f63ebb2360a17010238b0c4ff203148a", "planned_active_tokens": 63577, "realized_active_tokens": 63577, "cumulative_start": 333140, "cumulative_end": 396717, "loss_sum": 51936.846435546875, "token_normalized_loss": 0.8169125066540868, "grad_norm_before_clip": 0.5914584398269653, "learning_rates_at_step": { "lora": 1.0230011975331437e-05, "row_tokens": 1.0230011975331437e-05 }, "learning_rates_after_step": { "lora": 1.195096302912966e-05, "row_tokens": 1.195096302912966e-05 } }, { "update_id": 6, "row_count": 11, "row_ids_sha256": "32da753c48ca2be31ef7141417978ed620465b3c4d77f70d2eb60df352100af6", "input_ids_vector_sha256": "73047b774580e63f395e2d41a9d36c7e8edc9e5340579aa3a0df8d314efce70d", "labels_vector_sha256": "97b856875b5fdd6572f14cc407289bc013c31473662eb745b9089521b58ffc13", "planned_active_tokens": 66738, "realized_active_tokens": 66738, "cumulative_start": 396717, "cumulative_end": 463455, "loss_sum": 49541.56311035156, "token_normalized_loss": 0.7423291544600013, "grad_norm_before_clip": 0.6492569446563721, "learning_rates_at_step": { "lora": 1.195096302912966e-05, "row_tokens": 1.195096302912966e-05 }, "learning_rates_after_step": { "lora": 1.3707112893027593e-05, "row_tokens": 1.3707112893027593e-05 } }, { "update_id": 7, "row_count": 9, "row_ids_sha256": "4b8baa413c43ced9cc6fb7240e50dfaa6cafc3d182d0f34908a062ecf2174562", "input_ids_vector_sha256": "0420cfb1318fd714815901e62b7ad3ba2471cd0f73a96789a50bdcad2cd4874c", "labels_vector_sha256": "9ceee2b2701223e70908cb449bdda5be4265ff95fc8ce07d0308eff25c53636f", "planned_active_tokens": 68103, "realized_active_tokens": 68103, "cumulative_start": 463455, "cumulative_end": 531558, "loss_sum": 52130.83752441406, "token_normalized_loss": 0.7654705009238075, "grad_norm_before_clip": 0.401103138923645, "learning_rates_at_step": { "lora": 1.3707112893027593e-05, "row_tokens": 1.3707112893027593e-05 }, "learning_rates_after_step": { "lora": 1.5317748555172653e-05, "row_tokens": 1.5317748555172653e-05 } }, { "update_id": 8, "row_count": 9, "row_ids_sha256": "0f9fdda3fbd85896f8423c04a178f1c20d32f806aeb33da2314108a4e5686ddf", "input_ids_vector_sha256": "b1d78a757576b1d10a0b6e782cdc966267f6759ade53959f76bde85dd1591e73", "labels_vector_sha256": "80b35539ea809e7c2f93f6a9455b47b19a704c1bef7e08e91afa7408008cb83c", "planned_active_tokens": 62460, "realized_active_tokens": 62460, "cumulative_start": 531558, "cumulative_end": 594018, "loss_sum": 44707.494873046875, "token_normalized_loss": 0.7157780158989253, "grad_norm_before_clip": 0.31166955828666687, "learning_rates_at_step": { "lora": 1.5317748555172653e-05, "row_tokens": 1.5317748555172653e-05 }, "learning_rates_after_step": { "lora": 1.7074027352440916e-05, "row_tokens": 1.7074027352440916e-05 } }, { "update_id": 9, "row_count": 9, "row_ids_sha256": "7eb2305c32ff5a3beabb05be215543fc92c73daad7e0dbedae790c570561c98b", "input_ids_vector_sha256": "0d5cb32104549d0264cfc01e8b0a72fd4bd4600d7dbfe674ec60797eb207646b", "labels_vector_sha256": "63c12343cf75c4f9073ee3d5532587ed49fbdbb329caf23e5a3cd112d6302e4e", "planned_active_tokens": 68108, "realized_active_tokens": 68108, "cumulative_start": 594018, "cumulative_end": 662126, "loss_sum": 53851.1669921875, "token_normalized_loss": 0.7906731513506122, "grad_norm_before_clip": 0.4065991938114166, "learning_rates_at_step": { "lora": 1.7074027352440916e-05, "row_tokens": 1.7074027352440916e-05 }, "learning_rates_after_step": { "lora": 1.8663466368503953e-05, "row_tokens": 1.8663466368503953e-05 } }, { "update_id": 10, "row_count": 7, "row_ids_sha256": "79d8c01e4966aba58967498a5aa209d0986894b01dc504215b75efb03780c0b6", "input_ids_vector_sha256": "770c305471c43893a87f37a4ab873fb64f010b70734ddc2d10666ad8732f9290", "labels_vector_sha256": "cf73db436c1f0af5f96c1c438834d527bc339f17b21c525030d74f355025c98e", "planned_active_tokens": 61638, "realized_active_tokens": 61638, "cumulative_start": 662126, "cumulative_end": 723764, "loss_sum": 43472.7958984375, "token_normalized_loss": 0.7052921233401067, "grad_norm_before_clip": 0.2683122456073761, "learning_rates_at_step": { "lora": 1.8663466368503953e-05, "row_tokens": 1.8663466368503953e-05 }, "learning_rates_after_step": { "lora": 2.0350198505816958e-05, "row_tokens": 2.0350198505816958e-05 } }, { "update_id": 11, "row_count": 9, "row_ids_sha256": "fc6abef9fd96d22ee390318984028ce6619fc95cd08befc444f900768e7b8d9c", "input_ids_vector_sha256": "6e3e74c4caa82ce7834d189bdc72ac4f490a416613e5f71e544ed5655b196ac0", "labels_vector_sha256": "5f06f8d1c86346ce0e73f673e35618d6ed103acb3cac3523a020ed18c5e182b7", "planned_active_tokens": 65411, "realized_active_tokens": 65411, "cumulative_start": 723764, "cumulative_end": 789175, "loss_sum": 44002.976806640625, "token_normalized_loss": 0.672715243714981, "grad_norm_before_clip": 0.1857965886592865, "learning_rates_at_step": { "lora": 2.0350198505816958e-05, "row_tokens": 2.0350198505816958e-05 }, "learning_rates_after_step": { "lora": 2.2116173092533934e-05, "row_tokens": 2.2116173092533934e-05 } }, { "update_id": 12, "row_count": 11, "row_ids_sha256": "f4fb22561de8451d2f0fec6d14654d164ae6ed93daa67f789f7ed1ac5cad8d38", "input_ids_vector_sha256": "b5c5b38a087b1625afad0b9cd678e04eeafa7276daa5c9cb96afc3bc41e82c3e", "labels_vector_sha256": "5a0ab7c01bf1da215fd31cd9812bc1ef3695cfe19084f4aebc2c3e2891823ebe", "planned_active_tokens": 68484, "realized_active_tokens": 68484, "cumulative_start": 789175, "cumulative_end": 857659, "loss_sum": 44180.565673828125, "token_normalized_loss": 0.6451224471968361, "grad_norm_before_clip": 0.20373855531215668, "learning_rates_at_step": { "lora": 2.2116173092533934e-05, "row_tokens": 2.2116173092533934e-05 }, "learning_rates_after_step": { "lora": 2.3662161562796224e-05, "row_tokens": 2.3662161562796224e-05 } }, { "update_id": 13, "row_count": 7, "row_ids_sha256": "6e85cf51bab68c6b5d37e61f6e584193bc56fc0632ae4c9ad6bf0c67195924d8", "input_ids_vector_sha256": "12b37cf1da301a037282b26bb9322cf06cfd44bf1475c4fbd837203fc64fedb5", "labels_vector_sha256": "aba52936ded8ec7c0b2106015143139ccf93304a7dd8097ac5f50efec8777f46", "planned_active_tokens": 59953, "realized_active_tokens": 59953, "cumulative_start": 857659, "cumulative_end": 917612, "loss_sum": 41712.52880859375, "token_normalized_loss": 0.6957538206360607, "grad_norm_before_clip": 0.22265024483203888, "learning_rates_at_step": { "lora": 2.3662161562796224e-05, "row_tokens": 2.3662161562796224e-05 }, "learning_rates_after_step": { "lora": 2.5396341180390166e-05, "row_tokens": 2.5396341180390166e-05 } }, { "update_id": 14, "row_count": 9, "row_ids_sha256": "53ad6af77ca6f23c9a680d178fbbcd1c4b070f98567e5187c83b8f2a93d069a5", "input_ids_vector_sha256": "969fa30aae852885c133d92e3c495f9aeacbfb3dd9afc41927ce35a9a5d82f56", "labels_vector_sha256": "91ec34368c93fa36489583fbb1783a76e7af3cc78a2cce4c5e7554b6d4d3ff03", "planned_active_tokens": 67251, "realized_active_tokens": 67251, "cumulative_start": 917612, "cumulative_end": 984863, "loss_sum": 42732.900634765625, "token_normalized_loss": 0.6354240180036821, "grad_norm_before_clip": 0.2167738676071167, "learning_rates_at_step": { "lora": 2.5396341180390166e-05, "row_tokens": 2.5396341180390166e-05 }, "learning_rates_after_step": { "lora": 2.7226318292138265e-05, "row_tokens": 2.7226318292138265e-05 } }, { "update_id": 15, "row_count": 10, "row_ids_sha256": "6eccde6788b9f9e1b1e18c5e26d957c9aecf6137346be8a2d29762a18593a180", "input_ids_vector_sha256": "fb232617bff12c9edd4062a9411b7fca986a52089f39497b835b6fe7ca075bc2", "labels_vector_sha256": "1332f6c2eb45cb202913d269af97ee8c30d5915ad1e04f093b12ff2b23d5c2d0", "planned_active_tokens": 70966, "realized_active_tokens": 70966, "cumulative_start": 984863, "cumulative_end": 1055829, "loss_sum": 43083.601318359375, "token_normalized_loss": 0.6071020110807904, "grad_norm_before_clip": 0.15896962583065033, "learning_rates_at_step": { "lora": 2.7226318292138265e-05, "row_tokens": 2.7226318292138265e-05 }, "learning_rates_after_step": { "lora": 2.8868413696643503e-05, "row_tokens": 2.8868413696643503e-05 } }, { "update_id": 16, "row_count": 9, "row_ids_sha256": "f1a3f93df1e9fa3e45b88b0de19ca9566a726540cc78c46f8a074d97c498834b", "input_ids_vector_sha256": "dd438284a420906b8ac47035daff6a07bd1012555205d4c9b1d6770e7a9143d9", "labels_vector_sha256": "1542bafd05bed2244bcf81af1ea814283b65d12e4dc94a455c299922ab79ebbb", "planned_active_tokens": 63680, "realized_active_tokens": 63680, "cumulative_start": 1055829, "cumulative_end": 1119509, "loss_sum": 42113.238037109375, "token_normalized_loss": 0.6613259742008382, "grad_norm_before_clip": 0.3069671392440796, "learning_rates_at_step": { "lora": 2.8868413696643503e-05, "row_tokens": 2.8868413696643503e-05 }, "learning_rates_after_step": { "lora": 3.058304701529562e-05, "row_tokens": 3.058304701529562e-05 } }, { "update_id": 17, "row_count": 10, "row_ids_sha256": "63850f77c79c3c288372ef5070ae01534ddcc5893ff22680760699ac3523db9f", "input_ids_vector_sha256": "b69d48d5c275084771edb7f35f33d480297462f70db51f988b0412b364e04e7c", "labels_vector_sha256": "855710d16aed903d0c516aca2ab9ba158d4975b246f7c10c723cc6987974ca0e", "planned_active_tokens": 66493, "realized_active_tokens": 66493, "cumulative_start": 1119509, "cumulative_end": 1186002, "loss_sum": 42671.035400390625, "token_normalized_loss": 0.6417372565591961, "grad_norm_before_clip": 0.2351163625717163, "learning_rates_at_step": { "lora": 3.058304701529562e-05, "row_tokens": 3.058304701529562e-05 }, "learning_rates_after_step": { "lora": 3.213517271398556e-05, "row_tokens": 3.213517271398556e-05 } }, { "update_id": 18, "row_count": 8, "row_ids_sha256": "19847310bc96863fc5b02968f6b7e3135d82d63006ed2fa308ce54b10e2bc0e5", "input_ids_vector_sha256": "8f0c2e5c1b574ff55050dcc6f74a357186af0571975f710ca4e03ef62e0e9304", "labels_vector_sha256": "2184a79056b30658f2dac9a3ddb21f1d7040fff14972ccac34b7cbcf06e78bac", "planned_active_tokens": 60191, "realized_active_tokens": 60191, "cumulative_start": 1186002, "cumulative_end": 1246193, "loss_sum": 41032.1005859375, "token_normalized_loss": 0.6816982702719261, "grad_norm_before_clip": 0.21800492703914642, "learning_rates_at_step": { "lora": 3.213517271398556e-05, "row_tokens": 3.213517271398556e-05 }, "learning_rates_after_step": { "lora": 3.385488600742863e-05, "row_tokens": 3.385488600742863e-05 } }, { "update_id": 19, "row_count": 11, "row_ids_sha256": "2920e370daf4c560060e87b027f2a92a3b19c21bfe32401423ccc7bda6fc6126", "input_ids_vector_sha256": "7baaac08e0c824c1779bedb8836d7d9208d87f3ccb98cf84dffedf82a983d97b", "labels_vector_sha256": "e2462ba7f111c5985ade8aef796f6f518b1e68d6b7c8b5dee8e0f3ffdc325d60", "planned_active_tokens": 66690, "realized_active_tokens": 66690, "cumulative_start": 1246193, "cumulative_end": 1312883, "loss_sum": 41276.187438964844, "token_normalized_loss": 0.6189261874188761, "grad_norm_before_clip": 0.18529920279979706, "learning_rates_at_step": { "lora": 3.385488600742863e-05, "row_tokens": 3.385488600742863e-05 }, "learning_rates_after_step": { "lora": 3.550224189344328e-05, "row_tokens": 3.550224189344328e-05 } }, { "update_id": 20, "row_count": 8, "row_ids_sha256": "2ec893fb693ff3f2854eaeb7956ad6886707f815bed202cac2fb876a94be69de", "input_ids_vector_sha256": "10a389c41c9d87954cfb45bdd6b53e6b3a2be5ddd3fecf4ee182da9503d44128", "labels_vector_sha256": "a449d7e578e47d8fe9a4d7c2eeb2b332ce7ba031df732e93098f9dcb16a4a629", "planned_active_tokens": 63884, "realized_active_tokens": 63884, "cumulative_start": 1312883, "cumulative_end": 1376767, "loss_sum": 37978.200439453125, "token_normalized_loss": 0.5944868893534081, "grad_norm_before_clip": 0.1704716682434082, "learning_rates_at_step": { "lora": 3.550224189344328e-05, "row_tokens": 3.550224189344328e-05 }, "learning_rates_after_step": { "lora": 3.730124920963844e-05, "row_tokens": 3.730124920963844e-05 } }, { "update_id": 21, "row_count": 11, "row_ids_sha256": "675c3b228d49c848ba075df2424a88d75b4b7bee4491654bc08ba02c18e19c0f", "input_ids_vector_sha256": "9baec2515a0fb21db85b4447f883dad853fa4445d232a88dcd3d46bb62aaea56", "labels_vector_sha256": "3c76904e7b0eb4c58f3f7c2b2b8ede245d9d7e4cdd8c5df5c88f474da1c271a0", "planned_active_tokens": 69765, "realized_active_tokens": 69765, "cumulative_start": 1376767, "cumulative_end": 1446532, "loss_sum": 44348.646484375, "token_normalized_loss": 0.6356861819590769, "grad_norm_before_clip": 0.1544221192598343, "learning_rates_at_step": { "lora": 3.730124920963844e-05, "row_tokens": 3.730124920963844e-05 }, "learning_rates_after_step": { "lora": 3.8938419359397135e-05, "row_tokens": 3.8938419359397135e-05 } }, { "update_id": 22, "row_count": 9, "row_ids_sha256": "7dc8b499541351891bdd28ef0c9cbca0d222189eeb46feebad1f168656156025", "input_ids_vector_sha256": "aceb76a27f8da9ece20ade89334d223add7606a0f6d2adc9faf41392ba2c1777", "labels_vector_sha256": "70e6c614487d5d5d1241cb5ce39e484b5d44ca660c03f12b8525ae1c0ffeacc2", "planned_active_tokens": 63489, "realized_active_tokens": 63489, "cumulative_start": 1446532, "cumulative_end": 1510021, "loss_sum": 36991.659912109375, "token_normalized_loss": 0.5826467563217151, "grad_norm_before_clip": 0.12873713672161102, "learning_rates_at_step": { "lora": 3.8938419359397135e-05, "row_tokens": 3.8938419359397135e-05 }, "learning_rates_after_step": { "lora": 4.0749417479032856e-05, "row_tokens": 4.0749417479032856e-05 } }, { "update_id": 23, "row_count": 12, "row_ids_sha256": "85d00d36ec08fd9fb638146e385ac834b1c5fa638f82e7d20ff3ef30dbd5e314", "input_ids_vector_sha256": "ab7c6c2c3e2213102c24a7fb9f5dcc5d97a72094152ffaac22416593af28936f", "labels_vector_sha256": "020fb4569a01794f0137792b039b36e3aeba39e39543e5d578ace2e2ca399d9c", "planned_active_tokens": 70230, "realized_active_tokens": 70230, "cumulative_start": 1510021, "cumulative_end": 1580251, "loss_sum": 38804.303955078125, "token_normalized_loss": 0.5525317379336199, "grad_norm_before_clip": 0.1335451751947403, "learning_rates_at_step": { "lora": 4.0749417479032856e-05, "row_tokens": 4.0749417479032856e-05 }, "learning_rates_after_step": { "lora": 4.246175578369313e-05, "row_tokens": 4.246175578369313e-05 } }, { "update_id": 24, "row_count": 9, "row_ids_sha256": "5440ea485ac36b68783c06bfa3b83e1a093402b489c4f72735deab23ba10a879", "input_ids_vector_sha256": "ad28e259c4838fd107ad9e468eff9741606cb28ff5bf079112f48c2a650ec3b2", "labels_vector_sha256": "cf4540af61c017ec7aa9dcaa3e5b9aa21c7ba6fa6cfaaa72b08eba6c008da605", "planned_active_tokens": 66404, "realized_active_tokens": 66404, "cumulative_start": 1580251, "cumulative_end": 1646655, "loss_sum": 36193.791015625, "token_normalized_loss": 0.5450543794895639, "grad_norm_before_clip": 0.11348289251327515, "learning_rates_at_step": { "lora": 4.246175578369313e-05, "row_tokens": 4.246175578369313e-05 }, "learning_rates_after_step": { "lora": 4.403381458143587e-05, "row_tokens": 4.403381458143587e-05 } }, { "update_id": 25, "row_count": 8, "row_ids_sha256": "86fd751de3bad54ac986565d377d889172e38f7e836265e1c047b4e6d12070d5", "input_ids_vector_sha256": "4a07ae7de7f4181f61dcf1c4f9bdfddbe4b93a1255f2ea4da317c1c2554a3d67", "labels_vector_sha256": "8c9ce2822e6c734f23639e268430358fae5eda78c83d387c56c2751a421dc335", "planned_active_tokens": 60964, "realized_active_tokens": 60964, "cumulative_start": 1646655, "cumulative_end": 1707619, "loss_sum": 33993.53112792969, "token_normalized_loss": 0.5576000775528129, "grad_norm_before_clip": 0.12665008008480072, "learning_rates_at_step": { "lora": 4.403381458143587e-05, "row_tokens": 4.403381458143587e-05 }, "learning_rates_after_step": { "lora": 4.581892288030961e-05, "row_tokens": 4.581892288030961e-05 } }, { "update_id": 26, "row_count": 11, "row_ids_sha256": "7242c42c9d9ed2cc1c5a83f177e19b73f29769116ae3968a5c7d87bd9636e8dd", "input_ids_vector_sha256": "53704845d934d64879741662bdbe4ff905696e0f9fc25c190baa6957bbaaefbc", "labels_vector_sha256": "a332dbff008afa757f40cee48f33b926d06af0700b19a078d1e5662505b2007e", "planned_active_tokens": 69226, "realized_active_tokens": 69226, "cumulative_start": 1707619, "cumulative_end": 1776845, "loss_sum": 35740.179931640625, "token_normalized_loss": 0.5162826095923587, "grad_norm_before_clip": 0.10133293271064758, "learning_rates_at_step": { "lora": 4.581892288030961e-05, "row_tokens": 4.581892288030961e-05 }, "learning_rates_after_step": { "lora": 4.735820681531481e-05, "row_tokens": 4.735820681531481e-05 } }, { "update_id": 27, "row_count": 6, "row_ids_sha256": "1830ca0f1f044ad160ec75a482e4f910b2e8e84a2cb84f21f197f9b8504665d9", "input_ids_vector_sha256": "2c54b39183a2fec416f02b90ed841833bf55906de08a67045fcd58748b9808ce", "labels_vector_sha256": "1771a4d7a6cfb6ba5a954cb313ce9703669da457eb02046a8502c82af0bfd251", "planned_active_tokens": 59693, "realized_active_tokens": 59693, "cumulative_start": 1776845, "cumulative_end": 1836538, "loss_sum": 33712.59326171875, "token_normalized_loss": 0.5647662751364272, "grad_norm_before_clip": 0.10481393337249756, "learning_rates_at_step": { "lora": 4.735820681531481e-05, "row_tokens": 4.735820681531481e-05 }, "learning_rates_after_step": { "lora": 4.9099941928410004e-05, "row_tokens": 4.9099941928410004e-05 } }, { "update_id": 28, "row_count": 12, "row_ids_sha256": "c8c9ab4090247a8ad9563821e3211a508fb2e8657110b2072805ab3a9857b3f9", "input_ids_vector_sha256": "9c4eee0e31f46ded8bc4915aa90b4e73e4e683c4e3b079ed8c7ea5caebe2c835", "labels_vector_sha256": "c184889de9a1708d5dd075a6a3a748e9d39d59763ac89acf348c372cf8ba5a49", "planned_active_tokens": 67544, "realized_active_tokens": 67544, "cumulative_start": 1836538, "cumulative_end": 1904082, "loss_sum": 34574.23809814453, "token_normalized_loss": 0.5118772666431441, "grad_norm_before_clip": 0.10282161086797714, "learning_rates_at_step": { "lora": 4.9099941928410004e-05, "row_tokens": 4.9099941928410004e-05 }, "learning_rates_after_step": { "lora": 5.078822126616696e-05, "row_tokens": 5.078822126616696e-05 } }, { "update_id": 29, "row_count": 10, "row_ids_sha256": "e18d8400483275e8c74d7cd654f02629ac780fa3af278ae3da66fbab58f79438", "input_ids_vector_sha256": "41a4e03f09fa760283540c1473f383f16ec967633755a4a68da4bb1f9787aaf9", "labels_vector_sha256": "8bd7c87b3c11dd8349bcc309c1ed23ac6adf0dc8c55b656c4b350569494d1d11", "planned_active_tokens": 65471, "realized_active_tokens": 65471, "cumulative_start": 1904082, "cumulative_end": 1969553, "loss_sum": 34415.54895019531, "token_normalized_loss": 0.5256609636357367, "grad_norm_before_clip": 0.10110654681921005, "learning_rates_at_step": { "lora": 5.078822126616696e-05, "row_tokens": 5.078822126616696e-05 }, "learning_rates_after_step": { "lora": 5.25815297273936e-05, "row_tokens": 5.25815297273936e-05 } }, { "update_id": 30, "row_count": 12, "row_ids_sha256": "ea8bfb84392cc55aeff20b011bd1bdefeced206f34b1c18595b1446b7ef3e438", "input_ids_vector_sha256": "53c3c66d75a1fc66c593712c53129e74b90f0df400d3bc0f1f4ac3c425f28d8c", "labels_vector_sha256": "b0fa12263556ca9fb112cbbbc3939158b656f7adc41715841349be28c8fa3f3f", "planned_active_tokens": 69544, "realized_active_tokens": 69544, "cumulative_start": 1969553, "cumulative_end": 2039097, "loss_sum": 35476.366455078125, "token_normalized_loss": 0.510128356940615, "grad_norm_before_clip": 0.10392507910728455, "learning_rates_at_step": { "lora": 5.25815297273936e-05, "row_tokens": 5.25815297273936e-05 }, "learning_rates_after_step": { "lora": 5.4113129233527215e-05, "row_tokens": 5.4113129233527215e-05 } }, { "update_id": 31, "row_count": 9, "row_ids_sha256": "4cf335aa1f92de0d741e1d691b9dad8e996ed56139c71b69968388fe63ad1235", "input_ids_vector_sha256": "993f562ed00a45e137a4f1031abd37866dc25bec0ae8dc84688428a074f0e832", "labels_vector_sha256": "97d3d1f1206a76e6d7cc5fac6a2b72b4d361e7225163773b5145b42fbea65038", "planned_active_tokens": 59395, "realized_active_tokens": 59395, "cumulative_start": 2039097, "cumulative_end": 2098492, "loss_sum": 28162.560668945312, "token_normalized_loss": 0.47415709519227733, "grad_norm_before_clip": 0.10152719914913177, "learning_rates_at_step": { "lora": 5.4113129233527215e-05, "row_tokens": 5.4113129233527215e-05 }, "learning_rates_after_step": { "lora": 5.579738585012991e-05, "row_tokens": 5.579738585012991e-05 } }, { "update_id": 32, "row_count": 11, "row_ids_sha256": "b96bc3abfd5dc76dcee945306cb663cbeeb5973146ed5c82bc467814155d4430", "input_ids_vector_sha256": "94c8fd374e36b21ea771b4e673d095db4caceac071d80fbd82226784830cc081", "labels_vector_sha256": "a8115887d305c7de2c76b8eb20cf780139256c9223e3f66e46b1b387bddfb28c", "planned_active_tokens": 65315, "realized_active_tokens": 65315, "cumulative_start": 2098492, "cumulative_end": 2163807, "loss_sum": 33541.81481933594, "token_normalized_loss": 0.5135392301819787, "grad_norm_before_clip": 0.11111991852521896, "learning_rates_at_step": { "lora": 5.579738585012991e-05, "row_tokens": 5.579738585012991e-05 }, "learning_rates_after_step": { "lora": 5.758829615066844e-05, "row_tokens": 5.758829615066844e-05 } }, { "update_id": 33, "row_count": 11, "row_ids_sha256": "d8c72b68940c0d7088be6faad259bdda34a4cf2c92b53e2bb80ab15e732c6f99", "input_ids_vector_sha256": "26fc5c9d909e6384ca0312cf599db2035be0368c85f4069063f890defafc23b4", "labels_vector_sha256": "343818a3a53ef06b012ee2a7bdf76baece60ccec69d748ec99ba191c496377fb", "planned_active_tokens": 69451, "realized_active_tokens": 69451, "cumulative_start": 2163807, "cumulative_end": 2233258, "loss_sum": 34947.16552734375, "token_normalized_loss": 0.503191682298941, "grad_norm_before_clip": 0.10144543647766113, "learning_rates_at_step": { "lora": 5.758829615066844e-05, "row_tokens": 5.758829615066844e-05 }, "learning_rates_after_step": { "lora": 5.9157286334197356e-05, "row_tokens": 5.9157286334197356e-05 } }, { "update_id": 34, "row_count": 12, "row_ids_sha256": "93e96364ba53a475b8b5163dc78f41a23d8ccefde8098adfe935fa2015e3c436", "input_ids_vector_sha256": "b31c949773e089c68e29ff468bc674866b9e852e419def38ece2f6ceb76a67ed", "labels_vector_sha256": "2ca44ebaf30383ee1857f2512231eda7c5dc2116f7121781e7d80c93ddbd27f3", "planned_active_tokens": 60845, "realized_active_tokens": 60845, "cumulative_start": 2233258, "cumulative_end": 2294103, "loss_sum": 27627.380737304688, "token_normalized_loss": 0.4540616441335309, "grad_norm_before_clip": 0.1051018089056015, "learning_rates_at_step": { "lora": 5.9157286334197356e-05, "row_tokens": 5.9157286334197356e-05 }, "learning_rates_after_step": { "lora": 6.085487466129204e-05, "row_tokens": 6.085487466129204e-05 } }, { "update_id": 35, "row_count": 12, "row_ids_sha256": "626728d35e01b1aa689c01db9bd672a9457daee717197c24416f4c63d2b857bd", "input_ids_vector_sha256": "cbc2f7d549869f153eeee9d5d92a77eccb75346c56394589aab1432e5e4e5149", "labels_vector_sha256": "b529931ab1655fdbc0a15bbfe87e8805c78dfb22464e0ae6d8e0208e2831e366", "planned_active_tokens": 65832, "realized_active_tokens": 65832, "cumulative_start": 2294103, "cumulative_end": 2359935, "loss_sum": 32248.77850341797, "token_normalized_loss": 0.48986478465515204, "grad_norm_before_clip": 0.10345985740423203, "learning_rates_at_step": { "lora": 6.085487466129204e-05, "row_tokens": 6.085487466129204e-05 }, "learning_rates_after_step": { "lora": 6.253407708977785e-05, "row_tokens": 6.253407708977785e-05 } }, { "update_id": 36, "row_count": 12, "row_ids_sha256": "376ea5de04363fa4e532fd8fcf58bbaab180eeded2f727240d567452ec112607", "input_ids_vector_sha256": "f43ccc6b00c4a30fe426f7f44cf7e36283358a2b8a658c01462f12a7575c44fa", "labels_vector_sha256": "f868c2d60e1d733b82b60588538a751cb03dea3e9eca13f1455cd96efa066dce", "planned_active_tokens": 65119, "realized_active_tokens": 65119, "cumulative_start": 2359935, "cumulative_end": 2425054, "loss_sum": 30849.169494628906, "token_normalized_loss": 0.4737353075850198, "grad_norm_before_clip": 0.10214683413505554, "learning_rates_at_step": { "lora": 6.253407708977785e-05, "row_tokens": 6.253407708977785e-05 }, "learning_rates_after_step": { "lora": 6.428292932491519e-05, "row_tokens": 6.428292932491519e-05 } }, { "update_id": 37, "row_count": 11, "row_ids_sha256": "0117ee92bd08439d1e1a0f0f24f4f7237b23f956afbbb314e7264dde0347878d", "input_ids_vector_sha256": "edb6e0a708c17ca264ba22e0896577cde64add489950e99cd50cdfcb11824b29", "labels_vector_sha256": "65a29367224d6691d6a31ac812a090ba879bb242eede2bb21b4321831b332301", "planned_active_tokens": 67820, "realized_active_tokens": 67820, "cumulative_start": 2425054, "cumulative_end": 2492874, "loss_sum": 36117.39514160156, "token_normalized_loss": 0.532547849330604, "grad_norm_before_clip": 0.09725137799978256, "learning_rates_at_step": { "lora": 6.428292932491519e-05, "row_tokens": 6.428292932491519e-05 }, "learning_rates_after_step": { "lora": 6.599815573707082e-05, "row_tokens": 6.599815573707082e-05 } }, { "update_id": 38, "row_count": 11, "row_ids_sha256": "fd5980c2f73091dfee719094f4480000037e945f7c9c6cd1540e3ce0c1a6a443", "input_ids_vector_sha256": "80b92789ffa61321d5c10cec908fdeefb39a3528e1022dcde23250ff137ba511", "labels_vector_sha256": "3ed830f6c1ac610f51edfd29ef5559dfdf1c20b5e1063d7d19c3ed2386f5c9cf", "planned_active_tokens": 66516, "realized_active_tokens": 66516, "cumulative_start": 2492874, "cumulative_end": 2559390, "loss_sum": 30837.224243164062, "token_normalized_loss": 0.4636061134638893, "grad_norm_before_clip": 0.08943317085504532, "learning_rates_at_step": { "lora": 6.599815573707082e-05, "row_tokens": 6.599815573707082e-05 }, "learning_rates_after_step": { "lora": 6.784298597308077e-05, "row_tokens": 6.784298597308077e-05 } }, { "update_id": 39, "row_count": 11, "row_ids_sha256": "fdf22a7ec792a6434b23839f90ebeeac20497114a02a9f163220df268e418e10", "input_ids_vector_sha256": "39ffb3ddadbb4fd951f1a985258f1e464c3470d01068aff170b9572f7c21dc2f", "labels_vector_sha256": "e9970701e7e96eb2563aaade507d33d92035935ed097e9a22cccffa94dd9ff6a", "planned_active_tokens": 71542, "realized_active_tokens": 71542, "cumulative_start": 2559390, "cumulative_end": 2630932, "loss_sum": 32345.922241210938, "token_normalized_loss": 0.4521249369770336, "grad_norm_before_clip": 0.08517179638147354, "learning_rates_at_step": { "lora": 6.784298597308077e-05, "row_tokens": 6.784298597308077e-05 }, "learning_rates_after_step": { "lora": 6.955576265120016e-05, "row_tokens": 6.955576265120016e-05 } }, { "update_id": 40, "row_count": 9, "row_ids_sha256": "5604b5823f03e1be1de71f39bd76a62bd91373df006cd1669d42a59971bb471a", "input_ids_vector_sha256": "dcc5408facc45adba4984a8d14274e1f247a451504b6bf7645a42142be4fffd3", "labels_vector_sha256": "54ff015befe61c1dd317c579f4bea19c8a771756e43f79cd1c3b6ab51acb8557", "planned_active_tokens": 66421, "realized_active_tokens": 66421, "cumulative_start": 2630932, "cumulative_end": 2697353, "loss_sum": 30792.418212890625, "token_normalized_loss": 0.46359461936572205, "grad_norm_before_clip": 0.08355852216482162, "learning_rates_at_step": { "lora": 6.955576265120016e-05, "row_tokens": 6.955576265120016e-05 }, "learning_rates_after_step": { "lora": 7.105340110758923e-05, "row_tokens": 7.105340110758923e-05 } }, { "update_id": 41, "row_count": 9, "row_ids_sha256": "2ba3812822fcb95e650e18b3fc777efeea11cd2511350d70c28ebda63dbfb3f3", "input_ids_vector_sha256": "58039afe6f151b947ad34d08f4d80463472b3596754038988d483821b896668b", "labels_vector_sha256": "c6fb88c645b0edefdc1ecbf7d0d3c1d5c711e90e86f1c64b4862a6f01eecb189", "planned_active_tokens": 58078, "realized_active_tokens": 58078, "cumulative_start": 2697353, "cumulative_end": 2755431, "loss_sum": 26939.453857421875, "token_normalized_loss": 0.46384954470577283, "grad_norm_before_clip": 0.09518356621265411, "learning_rates_at_step": { "lora": 7.105340110758923e-05, "row_tokens": 7.105340110758923e-05 }, "learning_rates_after_step": { "lora": 7.268853411009673e-05, "row_tokens": 7.268853411009673e-05 } }, { "update_id": 42, "row_count": 11, "row_ids_sha256": "d6d9c6caff9ff3b8c7116615273acc7e2ef9bb7131e4a16581d46e22c5723645", "input_ids_vector_sha256": "cf325438d1ad4cc25842eddacb8c9832c04c8340f9c57a96f9c07cac4d927109", "labels_vector_sha256": "c823957a8c027dcf3b072773c31ac5d465f421b59e82e69f566606bfab2bab8b", "planned_active_tokens": 63410, "realized_active_tokens": 63410, "cumulative_start": 2755431, "cumulative_end": 2818841, "loss_sum": 27258.234252929688, "token_normalized_loss": 0.42987280007774303, "grad_norm_before_clip": 0.07802586257457733, "learning_rates_at_step": { "lora": 7.268853411009673e-05, "row_tokens": 7.268853411009673e-05 }, "learning_rates_after_step": { "lora": 7.43690516589599e-05, "row_tokens": 7.43690516589599e-05 } }, { "update_id": 43, "row_count": 9, "row_ids_sha256": "4e8ff473737a44084146cfd8ce19e996f6dbe2d32b3f1bbcb622eed87c0fe9dd", "input_ids_vector_sha256": "86928a941c1ffcdccff52b7aa8c44abed2822e5c1695ba88020cd1492d038a73", "labels_vector_sha256": "6d112636b88d3d30a935ee0b64fec00e56a540d08a7633007377dee02bd582fc", "planned_active_tokens": 65170, "realized_active_tokens": 65170, "cumulative_start": 2818841, "cumulative_end": 2884011, "loss_sum": 32307.433715820312, "token_normalized_loss": 0.4957408886883583, "grad_norm_before_clip": 0.0910777598619461, "learning_rates_at_step": { "lora": 7.43690516589599e-05, "row_tokens": 7.43690516589599e-05 }, "learning_rates_after_step": { "lora": 7.605764043680563e-05, "row_tokens": 7.605764043680563e-05 } }, { "update_id": 44, "row_count": 11, "row_ids_sha256": "2f8870a3dba7e993356e404ea8cab0c093c3266918fe920b68566feb2274076c", "input_ids_vector_sha256": "8a3a5c553638d9a5c7c9ad4ef56a264eca98d8de636caada84b55a3159d3a43f", "labels_vector_sha256": "20e464ace1b39190a5ac0e9953e813e830c137b04d52c35c953b5106c3200f90", "planned_active_tokens": 65483, "realized_active_tokens": 65483, "cumulative_start": 2884011, "cumulative_end": 2949494, "loss_sum": 29045.04559326172, "token_normalized_loss": 0.44355093067302537, "grad_norm_before_clip": 0.07740850001573563, "learning_rates_at_step": { "lora": 7.605764043680563e-05, "row_tokens": 7.605764043680563e-05 }, "learning_rates_after_step": { "lora": 7.785742135322278e-05, "row_tokens": 7.785742135322278e-05 } }, { "update_id": 45, "row_count": 10, "row_ids_sha256": "42145bc6646017760189c985af13db420735d112e760acd67204c4a4309b6eea", "input_ids_vector_sha256": "42efbc590efa738243a908db29263f53fe21a158bf9cdcb48128fbf1b5e6c777", "labels_vector_sha256": "548e2384baefb7c0c35f8793e5abb4e447c737b9afc484fbdf4ca0eea062060f", "planned_active_tokens": 69795, "realized_active_tokens": 69795, "cumulative_start": 2949494, "cumulative_end": 3019289, "loss_sum": 30680.898193359375, "token_normalized_loss": 0.43958590433927036, "grad_norm_before_clip": 0.07494062185287476, "learning_rates_at_step": { "lora": 7.785742135322278e-05, "row_tokens": 7.785742135322278e-05 }, "learning_rates_after_step": { "lora": 7.954123959636635e-05, "row_tokens": 7.954123959636635e-05 } }, { "update_id": 46, "row_count": 11, "row_ids_sha256": "a5770193f6eb96d61ff6b5e88364c9978d4ddc8e1e2269330b8dfcdece8233ee", "input_ids_vector_sha256": "b310b62ab2c6ec8d06ad5a3818547eb16890ebe6ef531b1de4b403de148d6d8f", "labels_vector_sha256": "b3b5ad758d0d9a1589964cd79b3f443377a9a3b3f5b509f6677b0068f5a07c8c", "planned_active_tokens": 65298, "realized_active_tokens": 65298, "cumulative_start": 3019289, "cumulative_end": 3084587, "loss_sum": 30651.642211914062, "token_normalized_loss": 0.4694116544444556, "grad_norm_before_clip": 0.08032367378473282, "learning_rates_at_step": { "lora": 7.954123959636635e-05, "row_tokens": 7.954123959636635e-05 }, "learning_rates_after_step": { "lora": 8.116041064762717e-05, "row_tokens": 8.116041064762717e-05 } }, { "update_id": 47, "row_count": 8, "row_ids_sha256": "90fa16e0dc9aa3ed3e2990563b34270b3f95f6b094facdb1996515b20f57afd8", "input_ids_vector_sha256": "da0cca16cf9d7b9773eae5b4860d50982f5d5b4911a155e2ade29758734ad445", "labels_vector_sha256": "773e976470270b6b4f52d83909b508dba646b98f87ae5a9d8b2d7c59f33d14d6", "planned_active_tokens": 62791, "realized_active_tokens": 62791, "cumulative_start": 3084587, "cumulative_end": 3147378, "loss_sum": 28450.702026367188, "token_normalized_loss": 0.45310159141225953, "grad_norm_before_clip": 0.07943978905677795, "learning_rates_at_step": { "lora": 8.116041064762717e-05, "row_tokens": 8.116041064762717e-05 }, "learning_rates_after_step": { "lora": 8.286921617794044e-05, "row_tokens": 8.286921617794044e-05 } }, { "update_id": 48, "row_count": 12, "row_ids_sha256": "53c0933454f0dd3b8ac18ea18aa62d678036f12be90f8c8e85f0061a4d58c20b", "input_ids_vector_sha256": "4aec3be8579acd6c8d41a823b7235127fd66553217570be183a3568b86d7e5c4", "labels_vector_sha256": "171ed19118ad1ae8b4199743a9f9b9af7ccd35bd4d580776ba84d883acf3ad0d", "planned_active_tokens": 66267, "realized_active_tokens": 66267, "cumulative_start": 3147378, "cumulative_end": 3213645, "loss_sum": 30797.515075683594, "token_normalized_loss": 0.46474889576536726, "grad_norm_before_clip": 0.08030830323696136, "learning_rates_at_step": { "lora": 8.286921617794044e-05, "row_tokens": 8.286921617794044e-05 }, "learning_rates_after_step": { "lora": 8.465435026348824e-05, "row_tokens": 8.465435026348824e-05 } }, { "update_id": 49, "row_count": 9, "row_ids_sha256": "82493d069af2e2cd4a071e702754232d8b74114eff265e1797741c1a6e1ab365", "input_ids_vector_sha256": "11ac94aa5f2d37b45a4d5adbaea0eec65feaedc49dc64baf1b297b8059921756", "labels_vector_sha256": "e1207a7a79682fac2858fd64d5ff43ae109a2b39f98dfa53280073522d0c1ea8", "planned_active_tokens": 69227, "realized_active_tokens": 69227, "cumulative_start": 3213645, "cumulative_end": 3282872, "loss_sum": 33148.30792236328, "token_normalized_loss": 0.478834962115407, "grad_norm_before_clip": 0.0828639343380928, "learning_rates_at_step": { "lora": 8.465435026348824e-05, "row_tokens": 8.465435026348824e-05 }, "learning_rates_after_step": { "lora": 8.631601775360937e-05, "row_tokens": 8.631601775360937e-05 } }, { "update_id": 50, "row_count": 12, "row_ids_sha256": "208a0ee8cf620704f4d4f88c0f6433a9a0d865cb8fa6a5fa32e5825a8db8b4cd", "input_ids_vector_sha256": "f2a22bf5e78c08fad3521bda3b2858907822d866d01aa85495ed54b09f377913", "labels_vector_sha256": "7c78fcbd543210c5a6ccca9f21f9463dff0660aad83dda75b653392a2a30ce5c", "planned_active_tokens": 64439, "realized_active_tokens": 64439, "cumulative_start": 3282872, "cumulative_end": 3347311, "loss_sum": 29468.776977539062, "token_normalized_loss": 0.45731276055710146, "grad_norm_before_clip": 0.08569789677858353, "learning_rates_at_step": { "lora": 8.631601775360937e-05, "row_tokens": 8.631601775360937e-05 }, "learning_rates_after_step": { "lora": 8.791180029149256e-05, "row_tokens": 8.791180029149256e-05 } }, { "update_id": 51, "row_count": 12, "row_ids_sha256": "0a261fa3135a44cf080bfdc287d0782112af2d5a50429bc6b0ff7e261d4b465a", "input_ids_vector_sha256": "028a3b068da6fd890312bb5ccde031b285e15adac514885d3ec100ca2bcb2b8d", "labels_vector_sha256": "acdfee7741c9eceb21e4d65833b004e8970ddc5e938bc8084df4e6feba036ba5", "planned_active_tokens": 61884, "realized_active_tokens": 61884, "cumulative_start": 3347311, "cumulative_end": 3409195, "loss_sum": 23758.20556640625, "token_normalized_loss": 0.38391515684839783, "grad_norm_before_clip": 0.07995553314685822, "learning_rates_at_step": { "lora": 8.791180029149256e-05, "row_tokens": 8.791180029149256e-05 }, "learning_rates_after_step": { "lora": 8.960570112419584e-05, "row_tokens": 8.960570112419584e-05 } }, { "update_id": 52, "row_count": 10, "row_ids_sha256": "ed4913a824d2614b6b9ca6d2fa824658f2f8bc34c6a6c0af2e87cbce2acbe3ea", "input_ids_vector_sha256": "4574a204323a1947ef06bd930c211357c3e1e1b4870ee9338855e1c3d9c22ad8", "labels_vector_sha256": "6049ba4b5f2c4c0e202d68c9819fc935b82bbb5fe29492e07acffbe4f04b1ab8", "planned_active_tokens": 65689, "realized_active_tokens": 65689, "cumulative_start": 3409195, "cumulative_end": 3474884, "loss_sum": 25226.410034179688, "token_normalized_loss": 0.38402791995889246, "grad_norm_before_clip": 0.06756339967250824, "learning_rates_at_step": { "lora": 8.960570112419584e-05, "row_tokens": 8.960570112419584e-05 }, "learning_rates_after_step": { "lora": 9.130176803752065e-05, "row_tokens": 9.130176803752065e-05 } }, { "update_id": 53, "row_count": 13, "row_ids_sha256": "53768438b698ce20b352cf08f1e6cdd2a12676444454f4ba36c9d9c87cc651d4", "input_ids_vector_sha256": "90a317c23a7e180484efa305083283d7c8ca6c88436c4abee767c638b1a53aad", "labels_vector_sha256": "fc71bddda50b14ca3af1c94c61fe1b0183bb1e5532ddfa1ed4d512c0fe53591b", "planned_active_tokens": 65773, "realized_active_tokens": 65773, "cumulative_start": 3474884, "cumulative_end": 3540657, "loss_sum": 23819.117431640625, "token_normalized_loss": 0.36214126513372696, "grad_norm_before_clip": 0.06687592715024948, "learning_rates_at_step": { "lora": 9.130176803752065e-05, "row_tokens": 9.130176803752065e-05 }, "learning_rates_after_step": { "lora": 9.295539008533328e-05, "row_tokens": 9.295539008533328e-05 } }, { "update_id": 54, "row_count": 8, "row_ids_sha256": "d10f3dbea1c00e29a806ee2e33a0423333c4da599cf1cd2e5313b8002d21469f", "input_ids_vector_sha256": "5f5ddca3557f4ea41e2bdc61c7a163534625601da2aedfe1d967bc407e4b45c5", "labels_vector_sha256": "223102eb0300c2405704f4d9cc7603f0bef0572d3cb7660a1f0379441f7e7a51", "planned_active_tokens": 64127, "realized_active_tokens": 64127, "cumulative_start": 3540657, "cumulative_end": 3604784, "loss_sum": 27361.409790039062, "token_normalized_loss": 0.42667534408344476, "grad_norm_before_clip": 0.07549665868282318, "learning_rates_at_step": { "lora": 9.295539008533328e-05, "row_tokens": 9.295539008533328e-05 }, "learning_rates_after_step": { "lora": 9.473838387693362e-05, "row_tokens": 9.473838387693362e-05 } }, { "update_id": 55, "row_count": 9, "row_ids_sha256": "64c21d8d9104b933bf6ae468a9f8402855d843736766713d69fa3b1f22500347", "input_ids_vector_sha256": "b482539ebf85cdc8ac6bc51c139371105df8f3f38ea9d91b647b5ef98b36cd1b", "labels_vector_sha256": "c204e8d29edd86e5c5b78e07bcab7a44ee1d4a8bc54888ae3363a08d679f2537", "planned_active_tokens": 69144, "realized_active_tokens": 69144, "cumulative_start": 3604784, "cumulative_end": 3673928, "loss_sum": 27575.548583984375, "token_normalized_loss": 0.3988133255811694, "grad_norm_before_clip": 0.07385663688182831, "learning_rates_at_step": { "lora": 9.473838387693362e-05, "row_tokens": 9.473838387693362e-05 }, "learning_rates_after_step": { "lora": 9.642743681491255e-05, "row_tokens": 9.642743681491255e-05 } }, { "update_id": 56, "row_count": 12, "row_ids_sha256": "38787b498da846ff88c2dbb85a577e85624c7d0bca28a097a7bcb4e1956166ce", "input_ids_vector_sha256": "dd8956e7bd11d21643a03fe2ce27baac66ea36f4924c70e04684da4c89c220cb", "labels_vector_sha256": "337c1ff5cd8a911d52ec39ac0fa8959e7b7db1dc4ae552910df312a0fa6153ec", "planned_active_tokens": 65501, "realized_active_tokens": 65501, "cumulative_start": 3673928, "cumulative_end": 3739429, "loss_sum": 26803.431701660156, "token_normalized_loss": 0.4092064503085473, "grad_norm_before_clip": 0.07135941833257675, "learning_rates_at_step": { "lora": 9.642743681491255e-05, "row_tokens": 9.642743681491255e-05 }, "learning_rates_after_step": { "lora": 9.816071389891418e-05, "row_tokens": 9.816071389891418e-05 } }, { "update_id": 57, "row_count": 9, "row_ids_sha256": "417f8d5db1694fb1a68fd3b87156de3c35d2ac1f88882489b0e9f901f8b41779", "input_ids_vector_sha256": "82904c52b797fe2fc707a2c8ffd16881f05c05e8f5889813b970d8eb8a508ae4", "labels_vector_sha256": "e8f15e3beccb56611630e379b474fd1c628191eab40efa46013fa9631dd243f0", "planned_active_tokens": 67216, "realized_active_tokens": 67216, "cumulative_start": 3739429, "cumulative_end": 3806645, "loss_sum": 25354.616821289062, "token_normalized_loss": 0.3772110334040863, "grad_norm_before_clip": 0.07026319205760956, "learning_rates_at_step": { "lora": 9.816071389891418e-05, "row_tokens": 9.816071389891418e-05 }, "learning_rates_after_step": { "lora": 9.999999898065967e-05, "row_tokens": 9.999999898065967e-05 } }, { "update_id": 58, "row_count": 12, "row_ids_sha256": "c0710e2ccee111bc9677f520e7009ed47a10fe2f4d38e3248c3b9c454e517cc5", "input_ids_vector_sha256": "cb911c3622fa27a56f7392770721b7e782ef9b55888065dbebc1758fe5d6350a", "labels_vector_sha256": "ffff21928eba7ca2d922e602707d0e6a0f5705d31e7fc998288a379ee9b51ebf", "planned_active_tokens": 75232, "realized_active_tokens": 75232, "cumulative_start": 3806645, "cumulative_end": 3881877, "loss_sum": 31433.773071289062, "token_normalized_loss": 0.4178245038187083, "grad_norm_before_clip": 0.07322302460670471, "learning_rates_at_step": { "lora": 9.999999898065967e-05, "row_tokens": 9.999999898065967e-05 }, "learning_rates_after_step": { "lora": 9.999979515662205e-05, "row_tokens": 9.999979515662205e-05 } }, { "update_id": 59, "row_count": 7, "row_ids_sha256": "cd0d757def3bcd7403c9d51dfa34c27d444adc40479d32304444a45996a0eac3", "input_ids_vector_sha256": "e5771a13f6b238656e431516d35a6fc79b2e9afa83e8cb9f02a1b2e3eeaa2ecd", "labels_vector_sha256": "5814cd552b8da1cb9de1e1c0451f590876756a83c12cbb5fad3ea2870429a469", "planned_active_tokens": 51452, "realized_active_tokens": 51452, "cumulative_start": 3881877, "cumulative_end": 3933329, "loss_sum": 20633.64892578125, "token_normalized_loss": 0.40102715007737794, "grad_norm_before_clip": 0.0790649875998497, "learning_rates_at_step": { "lora": 9.999979515662205e-05, "row_tokens": 9.999979515662205e-05 }, "learning_rates_after_step": { "lora": 9.99990012432321e-05, "row_tokens": 9.99990012432321e-05 } }, { "update_id": 60, "row_count": 11, "row_ids_sha256": "d67afef7433467dcadacfa8e997aa07f2dfcd9560d8268d462df8924f10c738d", "input_ids_vector_sha256": "96113d3b1aa7bc2b3b7cdc2a947adc1f65770bee2d7d4b172a0329f74d1303e8", "labels_vector_sha256": "f87d322e0d9d7aed113cc9a3a2d2e7dfe8efd931be660e4394fc4fd8a3c96813", "planned_active_tokens": 66877, "realized_active_tokens": 66877, "cumulative_start": 3933329, "cumulative_end": 4000206, "loss_sum": 29065.692993164062, "token_normalized_loss": 0.4346141871370436, "grad_norm_before_clip": 0.07662314176559448, "learning_rates_at_step": { "lora": 9.99990012432321e-05, "row_tokens": 9.99990012432321e-05 }, "learning_rates_after_step": { "lora": 9.999752768166757e-05, "row_tokens": 9.999752768166757e-05 } }, { "update_id": 61, "row_count": 12, "row_ids_sha256": "eff5b7b0ebccf5f2abe0853a686a707339b30b11f693da94520de5f317e83209", "input_ids_vector_sha256": "b9bd8d0c2d851766b54367acd1f4c7c731756764d4b724fd61d27d459f805f3c", "labels_vector_sha256": "4aa76a012e608e21f353a2ce6510ff050034cd10f6ae2481b493641b68a79fac", "planned_active_tokens": 70082, "realized_active_tokens": 70082, "cumulative_start": 4000206, "cumulative_end": 4070288, "loss_sum": 29824.9150390625, "token_normalized_loss": 0.4255716880092249, "grad_norm_before_clip": 0.06971070915460587, "learning_rates_at_step": { "lora": 9.999752768166757e-05, "row_tokens": 9.999752768166757e-05 }, "learning_rates_after_step": { "lora": 9.999570237049727e-05, "row_tokens": 9.999570237049727e-05 } }, { "update_id": 62, "row_count": 8, "row_ids_sha256": "6c5b28e2b46c591a8a23d120ed477b036ef08b8de2795289a85ef05af38228c2", "input_ids_vector_sha256": "684cbfa649717da048f0057737035613def1a89f69860cf63ef842d6d78f7272", "labels_vector_sha256": "e4246d20cfc6a3276ae35b7b5dce71fffd1df657480b15307cd54c63db0cdaf3", "planned_active_tokens": 61243, "realized_active_tokens": 61243, "cumulative_start": 4070288, "cumulative_end": 4131531, "loss_sum": 30263.60791015625, "token_normalized_loss": 0.49415619597596866, "grad_norm_before_clip": 0.08049321919679642, "learning_rates_at_step": { "lora": 9.999570237049727e-05, "row_tokens": 9.999570237049727e-05 }, "learning_rates_after_step": { "lora": 9.99932391579003e-05, "row_tokens": 9.99932391579003e-05 } }, { "update_id": 63, "row_count": 11, "row_ids_sha256": "e9fbd5f4151f7bfe447f0ffe38c073522cf4a7aafabd7afe678bafdfcaf3f372", "input_ids_vector_sha256": "0c132262326d5c2bf2007fbf3f11089fb568073159976a93783f5a5da8344b0a", "labels_vector_sha256": "cd8bcef59129c18834220b2b1b57818b09cf66bb6bced3084c9946e89c00cad1", "planned_active_tokens": 64470, "realized_active_tokens": 64470, "cumulative_start": 4131531, "cumulative_end": 4196001, "loss_sum": 28270.86669921875, "token_normalized_loss": 0.43851196989636654, "grad_norm_before_clip": 0.07884999364614487, "learning_rates_at_step": { "lora": 9.99932391579003e-05, "row_tokens": 9.99932391579003e-05 }, "learning_rates_after_step": { "lora": 9.998987245704459e-05, "row_tokens": 9.998987245704459e-05 } }, { "update_id": 64, "row_count": 11, "row_ids_sha256": "6aad4c4019d70004226365923d4cc6bf6632f264a7103832a12087e143183150", "input_ids_vector_sha256": "bbbaad0e3f34d2f18219a8b60c4ad7cca716d96f4202ae8149f1aedbc7245971", "labels_vector_sha256": "962f1922e0b678a1863ce36e28ee1325e851dc71fdd63b1643cb24522297d155", "planned_active_tokens": 71214, "realized_active_tokens": 71214, "cumulative_start": 4196001, "cumulative_end": 4267215, "loss_sum": 29433.177856445312, "token_normalized_loss": 0.413306061398676, "grad_norm_before_clip": 0.07077886164188385, "learning_rates_at_step": { "lora": 9.998987245704459e-05, "row_tokens": 9.998987245704459e-05 }, "learning_rates_after_step": { "lora": 9.998640100481254e-05, "row_tokens": 9.998640100481254e-05 } }, { "update_id": 65, "row_count": 10, "row_ids_sha256": "2dd365185bf53eef9357008f3eea21a685b2aa223f9c963d72c478997396c02a", "input_ids_vector_sha256": "34c22686cbc280e854a4f00420104131194fe953c7e794514c69328148b0a126", "labels_vector_sha256": "5cb41e8f179d4243fb1fde086a116d805d8413f6e27a07cfa6604c4863d03a2c", "planned_active_tokens": 61807, "realized_active_tokens": 61807, "cumulative_start": 4267215, "cumulative_end": 4329022, "loss_sum": 27888.89532470703, "token_normalized_loss": 0.45122551369111963, "grad_norm_before_clip": 0.07811310142278671, "learning_rates_at_step": { "lora": 9.998640100481254e-05, "row_tokens": 9.998640100481254e-05 }, "learning_rates_after_step": { "lora": 9.998190945101293e-05, "row_tokens": 9.998190945101293e-05 } }, { "update_id": 66, "row_count": 10, "row_ids_sha256": "89b31c74f92285b40e9430f0942e5cb34f326eac1f8149175e8d13bf0d480a1e", "input_ids_vector_sha256": "739f7da5000e27f145de29e69a6702ff109fe616efb6dd7df051bdf66d88692a", "labels_vector_sha256": "1f3cf8899eb6af2fe3ae21a4f752f28906a5dc51aaed059a7e9a9469edeee523", "planned_active_tokens": 69186, "realized_active_tokens": 69186, "cumulative_start": 4329022, "cumulative_end": 4398208, "loss_sum": 30125.772216796875, "token_normalized_loss": 0.4354316222472303, "grad_norm_before_clip": 0.07436662167310715, "learning_rates_at_step": { "lora": 9.998190945101293e-05, "row_tokens": 9.998190945101293e-05 }, "learning_rates_after_step": { "lora": 9.997749684475534e-05, "row_tokens": 9.997749684475534e-05 } }, { "update_id": 67, "row_count": 11, "row_ids_sha256": "0d1d1d963fcd146b50c33705f44d6af9d6cf92318019991bca26a9a5b337cfcc", "input_ids_vector_sha256": "3e3c95db8ed8929aeb8e072e35f0248f9ed9ea5c75aba73fea5545153dc6c90b", "labels_vector_sha256": "6c1b4c6709e56e6f83ce19a8a3fe41c124b18518a1749d28e4178e1c66f47d86", "planned_active_tokens": 59993, "realized_active_tokens": 59993, "cumulative_start": 4398208, "cumulative_end": 4458201, "loss_sum": 24505.98876953125, "token_normalized_loss": 0.40848080225245026, "grad_norm_before_clip": 0.07607767730951309, "learning_rates_at_step": { "lora": 9.997749684475534e-05, "row_tokens": 9.997749684475534e-05 }, "learning_rates_after_step": { "lora": 9.997184762355577e-05, "row_tokens": 9.997184762355577e-05 } }, { "update_id": 68, "row_count": 7, "row_ids_sha256": "d71b11da3f0a987799e17ec2df1f433326f607806e9c7eb7bdf21205c53ed628", "input_ids_vector_sha256": "6b198abd2411e8e77775af9e923c03aefe06dc1923a84c7c001da8a20bcc63b2", "labels_vector_sha256": "ccb796f787c04593cd1d0d5ed877f22f9368dd112d27adcb9ae9abb6c7a9fcbe", "planned_active_tokens": 68763, "realized_active_tokens": 68763, "cumulative_start": 4458201, "cumulative_end": 4526964, "loss_sum": 30890.043334960938, "token_normalized_loss": 0.44922477691434254, "grad_norm_before_clip": 0.0830104798078537, "learning_rates_at_step": { "lora": 9.997184762355577e-05, "row_tokens": 9.997184762355577e-05 }, "learning_rates_after_step": { "lora": 9.996606377236992e-05, "row_tokens": 9.996606377236992e-05 } }, { "update_id": 69, "row_count": 10, "row_ids_sha256": "050f0519eab66e27222510b680452a2bce0233583c348866fbf109814829558b", "input_ids_vector_sha256": "3e820b7778223d6d36776fca1b5851e08d7084084d0b615db937f9b83bed86be", "labels_vector_sha256": "322cbf557e8da35457f1b5da85d04180a31119d3097630d742d5625670872fde", "planned_active_tokens": 63562, "realized_active_tokens": 63562, "cumulative_start": 4526964, "cumulative_end": 4590526, "loss_sum": 27901.425537109375, "token_normalized_loss": 0.438963933436792, "grad_norm_before_clip": 0.08076531440019608, "learning_rates_at_step": { "lora": 9.996606377236992e-05, "row_tokens": 9.996606377236992e-05 }, "learning_rates_after_step": { "lora": 9.995939304403441e-05, "row_tokens": 9.995939304403441e-05 } }, { "update_id": 70, "row_count": 12, "row_ids_sha256": "de1089a117464ae6cdc72c0393b516299fb7b79f0875b4a8b94b75b471324954", "input_ids_vector_sha256": "ea1888267952d8b0eade8def92e2fe44bb793ad134e438b6e377cbcbcdf9ab60", "labels_vector_sha256": "8232ac6b2290f24c90b1eb12139abff2824c888a82701fafa03dbff6e20e9329", "planned_active_tokens": 66901, "realized_active_tokens": 66901, "cumulative_start": 4590526, "cumulative_end": 4657427, "loss_sum": 25231.567504882812, "token_normalized_loss": 0.37714783792294304, "grad_norm_before_clip": 0.07804589718580246, "learning_rates_at_step": { "lora": 9.995939304403441e-05, "row_tokens": 9.995939304403441e-05 }, "learning_rates_after_step": { "lora": 9.995199776905932e-05, "row_tokens": 9.995199776905932e-05 } }, { "update_id": 71, "row_count": 10, "row_ids_sha256": "14f0be00d1f583a555eb2b2677ed66424e61396a3353a14fc5b583ee319ddff1", "input_ids_vector_sha256": "d1e5f8ef13219e13da86f499149ee305cf2ac597675e4a37b634d0bde5e9044d", "labels_vector_sha256": "79fa679373cfed63624ebfefef5728e7d41319ebb6ca3dc4e30a9c63aa77dcb5", "planned_active_tokens": 68020, "realized_active_tokens": 68020, "cumulative_start": 4657427, "cumulative_end": 4725447, "loss_sum": 26721.189514160156, "token_normalized_loss": 0.39284312722964065, "grad_norm_before_clip": 0.07499025017023087, "learning_rates_at_step": { "lora": 9.995199776905932e-05, "row_tokens": 9.995199776905932e-05 }, "learning_rates_after_step": { "lora": 9.994424812703402e-05, "row_tokens": 9.994424812703402e-05 } }, { "update_id": 72, "row_count": 11, "row_ids_sha256": "e4a1d2a71b19da1ee5ecd22cb18e0d64dcbfede6be80d35350bcf95e810e37ae", "input_ids_vector_sha256": "0e4288afd1b8e05b0717f17f16c5891e510fd6b253f2622b512d409fd2d3eadb", "labels_vector_sha256": "299b4d45a8d3ec8fdba6b904d43c3939cec5e500955176c172c10f454784c5ee", "planned_active_tokens": 65863, "realized_active_tokens": 65863, "cumulative_start": 4725447, "cumulative_end": 4791310, "loss_sum": 28358.69219970703, "token_normalized_loss": 0.4305709153805176, "grad_norm_before_clip": 0.0785101130604744, "learning_rates_at_step": { "lora": 9.994424812703402e-05, "row_tokens": 9.994424812703402e-05 }, "learning_rates_after_step": { "lora": 9.993658246836847e-05, "row_tokens": 9.993658246836847e-05 } }, { "update_id": 73, "row_count": 10, "row_ids_sha256": "8fe3472d66df14e87f55f8ee8b77f0df052178adbd9261bc19e0d77d415fde03", "input_ids_vector_sha256": "9be7c83b8c4178272efee3f5a89c8b67d1155341bfcb91061a5b51016b556db0", "labels_vector_sha256": "b410430352d5ebd015c9062d4f7160850e63b5fe67de2159686a0b8d74a93098", "planned_active_tokens": 60781, "realized_active_tokens": 60781, "cumulative_start": 4791310, "cumulative_end": 4852091, "loss_sum": 25068.569915771484, "token_normalized_loss": 0.4124408929726639, "grad_norm_before_clip": 0.08205801993608475, "learning_rates_at_step": { "lora": 9.993658246836847e-05, "row_tokens": 9.993658246836847e-05 }, "learning_rates_after_step": { "lora": 9.992800555789923e-05, "row_tokens": 9.992800555789923e-05 } }, { "update_id": 74, "row_count": 11, "row_ids_sha256": "451aa3aa41755a039a45a595439d0f7fdc69eb58fe104964f71166c3bbb37a6e", "input_ids_vector_sha256": "70a650151858033f7e312c0dac8ec2fc3d7e655f61ca584e201f0524f46f8049", "labels_vector_sha256": "217eaddb3e8e0796dc72781b217e32103e7ce6c45d6cca11eedba46b2a304fb1", "planned_active_tokens": 63799, "realized_active_tokens": 63799, "cumulative_start": 4852091, "cumulative_end": 4915890, "loss_sum": 24247.644470214844, "token_normalized_loss": 0.38006308045917403, "grad_norm_before_clip": 0.0729987695813179, "learning_rates_at_step": { "lora": 9.992800555789923e-05, "row_tokens": 9.992800555789923e-05 }, "learning_rates_after_step": { "lora": 9.991807772055716e-05, "row_tokens": 9.991807772055716e-05 } }, { "update_id": 75, "row_count": 12, "row_ids_sha256": "3fb88b5db8b34d9d4b8387c17ab4b4845bceba2e16393e17af47d1d71a431843", "input_ids_vector_sha256": "1c17faa8dc791fb289df8e0fef16623a90d710332f9e742c7cff7c6dbde021c8", "labels_vector_sha256": "76d3a7f8c182b3dd3fde82ff4a013fa3e6a7325f37eef8cfaa96811772b85dd3", "planned_active_tokens": 69271, "realized_active_tokens": 69271, "cumulative_start": 4915890, "cumulative_end": 4985161, "loss_sum": 29557.065368652344, "token_normalized_loss": 0.42668743584836866, "grad_norm_before_clip": 0.07379594445228577, "learning_rates_at_step": { "lora": 9.991807772055716e-05, "row_tokens": 9.991807772055716e-05 }, "learning_rates_after_step": { "lora": 9.990874406112045e-05, "row_tokens": 9.990874406112045e-05 } }, { "update_id": 76, "row_count": 10, "row_ids_sha256": "1a50bf2791b6c8922d4ad9c57aba32a583fef86a7bde06417e23cb813c73d458", "input_ids_vector_sha256": "63d923ee3692c62fbe034a45a3451f0bc2f858090481de619a54fdc9d54044ca", "labels_vector_sha256": "1ba8cbcb59c1000569aa20f9f7887f5d3cd2e49e262c4175303cfedeec4cd568", "planned_active_tokens": 61390, "realized_active_tokens": 61390, "cumulative_start": 4985161, "cumulative_end": 5046551, "loss_sum": 26287.6357421875, "token_normalized_loss": 0.42820713051290926, "grad_norm_before_clip": 0.08297253400087357, "learning_rates_at_step": { "lora": 9.990874406112045e-05, "row_tokens": 9.990874406112045e-05 }, "learning_rates_after_step": { "lora": 9.98977674647222e-05, "row_tokens": 9.98977674647222e-05 } }, { "update_id": 77, "row_count": 12, "row_ids_sha256": "62208efceb84f49a35d6059e189a9bba32afec0cd255ba8b8d29006f59e542d4", "input_ids_vector_sha256": "83b2a8bac5af4aa18a71dc58d8ef6e58bc66574535d3ea06a1133eb23be513f7", "labels_vector_sha256": "cd5e1dcd4fe253790554de84d7f7bee813c621cf903be15730bebf1dff3027ab", "planned_active_tokens": 68308, "realized_active_tokens": 68308, "cumulative_start": 5046551, "cumulative_end": 5114859, "loss_sum": 20876.218627929688, "token_normalized_loss": 0.3056189410893261, "grad_norm_before_clip": 0.06756623834371567, "learning_rates_at_step": { "lora": 9.98977674647222e-05, "row_tokens": 9.98977674647222e-05 }, "learning_rates_after_step": { "lora": 9.98859298594048e-05, "row_tokens": 9.98859298594048e-05 } }, { "update_id": 78, "row_count": 11, "row_ids_sha256": "49df0e57d8fa120ed54a1a9aecde468922be849a82c56fc5fb8c1252f267e28c", "input_ids_vector_sha256": "06a86c33a100222a88d582ea4c563ce3c44b9599761d3a7855db73c7a628a095", "labels_vector_sha256": "2dece844e56ef70d6ae08bb5f7b302060a272974121a6d5d01b50a7b7e04ca48", "planned_active_tokens": 69675, "realized_active_tokens": 69675, "cumulative_start": 5114859, "cumulative_end": 5184534, "loss_sum": 30461.970153808594, "token_normalized_loss": 0.43720086334852665, "grad_norm_before_clip": 0.07636959105730057, "learning_rates_at_step": { "lora": 9.98859298594048e-05, "row_tokens": 9.98859298594048e-05 }, "learning_rates_after_step": { "lora": 9.987384681142344e-05, "row_tokens": 9.987384681142344e-05 } }, { "update_id": 79, "row_count": 11, "row_ids_sha256": "d4283f3b6328de3c33e6dec769a09aef4a972438730c606ce730f000785c11e2", "input_ids_vector_sha256": "94284a6dfc7307892e4d946145701135bbdd12825250c589fed5929725d6e19e", "labels_vector_sha256": "75dd57af1cf18d328a98e4f593bd5c97839f07186688f8ca9514df7c4b157126", "planned_active_tokens": 67486, "realized_active_tokens": 67486, "cumulative_start": 5184534, "cumulative_end": 5252020, "loss_sum": 27253.045837402344, "token_normalized_loss": 0.40383258509027564, "grad_norm_before_clip": 0.07880351692438126, "learning_rates_at_step": { "lora": 9.987384681142344e-05, "row_tokens": 9.987384681142344e-05 }, "learning_rates_after_step": { "lora": 9.986314994242357e-05, "row_tokens": 9.986314994242357e-05 } }, { "update_id": 80, "row_count": 10, "row_ids_sha256": "96f3bfe29158ffc6e3e599a6f66794d575e57c97f65ca3cacf6ce3ca3ea82dd1", "input_ids_vector_sha256": "d7bab4b196007cf317af28f4fffeea4167a916246494362b7890c0a53c828a0a", "labels_vector_sha256": "a717518feee3075b1723734c41557c2b81e876f2480af8567b960666784faf4e", "planned_active_tokens": 57095, "realized_active_tokens": 57095, "cumulative_start": 5252020, "cumulative_end": 5309115, "loss_sum": 22288.822326660156, "token_normalized_loss": 0.39038133508468614, "grad_norm_before_clip": 0.0819566398859024, "learning_rates_at_step": { "lora": 9.986314994242357e-05, "row_tokens": 9.986314994242357e-05 }, "learning_rates_after_step": { "lora": 9.984985455102489e-05, "row_tokens": 9.984985455102489e-05 } }, { "update_id": 81, "row_count": 13, "row_ids_sha256": "6c99f29361158171a41be30d169c57bae565cf1bff23b90a63f84fb9bb2e2622", "input_ids_vector_sha256": "929157d95822fe10934f2d4303b51ff8f28714970f718195ba08811b277f451f", "labels_vector_sha256": "20f85bae88f8021c6c7b66a6a1d525bb95c98f719d0c2eac383f4fdfeab7e6e7", "planned_active_tokens": 67942, "realized_active_tokens": 67942, "cumulative_start": 5309115, "cumulative_end": 5377057, "loss_sum": 28673.272399902344, "token_normalized_loss": 0.42202573371261287, "grad_norm_before_clip": 0.08162650465965271, "learning_rates_at_step": { "lora": 9.984985455102489e-05, "row_tokens": 9.984985455102489e-05 }, "learning_rates_after_step": { "lora": 9.983684647029269e-05, "row_tokens": 9.983684647029269e-05 } }, { "update_id": 82, "row_count": 9, "row_ids_sha256": "60318d84e9ecb96fbc8567ea58609afc68ee2f2102ae2b5a33d442892b59b88b", "input_ids_vector_sha256": "878e9f7ad1840bb7301d502917ee8353f672a422666980f5cb0ba2f02e03eb3d", "labels_vector_sha256": "dd4b673971dba08babd068e9252114f6ffde00539fc47fd5650d41e7dbcc42dd", "planned_active_tokens": 63623, "realized_active_tokens": 63623, "cumulative_start": 5377057, "cumulative_end": 5440680, "loss_sum": 25522.724731445312, "token_normalized_loss": 0.4011556313195749, "grad_norm_before_clip": 0.07837644219398499, "learning_rates_at_step": { "lora": 9.983684647029269e-05, "row_tokens": 9.983684647029269e-05 }, "learning_rates_after_step": { "lora": 9.98231039095416e-05, "row_tokens": 9.98231039095416e-05 } }, { "update_id": 83, "row_count": 12, "row_ids_sha256": "c69e9657af55987cdcdde3cd81abc457361f2b96ed4a3c1dbc9678a0812d70bd", "input_ids_vector_sha256": "3d2dd1416f29fbceab726337d58231d8af4ad9d40dffe4e844673022083845ec", "labels_vector_sha256": "8a72c1305dff89109e65733ef8c60df0d89ac4b26234d3baa866937d92b67bfa", "planned_active_tokens": 64521, "realized_active_tokens": 64521, "cumulative_start": 5440680, "cumulative_end": 5505201, "loss_sum": 24047.96240234375, "token_normalized_loss": 0.37271527723289705, "grad_norm_before_clip": 0.07615505903959274, "learning_rates_at_step": { "lora": 9.98231039095416e-05, "row_tokens": 9.98231039095416e-05 }, "learning_rates_after_step": { "lora": 9.980780613897258e-05, "row_tokens": 9.980780613897258e-05 } }, { "update_id": 84, "row_count": 15, "row_ids_sha256": "3b3ed3fb9f4d1be55ce4861c0f623f750ba03b129c12c6bb74508223a79a31fc", "input_ids_vector_sha256": "72e6edaf5a5508c66abd519521fa827982d47a84e13bc92e2bef73e0d384f715", "labels_vector_sha256": "91518ab0954bdbc889752e428e9a31cd7871187e7fe9d003eb5dc629dbdf17f3", "planned_active_tokens": 68945, "realized_active_tokens": 68945, "cumulative_start": 5505201, "cumulative_end": 5574146, "loss_sum": 24120.388244628906, "token_normalized_loss": 0.3498497098357953, "grad_norm_before_clip": 0.07256969064474106, "learning_rates_at_step": { "lora": 9.980780613897258e-05, "row_tokens": 9.980780613897258e-05 }, "learning_rates_after_step": { "lora": 9.979198912222123e-05, "row_tokens": 9.979198912222123e-05 } }, { "update_id": 85, "row_count": 8, "row_ids_sha256": "c0b8f8b09642fa84dfb94205de031e3b7aad1a2176835b2114abc6ec755282ae", "input_ids_vector_sha256": "45af8d00febd8d336b9928d7b56944fadd9c9f41d2c849f36c870ac9606e2601", "labels_vector_sha256": "7777c8edb49871cb32b42fab42f9c9a56fddf0ff0916367f553ef4894f84fae3", "planned_active_tokens": 68462, "realized_active_tokens": 68462, "cumulative_start": 5574146, "cumulative_end": 5642608, "loss_sum": 29144.711303710938, "token_normalized_loss": 0.4257063963032184, "grad_norm_before_clip": 0.08233818411827087, "learning_rates_at_step": { "lora": 9.979198912222123e-05, "row_tokens": 9.979198912222123e-05 }, "learning_rates_after_step": { "lora": 9.977741253105889e-05, "row_tokens": 9.977741253105889e-05 } }, { "update_id": 86, "row_count": 9, "row_ids_sha256": "4abc7dab2ad9ad2081e550a071284774c4faa58640f9335d49f9c7f91a1fa5d7", "input_ids_vector_sha256": "d00f61ceec5afca732d24bd55a1b2aa9aa93484ae1cde5c42e693e2ab36e03c9", "labels_vector_sha256": "e3bf5de2eee1ff9a46680a8dd76543ad19d5e685bceba6260f29413d65b8cbec", "planned_active_tokens": 60827, "realized_active_tokens": 60827, "cumulative_start": 5642608, "cumulative_end": 5703435, "loss_sum": 23325.3935546875, "token_normalized_loss": 0.38347104993978826, "grad_norm_before_clip": 0.07935347408056259, "learning_rates_at_step": { "lora": 9.977741253105889e-05, "row_tokens": 9.977741253105889e-05 }, "learning_rates_after_step": { "lora": 9.975990632181797e-05, "row_tokens": 9.975990632181797e-05 } }, { "update_id": 87, "row_count": 11, "row_ids_sha256": "d05f1d6123bde01de732103bfe9a5cdc4732a7ff5a9b554150ba3ff59fd6854d", "input_ids_vector_sha256": "4f23ec55852f0b323b3fdd2d4bc319c23634ecf3333c4658b599c2edede7616b", "labels_vector_sha256": "35480d52b3348b91a04e060816486d09b9739c5eb40867b5b716e2f6e4a16289", "planned_active_tokens": 70482, "realized_active_tokens": 70482, "cumulative_start": 5703435, "cumulative_end": 5773917, "loss_sum": 26511.458435058594, "token_normalized_loss": 0.37614509286141984, "grad_norm_before_clip": 0.07700742781162262, "learning_rates_at_step": { "lora": 9.975990632181797e-05, "row_tokens": 9.975990632181797e-05 }, "learning_rates_after_step": { "lora": 9.974365302111804e-05, "row_tokens": 9.974365302111804e-05 } }, { "update_id": 88, "row_count": 10, "row_ids_sha256": "6968b4b1d2d72bff969bc23b5ebdd035b734fe1e8f36e884957b450072fc51d7", "input_ids_vector_sha256": "8390e408450e34d73aedfc88b5228767ba61a42861026f1fd04d232e2cb51942", "labels_vector_sha256": "90a64ee53591416aa9768a5f842a3932e187d1b058d69c558ea31f0c52c5648e", "planned_active_tokens": 63176, "realized_active_tokens": 63176, "cumulative_start": 5773917, "cumulative_end": 5837093, "loss_sum": 23242.303161621094, "token_normalized_loss": 0.36789766939377444, "grad_norm_before_clip": 0.07671137899160385, "learning_rates_at_step": { "lora": 9.974365302111804e-05, "row_tokens": 9.974365302111804e-05 }, "learning_rates_after_step": { "lora": 9.97260224254965e-05, "row_tokens": 9.97260224254965e-05 } }, { "update_id": 89, "row_count": 13, "row_ids_sha256": "e4971127b0446b1ec8f4b3e37b117c3186dc9d0aac51942f4053b80e3c37529e", "input_ids_vector_sha256": "c9a57e9d644f2533daa94b4971720a4e670cb03862b60f4d1a8cff7934c8798b", "labels_vector_sha256": "6669ab75fcf7d68fceb1463a9c0a0080a08dbaa230fba4bb7a85348956741da3", "planned_active_tokens": 66310, "realized_active_tokens": 66310, "cumulative_start": 5837093, "cumulative_end": 5903403, "loss_sum": 25172.8466796875, "token_normalized_loss": 0.3796236869203363, "grad_norm_before_clip": 0.07664631307125092, "learning_rates_at_step": { "lora": 9.97260224254965e-05, "row_tokens": 9.97260224254965e-05 }, "learning_rates_after_step": { "lora": 9.970840557824979e-05, "row_tokens": 9.970840557824979e-05 } }, { "update_id": 90, "row_count": 9, "row_ids_sha256": "86f5136fcc7725e1bb0a542a28e1efa5d0b1b37ec5f444be9f13bfab088d61d2", "input_ids_vector_sha256": "ad339163688e37ec0ffa9b06dd4bb81d28f3ff9e60f3804c55c78410e936ef22", "labels_vector_sha256": "13dd444a4f95bae5438926c07b969523e13d3b8a7df2c34ccdac2276685f78d2", "planned_active_tokens": 64165, "realized_active_tokens": 64165, "cumulative_start": 5903403, "cumulative_end": 5967568, "loss_sum": 27459.687622070312, "token_normalized_loss": 0.427954299416665, "grad_norm_before_clip": 0.08326901495456696, "learning_rates_at_step": { "lora": 9.970840557824979e-05, "row_tokens": 9.970840557824979e-05 }, "learning_rates_after_step": { "lora": 9.968939181961605e-05, "row_tokens": 9.968939181961605e-05 } }, { "update_id": 91, "row_count": 8, "row_ids_sha256": "273658ae04efa2c05943907b3ea3606efe5d9d10e80ebe3b01f1f9f5be9e4f1f", "input_ids_vector_sha256": "f65c2c802f867e5891b1cf82cba70d6b100d85a2b3d06b2a159ede1122d54a2a", "labels_vector_sha256": "a6c918aedd797156891f78df4bc2c1eb13346ac2d362493e9034c67d7c420c01", "planned_active_tokens": 67120, "realized_active_tokens": 67120, "cumulative_start": 5967568, "cumulative_end": 6034688, "loss_sum": 31324.492431640625, "token_normalized_loss": 0.46669386817104624, "grad_norm_before_clip": 0.09153497964143753, "learning_rates_at_step": { "lora": 9.968939181961605e-05, "row_tokens": 9.968939181961605e-05 }, "learning_rates_after_step": { "lora": 9.967012798416968e-05, "row_tokens": 9.967012798416968e-05 } }, { "update_id": 92, "row_count": 9, "row_ids_sha256": "ed90d2875aa9235ef988daf58f32cc92ba1252b37c331b9ee546a8aae5573d9c", "input_ids_vector_sha256": "45a1861706bdb155d9d3bef1e57fd5b27e527a348ee6e5d72ae28da053251830", "labels_vector_sha256": "96a54cf58c7883c1638c599fd562325f955f3f740b0533e91fa78c3874839426", "planned_active_tokens": 65945, "realized_active_tokens": 65945, "cumulative_start": 6034688, "cumulative_end": 6100633, "loss_sum": 31839.517028808594, "token_normalized_loss": 0.48281927407397973, "grad_norm_before_clip": 0.08663981407880783, "learning_rates_at_step": { "lora": 9.967012798416968e-05, "row_tokens": 9.967012798416968e-05 }, "learning_rates_after_step": { "lora": 9.965008265003743e-05, "row_tokens": 9.965008265003743e-05 } }, { "update_id": 93, "row_count": 9, "row_ids_sha256": "f0f4db0d6258d0c06a6f2244daecfb066b201f2ad3471dc6d4da5fef3a49aed7", "input_ids_vector_sha256": "12615427f7029f36df437f3f0f5d172379094d0afdb2bfb74df60fac749fed7e", "labels_vector_sha256": "486db9eff37938bfb1fe1835427c100bd7b8de53f0f9efc94a21018b5f890706", "planned_active_tokens": 66613, "realized_active_tokens": 66613, "cumulative_start": 6100633, "cumulative_end": 6167246, "loss_sum": 28745.52899169922, "token_normalized_loss": 0.4315303167804966, "grad_norm_before_clip": 0.0810093954205513, "learning_rates_at_step": { "lora": 9.965008265003743e-05, "row_tokens": 9.965008265003743e-05 }, "learning_rates_after_step": { "lora": 9.963188420234777e-05, "row_tokens": 9.963188420234777e-05 } }, { "update_id": 94, "row_count": 10, "row_ids_sha256": "e0e393fee0fe09e1c15da1ec147aa5f5132f20bf0185345331e5d925bf6c6b45", "input_ids_vector_sha256": "f296094a89afef0d6cb979828952ea9886fd69ed7f96528e27149949f11bece5", "labels_vector_sha256": "a6cc1beb7cdd97a6b20f4d595c2d6aade145f440d39a9ce164d8110a6b039519", "planned_active_tokens": 58847, "realized_active_tokens": 58847, "cumulative_start": 6167246, "cumulative_end": 6226093, "loss_sum": 24224.678588867188, "token_normalized_loss": 0.411655285551807, "grad_norm_before_clip": 0.08718361705541611, "learning_rates_at_step": { "lora": 9.963188420234777e-05, "row_tokens": 9.963188420234777e-05 }, "learning_rates_after_step": { "lora": 9.960855020276933e-05, "row_tokens": 9.960855020276933e-05 } }, { "update_id": 95, "row_count": 12, "row_ids_sha256": "55b06f2a29e2da2cde0ec9fb2fd09ca75d238b9565a367fb787efe77981b2697", "input_ids_vector_sha256": "990596abb219b042a5f1e4200cb123fde8fa0491f96dc2f99cdd973ae8b721b2", "labels_vector_sha256": "9050981405b6963ba9733d72cb231dc379833385c3fedfc32facffde725860e3", "planned_active_tokens": 73372, "realized_active_tokens": 73372, "cumulative_start": 6226093, "cumulative_end": 6299465, "loss_sum": 29446.130859375, "token_normalized_loss": 0.4013265395433544, "grad_norm_before_clip": 0.07392188906669617, "learning_rates_at_step": { "lora": 9.960855020276933e-05, "row_tokens": 9.960855020276933e-05 }, "learning_rates_after_step": { "lora": 9.958864818433942e-05, "row_tokens": 9.958864818433942e-05 } }, { "update_id": 96, "row_count": 11, "row_ids_sha256": "363c54335ea60da2eb1617c58713f2c39f7f8758842f6d267d25c5103c750d72", "input_ids_vector_sha256": "a9605675be4e56d2842fa3276d9b68f25a7d9b0cb5ae8b19add2b28568467593", "labels_vector_sha256": "5eb60003695c47e19098b93c7eee74714c1a5eee878f3a144ea4fc7c27d12c3c", "planned_active_tokens": 60876, "realized_active_tokens": 60876, "cumulative_start": 6299465, "cumulative_end": 6360341, "loss_sum": 25638.18424987793, "token_normalized_loss": 0.42115421923053303, "grad_norm_before_clip": 0.08538123965263367, "learning_rates_at_step": { "lora": 9.958864818433942e-05, "row_tokens": 9.958864818433942e-05 }, "learning_rates_after_step": { "lora": 9.956556072872382e-05, "row_tokens": 9.956556072872382e-05 } }, { "update_id": 97, "row_count": 12, "row_ids_sha256": "7c72e5cc006324961b2fe8b41a18e44c4b7b58f574278fd7add7fc177bc1f84f", "input_ids_vector_sha256": "7035cfa0092bbdeb189efa8fb4b0ce57341493e185c406cb5a5f9d7b499d70c7", "labels_vector_sha256": "0f384f7a57a279ab87021f5e679a02cf2aacb4a68837ad69c60d89ffc063a8bc", "planned_active_tokens": 68810, "realized_active_tokens": 68810, "cumulative_start": 6360341, "cumulative_end": 6429151, "loss_sum": 26964.084838867188, "token_normalized_loss": 0.3918628809601393, "grad_norm_before_clip": 0.08256465941667557, "learning_rates_at_step": { "lora": 9.956556072872382e-05, "row_tokens": 9.956556072872382e-05 }, "learning_rates_after_step": { "lora": 9.954225284431694e-05, "row_tokens": 9.954225284431694e-05 } }, { "update_id": 98, "row_count": 11, "row_ids_sha256": "f09bbb949b2307ba704d4757e526356b11fecbc74fb0af7a2f539668c126bbad", "input_ids_vector_sha256": "7de5452ad979a56ed35ff5e3601f741b0abbad48c4be2301f93360f92b478fc6", "labels_vector_sha256": "294f83d32b13e04e01fc54d8066ece31b0c307eb54dda0168522660be196155d", "planned_active_tokens": 67644, "realized_active_tokens": 67644, "cumulative_start": 6429151, "cumulative_end": 6496795, "loss_sum": 28534.450561523438, "token_normalized_loss": 0.42183269117029504, "grad_norm_before_clip": 0.08756575733423233, "learning_rates_at_step": { "lora": 9.954225284431694e-05, "row_tokens": 9.954225284431694e-05 }, "learning_rates_after_step": { "lora": 9.952109797341398e-05, "row_tokens": 9.952109797341398e-05 } }, { "update_id": 99, "row_count": 11, "row_ids_sha256": "d402c6915bea979d42be21cddb4a0188872cdf805477aa53c6736f135f683464", "input_ids_vector_sha256": "d653cfb1f4a16df2317fc12b821aaf3024182092bc1647b33d0a7a0bed551e07", "labels_vector_sha256": "9066277cbc7d639d3f619ec67d6481cb4db39c9121da2f0a84acf44f00cec4a1", "planned_active_tokens": 59926, "realized_active_tokens": 59926, "cumulative_start": 6496795, "cumulative_end": 6556721, "loss_sum": 23778.8134765625, "token_normalized_loss": 0.3968029482455445, "grad_norm_before_clip": 0.08255874365568161, "learning_rates_at_step": { "lora": 9.952109797341398e-05, "row_tokens": 9.952109797341398e-05 }, "learning_rates_after_step": { "lora": 9.949723474507021e-05, "row_tokens": 9.949723474507021e-05 } }, { "update_id": 100, "row_count": 12, "row_ids_sha256": "1262179d2f149441a1387952bd904a0b0fd87263449e17ed17ab66e316979170", "input_ids_vector_sha256": "d5d802f86d1f4e1864f47161659046fe503aecd989e7bf930fc50a4c744a1a1c", "labels_vector_sha256": "8a0915bec589c9acd0e63a92786e91929fa4cb65bfb658a3d1a27972e1ec7c0f", "planned_active_tokens": 66038, "realized_active_tokens": 66038, "cumulative_start": 6556721, "cumulative_end": 6622759, "loss_sum": 24899.327270507812, "token_normalized_loss": 0.37704544762875636, "grad_norm_before_clip": 0.08221735060214996, "learning_rates_at_step": { "lora": 9.949723474507021e-05, "row_tokens": 9.949723474507021e-05 }, "learning_rates_after_step": { "lora": 9.94739582895791e-05, "row_tokens": 9.94739582895791e-05 } }, { "update_id": 101, "row_count": 12, "row_ids_sha256": "c5c86250f5e2f2f5f4830f138f80796ebf7da448ae471620916a1c1dd376f25e", "input_ids_vector_sha256": "ce11cc86fa109b57b49187b5d4226adf63e1013f5408a69cdd22921bfef504f6", "labels_vector_sha256": "4c30cccd21d580ee6e7727877f5a6fe1de646732b6f497ab5c2868f5e0e8465d", "planned_active_tokens": 62928, "realized_active_tokens": 62928, "cumulative_start": 6622759, "cumulative_end": 6685687, "loss_sum": 27849.043701171875, "token_normalized_loss": 0.44255408881852076, "grad_norm_before_clip": 0.09509769827127457, "learning_rates_at_step": { "lora": 9.94739582895791e-05, "row_tokens": 9.94739582895791e-05 }, "learning_rates_after_step": { "lora": 9.944790350470843e-05, "row_tokens": 9.944790350470843e-05 } }, { "update_id": 102, "row_count": 11, "row_ids_sha256": "1f46fecf9be40765728ef411204fbe183ace2d3b33936c516b8b47dcd2c2c6df", "input_ids_vector_sha256": "4e43bc563f57b25ff42f1e46575e94c717787179da193dfc71bf1e924ee5cd5b", "labels_vector_sha256": "1feeff34b63e9b658724958929bc3bbc209630fb8eaa9dbc27b539fe816f8596", "planned_active_tokens": 68818, "realized_active_tokens": 68818, "cumulative_start": 6685687, "cumulative_end": 6754505, "loss_sum": 28828.086547851562, "token_normalized_loss": 0.41890328907918806, "grad_norm_before_clip": 0.08459773659706116, "learning_rates_at_step": { "lora": 9.944790350470843e-05, "row_tokens": 9.944790350470843e-05 }, "learning_rates_after_step": { "lora": 9.942213574891903e-05, "row_tokens": 9.942213574891903e-05 } }, { "update_id": 103, "row_count": 12, "row_ids_sha256": "249938bfe6972b98186420f65e1ae79275ccc05d7c0bd0bafa2ccfa34d86a3d8", "input_ids_vector_sha256": "99a41248cd4e72d814728a7b623337ecfc2c720b83a6c97bd1ac97d6d141a695", "labels_vector_sha256": "281430599d6c39b641e57cf4404d765a02935d1478284d4832ce5425d99dc46f", "planned_active_tokens": 66489, "realized_active_tokens": 66489, "cumulative_start": 6754505, "cumulative_end": 6820994, "loss_sum": 25730.649169921875, "token_normalized_loss": 0.386991068747039, "grad_norm_before_clip": 0.08044266700744629, "learning_rates_at_step": { "lora": 9.942213574891903e-05, "row_tokens": 9.942213574891903e-05 }, "learning_rates_after_step": { "lora": 9.93948393185295e-05, "row_tokens": 9.93948393185295e-05 } }, { "update_id": 104, "row_count": 10, "row_ids_sha256": "c6fbeaa7ac45afdfdef207fe0b7cb7c13d12a2ab7a13b57c600afb7e2379fd66", "input_ids_vector_sha256": "dbc38cbccd2bfa7f798a05be02e35a7eeeacd144b41c6244ebf76d78c4f835a5", "labels_vector_sha256": "061da73761dba03093c31e5eb71fdf9bc2b8e6fa503be1c808e6049a4103a8e7", "planned_active_tokens": 68845, "realized_active_tokens": 68845, "cumulative_start": 6820994, "cumulative_end": 6889839, "loss_sum": 23824.658416748047, "token_normalized_loss": 0.3460622908961878, "grad_norm_before_clip": 0.07725279778242111, "learning_rates_at_step": { "lora": 9.93948393185295e-05, "row_tokens": 9.93948393185295e-05 }, "learning_rates_after_step": { "lora": 9.937168716790695e-05, "row_tokens": 9.937168716790695e-05 } }, { "update_id": 105, "row_count": 10, "row_ids_sha256": "63f2451bb4ac6bf732c93055c444c0479a6cccc182332cd980d217e3f08f3710", "input_ids_vector_sha256": "e8fc8006e223568f483990d141ab7424782d530f1826320892fb6b81468b786d", "labels_vector_sha256": "71540914e6a1bccfdada2d07d7fd3160cc6ac5be22d7b70824cdd18dd0d309e1", "planned_active_tokens": 57192, "realized_active_tokens": 57192, "cumulative_start": 6889839, "cumulative_end": 6947031, "loss_sum": 22523.593383789062, "token_normalized_loss": 0.39382419540825747, "grad_norm_before_clip": 0.09234721958637238, "learning_rates_at_step": { "lora": 9.937168716790695e-05, "row_tokens": 9.937168716790695e-05 }, "learning_rates_after_step": { "lora": 9.934396069818935e-05, "row_tokens": 9.934396069818935e-05 } }, { "update_id": 106, "row_count": 11, "row_ids_sha256": "a782fbf55c2d5a1fe9b58c3174d8f2c7fb76e66a9d095aa111b26d228d59b6cd", "input_ids_vector_sha256": "449fdac645faba2ecf78cee14476941c320b87c2816c0df471a1d15f315fa8ab", "labels_vector_sha256": "280398db1dff7bbcee5f5d09ac26abbef0ea6713db6558f5a006105f8f12ef6b", "planned_active_tokens": 67131, "realized_active_tokens": 67131, "cumulative_start": 6947031, "cumulative_end": 7014162, "loss_sum": 25866.519165039062, "token_normalized_loss": 0.38531407494360376, "grad_norm_before_clip": 0.0854402706027031, "learning_rates_at_step": { "lora": 9.934396069818935e-05, "row_tokens": 9.934396069818935e-05 }, "learning_rates_after_step": { "lora": 9.931634158388093e-05, "row_tokens": 9.931634158388093e-05 } }, { "update_id": 107, "row_count": 12, "row_ids_sha256": "dbc351cd523f0addce30591955726bb85511dae0f5497eb66de2b79184867277", "input_ids_vector_sha256": "b6de1be9943bfea9646cfe639bcdcdde249fbb6258b68cae34003d6a6eb77a19", "labels_vector_sha256": "cfd78e258ca6cee741a30e052cc3def520460b324a299a520cf89d7276c0c265", "planned_active_tokens": 65484, "realized_active_tokens": 65484, "cumulative_start": 7014162, "cumulative_end": 7079646, "loss_sum": 25485.252807617188, "token_normalized_loss": 0.3891828967017468, "grad_norm_before_clip": 0.08194433897733688, "learning_rates_at_step": { "lora": 9.931634158388093e-05, "row_tokens": 9.931634158388093e-05 }, "learning_rates_after_step": { "lora": 9.928748912965441e-05, "row_tokens": 9.928748912965441e-05 } }, { "update_id": 108, "row_count": 11, "row_ids_sha256": "1f0f347613271d2f6877c70241c7289867b6c5610984b95d7103ee8b928d7c6a", "input_ids_vector_sha256": "7e5e37e8832a868f0f3e8f5a0464aa9de2f77ada8b5d3ecdbfaf418577ba00b2", "labels_vector_sha256": "b3912dea93e1cc92bb850dcc0b743a55d2efbbfef3c99b82aee38c2b9d4131c1", "planned_active_tokens": 67020, "realized_active_tokens": 67020, "cumulative_start": 7079646, "cumulative_end": 7146666, "loss_sum": 27263.20379638672, "token_normalized_loss": 0.40679205903292626, "grad_norm_before_clip": 0.0845848098397255, "learning_rates_at_step": { "lora": 9.928748912965441e-05, "row_tokens": 9.928748912965441e-05 }, "learning_rates_after_step": { "lora": 9.925585098750395e-05, "row_tokens": 9.925585098750395e-05 } }, { "update_id": 109, "row_count": 12, "row_ids_sha256": "ac2ecddb956db4605ebb214bcdda3c274539a9e2e715b983b23d04e761792d7b", "input_ids_vector_sha256": "d3244ef85001399f84ffb4907f8015252cbfcecfd23910af07160fdfd7ffa950", "labels_vector_sha256": "efff4b0af45f637ded1df9e4f80bd4492bf03e867d27092097fd96a93a5662fe", "planned_active_tokens": 71960, "realized_active_tokens": 71960, "cumulative_start": 7146666, "cumulative_end": 7218626, "loss_sum": 27900.459899902344, "token_normalized_loss": 0.3877217884922505, "grad_norm_before_clip": 0.07925325632095337, "learning_rates_at_step": { "lora": 9.925585098750395e-05, "row_tokens": 9.925585098750395e-05 }, "learning_rates_after_step": { "lora": 9.922731568753672e-05, "row_tokens": 9.922731568753672e-05 } }, { "update_id": 110, "row_count": 12, "row_ids_sha256": "dd7cafcb9954bd718c993705c0bbfef46375cd2064f4acf1007243b77553ce35", "input_ids_vector_sha256": "8dcd5416f20e98418a56f3a52427e68408a9b53fa138adfcd1ce2b87e3ae5679", "labels_vector_sha256": "9950537045a1d36fd70e0475159ababc3d8a251327441132ca84876275cbe8ce", "planned_active_tokens": 63611, "realized_active_tokens": 63611, "cumulative_start": 7218626, "cumulative_end": 7282237, "loss_sum": 21323.027313232422, "token_normalized_loss": 0.3352097485219918, "grad_norm_before_clip": 0.08110537379980087, "learning_rates_at_step": { "lora": 9.922731568753672e-05, "row_tokens": 9.922731568753672e-05 }, "learning_rates_after_step": { "lora": 9.92007075156098e-05, "row_tokens": 9.92007075156098e-05 } }, { "update_id": 111, "row_count": 10, "row_ids_sha256": "a889aaa4e345e2e388194031e4b06921c021cd6b8d3b2b2dd38d99c78ce0e3a6", "input_ids_vector_sha256": "fc6595bd4e866d0527ffddc7d90edc6984fab1909266925a917712882b0c875d", "labels_vector_sha256": "5444a4b963545494cb845387f2f75bbe5a1118084bc15cae24d1451bd15a5093", "planned_active_tokens": 58273, "realized_active_tokens": 58273, "cumulative_start": 7282237, "cumulative_end": 7340510, "loss_sum": 23471.60626220703, "token_normalized_loss": 0.4027869898959558, "grad_norm_before_clip": 0.09559818357229233, "learning_rates_at_step": { "lora": 9.92007075156098e-05, "row_tokens": 9.92007075156098e-05 }, "learning_rates_after_step": { "lora": 9.916864898793246e-05, "row_tokens": 9.916864898793246e-05 } }, { "update_id": 112, "row_count": 13, "row_ids_sha256": "f0a1a6d6e6a3b5d4eb9d982ba777c2b811e2df468382689abeb4ab6b9be604f7", "input_ids_vector_sha256": "44a99fc5d997ee8cd561cbd499f6a2fd7e57b71b0e218793b7f39b918c5f1bd4", "labels_vector_sha256": "41b4fc22bb08b19074997710028deb19e2894e0b5c7e86fe752fa883b7272dae", "planned_active_tokens": 68946, "realized_active_tokens": 68946, "cumulative_start": 7340510, "cumulative_end": 7409456, "loss_sum": 23896.96011352539, "token_normalized_loss": 0.3466040105811126, "grad_norm_before_clip": 0.08231980353593826, "learning_rates_at_step": { "lora": 9.916864898793246e-05, "row_tokens": 9.916864898793246e-05 }, "learning_rates_after_step": { "lora": 9.913781756969285e-05, "row_tokens": 9.913781756969285e-05 } }, { "update_id": 113, "row_count": 10, "row_ids_sha256": "2f7a5e8fd9b0fbb0402f4c06534ae875e7f51b6ee81f32a1e37807bc530d6ea3", "input_ids_vector_sha256": "998c4c0841f39be451a90c94edd282d046783f56b357320db8b7c9bd39082875", "labels_vector_sha256": "6e43384574e4b2c3cf0ac22c8fb59139a418eb1d2863153cd64e8f7cf4bec5ff", "planned_active_tokens": 65074, "realized_active_tokens": 65074, "cumulative_start": 7409456, "cumulative_end": 7474530, "loss_sum": 25267.777954101562, "token_normalized_loss": 0.38829298881429697, "grad_norm_before_clip": 0.0813005268573761, "learning_rates_at_step": { "lora": 9.913781756969285e-05, "row_tokens": 9.913781756969285e-05 }, "learning_rates_after_step": { "lora": 9.910506869293945e-05, "row_tokens": 9.910506869293945e-05 } }, { "update_id": 114, "row_count": 12, "row_ids_sha256": "9b046588175990e361e4297d50908d2370ce65b70cd1f54f919bfb9437646d8f", "input_ids_vector_sha256": "140e1962367fa9f4deb03497bc2f7dd2e43b1db1eb48a4b6a856b6762fbd83b9", "labels_vector_sha256": "8beb9adc17db93ef102caf6f0280055b7eb5d09ef2c3bfb9b46738e835a14d47", "planned_active_tokens": 67870, "realized_active_tokens": 67870, "cumulative_start": 7474530, "cumulative_end": 7542400, "loss_sum": 25254.611938476562, "token_normalized_loss": 0.3721027248928328, "grad_norm_before_clip": 0.07928209006786346, "learning_rates_at_step": { "lora": 9.910506869293945e-05, "row_tokens": 9.910506869293945e-05 }, "learning_rates_after_step": { "lora": 9.90752493363739e-05, "row_tokens": 9.90752493363739e-05 } }, { "update_id": 115, "row_count": 10, "row_ids_sha256": "0e949f7ef33589c54dbd1c63e0b7b00aa2eaa3362258a6395f4aaa3d7e4d0952", "input_ids_vector_sha256": "25681924d7edfa9f469d525ab0dc32e7d962a217cd6252b36bbb81b0e37dd146", "labels_vector_sha256": "0706ae26c781691473d72cdcc5506ad2e3db341f09dfa824715468b4efa6b3f6", "planned_active_tokens": 60736, "realized_active_tokens": 60736, "cumulative_start": 7542400, "cumulative_end": 7603136, "loss_sum": 22527.82940673828, "token_normalized_loss": 0.37091394571157604, "grad_norm_before_clip": 0.08142638951539993, "learning_rates_at_step": { "lora": 9.90752493363739e-05, "row_tokens": 9.90752493363739e-05 }, "learning_rates_after_step": { "lora": 9.904075407297466e-05, "row_tokens": 9.904075407297466e-05 } }, { "update_id": 116, "row_count": 10, "row_ids_sha256": "5f3028c10a882a169bac0cdc6fd1fb00b24c049e323cd07e8183c2cd622f9ad4", "input_ids_vector_sha256": "1d598f2fc9d14ffece961ede46ebefa70cba9727322d0cfaa3ea5ad6b4369454", "labels_vector_sha256": "0de28ed9fdf3e03b3456b2569a7d792383fa807d16853a2dc8d5ea1be3ba5106", "planned_active_tokens": 69062, "realized_active_tokens": 69062, "cumulative_start": 7603136, "cumulative_end": 7672198, "loss_sum": 32729.186462402344, "token_normalized_loss": 0.4739102033303748, "grad_norm_before_clip": 0.09517966955900192, "learning_rates_at_step": { "lora": 9.904075407297466e-05, "row_tokens": 9.904075407297466e-05 }, "learning_rates_after_step": { "lora": 9.900589606082425e-05, "row_tokens": 9.900589606082425e-05 } }, { "update_id": 117, "row_count": 16, "row_ids_sha256": "4d2c1c8e503f49c6e309245a35d27d883ebe7a414270082a759e69713e0249a7", "input_ids_vector_sha256": "cb9b91f275e257575cda9cdeb5d07314acc250dc3acebf19613756edd317a006", "labels_vector_sha256": "26558e77fdf2d95a1a4ceec699c580699c95d5948f4618eba3e5a5e075c460a2", "planned_active_tokens": 68550, "realized_active_tokens": 68550, "cumulative_start": 7672198, "cumulative_end": 7740748, "loss_sum": 27882.189575195312, "token_normalized_loss": 0.40674237162939914, "grad_norm_before_clip": 0.08357814699411392, "learning_rates_at_step": { "lora": 9.900589606082425e-05, "row_tokens": 9.900589606082425e-05 }, "learning_rates_after_step": { "lora": 9.897308685206417e-05, "row_tokens": 9.897308685206417e-05 } }, { "update_id": 118, "row_count": 10, "row_ids_sha256": "804d67e3815c071a5ad9cde5cc2d8682bc7c55db8a33b4b9f51b55923113ab5d", "input_ids_vector_sha256": "21f6dc5dc7e2a0b493fa2361bd57f8d6e082cdbcdc1c01c7daaa93f28adce76c", "labels_vector_sha256": "2e2c9a1e77206b387ebe4eeeae4c172b47f6e42e1052fbcb724bf1af0a19e30f", "planned_active_tokens": 63442, "realized_active_tokens": 63442, "cumulative_start": 7740748, "cumulative_end": 7804190, "loss_sum": 27165.241455078125, "token_normalized_loss": 0.42819018087510047, "grad_norm_before_clip": 0.08549845963716507, "learning_rates_at_step": { "lora": 9.897308685206417e-05, "row_tokens": 9.897308685206417e-05 }, "learning_rates_after_step": { "lora": 9.89402997355009e-05, "row_tokens": 9.89402997355009e-05 } }, { "update_id": 119, "row_count": 10, "row_ids_sha256": "1ea9b57c57e9269cb64217d2fab06fded8f2e15d686c73892e6db5c3122d5cd2", "input_ids_vector_sha256": "251c027bfd264cf8b99bb8c899471d4d4803eff00a693bd1fd729b8b327c5d66", "labels_vector_sha256": "2e640194ed629dcb3c6a5df5b6852d3a9ac88819e1184070199a1a7eb1573e80", "planned_active_tokens": 62405, "realized_active_tokens": 62405, "cumulative_start": 7804190, "cumulative_end": 7866595, "loss_sum": 23584.56201171875, "token_normalized_loss": 0.37792744189918676, "grad_norm_before_clip": 0.08081217855215073, "learning_rates_at_step": { "lora": 9.89402997355009e-05, "row_tokens": 9.89402997355009e-05 }, "learning_rates_after_step": { "lora": 9.890504512810954e-05, "row_tokens": 9.890504512810954e-05 } }, { "update_id": 120, "row_count": 9, "row_ids_sha256": "39092eafdbf77eba3fe1ab05c7e9e42a78d46e07fb970975ae383dde22ab854e", "input_ids_vector_sha256": "b11bda5f2e848fa47d5b7ac829ff9692772826e6e49774697736d7b9b9aaabec", "labels_vector_sha256": "e70afce70c84fdce69003cb24db581bbf2ae42423e26df11f55b2dfd668a1ed0", "planned_active_tokens": 66045, "realized_active_tokens": 66045, "cumulative_start": 7866595, "cumulative_end": 7932640, "loss_sum": 27441.385498046875, "token_normalized_loss": 0.4154952759186445, "grad_norm_before_clip": 0.08651237189769745, "learning_rates_at_step": { "lora": 9.890504512810954e-05, "row_tokens": 9.890504512810954e-05 }, "learning_rates_after_step": { "lora": 9.887024232540207e-05, "row_tokens": 9.887024232540207e-05 } }, { "update_id": 121, "row_count": 8, "row_ids_sha256": "b19377bc63a9ab6cc5f89c42fdf273bec4bb5e09a7f64a1ead8601f6a6acba1e", "input_ids_vector_sha256": "27f43d69b9b685a50a3af5ea5f316a7d1026317b98ef9b1ccc52a323b99a87d8", "labels_vector_sha256": "4a2cba34433eb66b0567a480128cf6bee3e3acb590b32df2a9411a9497ebe856", "planned_active_tokens": 64175, "realized_active_tokens": 64175, "cumulative_start": 7932640, "cumulative_end": 7996815, "loss_sum": 26149.437744140625, "token_normalized_loss": 0.40747078681948773, "grad_norm_before_clip": 0.08648530393838882, "learning_rates_at_step": { "lora": 9.887024232540207e-05, "row_tokens": 9.887024232540207e-05 }, "learning_rates_after_step": { "lora": 9.883121069361206e-05, "row_tokens": 9.883121069361206e-05 } }, { "update_id": 122, "row_count": 13, "row_ids_sha256": "d667b6d8c0496dae2c8bef6e84e5a3018a8fff8aac1fe3e4fc1f8748c8d8addf", "input_ids_vector_sha256": "5698e7eb7d8ddcc686de52d31bab4a240f07a1351e41ff8af34c60b860c7d594", "labels_vector_sha256": "28c224648dc150ac26079f796921d2bfcfe4fe9e38d6a2c5106b51ab6ef3f2d9", "planned_active_tokens": 70821, "realized_active_tokens": 70821, "cumulative_start": 7996815, "cumulative_end": 8067636, "loss_sum": 29773.926147460938, "token_normalized_loss": 0.4204109818762929, "grad_norm_before_clip": 0.08065130561590195, "learning_rates_at_step": { "lora": 9.883121069361206e-05, "row_tokens": 9.883121069361206e-05 }, "learning_rates_after_step": { "lora": 9.879701883021469e-05, "row_tokens": 9.879701883021469e-05 } }, { "update_id": 123, "row_count": 10, "row_ids_sha256": "55c83924ba37f4305ac3c87d57b78227283472d1837508fe70269c09402e50b2", "input_ids_vector_sha256": "380e7a46bd1786242bcb6a14c709ebc2fa0928a0ebcfc228e2ce2dcaa7e9e325", "labels_vector_sha256": "539b882bb91c864067bba7902c4b888ffcbcecb2af86cf41742decaa68c3649d", "planned_active_tokens": 61085, "realized_active_tokens": 61085, "cumulative_start": 8067636, "cumulative_end": 8128721, "loss_sum": 21111.45166015625, "token_normalized_loss": 0.34560778685694116, "grad_norm_before_clip": 0.08857929706573486, "learning_rates_at_step": { "lora": 9.879701883021469e-05, "row_tokens": 9.879701883021469e-05 }, "learning_rates_after_step": { "lora": 9.876062501063958e-05, "row_tokens": 9.876062501063958e-05 } }, { "update_id": 124, "row_count": 13, "row_ids_sha256": "af397006b7a1608170f52339844e8a65b0157f3f803080a2fc6b82f48d4873d1", "input_ids_vector_sha256": "dda41770677410667a8afb33b208643da96e4c2bc87bdcaa228b3bc41bed42ff", "labels_vector_sha256": "ce67cfced220e49c09a9361db1acef6e8257ddd9ebc49de9cf09e7311791f71d", "planned_active_tokens": 64084, "realized_active_tokens": 64084, "cumulative_start": 8128721, "cumulative_end": 8192805, "loss_sum": 24957.58282470703, "token_normalized_loss": 0.3894510770973571, "grad_norm_before_clip": 0.08942727744579315, "learning_rates_at_step": { "lora": 9.876062501063958e-05, "row_tokens": 9.876062501063958e-05 }, "learning_rates_after_step": { "lora": 9.872266585468822e-05, "row_tokens": 9.872266585468822e-05 } }, { "update_id": 125, "row_count": 12, "row_ids_sha256": "b625d9ad309d3f250d73d21a2765202218e3ccee3cdc7060c074f712e554383f", "input_ids_vector_sha256": "e2ee2a6dadc5d47b6d236b08a16aedbb15593b98e4182b1b6b058882cc08c1eb", "labels_vector_sha256": "011a5cc9e544ad8e8cc9d8a024531c2ebdb3dad58acbf12542d175896d82d29e", "planned_active_tokens": 65858, "realized_active_tokens": 65858, "cumulative_start": 8192805, "cumulative_end": 8258663, "loss_sum": 23558.142211914062, "token_normalized_loss": 0.35771116966676886, "grad_norm_before_clip": 0.08146532624959946, "learning_rates_at_step": { "lora": 9.872266585468822e-05, "row_tokens": 9.872266585468822e-05 }, "learning_rates_after_step": { "lora": 9.868410511789531e-05, "row_tokens": 9.868410511789531e-05 } }, { "update_id": 126, "row_count": 13, "row_ids_sha256": "0b146fdfb2634296ebe4de6b93ce5850d0e948033e0f259aef75b6d68af7e821", "input_ids_vector_sha256": "e63365e7ee118baff0ad278bf2a70769b294c33fddc34c2d702457bedc21c935", "labels_vector_sha256": "59833add9adbb0f1642d9ecbaf4ea48f4cbd6a1b9c2b5520c2e4838f4fd7638c", "planned_active_tokens": 65920, "realized_active_tokens": 65920, "cumulative_start": 8258663, "cumulative_end": 8324583, "loss_sum": 25026.300384521484, "token_normalized_loss": 0.3796465470952895, "grad_norm_before_clip": 0.08001993596553802, "learning_rates_at_step": { "lora": 9.868410511789531e-05, "row_tokens": 9.868410511789531e-05 }, "learning_rates_after_step": { "lora": 9.864358182713425e-05, "row_tokens": 9.864358182713425e-05 } }, { "update_id": 127, "row_count": 12, "row_ids_sha256": "aa7ee08a923ac619981b7701ea39c68610901af89389f6520c58fb21e2b17819", "input_ids_vector_sha256": "e9590a9c096278477a0e7f51004067d885764c3b274ac6915c90a683b810c943", "labels_vector_sha256": "b5f27f7e3e6d702a84cb8b14f456f38d9159c50f4561597b153e625973f90d09", "planned_active_tokens": 68256, "realized_active_tokens": 68256, "cumulative_start": 8324583, "cumulative_end": 8392839, "loss_sum": 23193.584106445312, "token_normalized_loss": 0.33980286138134835, "grad_norm_before_clip": 0.07627192884683609, "learning_rates_at_step": { "lora": 9.864358182713425e-05, "row_tokens": 9.864358182713425e-05 }, "learning_rates_after_step": { "lora": 9.86066293647648e-05, "row_tokens": 9.86066293647648e-05 } }, { "update_id": 128, "row_count": 10, "row_ids_sha256": "2d94c1cffc99e20990e726d0c53d6e4092adaa562983fdafb107da1f7a046529", "input_ids_vector_sha256": "b9adde8b0b51f6ff5afe4829cc6f9896407516aef500a31b7e062f085ba7e227", "labels_vector_sha256": "9548bb353bafa8c792ef843040d58f464b83810b7dd65cdd12da627e0feb3e2c", "planned_active_tokens": 61370, "realized_active_tokens": 61370, "cumulative_start": 8392839, "cumulative_end": 8454209, "loss_sum": 24098.95458984375, "token_normalized_loss": 0.3926829817474947, "grad_norm_before_clip": 0.08667352795600891, "learning_rates_at_step": { "lora": 9.86066293647648e-05, "row_tokens": 9.86066293647648e-05 }, "learning_rates_after_step": { "lora": 9.856542122786032e-05, "row_tokens": 9.856542122786032e-05 } }, { "update_id": 129, "row_count": 11, "row_ids_sha256": "57e6d70bb93ba270fe3885719e532dc4d248ae4f7c0ddacd96ae8c5666b1e1db", "input_ids_vector_sha256": "231d8e7beb3785b02c58f930373fbbbae4b78c4845795a094ad6e02bdb8783c6", "labels_vector_sha256": "04a9a65885ee013b0d065f3fb87a5e27474913208ebe627b440573eb85d6e8b3", "planned_active_tokens": 67499, "realized_active_tokens": 67499, "cumulative_start": 8454209, "cumulative_end": 8521708, "loss_sum": 21010.10223388672, "token_normalized_loss": 0.3112653851743984, "grad_norm_before_clip": 0.0731717199087143, "learning_rates_at_step": { "lora": 9.856542122786032e-05, "row_tokens": 9.856542122786032e-05 }, "learning_rates_after_step": { "lora": 9.852383784668902e-05, "row_tokens": 9.852383784668902e-05 } }, { "update_id": 130, "row_count": 11, "row_ids_sha256": "47f1ed69306f0ca584cf497a0df238f45fe20a8fabc1440f363633140f98f160", "input_ids_vector_sha256": "44fb47d02b5354791d82c15e33edd12cda7743dc143473fb2ea397ba906207af", "labels_vector_sha256": "6a29436412658daffcde02f29b9d388777c3522b3caa4f4b99c762f22206c804", "planned_active_tokens": 67152, "realized_active_tokens": 67152, "cumulative_start": 8521708, "cumulative_end": 8588860, "loss_sum": 23812.23291015625, "token_normalized_loss": 0.3546019911567228, "grad_norm_before_clip": 0.07932355999946594, "learning_rates_at_step": { "lora": 9.852383784668902e-05, "row_tokens": 9.852383784668902e-05 }, "learning_rates_after_step": { "lora": 9.848224537275485e-05, "row_tokens": 9.848224537275485e-05 } }, { "update_id": 131, "row_count": 12, "row_ids_sha256": "8c97b3ae9cd4f7a4651ed3a032aababcb6392e1e23f32817143fbc0c085d6499", "input_ids_vector_sha256": "6d343c94d750d826689809b7c156445b51368952ee8b07a4b94f4c3575e0b3df", "labels_vector_sha256": "b7d6a20583303fe8dacf2231729e0fee878d4b5e6e326ff07097556c7a0af15a", "planned_active_tokens": 66241, "realized_active_tokens": 66241, "cumulative_start": 8588860, "cumulative_end": 8655101, "loss_sum": 24620.08953857422, "token_normalized_loss": 0.37167448466318775, "grad_norm_before_clip": 0.07868922501802444, "learning_rates_at_step": { "lora": 9.848224537275485e-05, "row_tokens": 9.848224537275485e-05 }, "learning_rates_after_step": { "lora": 9.844068314844952e-05, "row_tokens": 9.844068314844952e-05 } }, { "update_id": 132, "row_count": 12, "row_ids_sha256": "8543690765de2732096d3ce7d58507457590f621ce8903430db4dd2630929436", "input_ids_vector_sha256": "316fd9138ca36e61ae0cabc730af2ab99fcb1432064038fb8c3507a0b48e7235", "labels_vector_sha256": "cf0bcabe6b225b8bb1500cabfa7e69f820b6c52e914e070a6b82df8000fe4d3b", "planned_active_tokens": 65306, "realized_active_tokens": 65306, "cumulative_start": 8655101, "cumulative_end": 8720407, "loss_sum": 23761.70962524414, "token_normalized_loss": 0.36385186085879, "grad_norm_before_clip": 0.0860755667090416, "learning_rates_at_step": { "lora": 9.844068314844952e-05, "row_tokens": 9.844068314844952e-05 }, "learning_rates_after_step": { "lora": 9.839949661730791e-05, "row_tokens": 9.839949661730791e-05 } }, { "update_id": 133, "row_count": 10, "row_ids_sha256": "8450acd0f1459334976b93b4fd066b50c774c3055f877dc65178787846e7188b", "input_ids_vector_sha256": "2edc45b682a325d41fa061d269b51cf63666e574ff9491bd83ba0943f7f2d432", "labels_vector_sha256": "604ddb4cc60bc512087da0b92c472f6a67cf8c691b751cd4c7978942698ea16f", "planned_active_tokens": 63876, "realized_active_tokens": 63876, "cumulative_start": 8720407, "cumulative_end": 8784283, "loss_sum": 25149.316650390625, "token_normalized_loss": 0.39372090691951006, "grad_norm_before_clip": 0.08238602429628372, "learning_rates_at_step": { "lora": 9.839949661730791e-05, "row_tokens": 9.839949661730791e-05 }, "learning_rates_after_step": { "lora": 9.83570091227946e-05, "row_tokens": 9.83570091227946e-05 } }, { "update_id": 134, "row_count": 11, "row_ids_sha256": "1f183b2270f645be639b2d8e7057ff746b7d4e146e57287a17f8e7d25934757a", "input_ids_vector_sha256": "544e5febd5046c9cbc988de8d2ab2baf34acdf438ef24aa4a04f3f0876c5ffea", "labels_vector_sha256": "2fcafbfccd1147c4e476ffbb37efe837bf83a5ba352902f7109ba155549ebae7", "planned_active_tokens": 65052, "realized_active_tokens": 65052, "cumulative_start": 8784283, "cumulative_end": 8849335, "loss_sum": 25791.99853515625, "token_normalized_loss": 0.39648279123095753, "grad_norm_before_clip": 0.08576016873121262, "learning_rates_at_step": { "lora": 9.83570091227946e-05, "row_tokens": 9.83570091227946e-05 }, "learning_rates_after_step": { "lora": 9.831424541209289e-05, "row_tokens": 9.831424541209289e-05 } }, { "update_id": 135, "row_count": 12, "row_ids_sha256": "1a57aa2615cb1ba772c4842360f62bc54da42dc9dd24c5587827fa5bf2e1323c", "input_ids_vector_sha256": "0d32ed6f79fee4f99013f596b1ca0442586ffdc50174640534dd6501c117fcd3", "labels_vector_sha256": "016c11f56198d01c3bdd86b270458a2f787155b136333096966048aec0f6feb9", "planned_active_tokens": 64645, "realized_active_tokens": 64645, "cumulative_start": 8849335, "cumulative_end": 8913980, "loss_sum": 24654.54214477539, "token_normalized_loss": 0.38138358952394447, "grad_norm_before_clip": 0.07995450496673584, "learning_rates_at_step": { "lora": 9.831424541209289e-05, "row_tokens": 9.831424541209289e-05 }, "learning_rates_after_step": { "lora": 9.826621432124612e-05, "row_tokens": 9.826621432124612e-05 } }, { "update_id": 136, "row_count": 11, "row_ids_sha256": "cd8a37e87c38e841906fee0b07d6f8436ee31379e088f4c309f6305165202c78", "input_ids_vector_sha256": "db591e05b5a056585650210978f8a920a5057bd93b28caf71d95c022cc55541c", "labels_vector_sha256": "573411b6995ae5f475476bba80cc0c79a883f76df2716f6092fff569edc3d6d7", "planned_active_tokens": 71654, "realized_active_tokens": 71654, "cumulative_start": 8913980, "cumulative_end": 8985634, "loss_sum": 29045.444580078125, "token_normalized_loss": 0.40535691768886767, "grad_norm_before_clip": 0.08049275726079941, "learning_rates_at_step": { "lora": 9.826621432124612e-05, "row_tokens": 9.826621432124612e-05 }, "learning_rates_after_step": { "lora": 9.822298384409496e-05, "row_tokens": 9.822298384409496e-05 } }, { "update_id": 137, "row_count": 11, "row_ids_sha256": "fef9ee90ef370bba554d000ff22345cb145f46bf62a0540dc44544f63aa07811", "input_ids_vector_sha256": "afd94b33a6f15c604cf378e9afcfc2cafc07b5ec2997c694cecf06aad68a023f", "labels_vector_sha256": "f7250e0507818b0df01b85e02346fbad98e02c556f43cdf4e418ac60764344f0", "planned_active_tokens": 63663, "realized_active_tokens": 63663, "cumulative_start": 8985634, "cumulative_end": 9049297, "loss_sum": 23969.50079345703, "token_normalized_loss": 0.3765059892473969, "grad_norm_before_clip": 0.08164192736148834, "learning_rates_at_step": { "lora": 9.822298384409496e-05, "row_tokens": 9.822298384409496e-05 }, "learning_rates_after_step": { "lora": 9.817782565764874e-05, "row_tokens": 9.817782565764874e-05 } }, { "update_id": 138, "row_count": 12, "row_ids_sha256": "8befd48833eabb46345ff92a7032bf8bcfe4ba7f1a0bb585ed7e7569b888ee8a", "input_ids_vector_sha256": "21ad10dc27f8be98584d04457e0337895be4beebd97cbeb7459e432e6dada87c", "labels_vector_sha256": "c61de71832e084541f23ebf14db59c913134527b210c160a5b68a3e35f57d230", "planned_active_tokens": 65695, "realized_active_tokens": 65695, "cumulative_start": 9049297, "cumulative_end": 9114992, "loss_sum": 25240.409729003906, "token_normalized_loss": 0.38420594762164406, "grad_norm_before_clip": 0.08563084155321121, "learning_rates_at_step": { "lora": 9.817782565764874e-05, "row_tokens": 9.817782565764874e-05 }, "learning_rates_after_step": { "lora": 9.813034968833751e-05, "row_tokens": 9.813034968833751e-05 } }, { "update_id": 139, "row_count": 10, "row_ids_sha256": "6dc2051ed279cc80c0b25844d7c0612e654da263a83b4e0a665475f19f705e1a", "input_ids_vector_sha256": "a7c30690eee052814cdc5b61c49b4f2aa048ee0dd63063c35429f230f55cd60c", "labels_vector_sha256": "0ad7f19e3b4fadddd75642352715499ee60cab251c120612086867563fc76013", "planned_active_tokens": 68211, "realized_active_tokens": 68211, "cumulative_start": 9114992, "cumulative_end": 9183203, "loss_sum": 27936.753295898438, "token_normalized_loss": 0.4095637550526812, "grad_norm_before_clip": 0.08719784766435623, "learning_rates_at_step": { "lora": 9.813034968833751e-05, "row_tokens": 9.813034968833751e-05 }, "learning_rates_after_step": { "lora": 9.808920953818794e-05, "row_tokens": 9.808920953818794e-05 } }, { "update_id": 140, "row_count": 10, "row_ids_sha256": "c6fe2005fdcaf8216e1b90ad14319abdd2b83671e99d94f329a441f31eddf35a", "input_ids_vector_sha256": "cc53c7e1e6083fcef3e2423700e75956e5325b58bd9ae9443a6a78c94a34fbb3", "labels_vector_sha256": "6b3afb2cfbb2ad0d5b2417a81b38255ac65c77486c80f9aa0192487ee83d8639", "planned_active_tokens": 58424, "realized_active_tokens": 58424, "cumulative_start": 9183203, "cumulative_end": 9241627, "loss_sum": 23366.270446777344, "token_normalized_loss": 0.39994301052268494, "grad_norm_before_clip": 0.08837229013442993, "learning_rates_at_step": { "lora": 9.808920953818794e-05, "row_tokens": 9.808920953818794e-05 }, "learning_rates_after_step": { "lora": 9.804196023913578e-05, "row_tokens": 9.804196023913578e-05 } }, { "update_id": 141, "row_count": 14, "row_ids_sha256": "85a953d2a8c8ef939af0825ae4c5bf3168c599f2aadb58042013b81d4d6e08ff", "input_ids_vector_sha256": "986510a3299e63023943909189f4a328849bf6b09b68e581d29d9aa1dce35ccd", "labels_vector_sha256": "00fd24ce4578a2a8c36d3f12b34595b8afdebe8c1d38229c837a7fc82cf2e070", "planned_active_tokens": 66344, "realized_active_tokens": 66344, "cumulative_start": 9241627, "cumulative_end": 9307971, "loss_sum": 23477.15606689453, "token_normalized_loss": 0.3538700721526367, "grad_norm_before_clip": 0.07850377261638641, "learning_rates_at_step": { "lora": 9.804196023913578e-05, "row_tokens": 9.804196023913578e-05 }, "learning_rates_after_step": { "lora": 9.799527270246967e-05, "row_tokens": 9.799527270246967e-05 } }, { "update_id": 142, "row_count": 12, "row_ids_sha256": "f6fa56585796dc222275209f9b6774cfc8303cc2cdfcd6449ab88bac815e4103", "input_ids_vector_sha256": "656cfe3086e89a8395321939d50ee89d61657458effbf6ee57a4382ba89d5608", "labels_vector_sha256": "568b5758b26b14d39ac94e99b54dc8ed2a12f37f1417c7388d650b32fe1253ea", "planned_active_tokens": 64789, "realized_active_tokens": 64789, "cumulative_start": 9307971, "cumulative_end": 9372760, "loss_sum": 27527.08837890625, "token_normalized_loss": 0.42487287006908964, "grad_norm_before_clip": 0.08493170142173767, "learning_rates_at_step": { "lora": 9.799527270246967e-05, "row_tokens": 9.799527270246967e-05 }, "learning_rates_after_step": { "lora": 9.794354663082823e-05, "row_tokens": 9.794354663082823e-05 } }, { "update_id": 143, "row_count": 9, "row_ids_sha256": "3b8d6b9b871ed05d60aea281490b0a06b2370ee65dec0701b82ccbb1f01d281c", "input_ids_vector_sha256": "de46d1a067fd23e0b5238189a3abdaacd39c96444fe24415ca7b19fbcfa6598a", "labels_vector_sha256": "83cc4f8e2468e446aa7659c6382e981aa9626e22cd8613a215e97e5584454857", "planned_active_tokens": 70924, "realized_active_tokens": 70924, "cumulative_start": 9372760, "cumulative_end": 9443684, "loss_sum": 31489.68603515625, "token_normalized_loss": 0.44399196372393335, "grad_norm_before_clip": 0.08578071743249893, "learning_rates_at_step": { "lora": 9.794354663082823e-05, "row_tokens": 9.794354663082823e-05 }, "learning_rates_after_step": { "lora": 9.789761452028556e-05, "row_tokens": 9.789761452028556e-05 } }, { "update_id": 144, "row_count": 10, "row_ids_sha256": "9338fad86cf11ff2b1e0180bba33b7869b807f727128ef98459b4a46ba85e21f", "input_ids_vector_sha256": "4559068a2ca1e04d022b009b5315cd2a3277550cefb91785d9e1d0c11a4c31d1", "labels_vector_sha256": "71b4d5ecdf37d7350fdfd2b391b70b3dea4eb6d83b80c4357fac30a40e776ade", "planned_active_tokens": 62251, "realized_active_tokens": 62251, "cumulative_start": 9443684, "cumulative_end": 9505935, "loss_sum": 27663.32403564453, "token_normalized_loss": 0.4443836088680428, "grad_norm_before_clip": 0.09364679455757141, "learning_rates_at_step": { "lora": 9.789761452028556e-05, "row_tokens": 9.789761452028556e-05 }, "learning_rates_after_step": { "lora": 9.784869078613243e-05, "row_tokens": 9.784869078613243e-05 } }, { "update_id": 145, "row_count": 11, "row_ids_sha256": "781b92f6c73b6facc09b3f0e83d7fa0f265e88729de7bb9912889cff2684be0c", "input_ids_vector_sha256": "7ce9e909f418069eab8420c5ba4620de975c5032ba1391809bfd5e1d024adccc", "labels_vector_sha256": "085b33a2347e6d743dbe3bc9e8eeccc6a55323006bc00468d8e87359c76a8289", "planned_active_tokens": 65578, "realized_active_tokens": 65578, "cumulative_start": 9505935, "cumulative_end": 9571513, "loss_sum": 27275.69647216797, "token_normalized_loss": 0.4159275438739817, "grad_norm_before_clip": 0.08091157674789429, "learning_rates_at_step": { "lora": 9.784869078613243e-05, "row_tokens": 9.784869078613243e-05 }, "learning_rates_after_step": { "lora": 9.779377501044264e-05, "row_tokens": 9.779377501044264e-05 } }, { "update_id": 146, "row_count": 11, "row_ids_sha256": "834733b8c6fe5f35bc88268a949822b337559f95fe31f01b57ff6d7bde2b44fd", "input_ids_vector_sha256": "40fd892f0372834e067fe8c5f40d6d9e57668b28fbe590bea3b740fe5a9a63f3", "labels_vector_sha256": "e4a6a2276bcc11babf9b1275fdb1ed9c1b4c17971912de6346610809ccb64aa3", "planned_active_tokens": 72747, "realized_active_tokens": 72747, "cumulative_start": 9571513, "cumulative_end": 9644260, "loss_sum": 31389.596710205078, "token_normalized_loss": 0.4314899131263843, "grad_norm_before_clip": 0.08104221522808075, "learning_rates_at_step": { "lora": 9.779377501044264e-05, "row_tokens": 9.779377501044264e-05 }, "learning_rates_after_step": { "lora": 9.775023627641584e-05, "row_tokens": 9.775023627641584e-05 } }, { "update_id": 147, "row_count": 13, "row_ids_sha256": "37d336a2a04b4f9dd8b179c3884c403044c02be6d31e9ba4705acd979b3bcfb1", "input_ids_vector_sha256": "bacbbcf4be617bc8129c22feecb37e046f5f2b51b97dde26eb4ea523cd85efb5", "labels_vector_sha256": "67d160be6465e9061a311c321b9046e36958e1ca4363e4f67b51c8a864214c96", "planned_active_tokens": 57049, "realized_active_tokens": 57049, "cumulative_start": 9644260, "cumulative_end": 9701309, "loss_sum": 19496.255950927734, "token_normalized_loss": 0.34174579661217086, "grad_norm_before_clip": 0.07856439799070358, "learning_rates_at_step": { "lora": 9.775023627641584e-05, "row_tokens": 9.775023627641584e-05 }, "learning_rates_after_step": { "lora": 9.769886332981444e-05, "row_tokens": 9.769886332981444e-05 } }, { "update_id": 148, "row_count": 14, "row_ids_sha256": "3760fbd00132bd6ca90ffc1a48dc1f059b346b4e35dd33511100b939e3f6893c", "input_ids_vector_sha256": "ecfa9ab390dece7564313e499ac38a9fa30f483c82caf31c313acf3b6ab245c1", "labels_vector_sha256": "26460335eedfc9cf8fd62a91c293bfd1e95479684321ef93c204d7b47df417b8", "planned_active_tokens": 66625, "realized_active_tokens": 66625, "cumulative_start": 9701309, "cumulative_end": 9767934, "loss_sum": 23131.59097290039, "token_normalized_loss": 0.34719085888030604, "grad_norm_before_clip": 0.07677186280488968, "learning_rates_at_step": { "lora": 9.769886332981444e-05, "row_tokens": 9.769886332981444e-05 }, "learning_rates_after_step": { "lora": 9.764794859195151e-05, "row_tokens": 9.764794859195151e-05 } }, { "update_id": 149, "row_count": 12, "row_ids_sha256": "ee52ffe986b8442c324e7a3536874077ba69501a7989601116aaa9bd68adc888", "input_ids_vector_sha256": "f2cbce7f120ff4b51dc9dc33d02890bfc71b0fe10b3d70b6aa2ebc4dd6e3b2c4", "labels_vector_sha256": "5bfd3ea24b8db9d38f442bb67c27abf87d3fd01d850a645e2d51147fb33651d5", "planned_active_tokens": 65318, "realized_active_tokens": 65318, "cumulative_start": 9767934, "cumulative_end": 9833252, "loss_sum": 25423.810424804688, "token_normalized_loss": 0.3892313056861001, "grad_norm_before_clip": 0.08002079278230667, "learning_rates_at_step": { "lora": 9.764794859195151e-05, "row_tokens": 9.764794859195151e-05 }, "learning_rates_after_step": { "lora": 9.759770423521411e-05, "row_tokens": 9.759770423521411e-05 } }, { "update_id": 150, "row_count": 11, "row_ids_sha256": "469852c0cd08a88a36f5ad2e43b376809e8d26421af52a52fbe636d78e45d41a", "input_ids_vector_sha256": "cb149f714dfa221dfce2a95726533e58c29836ce0b87c6049903b0393f93b2d0", "labels_vector_sha256": "cf99f763cca1eda7d4956cb6a968d885a70f62341e376ee23011a2035ca61fa3", "planned_active_tokens": 63785, "realized_active_tokens": 63785, "cumulative_start": 9833252, "cumulative_end": 9897037, "loss_sum": 22884.868591308594, "token_normalized_loss": 0.3587813528464152, "grad_norm_before_clip": 0.07844919711351395, "learning_rates_at_step": { "lora": 9.759770423521411e-05, "row_tokens": 9.759770423521411e-05 }, "learning_rates_after_step": { "lora": 9.754310195365933e-05, "row_tokens": 9.754310195365933e-05 } }, { "update_id": 151, "row_count": 15, "row_ids_sha256": "7bc5b525d405c69c66e521beddc0363c38d0be6a34a40df0d9b2604c30773aee", "input_ids_vector_sha256": "7e5bb2dee5dc74c71f0b13027cb69ca5800431209e49a4bb22cee0c10f75a79f", "labels_vector_sha256": "8f36fa600064a87cfb0def03a001c4734b5176b407fb6c8716268cb809063207", "planned_active_tokens": 68584, "realized_active_tokens": 68584, "cumulative_start": 9897037, "cumulative_end": 9965621, "loss_sum": 22525.500274658203, "token_normalized_loss": 0.32843666561673573, "grad_norm_before_clip": 0.0710967406630516, "learning_rates_at_step": { "lora": 9.754310195365933e-05, "row_tokens": 9.754310195365933e-05 }, "learning_rates_after_step": { "lora": 9.7490771999757e-05, "row_tokens": 9.7490771999757e-05 } }, { "update_id": 152, "row_count": 11, "row_ids_sha256": "e7883c93c1dde241165c9f785c486321266ffb18adf5413e18e2e6ea2baba17a", "input_ids_vector_sha256": "37b3e4dc23d6b02cc1798c3c371085dcc14feec08c3b58445b4da89f02ff5b6f", "labels_vector_sha256": "f133f3bc5f612bc23990cfa61e31a88dce778dd5b54e0ef15cbe4bcab01c1a4a", "planned_active_tokens": 65036, "realized_active_tokens": 65036, "cumulative_start": 9965621, "cumulative_end": 10030657, "loss_sum": 26839.203033447266, "token_normalized_loss": 0.4126822534203713, "grad_norm_before_clip": 0.13353073596954346, "learning_rates_at_step": { "lora": 9.7490771999757e-05, "row_tokens": 9.7490771999757e-05 }, "learning_rates_after_step": { "lora": 9.744044035198765e-05, "row_tokens": 9.744044035198765e-05 } }, { "update_id": 153, "row_count": 8, "row_ids_sha256": "2597a7cada4155573203c5edee3ebe2521df956cd30325343647d2227bbd79f3", "input_ids_vector_sha256": "50c72863fcba6326ce1c149453fb44956b6b52cbe009f8d9baf7cc81eb9206c6", "labels_vector_sha256": "afd2c9e9b7ad394711a6e86cbb42dd061f1b9faef914b849f90de3e417710373", "planned_active_tokens": 61932, "realized_active_tokens": 61932, "cumulative_start": 10030657, "cumulative_end": 10092589, "loss_sum": 28452.423828125, "token_normalized_loss": 0.45941393509211714, "grad_norm_before_clip": 0.082383893430233, "learning_rates_at_step": { "lora": 9.744044035198765e-05, "row_tokens": 9.744044035198765e-05 }, "learning_rates_after_step": { "lora": 9.73858010228113e-05, "row_tokens": 9.73858010228113e-05 } }, { "update_id": 154, "row_count": 8, "row_ids_sha256": "7f4b7902a1669eb4b0548c868c5ed40eae868638527b4ce7bae41885b44a54f6", "input_ids_vector_sha256": "0cbc4b6a55f6be5404c672789478a8358da793f1d2fb5bc5b4813419d792efbf", "labels_vector_sha256": "56f1a9d5e3391d5224961f58421ff95f636ad7f03a7cf445ea465c6a4934f658", "planned_active_tokens": 66565, "realized_active_tokens": 66565, "cumulative_start": 10092589, "cumulative_end": 10159154, "loss_sum": 27422.846923828125, "token_normalized_loss": 0.4119709595707673, "grad_norm_before_clip": 0.07237692177295685, "learning_rates_at_step": { "lora": 9.73858010228113e-05, "row_tokens": 9.73858010228113e-05 }, "learning_rates_after_step": { "lora": 9.732859954899154e-05, "row_tokens": 9.732859954899154e-05 } }, { "update_id": 155, "row_count": 9, "row_ids_sha256": "96833350c4f9c3f8218f6ced7e6eecb46e128efed3abda50c4b97e57d3f11aaf", "input_ids_vector_sha256": "a3d4e25a1eb92f654e6792d8f87f01f7c09c25dc5d53a7d8e39fe6d2e37fd36f", "labels_vector_sha256": "c22fa2b70c92987ee9266a7a9dfa56fb0203a069f95970ae42e948c820dc4987", "planned_active_tokens": 68965, "realized_active_tokens": 68965, "cumulative_start": 10159154, "cumulative_end": 10228119, "loss_sum": 29508.946533203125, "token_normalized_loss": 0.4278829338534492, "grad_norm_before_clip": 0.07305094599723816, "learning_rates_at_step": { "lora": 9.732859954899154e-05, "row_tokens": 9.732859954899154e-05 }, "learning_rates_after_step": { "lora": 9.727330126569229e-05, "row_tokens": 9.727330126569229e-05 } }, { "update_id": 156, "row_count": 8, "row_ids_sha256": "922711155953251f0a41af9aac68b167fafeadc80b505982305fa68a4e663558", "input_ids_vector_sha256": "513891a344ac5ab2f6c368351abcaaa981f53f6fdca0b798e8164dbfc6253470", "labels_vector_sha256": "0a72b61958c8450e8b493563fe015517c7877ee14c1fd04890ebd0c7210ede2d", "planned_active_tokens": 65991, "realized_active_tokens": 65991, "cumulative_start": 10228119, "cumulative_end": 10294110, "loss_sum": 30641.645141601562, "token_normalized_loss": 0.46433066844875154, "grad_norm_before_clip": 0.07937274873256683, "learning_rates_at_step": { "lora": 9.727330126569229e-05, "row_tokens": 9.727330126569229e-05 }, "learning_rates_after_step": { "lora": 9.722121039694184e-05, "row_tokens": 9.722121039694184e-05 } }, { "update_id": 157, "row_count": 7, "row_ids_sha256": "985c679782cfd58671111692e2caffc7d6da19181dbe3c9fe7c3b7fde7f50e02", "input_ids_vector_sha256": "2bc646eb5586de1a1dbc552278949b009fedcc11a6d308a014140189f036b0b4", "labels_vector_sha256": "85ef36d4d606b105015f5ad0500dd54cc5ad35a961682b67c46bd07b32691409", "planned_active_tokens": 61571, "realized_active_tokens": 61571, "cumulative_start": 10294110, "cumulative_end": 10355681, "loss_sum": 28673.649841308594, "token_normalized_loss": 0.4657005707444835, "grad_norm_before_clip": 0.08385823667049408, "learning_rates_at_step": { "lora": 9.722121039694184e-05, "row_tokens": 9.722121039694184e-05 }, "learning_rates_after_step": { "lora": 9.716355428137581e-05, "row_tokens": 9.716355428137581e-05 } }, { "update_id": 158, "row_count": 10, "row_ids_sha256": "b8532294391d9eca65ca5ac2fcb68d29ef45fe75298d524dbcfcfadaca64f5aa", "input_ids_vector_sha256": "b5b1ce07b104472b76ccc80b8b1f60d8b250eb22124e5d281929298b8e303f1a", "labels_vector_sha256": "4413a897c138687e05d6891a50811ac1e048fd340f7dc2aa2184389334c794fa", "planned_active_tokens": 67499, "realized_active_tokens": 67499, "cumulative_start": 10355681, "cumulative_end": 10423180, "loss_sum": 31340.703979492188, "token_normalized_loss": 0.4643136043421708, "grad_norm_before_clip": 0.07773906737565994, "learning_rates_at_step": { "lora": 9.716355428137581e-05, "row_tokens": 9.716355428137581e-05 }, "learning_rates_after_step": { "lora": 9.71012328354402e-05, "row_tokens": 9.71012328354402e-05 } }, { "update_id": 159, "row_count": 7, "row_ids_sha256": "3d766e28d3660eaf0e1475211fa6acf1c692f8d76949e9d63d2002f86e5ba1af", "input_ids_vector_sha256": "5461331aec93ce9d71264c842156337b1ce607810f99a5ecf5eac2b992d25888", "labels_vector_sha256": "436216ea2d768daf9ee10d707fba4c06b05fe7242b1adaf5b8ba05dc135f9234", "planned_active_tokens": 72216, "realized_active_tokens": 72216, "cumulative_start": 10423180, "cumulative_end": 10495396, "loss_sum": 30516.442626953125, "token_normalized_loss": 0.4225717656330055, "grad_norm_before_clip": 0.07372262328863144, "learning_rates_at_step": { "lora": 9.71012328354402e-05, "row_tokens": 9.71012328354402e-05 }, "learning_rates_after_step": { "lora": 9.704581867867513e-05, "row_tokens": 9.704581867867513e-05 } }, { "update_id": 160, "row_count": 8, "row_ids_sha256": "9f9ca0999fa76e83dd25133da2b7ef610208f5a63a2f2146f67cdb4d0c9fdfe6", "input_ids_vector_sha256": "319f9b0a73e2698d503eddfe0f814da4ac9cef64cc4e765d37713e6a70b5b1c1", "labels_vector_sha256": "00927511a7c986262d51e149236bc5c3082a1fbc1a41e46694c97b1eea451ecc", "planned_active_tokens": 63582, "realized_active_tokens": 63582, "cumulative_start": 10495396, "cumulative_end": 10558978, "loss_sum": 23890.76171875, "token_normalized_loss": 0.37574725108914475, "grad_norm_before_clip": 0.07007652521133423, "learning_rates_at_step": { "lora": 9.704581867867513e-05, "row_tokens": 9.704581867867513e-05 }, "learning_rates_after_step": { "lora": 9.698657566216339e-05, "row_tokens": 9.698657566216339e-05 } }, { "update_id": 161, "row_count": 7, "row_ids_sha256": "18467f0365a48c212e3067a14b5de01374554ee76939b393484eace9057218d1", "input_ids_vector_sha256": "b042de4d59de989f99eb02172c9755b7746b3ad6b08e1c5df34fa4652bb608a8", "labels_vector_sha256": "d74ce87756190c6e73cd66b72467dacf61ded96e207dc0d7c018ab47fd0f42a8", "planned_active_tokens": 67339, "realized_active_tokens": 67339, "cumulative_start": 10558978, "cumulative_end": 10626317, "loss_sum": 28584.04150390625, "token_normalized_loss": 0.42447974433695557, "grad_norm_before_clip": 0.07412472367286682, "learning_rates_at_step": { "lora": 9.698657566216339e-05, "row_tokens": 9.698657566216339e-05 }, "learning_rates_after_step": { "lora": 9.693679250264295e-05, "row_tokens": 9.693679250264295e-05 } }, { "update_id": 162, "row_count": 7, "row_ids_sha256": "5daaff129c852a5a6785915f7068b09b0af159f4108f114a4ce6bae7ddd80c62", "input_ids_vector_sha256": "5926785fc9879b119430a2941f7fe759f616b3582aef7b9b2d5d8d934daa2c12", "labels_vector_sha256": "fb73a4bb1e7c11b71baccc2508544f703c25f5afccab70c9eb4a767a4ccb54de", "planned_active_tokens": 56092, "realized_active_tokens": 56092, "cumulative_start": 10626317, "cumulative_end": 10682409, "loss_sum": 23989.02392578125, "token_normalized_loss": 0.42767282189583633, "grad_norm_before_clip": 0.08012495189905167, "learning_rates_at_step": { "lora": 9.693679250264295e-05, "row_tokens": 9.693679250264295e-05 }, "learning_rates_after_step": { "lora": 9.687673066643061e-05, "row_tokens": 9.687673066643061e-05 } }, { "update_id": 163, "row_count": 8, "row_ids_sha256": "4da0d24a421c9b552e1b1d4154585dfae78ac1c2b412725321c44f2acc961c91", "input_ids_vector_sha256": "67882a975b080173defb5a6a5fdedfcb4f3f78a1eedc42451990f18c8d636c79", "labels_vector_sha256": "f69c0274bd72625bf8e6a9e9fff6c6b0775220bb975bfa0f2cbb1b5be6fe5ed9", "planned_active_tokens": 67089, "realized_active_tokens": 67089, "cumulative_start": 10682409, "cumulative_end": 10749498, "loss_sum": 26211.592041015625, "token_normalized_loss": 0.3906988036938339, "grad_norm_before_clip": 0.07174266129732132, "learning_rates_at_step": { "lora": 9.687673066643061e-05, "row_tokens": 9.687673066643061e-05 }, "learning_rates_after_step": { "lora": 9.681430958183047e-05, "row_tokens": 9.681430958183047e-05 } }, { "update_id": 164, "row_count": 8, "row_ids_sha256": "1552ce661af27d2b85f2f6ac9754d0f0cc83e2196dcb9195f89d7682ce61e572", "input_ids_vector_sha256": "db87c28e2def0d95489132f2acb86581c71ba8aee73a4d4ffda6b73dc4fbc835", "labels_vector_sha256": "24aa24c79bca275cf3d495463cf66e359f15672b8a276f4db12286b263ce2ba5", "planned_active_tokens": 69066, "realized_active_tokens": 69066, "cumulative_start": 10749498, "cumulative_end": 10818564, "loss_sum": 30910.844482421875, "token_normalized_loss": 0.44755515713117705, "grad_norm_before_clip": 0.07334943860769272, "learning_rates_at_step": { "lora": 9.681430958183047e-05, "row_tokens": 9.681430958183047e-05 }, "learning_rates_after_step": { "lora": 9.674529499906386e-05, "row_tokens": 9.674529499906386e-05 } }, { "update_id": 165, "row_count": 10, "row_ids_sha256": "c9a2449da51b3e4741c5635ef3185b9b475fc6ce31e1d471b7f1954e371fd57b", "input_ids_vector_sha256": "11817b07f3865f3ed662fff6ddae8996e999c0c5802df97f9d4d42fd8d46e2ff", "labels_vector_sha256": "37eb25dab02fc65c12feb3504ea050d54165c3cde66327ce34d589c429033dca", "planned_active_tokens": 75604, "realized_active_tokens": 75604, "cumulative_start": 10818564, "cumulative_end": 10894168, "loss_sum": 30325.448852539062, "token_normalized_loss": 0.4011090531260127, "grad_norm_before_clip": 0.06902953237295151, "learning_rates_at_step": { "lora": 9.674529499906386e-05, "row_tokens": 9.674529499906386e-05 }, "learning_rates_after_step": { "lora": 9.669519984676364e-05, "row_tokens": 9.669519984676364e-05 } }, { "update_id": 166, "row_count": 7, "row_ids_sha256": "ff09e5a2c2137210dc8fa8a1f8e41b28c4e4b4811f39effb56b84ef9a863d7a7", "input_ids_vector_sha256": "e3659070cacb9d58d1875c6fc13175da2504c50eab941b649dee09ddef7c0554", "labels_vector_sha256": "1326befa09402bc08c5762d3c11beead09f8bc93ba1d4b67b55d07e8fd60802c", "planned_active_tokens": 54394, "realized_active_tokens": 54394, "cumulative_start": 10894168, "cumulative_end": 10948562, "loss_sum": 21447.322631835938, "token_normalized_loss": 0.39429574276273005, "grad_norm_before_clip": 0.08299120515584946, "learning_rates_at_step": { "lora": 9.669519984676364e-05, "row_tokens": 9.669519984676364e-05 }, "learning_rates_after_step": { "lora": 9.663659224168382e-05, "row_tokens": 9.663659224168382e-05 } }, { "update_id": 167, "row_count": 8, "row_ids_sha256": "7002aa942fc839a417b212a3be81b9f208fbac82c4502921bce5a21fed33cc1e", "input_ids_vector_sha256": "df5f7f65bb28f23c0985505f8d9a0d7b50c34099bc31c17c18c2b4f2e1a6e515", "labels_vector_sha256": "a2de2a95415475d113fa177818d70fc3707b357fa969347bb206e46e32296d9a", "planned_active_tokens": 63134, "realized_active_tokens": 63134, "cumulative_start": 10948562, "cumulative_end": 11011696, "loss_sum": 26320.551025390625, "token_normalized_loss": 0.41689978498733843, "grad_norm_before_clip": 0.07730015367269516, "learning_rates_at_step": { "lora": 9.663659224168382e-05, "row_tokens": 9.663659224168382e-05 }, "learning_rates_after_step": { "lora": 9.657671948588964e-05, "row_tokens": 9.657671948588964e-05 } }, { "update_id": 168, "row_count": 8, "row_ids_sha256": "66926af0de74b0a19d3ee71967c26095f19c97e383b8f8630ab20c25e9dd615c", "input_ids_vector_sha256": "4183d47aad26876edff05d3287a1ee80592adfb9a19992766061641f2ed10274", "labels_vector_sha256": "38eec7f8abcdb1e5a5f33d339ec86ea3757bb099e10b34a82b3b233e839c52d0", "planned_active_tokens": 63951, "realized_active_tokens": 63951, "cumulative_start": 11011696, "cumulative_end": 11075647, "loss_sum": 25328.655212402344, "token_normalized_loss": 0.3960634737909078, "grad_norm_before_clip": 0.07478391379117966, "learning_rates_at_step": { "lora": 9.657671948588964e-05, "row_tokens": 9.657671948588964e-05 }, "learning_rates_after_step": { "lora": 9.650936782416739e-05, "row_tokens": 9.650936782416739e-05 } }, { "update_id": 169, "row_count": 9, "row_ids_sha256": "7db62c86c829f131f2267e6f38ea38f97f7419b2267787ed9ff9d2b6eda24e6f", "input_ids_vector_sha256": "17446f4b00c4442e0642176e5cfbc8778da8590784fad2fb9e3e85221b270f1e", "labels_vector_sha256": "fecf19c6a1e455b2fed0b3f7140e4e25ed5461dd94749189f6178166ddbc5dcc", "planned_active_tokens": 71298, "realized_active_tokens": 71298, "cumulative_start": 11075647, "cumulative_end": 11146945, "loss_sum": 25768.523803710938, "token_normalized_loss": 0.36142000902845717, "grad_norm_before_clip": 0.06545590609312057, "learning_rates_at_step": { "lora": 9.650936782416739e-05, "row_tokens": 9.650936782416739e-05 }, "learning_rates_after_step": { "lora": 9.644701265441141e-05, "row_tokens": 9.644701265441141e-05 } }, { "update_id": 170, "row_count": 13, "row_ids_sha256": "4a860d8849f58c32918e177b43409e2819b06017ec9ea054f27a482c28eec7c1", "input_ids_vector_sha256": "96290ac70cdcaf051de996641843eddb42b708897f35ce69742278e00da04f3a", "labels_vector_sha256": "237c661aa13133eaba3cffbcb684c52115645e9f9adaf0b20f59fd65ebb6dcf2", "planned_active_tokens": 65420, "realized_active_tokens": 65420, "cumulative_start": 11146945, "cumulative_end": 11212365, "loss_sum": 24076.221557617188, "token_normalized_loss": 0.3680253983127054, "grad_norm_before_clip": 0.0831792801618576, "learning_rates_at_step": { "lora": 9.644701265441141e-05, "row_tokens": 9.644701265441141e-05 }, "learning_rates_after_step": { "lora": 9.638802683970887e-05, "row_tokens": 9.638802683970887e-05 } }, { "update_id": 171, "row_count": 12, "row_ids_sha256": "2619f10c15ceed9e01ac64d7dd0ef4888dbd355e088f45a0056169e9147be679", "input_ids_vector_sha256": "f1993463fffe29cee9bdfe0582c4597a3c966b6412f61f3468d7da2539253583", "labels_vector_sha256": "c8ea783790b3ba340370829ba1710f1b6f3053debe3899ae62e4e6e6921ff94a", "planned_active_tokens": 61378, "realized_active_tokens": 61378, "cumulative_start": 11212365, "cumulative_end": 11273743, "loss_sum": 24048.032684326172, "token_normalized_loss": 0.3918021552400888, "grad_norm_before_clip": 0.08569684624671936, "learning_rates_at_step": { "lora": 9.638802683970887e-05, "row_tokens": 9.638802683970887e-05 }, "learning_rates_after_step": { "lora": 9.632500211406623e-05, "row_tokens": 9.632500211406623e-05 } }, { "update_id": 172, "row_count": 11, "row_ids_sha256": "901faea83451db89a67064b6c8b34b6ab6f1ee2ea1b13b74e57d1b615b70a8ed", "input_ids_vector_sha256": "1b03730237c905fece20c166061749d4944e16e476300cd32abb393915e4eb6e", "labels_vector_sha256": "6f842f43f647e890e801faa68992b2f8d3ef05b4dc375b52d5e363d0f2e79c71", "planned_active_tokens": 65050, "realized_active_tokens": 65050, "cumulative_start": 11273743, "cumulative_end": 11338793, "loss_sum": 25591.840576171875, "token_normalized_loss": 0.3934179950218582, "grad_norm_before_clip": 0.08057206124067307, "learning_rates_at_step": { "lora": 9.632500211406623e-05, "row_tokens": 9.632500211406623e-05 }, "learning_rates_after_step": { "lora": 9.626078323244459e-05, "row_tokens": 9.626078323244459e-05 } }, { "update_id": 173, "row_count": 14, "row_ids_sha256": "ade979a838178aa222d0d86c8f3b5a9fdad6593bf4022e1b8569f1feedcb3e2f", "input_ids_vector_sha256": "0c4b410240b927972f38825e756c54c758d7f1f67d92d1e0859a8b9b7fab22ef", "labels_vector_sha256": "87dac8d37126932911717165ed6cc949efde1bb5b1e67b1a93ec33c681263eaf", "planned_active_tokens": 65733, "realized_active_tokens": 65733, "cumulative_start": 11338793, "cumulative_end": 11404526, "loss_sum": 22898.974487304688, "token_normalized_loss": 0.3483634473902711, "grad_norm_before_clip": 0.08047305047512054, "learning_rates_at_step": { "lora": 9.626078323244459e-05, "row_tokens": 9.626078323244459e-05 }, "learning_rates_after_step": { "lora": 9.61929787383292e-05, "row_tokens": 9.61929787383292e-05 } }, { "update_id": 174, "row_count": 14, "row_ids_sha256": "a091eb3aaa49af67d8494df521b6a293230b0219b2770144d36fcb5ddcf38dc2", "input_ids_vector_sha256": "ee237ae4da536ad2cf013ca449b93f83913aa53d6df5786462f3ffafab49c02b", "labels_vector_sha256": "ddd041026ef1566747af6b622f27c38697b99ad12a91377426b0ad9bd70b5546", "planned_active_tokens": 68817, "realized_active_tokens": 68817, "cumulative_start": 11404526, "cumulative_end": 11473343, "loss_sum": 23873.640350341797, "token_normalized_loss": 0.3469148662444134, "grad_norm_before_clip": 0.07473944872617722, "learning_rates_at_step": { "lora": 9.61929787383292e-05, "row_tokens": 9.61929787383292e-05 }, "learning_rates_after_step": { "lora": 9.612186522404085e-05, "row_tokens": 9.612186522404085e-05 } }, { "update_id": 175, "row_count": 13, "row_ids_sha256": "4977ebf5882bde26743db4f0f2b7838dd05031ce5059158e8b371d95a884ce5f", "input_ids_vector_sha256": "2e724080f727c424417a018958d521382d4163e23792bbd28ec73763efcc49ad", "labels_vector_sha256": "29bd5ce1a9c4ad17557d272197c0aafa63f40d8d059939fb89cb4ddcc297e4bc", "planned_active_tokens": 71546, "realized_active_tokens": 71546, "cumulative_start": 11473343, "cumulative_end": 11544889, "loss_sum": 26093.735076904297, "token_normalized_loss": 0.36471270339228323, "grad_norm_before_clip": 0.07679612189531326, "learning_rates_at_step": { "lora": 9.612186522404085e-05, "row_tokens": 9.612186522404085e-05 }, "learning_rates_after_step": { "lora": 9.605970226055057e-05, "row_tokens": 9.605970226055057e-05 } }, { "update_id": 176, "row_count": 12, "row_ids_sha256": "8b56dd39bd618f8686f07b854c7f139fe12e8a2d41aa338c1209df9123cae2de", "input_ids_vector_sha256": "fb7a05fae8ed1dd7b218765d993642735be703a6e164b5bd80945b699be63b95", "labels_vector_sha256": "93f9235061c552d17a8b59ff2f7e0e29e9936e56fcf89821ad0172c51e5fcbdf", "planned_active_tokens": 62027, "realized_active_tokens": 62027, "cumulative_start": 11544889, "cumulative_end": 11606916, "loss_sum": 22071.327606201172, "token_normalized_loss": 0.3558341948861169, "grad_norm_before_clip": 0.08137503266334534, "learning_rates_at_step": { "lora": 9.605970226055057e-05, "row_tokens": 9.605970226055057e-05 }, "learning_rates_after_step": { "lora": 9.59959321361402e-05, "row_tokens": 9.59959321361402e-05 } }, { "update_id": 177, "row_count": 13, "row_ids_sha256": "4e2eb0f44e37bf7f7aa593acce52aec545e6fc2de6297ab29be7667d9acd6b48", "input_ids_vector_sha256": "f14b990ff5a79c8b3c96891f351c1f6014aa85f2386a0806a4032e27836a68f0", "labels_vector_sha256": "a1e8d69bf6377c0cca091a69d597fc6808d11154e6117613ab431d9e5ba985d3", "planned_active_tokens": 63145, "realized_active_tokens": 63145, "cumulative_start": 11606916, "cumulative_end": 11670061, "loss_sum": 22842.397979736328, "token_normalized_loss": 0.3617451576488452, "grad_norm_before_clip": 0.0810239315032959, "learning_rates_at_step": { "lora": 9.59959321361402e-05, "row_tokens": 9.59959321361402e-05 }, "learning_rates_after_step": { "lora": 9.593057237652524e-05, "row_tokens": 9.593057237652524e-05 } }, { "update_id": 178, "row_count": 12, "row_ids_sha256": "8e6ffea0200154ea8167c498ccf82bdc9435642b07d5d6dc54d361fae7d062d9", "input_ids_vector_sha256": "0b29eac3f6eca8e3a4ccb594dda35f91c34b5b6730a9bb118af2e7627f51f440", "labels_vector_sha256": "3b0f4cebfd8a9bfdd0827318df22f7ce015274705e9485c985b7b9ccc88c7b97", "planned_active_tokens": 64221, "realized_active_tokens": 64221, "cumulative_start": 11670061, "cumulative_end": 11734282, "loss_sum": 24064.751953125, "token_normalized_loss": 0.3747178018580371, "grad_norm_before_clip": 0.09058086574077606, "learning_rates_at_step": { "lora": 9.593057237652524e-05, "row_tokens": 9.593057237652524e-05 }, "learning_rates_after_step": { "lora": 9.586534955169788e-05, "row_tokens": 9.586534955169788e-05 } }, { "update_id": 179, "row_count": 9, "row_ids_sha256": "e8f915c751617abf290fae5c7a884e891b2a828e0dcaeeb73f2fa75f2e8e156b", "input_ids_vector_sha256": "ece02488e2b84ed767ac1acceac449d37802db627d2229ae95361bdf54d71516", "labels_vector_sha256": "17082c407676efd51cfed898d3c62f4a55f0e5e6ca127e790785f8d53f45e7f3", "planned_active_tokens": 63596, "realized_active_tokens": 63596, "cumulative_start": 11734282, "cumulative_end": 11797878, "loss_sum": 25580.17431640625, "token_normalized_loss": 0.4022292961256408, "grad_norm_before_clip": 0.0829441025853157, "learning_rates_at_step": { "lora": 9.586534955169788e-05, "row_tokens": 9.586534955169788e-05 }, "learning_rates_after_step": { "lora": 9.579387299927272e-05, "row_tokens": 9.579387299927272e-05 } }, { "update_id": 180, "row_count": 12, "row_ids_sha256": "fa78703d28af26a54c24e3226a1884628f540853c25c4555c0ee4bece5c72355", "input_ids_vector_sha256": "35b040d1bfa11d437940cf7f5774a8d3f91c7807335de6ce8bbc2d2647c56906", "labels_vector_sha256": "41d16f352bbf6972c9f94dca72c3dda48e6b00a9b72aad1c8dbe0c7ef3bdf45a", "planned_active_tokens": 69145, "realized_active_tokens": 69145, "cumulative_start": 11797878, "cumulative_end": 11867023, "loss_sum": 25448.08026123047, "token_normalized_loss": 0.3680393414018435, "grad_norm_before_clip": 0.07899591326713562, "learning_rates_at_step": { "lora": 9.579387299927272e-05, "row_tokens": 9.579387299927272e-05 }, "learning_rates_after_step": { "lora": 9.572372785678811e-05, "row_tokens": 9.572372785678811e-05 } }, { "update_id": 181, "row_count": 14, "row_ids_sha256": "ae10817ca6b646b14657ac68f10694957a495f16d2d15984c76e8f6a681710fa", "input_ids_vector_sha256": "6c863c623b0f892971c7840b9ba90b20ac3f990a8b60fa662d393839794a2bae", "labels_vector_sha256": "f588b3ce5a410a756176bfb1fae1d3dec3722d2fb692e5dccb0ce2d9f8b59a8b", "planned_active_tokens": 67313, "realized_active_tokens": 67313, "cumulative_start": 11867023, "cumulative_end": 11934336, "loss_sum": 21249.898376464844, "token_normalized_loss": 0.31568788163452594, "grad_norm_before_clip": 0.0711819976568222, "learning_rates_at_step": { "lora": 9.572372785678811e-05, "row_tokens": 9.572372785678811e-05 }, "learning_rates_after_step": { "lora": 9.565746675970982e-05, "row_tokens": 9.565746675970982e-05 } }, { "update_id": 182, "row_count": 12, "row_ids_sha256": "7958206751d967054574de312196da3ea4b27f925158ed5319acf46a685ccfbf", "input_ids_vector_sha256": "b0cf945a405e094227b5f73ee263c793c171138d046222a83a9245912f1c629b", "labels_vector_sha256": "eca243e21ffd6935439fb78ea50f5b0fe2472b1603b99004182e48b478f77579", "planned_active_tokens": 63103, "realized_active_tokens": 63103, "cumulative_start": 11934336, "cumulative_end": 11997439, "loss_sum": 23876.784271240234, "token_normalized_loss": 0.3783779578029608, "grad_norm_before_clip": 0.08397044241428375, "learning_rates_at_step": { "lora": 9.565746675970982e-05, "row_tokens": 9.565746675970982e-05 }, "learning_rates_after_step": { "lora": 9.559105924222429e-05, "row_tokens": 9.559105924222429e-05 } }, { "update_id": 183, "row_count": 12, "row_ids_sha256": "a2ce4643d0294deb9620ca1bd3058e3b742f0424bfed872a062ac898a0d7a6af", "input_ids_vector_sha256": "fec929acddebeefc825bf087ce681e8e91eb6799beea9517196f4f9c2347f651", "labels_vector_sha256": "59d3a910ce04cbf6665cc41775f18eceb86c7d1025bc3045cd077ec3ffbf6697", "planned_active_tokens": 62783, "realized_active_tokens": 62783, "cumulative_start": 11997439, "cumulative_end": 12060222, "loss_sum": 21444.951568603516, "token_normalized_loss": 0.34157258443533306, "grad_norm_before_clip": 0.07624668627977371, "learning_rates_at_step": { "lora": 9.559105924222429e-05, "row_tokens": 9.559105924222429e-05 }, "learning_rates_after_step": { "lora": 9.551697697499142e-05, "row_tokens": 9.551697697499142e-05 } }, { "update_id": 184, "row_count": 12, "row_ids_sha256": "12a7a8f2ab20091ae0132e360347e59b914b4301211dfc31844f186c3c9bf393", "input_ids_vector_sha256": "98f3a251f7022cceafcb6a69e29830557078fe829c20c79f97ba3adbdf5395e7", "labels_vector_sha256": "ff0d34a9bbaffab09e08c99de7602bd1213059010d456a81268ccd57d6f55fb9", "planned_active_tokens": 69509, "realized_active_tokens": 69509, "cumulative_start": 12060222, "cumulative_end": 12129731, "loss_sum": 25742.670532226562, "token_normalized_loss": 0.370350178138465, "grad_norm_before_clip": 0.08280965685844421, "learning_rates_at_step": { "lora": 9.551697697499142e-05, "row_tokens": 9.551697697499142e-05 }, "learning_rates_after_step": { "lora": 9.545027117212908e-05, "row_tokens": 9.545027117212908e-05 } }, { "update_id": 185, "row_count": 11, "row_ids_sha256": "93c2a28cc7616b8efd3fce56e7efc42c43cc25593b6c47f4a4853842f88c1bec", "input_ids_vector_sha256": "f85b1e04813696346283b4c7ed4daef96e579af1f8d771fe06957b0a498b9eef", "labels_vector_sha256": "9c4f78102691f47111a01ab2dd4b5c6e8b713aa0ab189ee5384b2dc003ac2321", "planned_active_tokens": 62121, "realized_active_tokens": 62121, "cumulative_start": 12129731, "cumulative_end": 12191852, "loss_sum": 22113.63409423828, "token_normalized_loss": 0.35597678875482175, "grad_norm_before_clip": 0.07921116054058075, "learning_rates_at_step": { "lora": 9.545027117212908e-05, "row_tokens": 9.545027117212908e-05 }, "learning_rates_after_step": { "lora": 9.537958538026302e-05, "row_tokens": 9.537958538026302e-05 } }, { "update_id": 186, "row_count": 13, "row_ids_sha256": "c7ed081acb4bad0fe1d78b2730adb126da82b1bb0ae853a16e8f90cc5aa09b23", "input_ids_vector_sha256": "48d949deee1030bff18afc9a6f1953f2da065cb5ebf9a5d100aed494d557fb42", "labels_vector_sha256": "e463905d34a540cfaf71f6a28bbb5cb8ee0ecaab5df9e4c51b65e5c982d1821f", "planned_active_tokens": 65356, "realized_active_tokens": 65356, "cumulative_start": 12191852, "cumulative_end": 12257208, "loss_sum": 24999.857025146484, "token_normalized_loss": 0.3825181624509836, "grad_norm_before_clip": 0.0880923643708229, "learning_rates_at_step": { "lora": 9.537958538026302e-05, "row_tokens": 9.537958538026302e-05 }, "learning_rates_after_step": { "lora": 9.530893347636159e-05, "row_tokens": 9.530893347636159e-05 } }, { "update_id": 187, "row_count": 13, "row_ids_sha256": "7aaf94e59aab803848b7a70089b7bf787c3dd89a7075c546a387158733977828", "input_ids_vector_sha256": "ab71b7f4cf4ff42b869eb64b997cbba1265d69434bd58c1dc04557db445ffbed", "labels_vector_sha256": "6c61c1ceaf39c7acd64a4bf60ec43ffef355172045e616d6fd0f07cea52c2cf2", "planned_active_tokens": 64851, "realized_active_tokens": 64851, "cumulative_start": 12257208, "cumulative_end": 12322059, "loss_sum": 23513.56768798828, "token_normalized_loss": 0.36257833630920544, "grad_norm_before_clip": 0.07745075225830078, "learning_rates_at_step": { "lora": 9.530893347636159e-05, "row_tokens": 9.530893347636159e-05 }, "learning_rates_after_step": { "lora": 9.523793944670471e-05, "row_tokens": 9.523793944670471e-05 } }, { "update_id": 188, "row_count": 13, "row_ids_sha256": "8b9cab73c62c7ae7217e2fd9d9bd6505cd450ca5417973ca744eb24507701b3e", "input_ids_vector_sha256": "b6cce0998c8629325916cc3d60d41f147341a7fa822b12edb5069eeedc600f04", "labels_vector_sha256": "95a2ac79061e584b7c52559d6af7170ae81f0e61a6cbfa15fb8419a56938b056", "planned_active_tokens": 64699, "realized_active_tokens": 64699, "cumulative_start": 12322059, "cumulative_end": 12386758, "loss_sum": 24186.043701171875, "token_normalized_loss": 0.37382407303315157, "grad_norm_before_clip": 0.08441554009914398, "learning_rates_at_step": { "lora": 9.523793944670471e-05, "row_tokens": 9.523793944670471e-05 }, "learning_rates_after_step": { "lora": 9.516479980469484e-05, "row_tokens": 9.516479980469484e-05 } }, { "update_id": 189, "row_count": 12, "row_ids_sha256": "31a2a333278cb3210d9a4634cc4aa72b38d4d7c939c927d5be68aef154d41996", "input_ids_vector_sha256": "e318f8a18dbefa24423395149901740fbd08c462b2c1747c227e8f468292baff", "labels_vector_sha256": "b87bfe3b706d99ed97461cc73d59ee67e3c27ad6012cd697d8c42312fdb39fb2", "planned_active_tokens": 66177, "realized_active_tokens": 66177, "cumulative_start": 12386758, "cumulative_end": 12452935, "loss_sum": 22632.19110107422, "token_normalized_loss": 0.341994818457685, "grad_norm_before_clip": 0.08089406043291092, "learning_rates_at_step": { "lora": 9.516479980469484e-05, "row_tokens": 9.516479980469484e-05 }, "learning_rates_after_step": { "lora": 9.509208979981991e-05, "row_tokens": 9.509208979981991e-05 } }, { "update_id": 190, "row_count": 15, "row_ids_sha256": "fb191530aada535b2cd206b28023847184b449d90d26141fde01a41dd4d76367", "input_ids_vector_sha256": "1c86a2d757f9104f6985e6013a81ee75180b5e387a60b0fa9dd543d7376f67d4", "labels_vector_sha256": "915e1e7ea3170ebf794596906a6faf08bb2695777e9be8c86f3c3a45b7d482b4", "planned_active_tokens": 65319, "realized_active_tokens": 65319, "cumulative_start": 12452935, "cumulative_end": 12518254, "loss_sum": 21353.666046142578, "token_normalized_loss": 0.3269135480662989, "grad_norm_before_clip": 0.07508543878793716, "learning_rates_at_step": { "lora": 9.509208979981991e-05, "row_tokens": 9.509208979981991e-05 }, "learning_rates_after_step": { "lora": 9.501390200122173e-05, "row_tokens": 9.501390200122173e-05 } }, { "update_id": 191, "row_count": 15, "row_ids_sha256": "208c25363d7da01c483e689e7eac337186420e018b9a82201436e555bb2c5391", "input_ids_vector_sha256": "1296dba0145d6d97b1417012b7065fe7b81d3cf1d3becfc3521971c15d173ccb", "labels_vector_sha256": "26cd2f1c3e95f6d2f908e196be48553403b0793930e97fa621bace32c28c4ff0", "planned_active_tokens": 69730, "realized_active_tokens": 69730, "cumulative_start": 12518254, "cumulative_end": 12587984, "loss_sum": 22819.40135192871, "token_normalized_loss": 0.3272537122031939, "grad_norm_before_clip": 0.07124380022287369, "learning_rates_at_step": { "lora": 9.501390200122173e-05, "row_tokens": 9.501390200122173e-05 }, "learning_rates_after_step": { "lora": 9.494113230941128e-05, "row_tokens": 9.494113230941128e-05 } }, { "update_id": 192, "row_count": 10, "row_ids_sha256": "39cb2fe7cc9c5dc960f96f954bdf9ede3c81c8cf34c78d895863484494e39895", "input_ids_vector_sha256": "185e6ff925b09af410117e618fc6341389a57d576f9f67d33c5f4c37d5153fe4", "labels_vector_sha256": "84434fc86c8ef94ca0244814682b60ca70d5269e4364346b2a97bde894139298", "planned_active_tokens": 64434, "realized_active_tokens": 64434, "cumulative_start": 12587984, "cumulative_end": 12652418, "loss_sum": 23825.853576660156, "token_normalized_loss": 0.36977144949343754, "grad_norm_before_clip": 0.0853351354598999, "learning_rates_at_step": { "lora": 9.494113230941128e-05, "row_tokens": 9.494113230941128e-05 }, "learning_rates_after_step": { "lora": 9.486966631582274e-05, "row_tokens": 9.486966631582274e-05 } }, { "update_id": 193, "row_count": 11, "row_ids_sha256": "dc638a22ed3e3b79f6e10f658132cc095361ae6627cc5f97d822eec9356302de", "input_ids_vector_sha256": "bfc9a86329ac58864528804ff28fd5dc6d82c59c06900d0fb4d0b2c01d66035c", "labels_vector_sha256": "c51d3bc630d1687336550249ac00138f692ef2538cc06bc23771f26b491a3e59", "planned_active_tokens": 62854, "realized_active_tokens": 62854, "cumulative_start": 12652418, "cumulative_end": 12715272, "loss_sum": 20153.154663085938, "token_normalized_loss": 0.32063440136007154, "grad_norm_before_clip": 0.07848037779331207, "learning_rates_at_step": { "lora": 9.486966631582274e-05, "row_tokens": 9.486966631582274e-05 }, "learning_rates_after_step": { "lora": 9.479414644212294e-05, "row_tokens": 9.479414644212294e-05 } }, { "update_id": 194, "row_count": 11, "row_ids_sha256": "6dcafda527795ffa49443c565c974c899dc02065e8479c5160d3fd9726bb72f2", "input_ids_vector_sha256": "020c9c0fe0752f1b4efd3135b83f7a5e69ed9d2985b3950be67563136c8ef471", "labels_vector_sha256": "56836ea9b9b5acacfd8d8eea6f92bbba48c107fde3018dcfca307a9ce12b0e5e", "planned_active_tokens": 65971, "realized_active_tokens": 65971, "cumulative_start": 12715272, "cumulative_end": 12781243, "loss_sum": 21431.29217529297, "token_normalized_loss": 0.32485928931337965, "grad_norm_before_clip": 0.07227052003145218, "learning_rates_at_step": { "lora": 9.479414644212294e-05, "row_tokens": 9.479414644212294e-05 }, "learning_rates_after_step": { "lora": 9.471678786169065e-05, "row_tokens": 9.471678786169065e-05 } }, { "update_id": 195, "row_count": 14, "row_ids_sha256": "3248ab0cff04df18328efcf1ed9455b140ffed800812a1187f4584896053cf6d", "input_ids_vector_sha256": "d7ad139ae5371adce83975c77b6cb5e1e04f5aefe9974a54835f654978eac098", "labels_vector_sha256": "c9db216f9bec8bf38b17e4bc03097c630d4366701049f1e8918c663653e91e4d", "planned_active_tokens": 67110, "realized_active_tokens": 67110, "cumulative_start": 12781243, "cumulative_end": 12848353, "loss_sum": 20942.316650390625, "token_normalized_loss": 0.31205955372359745, "grad_norm_before_clip": 0.07287623733282089, "learning_rates_at_step": { "lora": 9.471678786169065e-05, "row_tokens": 9.471678786169065e-05 }, "learning_rates_after_step": { "lora": 9.464137258589912e-05, "row_tokens": 9.464137258589912e-05 } }, { "update_id": 196, "row_count": 12, "row_ids_sha256": "548336a90ced059e853bd79566ad0c82e7240a3baf8e31856d12c3977764ae5b", "input_ids_vector_sha256": "d241fed3523b2a931ad8ee5fbaf86c6ab585322155c5b0d20900733ff12d8213", "labels_vector_sha256": "7dca11bf3850562df1e0ddb0929cb442e151c158c588b9bf2d33011c29011d52", "planned_active_tokens": 64979, "realized_active_tokens": 64979, "cumulative_start": 12848353, "cumulative_end": 12913332, "loss_sum": 24939.62727355957, "token_normalized_loss": 0.3838105737785988, "grad_norm_before_clip": 0.0830351710319519, "learning_rates_at_step": { "lora": 9.464137258589912e-05, "row_tokens": 9.464137258589912e-05 }, "learning_rates_after_step": { "lora": 9.456603825483006e-05, "row_tokens": 9.456603825483006e-05 } }, { "update_id": 197, "row_count": 11, "row_ids_sha256": "9304932f67b685626c6410693fb4b2bde5208c04f6b5324cf4cc01f735fc332f", "input_ids_vector_sha256": "ee0e8e2d6d1ac4c3eac8ceb52fa807cad71ea19fb1f520ef177c142f2c9a3e0f", "labels_vector_sha256": "dc16df47d1c0dd0998f769883eed943e75ce08f78696d978ce8c4c29e379a194", "planned_active_tokens": 64480, "realized_active_tokens": 64480, "cumulative_start": 12913332, "cumulative_end": 12977812, "loss_sum": 24696.758728027344, "token_normalized_loss": 0.3830142482634514, "grad_norm_before_clip": 0.0763038769364357, "learning_rates_at_step": { "lora": 9.456603825483006e-05, "row_tokens": 9.456603825483006e-05 }, "learning_rates_after_step": { "lora": 9.448657985990935e-05, "row_tokens": 9.448657985990935e-05 } }, { "update_id": 198, "row_count": 10, "row_ids_sha256": "4daf1b80a41a702c706ca358148df4adce7dff1fe5ee3887b1e034991953694e", "input_ids_vector_sha256": "9168f33e076ef552eb51323cb82ad25a6c3263f68b41dfd3fd97de83e42cffec", "labels_vector_sha256": "87d4693da90f5b61ddaa847c33394f1948510ebd4394ef12769b72df3d39bb99", "planned_active_tokens": 67555, "realized_active_tokens": 67555, "cumulative_start": 12977812, "cumulative_end": 13045367, "loss_sum": 24359.146545410156, "token_normalized_loss": 0.3605824372053905, "grad_norm_before_clip": 0.07548870146274567, "learning_rates_at_step": { "lora": 9.448657985990935e-05, "row_tokens": 9.448657985990935e-05 }, "learning_rates_after_step": { "lora": 9.441324046250209e-05, "row_tokens": 9.441324046250209e-05 } }, { "update_id": 199, "row_count": 13, "row_ids_sha256": "bbc1b7f2342687ee5eebbb8e584bed8869459e22372831f646ea538d937ec389", "input_ids_vector_sha256": "7b9a12f366ae264ce8e43131fa1a88d75d24b8b6a4e8876072bee5f25f32fee0", "labels_vector_sha256": "b1c4c209ad490c64451e86b7cd31ee61da1c625205a56bf44441aabb67580b1b", "planned_active_tokens": 61947, "realized_active_tokens": 61947, "cumulative_start": 13045367, "cumulative_end": 13107314, "loss_sum": 17317.731689453125, "token_normalized_loss": 0.27955722939695427, "grad_norm_before_clip": 0.07172242552042007, "learning_rates_at_step": { "lora": 9.441324046250209e-05, "row_tokens": 9.441324046250209e-05 }, "learning_rates_after_step": { "lora": 9.433413030033977e-05, "row_tokens": 9.433413030033977e-05 } }, { "update_id": 200, "row_count": 14, "row_ids_sha256": "5e922a6543b576a431f1a0dea9dfee3f7935421554cf9ecc34e75df3ebaccea6", "input_ids_vector_sha256": "cfb0cde95b3c249025eca20689f6502b152e745ff4f30307570efd1e711945fc", "labels_vector_sha256": "5e936ba8bc4a21f2cf9b5ec5c45c571880741236afa8c2e7771899a1aab26c93", "planned_active_tokens": 66394, "realized_active_tokens": 66394, "cumulative_start": 13107314, "cumulative_end": 13173708, "loss_sum": 21403.89126586914, "token_normalized_loss": 0.32237689047005963, "grad_norm_before_clip": 0.07108402997255325, "learning_rates_at_step": { "lora": 9.433413030033977e-05, "row_tokens": 9.433413030033977e-05 }, "learning_rates_after_step": { "lora": 9.4254187120246e-05, "row_tokens": 9.4254187120246e-05 } }, { "update_id": 201, "row_count": 12, "row_ids_sha256": "7f692f12bb8f41fa0bde9beef8622c8897e8e2cd77553a3dc077ea8af7e13267", "input_ids_vector_sha256": "c7c7f080bce90f5034218cd1770aad051cf6101d190c79b9bfa4c609a4c2f133", "labels_vector_sha256": "abffe7e8856e351d03b84479a53d962e326ea43dc79ea3ea650602edd032f94b", "planned_active_tokens": 66652, "realized_active_tokens": 66652, "cumulative_start": 13173708, "cumulative_end": 13240360, "loss_sum": 24382.60107421875, "token_normalized_loss": 0.3658194964024898, "grad_norm_before_clip": 0.08057540655136108, "learning_rates_at_step": { "lora": 9.4254187120246e-05, "row_tokens": 9.4254187120246e-05 }, "learning_rates_after_step": { "lora": 9.417152088660309e-05, "row_tokens": 9.417152088660309e-05 } }, { "update_id": 202, "row_count": 11, "row_ids_sha256": "9eb05858d3253788e02f52a01a4095c277d2c5f10ed6c83af5377ade1a3847ca", "input_ids_vector_sha256": "5747d933074d772321e4bf4ec7e02daeb2f670f1303e0d4fa52a35c963583ab3", "labels_vector_sha256": "927d13e8535c17f8b8167eb89c7a8e55a0183538febd2314980de20ce58e1085", "planned_active_tokens": 68466, "realized_active_tokens": 68466, "cumulative_start": 13240360, "cumulative_end": 13308826, "loss_sum": 27654.525024414062, "token_normalized_loss": 0.4039161777292972, "grad_norm_before_clip": 0.07960962504148483, "learning_rates_at_step": { "lora": 9.417152088660309e-05, "row_tokens": 9.417152088660309e-05 }, "learning_rates_after_step": { "lora": 9.40965167475732e-05, "row_tokens": 9.40965167475732e-05 } }, { "update_id": 203, "row_count": 12, "row_ids_sha256": "86928ab09972e02dc51bda213820a932f74d27d98769e891f99e33202a2478fe", "input_ids_vector_sha256": "6856a0202fb9357899f548b56b813545b7ded87786093e5236f5d00da19d7871", "labels_vector_sha256": "00966811b36211c5b1c5c295717f88f6eb4b60842f41fe04d17655261e8eb082", "planned_active_tokens": 61727, "realized_active_tokens": 61727, "cumulative_start": 13308826, "cumulative_end": 13370553, "loss_sum": 19688.92837524414, "token_normalized_loss": 0.31896784835232783, "grad_norm_before_clip": 0.07621832191944122, "learning_rates_at_step": { "lora": 9.40965167475732e-05, "row_tokens": 9.40965167475732e-05 }, "learning_rates_after_step": { "lora": 9.40141701077309e-05, "row_tokens": 9.40141701077309e-05 } }, { "update_id": 204, "row_count": 14, "row_ids_sha256": "57c482bff4ce47ed42e32843830fce276858f01a913e1ebbba645e689e9f9ea9", "input_ids_vector_sha256": "823f8c5c9cad1a59075e84945c368b49c5491ef9025ce01e822e91cde27f38e2", "labels_vector_sha256": "5f1652f92861ab8cd0e2e5fe4a762885cf021d2541f01913f9e96e4b57ca2493", "planned_active_tokens": 67348, "realized_active_tokens": 67348, "cumulative_start": 13370553, "cumulative_end": 13437901, "loss_sum": 24101.100372314453, "token_normalized_loss": 0.35785918471691, "grad_norm_before_clip": 0.07695183902978897, "learning_rates_at_step": { "lora": 9.40141701077309e-05, "row_tokens": 9.40141701077309e-05 }, "learning_rates_after_step": { "lora": 9.393436712967925e-05, "row_tokens": 9.393436712967925e-05 } }, { "update_id": 205, "row_count": 15, "row_ids_sha256": "fc026b50f32d41bf5dc35980db98741536e1ffbd0a3670a194dfa677b95aa2cd", "input_ids_vector_sha256": "af734635671f02df0289da08c663c7c338c3872e7b1a5212d3057d53585ab6c8", "labels_vector_sha256": "eb0deac6eb5c6fd6bed55c40e8d6e528a05b1530c0d35f934db969d92c6fc933", "planned_active_tokens": 64855, "realized_active_tokens": 64855, "cumulative_start": 13437901, "cumulative_end": 13502756, "loss_sum": 21330.712829589844, "token_normalized_loss": 0.32889850943782045, "grad_norm_before_clip": 0.07782270014286041, "learning_rates_at_step": { "lora": 9.393436712967925e-05, "row_tokens": 9.393436712967925e-05 }, "learning_rates_after_step": { "lora": 9.38549815644763e-05, "row_tokens": 9.38549815644763e-05 } }, { "update_id": 206, "row_count": 15, "row_ids_sha256": "945a9ef847a14f5afe4f6686ef8aedb79c1e8788f2dd36993fe44f11f5577909", "input_ids_vector_sha256": "04eafa4dcae672e75ed52ed34bc3deae352069c5997f1b5c4c96ad99c2c53953", "labels_vector_sha256": "1ade81c9e42e47655d48f510ab97f3345c94f4bc1ce894db364d63b655a29feb", "planned_active_tokens": 64121, "realized_active_tokens": 64121, "cumulative_start": 13502756, "cumulative_end": 13566877, "loss_sum": 19174.339935302734, "token_normalized_loss": 0.2990337008983443, "grad_norm_before_clip": 0.07251036912202835, "learning_rates_at_step": { "lora": 9.38549815644763e-05, "row_tokens": 9.38549815644763e-05 }, "learning_rates_after_step": { "lora": 9.37702680861944e-05, "row_tokens": 9.37702680861944e-05 } }, { "update_id": 207, "row_count": 16, "row_ids_sha256": "5f94259942b55f7a38e2f716b0635187041e51dbaaca13df2e5a52e723c155df", "input_ids_vector_sha256": "78cbeca2a0f77f6f4a6bc64a7298c3d02dcf5943529d30ba6ed06122d56430ec", "labels_vector_sha256": "6ce089e10683761553c93f56646f14a29203e1ab71a093b918bca22dd1bcb29c", "planned_active_tokens": 67999, "realized_active_tokens": 67999, "cumulative_start": 13566877, "cumulative_end": 13634876, "loss_sum": 22961.347625732422, "token_normalized_loss": 0.33767184261139754, "grad_norm_before_clip": 0.07512258738279343, "learning_rates_at_step": { "lora": 9.37702680861944e-05, "row_tokens": 9.37702680861944e-05 }, "learning_rates_after_step": { "lora": 9.368599068022696e-05, "row_tokens": 9.368599068022696e-05 } }, { "update_id": 208, "row_count": 16, "row_ids_sha256": "90eb43d8988e1446c5c25f69217c0ed0dc5d4095cbd537474e22808f1ca600c3", "input_ids_vector_sha256": "a3aa7f19fc35a2abac5fe216769218611ce3c8faed94b087af2feaf88ba6d4e7", "labels_vector_sha256": "2cfaadb78d3107f245629b45b87f2614caaf94d660fa0fc74487bdc53e4bb236", "planned_active_tokens": 67222, "realized_active_tokens": 67222, "cumulative_start": 13634876, "cumulative_end": 13702098, "loss_sum": 18808.442581176758, "token_normalized_loss": 0.2797959385495338, "grad_norm_before_clip": 0.07099375873804092, "learning_rates_at_step": { "lora": 9.368599068022696e-05, "row_tokens": 9.368599068022696e-05 }, "learning_rates_after_step": { "lora": 9.360969701838717e-05, "row_tokens": 9.360969701838717e-05 } }, { "update_id": 209, "row_count": 14, "row_ids_sha256": "28309716cc38eb73cbc0373b044d002c2d95ae2d236e1d6722d35ead09750943", "input_ids_vector_sha256": "acf39be670562871620929eef7fb2635ddc3704905aa43eddf3853169e557894", "labels_vector_sha256": "0f81c0e01cb032111723a6e17d37ce1f63566b376893dcb6590fe2a808c12ccb", "planned_active_tokens": 60494, "realized_active_tokens": 60494, "cumulative_start": 13702098, "cumulative_end": 13762592, "loss_sum": 21995.16534423828, "token_normalized_loss": 0.3635925107322756, "grad_norm_before_clip": 0.08112706243991852, "learning_rates_at_step": { "lora": 9.360969701838717e-05, "row_tokens": 9.360969701838717e-05 }, "learning_rates_after_step": { "lora": 9.351747676356895e-05, "row_tokens": 9.351747676356895e-05 } }, { "update_id": 210, "row_count": 15, "row_ids_sha256": "d3e863a29cd5612519fb61539e0062c17cb0f34849b489324265d024d19adc5a", "input_ids_vector_sha256": "c74136054ebe582c4d7f55cb2877441530f65485418aae8c362f31ce4dc64c1a", "labels_vector_sha256": "c86f7032fb531800d6848cacdf4e369f907b92b222190d0dc7350d784e1f8289", "planned_active_tokens": 72675, "realized_active_tokens": 72675, "cumulative_start": 13762592, "cumulative_end": 13835267, "loss_sum": 26824.376831054688, "token_normalized_loss": 0.3691004723915334, "grad_norm_before_clip": 0.07402575016021729, "learning_rates_at_step": { "lora": 9.351747676356895e-05, "row_tokens": 9.351747676356895e-05 }, "learning_rates_after_step": { "lora": 9.34413251790774e-05, "row_tokens": 9.34413251790774e-05 } }, { "update_id": 211, "row_count": 15, "row_ids_sha256": "77f99a1623b294029ca46a77c21035139be89ad8fd50c1b558b12147a35e376a", "input_ids_vector_sha256": "7a17235675ffd3c7e8a2e974a099dd20714585603e974bc2bc68535d1fe72798", "labels_vector_sha256": "a1f5ddc1af688096d9c83642128e343cf9108d143c3b4f88ed8f9297f8ef0b34", "planned_active_tokens": 59650, "realized_active_tokens": 59650, "cumulative_start": 13835267, "cumulative_end": 13894917, "loss_sum": 18944.612106323242, "token_normalized_loss": 0.3175961794857207, "grad_norm_before_clip": 0.07546184957027435, "learning_rates_at_step": { "lora": 9.34413251790774e-05, "row_tokens": 9.34413251790774e-05 }, "learning_rates_after_step": { "lora": 9.335844602656205e-05, "row_tokens": 9.335844602656205e-05 } }, { "update_id": 212, "row_count": 16, "row_ids_sha256": "74ff2cb3d861a30fbd43b2da71457870d297d14da9fc9e417f29b88629b9cbc2", "input_ids_vector_sha256": "0deee2a3c717291e41cde2d06fefc4734c091c63bae3db98987f0cde75234dcb", "labels_vector_sha256": "797cf788253146dfbd81860f56b11a7452c1af5910b57f1dd2abf787e0e7d82e", "planned_active_tokens": 64555, "realized_active_tokens": 64555, "cumulative_start": 13894917, "cumulative_end": 13959472, "loss_sum": 21180.120086669922, "token_normalized_loss": 0.328094184597164, "grad_norm_before_clip": 0.07653255015611649, "learning_rates_at_step": { "lora": 9.335844602656205e-05, "row_tokens": 9.335844602656205e-05 }, "learning_rates_after_step": { "lora": 9.32702393484651e-05, "row_tokens": 9.32702393484651e-05 } }, { "update_id": 213, "row_count": 15, "row_ids_sha256": "f64faf2715c697e6c216dc65dd4399b36633eea89c8f08250737bc21b95597c2", "input_ids_vector_sha256": "125e607e1c722e1a5bbabc77ab7db4c65904a0a5fead4b5f564fd1273674275a", "labels_vector_sha256": "bb4048446c11717cea856330acf4fca2d250905daa54ae3846429451f7d3d0b9", "planned_active_tokens": 68295, "realized_active_tokens": 68295, "cumulative_start": 13959472, "cumulative_end": 14027767, "loss_sum": 23150.501434326172, "token_normalized_loss": 0.3389779842495962, "grad_norm_before_clip": 0.07241765409708023, "learning_rates_at_step": { "lora": 9.32702393484651e-05, "row_tokens": 9.32702393484651e-05 }, "learning_rates_after_step": { "lora": 9.318690245342938e-05, "row_tokens": 9.318690245342938e-05 } }, { "update_id": 214, "row_count": 17, "row_ids_sha256": "d1500ac2f8000f5ed0da6e3b6a186a7fbe6efb813ab9bd3bbbea0eabf46c2368", "input_ids_vector_sha256": "0d6999f912e431446a5fccb5e8f6df7f8db03204f6e20e3b3ce6b49e7f201798", "labels_vector_sha256": "f0bdda36478357d6b0dd4b778e2372152530e592f05236fddd16c689b6c0fbec", "planned_active_tokens": 64144, "realized_active_tokens": 64144, "cumulative_start": 14027767, "cumulative_end": 14091911, "loss_sum": 20597.651977539062, "token_normalized_loss": 0.32111580159545805, "grad_norm_before_clip": 0.072569340467453, "learning_rates_at_step": { "lora": 9.318690245342938e-05, "row_tokens": 9.318690245342938e-05 }, "learning_rates_after_step": { "lora": 9.310315464669292e-05, "row_tokens": 9.310315464669292e-05 } }, { "update_id": 215, "row_count": 12, "row_ids_sha256": "eca92ecbbd72276064cc9b7ed925e6ae59cf9424924733d9702c396e803d616a", "input_ids_vector_sha256": "50c33f002554e9b7f9c0e9017dcfec218a160e1a51db7fbb19400122b15f4ada", "labels_vector_sha256": "9fea08d83300ab7149c74cf8d5344d4a49ea3d7249ecd5e545f0188c04f60794", "planned_active_tokens": 64095, "realized_active_tokens": 64095, "cumulative_start": 14091911, "cumulative_end": 14156006, "loss_sum": 21491.447235107422, "token_normalized_loss": 0.3353061429925489, "grad_norm_before_clip": 0.07653530687093735, "learning_rates_at_step": { "lora": 9.310315464669292e-05, "row_tokens": 9.310315464669292e-05 }, "learning_rates_after_step": { "lora": 9.301718732040532e-05, "row_tokens": 9.301718732040532e-05 } }, { "update_id": 216, "row_count": 15, "row_ids_sha256": "e0c7037b20871794fc6753525910cc24d9fdfd031231d5ba5bb42ef10ec3021e", "input_ids_vector_sha256": "e23c38af4bac7425d8ed99d6110531e052903b5bed83fb605ad61ad12418f20b", "labels_vector_sha256": "43281bb6eae3ad0eb753d8952acd644e17cc1db3fa9478df854df53f50a50025", "planned_active_tokens": 65420, "realized_active_tokens": 65420, "cumulative_start": 14156006, "cumulative_end": 14221426, "loss_sum": 20567.623992919922, "token_normalized_loss": 0.31439351869336474, "grad_norm_before_clip": 0.07326708734035492, "learning_rates_at_step": { "lora": 9.301718732040532e-05, "row_tokens": 9.301718732040532e-05 }, "learning_rates_after_step": { "lora": 9.292306785159944e-05, "row_tokens": 9.292306785159944e-05 } }, { "update_id": 217, "row_count": 17, "row_ids_sha256": "bc242623026e4ee447cbfee633a6025bbc7fe2e1bb7814504b51c04f86c8e1d9", "input_ids_vector_sha256": "0f5b00c36adc5331b1927aa4dbea055311c067753755fcd2506b96296467b9e9", "labels_vector_sha256": "3972c44f198689b029a08165ad9ea796a568f2fcead9e55dcd4933a71212cb3d", "planned_active_tokens": 71198, "realized_active_tokens": 71198, "cumulative_start": 14221426, "cumulative_end": 14292624, "loss_sum": 21573.78140258789, "token_normalized_loss": 0.30301105933576633, "grad_norm_before_clip": 0.06744853407144547, "learning_rates_at_step": { "lora": 9.292306785159944e-05, "row_tokens": 9.292306785159944e-05 }, "learning_rates_after_step": { "lora": 9.284142017101563e-05, "row_tokens": 9.284142017101563e-05 } }, { "update_id": 218, "row_count": 10, "row_ids_sha256": "ce1067a6eb58e669307f8811b7a02aceccff32ce409bd2cbf2a6081f91ff3796", "input_ids_vector_sha256": "73385d8d662f8208ef959b3234624b00ede3d46a5813468e939f501589bcc106", "labels_vector_sha256": "9c11b4d9a617686845e1999ec7be58c4262f770bfeea60e51faee009cf67863a", "planned_active_tokens": 61410, "realized_active_tokens": 61410, "cumulative_start": 14292624, "cumulative_end": 14354034, "loss_sum": 22471.23681640625, "token_normalized_loss": 0.36592145931291725, "grad_norm_before_clip": 0.08525923639535904, "learning_rates_at_step": { "lora": 9.284142017101563e-05, "row_tokens": 9.284142017101563e-05 }, "learning_rates_after_step": { "lora": 9.274670767958702e-05, "row_tokens": 9.274670767958702e-05 } }, { "update_id": 219, "row_count": 14, "row_ids_sha256": "f70b9916345d38e95da9ffeb40ec264e292284e05df1118803f1922ef878b8ba", "input_ids_vector_sha256": "a9b87b63875733aced1daef253aaa9d180d88ff0cdc107e9f1370f4609df3a9b", "labels_vector_sha256": "0cf03d3cd0326fb189a00f6b88ecc0aa35e9cbaddd9d61041cb0bb4c3560dc8e", "planned_active_tokens": 70833, "realized_active_tokens": 70833, "cumulative_start": 14354034, "cumulative_end": 14424867, "loss_sum": 23972.102020263672, "token_normalized_loss": 0.3384312681979257, "grad_norm_before_clip": 0.07522421330213547, "learning_rates_at_step": { "lora": 9.274670767958702e-05, "row_tokens": 9.274670767958702e-05 }, "learning_rates_after_step": { "lora": 9.266151640059328e-05, "row_tokens": 9.266151640059328e-05 } }, { "update_id": 220, "row_count": 12, "row_ids_sha256": "bf5700fdf6d9cb0a6ff124cac7a3b70f1865aa8ff5001f6e5653e1393cd40d41", "input_ids_vector_sha256": "54c3956d7346cc585e2dabc2193aeb0a9b15fd0605e2968d2de36b80401b749c", "labels_vector_sha256": "756b837e5baccc0dfa83eb466a76f728657baf94357dde60c6f7153e903454ff", "planned_active_tokens": 63349, "realized_active_tokens": 63349, "cumulative_start": 14424867, "cumulative_end": 14488216, "loss_sum": 19845.64825439453, "token_normalized_loss": 0.31327484655471327, "grad_norm_before_clip": 0.07719442993402481, "learning_rates_at_step": { "lora": 9.266151640059328e-05, "row_tokens": 9.266151640059328e-05 }, "learning_rates_after_step": { "lora": 9.257387038352148e-05, "row_tokens": 9.257387038352148e-05 } }, { "update_id": 221, "row_count": 12, "row_ids_sha256": "1ce2dc7f7a99238e9713907a1f80dc9bc7fbb0634bab219504f7582268c32785", "input_ids_vector_sha256": "eb809438251cb66ff617d9d831494be6a5d36925ac50278b733ce1597c7c563c", "labels_vector_sha256": "c41b6320e4e208956e0457d724061c80594066b222232a0094efc1428b7a7de1", "planned_active_tokens": 64822, "realized_active_tokens": 64822, "cumulative_start": 14488216, "cumulative_end": 14553038, "loss_sum": 24045.455078125, "token_normalized_loss": 0.37094589920281695, "grad_norm_before_clip": 0.0784229189157486, "learning_rates_at_step": { "lora": 9.257387038352148e-05, "row_tokens": 9.257387038352148e-05 }, "learning_rates_after_step": { "lora": 9.248776067563907e-05, "row_tokens": 9.248776067563907e-05 } }, { "update_id": 222, "row_count": 16, "row_ids_sha256": "68452381e52ec26422d7f408b304fbfb4f62f400d886e0efbdbddf9966f85ec4", "input_ids_vector_sha256": "f3a61df7ee0c4227707b03e434b51fa5c48a9280394193b901732344432e2b6e", "labels_vector_sha256": "d8bb9b7e3bb8dd969ad90cc76f5c7adcca69d516e27c13ed25522d6ff06e6c97", "planned_active_tokens": 63344, "realized_active_tokens": 63344, "cumulative_start": 14553038, "cumulative_end": 14616382, "loss_sum": 16192.586486816406, "token_normalized_loss": 0.2556293648461797, "grad_norm_before_clip": 0.070048987865448, "learning_rates_at_step": { "lora": 9.248776067563907e-05, "row_tokens": 9.248776067563907e-05 }, "learning_rates_after_step": { "lora": 9.239794609544364e-05, "row_tokens": 9.239794609544364e-05 } }, { "update_id": 223, "row_count": 14, "row_ids_sha256": "c43e3fde0cc096f8c88758c7f72e7d293da09ee5a51281774777b82323b28b60", "input_ids_vector_sha256": "1cc2651146d8e00a1b339eb7eaa82a631d39211368ce491aaf32f958c14a03ff", "labels_vector_sha256": "58c1eb637d3b4071266090f7dce008ebdd913e2b38732b2c504e66517b371767", "planned_active_tokens": 65715, "realized_active_tokens": 65715, "cumulative_start": 14616382, "cumulative_end": 14682097, "loss_sum": 19231.271942138672, "token_normalized_loss": 0.2926466094824419, "grad_norm_before_clip": 0.07189232856035233, "learning_rates_at_step": { "lora": 9.239794609544364e-05, "row_tokens": 9.239794609544364e-05 }, "learning_rates_after_step": { "lora": 9.230142647868326e-05, "row_tokens": 9.230142647868326e-05 } }, { "update_id": 224, "row_count": 10, "row_ids_sha256": "93eca3db58033336ceaa3acb265b2293187f6eb845d973f79d9be5b2eb6b4253", "input_ids_vector_sha256": "32e58ac89958b36f8c627d3cecde7660222d998b450425f3dd51038f54a5d564", "labels_vector_sha256": "bd0ece3b9c88abcfcc0674b9e972e2cf299db6055b767ee4dd93b7fe16a13d40", "planned_active_tokens": 70225, "realized_active_tokens": 70225, "cumulative_start": 14682097, "cumulative_end": 14752322, "loss_sum": 25077.149780273438, "token_normalized_loss": 0.35709718448235583, "grad_norm_before_clip": 0.07958021759986877, "learning_rates_at_step": { "lora": 9.230142647868326e-05, "row_tokens": 9.230142647868326e-05 }, "learning_rates_after_step": { "lora": 9.221915292021029e-05, "row_tokens": 9.221915292021029e-05 } }, { "update_id": 225, "row_count": 12, "row_ids_sha256": "095f03357b04231ceff23b576dcab908b33f3ceb6fdd28edfbe9729010b81574", "input_ids_vector_sha256": "642be18224bd289ed0fa9963eb8b3c1f8eeec35211dc1fe413920a1ea3ad0657", "labels_vector_sha256": "20d1a59ae72d4ff8f3b3360e618d180f503109efc8f66d94799c46ff0a7eeaa6", "planned_active_tokens": 59542, "realized_active_tokens": 59542, "cumulative_start": 14752322, "cumulative_end": 14811864, "loss_sum": 19716.519744873047, "token_normalized_loss": 0.33113633644944823, "grad_norm_before_clip": 0.08275574445724487, "learning_rates_at_step": { "lora": 9.221915292021029e-05, "row_tokens": 9.221915292021029e-05 }, "learning_rates_after_step": { "lora": 9.211997779769134e-05, "row_tokens": 9.211997779769134e-05 } }, { "update_id": 226, "row_count": 14, "row_ids_sha256": "d94757c9bdc863824193425e684c4fd8cae3ad4ceb2011cbb050138d45e5bf1d", "input_ids_vector_sha256": "4154e9a9865b5d42cf89ea5450b2f04facbcc5fa97500c500b18707b7625566b", "labels_vector_sha256": "98d12a09e0c8f786c0c4c901b859324d8be4ef590d445046bde62cbee1950e81", "planned_active_tokens": 71392, "realized_active_tokens": 71392, "cumulative_start": 14811864, "cumulative_end": 14883256, "loss_sum": 23863.44369506836, "token_normalized_loss": 0.334259352519447, "grad_norm_before_clip": 0.07507393509149551, "learning_rates_at_step": { "lora": 9.211997779769134e-05, "row_tokens": 9.211997779769134e-05 }, "learning_rates_after_step": { "lora": 9.203365696414088e-05, "row_tokens": 9.203365696414088e-05 } }, { "update_id": 227, "row_count": 12, "row_ids_sha256": "7937ed759ca491fd7e842a17fd798e9754866d0dffac93595a9b73c23b9973c7", "input_ids_vector_sha256": "8cb5c0d45181f20cd8ce7b02e27d0949a39cff205929fac106e09f9fbd6b8620", "labels_vector_sha256": "dca262717b2783e8e39bc174b22e49a4d2dfc32aff772eec1c7538bdd1bd0184", "planned_active_tokens": 61805, "realized_active_tokens": 61805, "cumulative_start": 14883256, "cumulative_end": 14945061, "loss_sum": 21375.96240234375, "token_normalized_loss": 0.34586137694917485, "grad_norm_before_clip": 0.08317598700523376, "learning_rates_at_step": { "lora": 9.203365696414088e-05, "row_tokens": 9.203365696414088e-05 }, "learning_rates_after_step": { "lora": 9.194164777314238e-05, "row_tokens": 9.194164777314238e-05 } }, { "update_id": 228, "row_count": 16, "row_ids_sha256": "62c93e6eec06cde3d1eff3a377cf9743ee8d4a18c75bb3b532532f96849b7942", "input_ids_vector_sha256": "36d8d2ba9067dee2bef97e48853c73b5cef23a10072d2c8c503cc742b309de63", "labels_vector_sha256": "111626f61321d6a70716393d95e4be11937b1e6c30e0592ddab0af42864b4b34", "planned_active_tokens": 65542, "realized_active_tokens": 65542, "cumulative_start": 14945061, "cumulative_end": 15010603, "loss_sum": 18624.321548461914, "token_normalized_loss": 0.28415857844530096, "grad_norm_before_clip": 0.07473009079694748, "learning_rates_at_step": { "lora": 9.194164777314238e-05, "row_tokens": 9.194164777314238e-05 }, "learning_rates_after_step": { "lora": 9.185062962041326e-05, "row_tokens": 9.185062962041326e-05 } }, { "update_id": 229, "row_count": 13, "row_ids_sha256": "8f5199ab501b49913a016529b8efce0f6e6cd83bbd8f59b446869663a6d89264", "input_ids_vector_sha256": "c2f55dd60478166165985c5fe7d25259e01e598cc7b859f3d2b2ea008dcaf1e0", "labels_vector_sha256": "a5d082eaa753d4b6e722994a46cd17404e612d9c5cc955b46c25a64cb159ed24", "planned_active_tokens": 64501, "realized_active_tokens": 64501, "cumulative_start": 15010603, "cumulative_end": 15075104, "loss_sum": 19493.270874023438, "token_normalized_loss": 0.30221656833263727, "grad_norm_before_clip": 0.07419600337743759, "learning_rates_at_step": { "lora": 9.185062962041326e-05, "row_tokens": 9.185062962041326e-05 }, "learning_rates_after_step": { "lora": 9.175180582508202e-05, "row_tokens": 9.175180582508202e-05 } }, { "update_id": 230, "row_count": 16, "row_ids_sha256": "f54906b017c8ba22147facec1a08225f6e226ec3588a6d691873869a3fe4e194", "input_ids_vector_sha256": "127a9484e4d6af2e7063905819d0dd50eedc70c64e9f3f93d2f1ce22506661d3", "labels_vector_sha256": "e5a9f8affc40352bdbeaca8fae17f95bc1d97a0979df7bf32ef4ca0637119274", "planned_active_tokens": 69662, "realized_active_tokens": 69662, "cumulative_start": 15075104, "cumulative_end": 15144766, "loss_sum": 24184.830505371094, "token_normalized_loss": 0.3471739327807283, "grad_norm_before_clip": 0.07684659957885742, "learning_rates_at_step": { "lora": 9.175180582508202e-05, "row_tokens": 9.175180582508202e-05 }, "learning_rates_after_step": { "lora": 9.166491091850149e-05, "row_tokens": 9.166491091850149e-05 } }, { "update_id": 231, "row_count": 12, "row_ids_sha256": "cc0be1f902075f36c5caf086d189b4b2e2d4b6202030956b83a7ccdd839e040a", "input_ids_vector_sha256": "28c54ba91b704e0918bf2f715f4ddd84e4005b7df68bc22e81ae7203b1ab3f6f", "labels_vector_sha256": "0d0953f1b7563d89f7eccafd1062e3d83caf5fe39b5598d2763f57fd0118e312", "planned_active_tokens": 60940, "realized_active_tokens": 60940, "cumulative_start": 15144766, "cumulative_end": 15205706, "loss_sum": 20267.06690979004, "token_normalized_loss": 0.3325741206069911, "grad_norm_before_clip": 0.08094453811645508, "learning_rates_at_step": { "lora": 9.166491091850149e-05, "row_tokens": 9.166491091850149e-05 }, "learning_rates_after_step": { "lora": 9.156795501221606e-05, "row_tokens": 9.156795501221606e-05 } }, { "update_id": 232, "row_count": 16, "row_ids_sha256": "1179c953def62d1c9cfb028e75b52fe48cff8acae2038c435bd899b3c738ebd7", "input_ids_vector_sha256": "5500d8b58f5caec27eaac112ad33d474823a4a58592a94c2a5139e9d2677b839", "labels_vector_sha256": "062929110c881a3fdf5a9abde0b82f1c87d868c3ced71555b8aab59d711eaa99", "planned_active_tokens": 67656, "realized_active_tokens": 67656, "cumulative_start": 15205706, "cumulative_end": 15273362, "loss_sum": 22190.94696044922, "token_normalized_loss": 0.3279967328906412, "grad_norm_before_clip": 0.07566488534212112, "learning_rates_at_step": { "lora": 9.156795501221606e-05, "row_tokens": 9.156795501221606e-05 }, "learning_rates_after_step": { "lora": 9.147681985302498e-05, "row_tokens": 9.147681985302498e-05 } }, { "update_id": 233, "row_count": 13, "row_ids_sha256": "cc76c6426e9abc2706ea21da713b534bd758fdb9f9c38c40690f03577d83390b", "input_ids_vector_sha256": "168fce558efad2a11ba0c36d4a74aae1937ec87c5ebe6785e64c43cecc30c823", "labels_vector_sha256": "b0f66f47c35b58a0a3baea4e95cdfccbed6049cb3d093097c1952a90e048116e", "planned_active_tokens": 63273, "realized_active_tokens": 63273, "cumulative_start": 15273362, "cumulative_end": 15336635, "loss_sum": 19035.510498046875, "token_normalized_loss": 0.30084728870208266, "grad_norm_before_clip": 0.07651006430387497, "learning_rates_at_step": { "lora": 9.147681985302498e-05, "row_tokens": 9.147681985302498e-05 }, "learning_rates_after_step": { "lora": 9.1381642202738e-05, "row_tokens": 9.1381642202738e-05 } }, { "update_id": 234, "row_count": 14, "row_ids_sha256": "e9caba307c3fd92eea92387e4840d01cd6a300703d0494364f6776c4d85c1b9d", "input_ids_vector_sha256": "b646643afa857542c0372448212d9f4a197ec203b29014b155d57cd4fe50db9f", "labels_vector_sha256": "6789792d6fb64da9b4eb3371bd0478d3f85f4c6c5a69580c927364275a222475", "planned_active_tokens": 65753, "realized_active_tokens": 65753, "cumulative_start": 15336635, "cumulative_end": 15402388, "loss_sum": 21986.855209350586, "token_normalized_loss": 0.3343855825490941, "grad_norm_before_clip": 0.07656753808259964, "learning_rates_at_step": { "lora": 9.1381642202738e-05, "row_tokens": 9.1381642202738e-05 }, "learning_rates_after_step": { "lora": 9.128022021101366e-05, "row_tokens": 9.128022021101366e-05 } }, { "update_id": 235, "row_count": 16, "row_ids_sha256": "0ee56c211314f97762bdba90d034d3a5b4032d4365d05eb00d639a76cf4afc8f", "input_ids_vector_sha256": "c1acba1a32b54b2ca9b35726997653096adfea5068ce2651bf5fe29b1c31f4e2", "labels_vector_sha256": "66d9e9027a700343bc5c11f4cc317b0be674aeba3fbf36654f0eb4b5d8c4517d", "planned_active_tokens": 69706, "realized_active_tokens": 69706, "cumulative_start": 15402388, "cumulative_end": 15472094, "loss_sum": 21903.966400146484, "token_normalized_loss": 0.31423358678085794, "grad_norm_before_clip": 0.07312610000371933, "learning_rates_at_step": { "lora": 9.128022021101366e-05, "row_tokens": 9.128022021101366e-05 }, "learning_rates_after_step": { "lora": 9.118786825417047e-05, "row_tokens": 9.118786825417047e-05 } }, { "update_id": 236, "row_count": 17, "row_ids_sha256": "c66f051ab3005480205d59b20a7db588d55c3227cd416c4282496d410ab132c7", "input_ids_vector_sha256": "0eece23b5bed23fe89b234afb41bd72e03a3747cd4c6c796480630e7aa2b469a", "labels_vector_sha256": "d0e48975ec38f80e34ebf854ffbb92afdfa4ebf221eabe91ddf662e6078aed6e", "planned_active_tokens": 63154, "realized_active_tokens": 63154, "cumulative_start": 15472094, "cumulative_end": 15535248, "loss_sum": 18041.844696044922, "token_normalized_loss": 0.2856801579637857, "grad_norm_before_clip": 0.07230637967586517, "learning_rates_at_step": { "lora": 9.118786825417047e-05, "row_tokens": 9.118786825417047e-05 }, "learning_rates_after_step": { "lora": 9.108795793349308e-05, "row_tokens": 9.108795793349308e-05 } }, { "update_id": 237, "row_count": 14, "row_ids_sha256": "ec71c32e197bdf7741be850320504d49d1eba8481a5202b933b3543332b56b37", "input_ids_vector_sha256": "e80ede5f2714afa334fea5675cff09a66d03ec0f8f34860a0dc6489e7d2d5856", "labels_vector_sha256": "6da9e865f6f0f3968011523e9143482322761198fa5ac8fc6e1fd435dd95199c", "planned_active_tokens": 67987, "realized_active_tokens": 67987, "cumulative_start": 15535248, "cumulative_end": 15603235, "loss_sum": 23112.107879638672, "token_normalized_loss": 0.33994892964300044, "grad_norm_before_clip": 0.07406521588563919, "learning_rates_at_step": { "lora": 9.108795793349308e-05, "row_tokens": 9.108795793349308e-05 }, "learning_rates_after_step": { "lora": 9.099362030916094e-05, "row_tokens": 9.099362030916094e-05 } }, { "update_id": 238, "row_count": 14, "row_ids_sha256": "af41af65644c2cb3d39c3b0f5c651268a23816184f730c1f5c6db2e1a06ce20c", "input_ids_vector_sha256": "d1393c65195b4e326921e2d809f7edbca0c0dcecdc4822f8abee8432050a7897", "labels_vector_sha256": "9330400bd8d21981b6f81dc8bbf4aaf341ffe3c631dca7525f3a9ce43d899e52", "planned_active_tokens": 63880, "realized_active_tokens": 63880, "cumulative_start": 15603235, "cumulative_end": 15667115, "loss_sum": 21623.524780273438, "token_normalized_loss": 0.33850226644135, "grad_norm_before_clip": 0.07769907265901566, "learning_rates_at_step": { "lora": 9.099362030916094e-05, "row_tokens": 9.099362030916094e-05 }, "learning_rates_after_step": { "lora": 9.088415943478743e-05, "row_tokens": 9.088415943478743e-05 } }, { "update_id": 239, "row_count": 14, "row_ids_sha256": "001eb879c8b62f8666aa2ea5258b749ae36e6a6ec2073f297fa94c7e7a052af0", "input_ids_vector_sha256": "9adc1da15b5b0d297902e80500fb7bbd7ecb7f26ed401a20e15a840cc5b6dd98", "labels_vector_sha256": "34d4d8bca51af7619ccf06cc91c30469d6667532c005d5bde0e83160262cc0c2", "planned_active_tokens": 73744, "realized_active_tokens": 73744, "cumulative_start": 15667115, "cumulative_end": 15740859, "loss_sum": 26634.682647705078, "token_normalized_loss": 0.36117762323314545, "grad_norm_before_clip": 0.07443805038928986, "learning_rates_at_step": { "lora": 9.088415943478743e-05, "row_tokens": 9.088415943478743e-05 }, "learning_rates_after_step": { "lora": 9.080041373034683e-05, "row_tokens": 9.080041373034683e-05 } }, { "update_id": 240, "row_count": 11, "row_ids_sha256": "0b7ef84b6fda030a047f119350be771daec4f9c779a64f468ffd370af59b48f5", "input_ids_vector_sha256": "ca652690a734730fb31dd240b739fd38d61912c070852ad7c163c9ebe23a7ff4", "labels_vector_sha256": "90a56bca4c274b5fe4dd11552d26d4ec74d3fac3263cfbef281556717278d6e2", "planned_active_tokens": 56151, "realized_active_tokens": 56151, "cumulative_start": 15740859, "cumulative_end": 15797010, "loss_sum": 19899.898071289062, "token_normalized_loss": 0.3543997091999975, "grad_norm_before_clip": 0.08258607238531113, "learning_rates_at_step": { "lora": 9.080041373034683e-05, "row_tokens": 9.080041373034683e-05 }, "learning_rates_after_step": { "lora": 9.069900564227573e-05, "row_tokens": 9.069900564227573e-05 } }, { "update_id": 241, "row_count": 12, "row_ids_sha256": "7a72eec6ccf59a6877ecb49f266264c3ec44483b7349e27031697e4ba2e3b76c", "input_ids_vector_sha256": "b503fc03d40e1d0edbd8236014b0cd15232b4fe66fea0f2ad09d6d0dbea82845", "labels_vector_sha256": "171ec9c9b2f51c4f8db3d0080aa5002fed8f227798609644e79fc97a8d8f0f46", "planned_active_tokens": 67687, "realized_active_tokens": 67687, "cumulative_start": 15797010, "cumulative_end": 15864697, "loss_sum": 22450.62466430664, "token_normalized_loss": 0.3316829622277046, "grad_norm_before_clip": 0.07294460386037827, "learning_rates_at_step": { "lora": 9.069900564227573e-05, "row_tokens": 9.069900564227573e-05 }, "learning_rates_after_step": { "lora": 9.060741205862071e-05, "row_tokens": 9.060741205862071e-05 } }, { "update_id": 242, "row_count": 17, "row_ids_sha256": "3fdfa5ae534aa5ba5fde3dbdcf38761985b0eb932be116a4c71833478f01aeb6", "input_ids_vector_sha256": "9a1be792020d564bd4e08e3fd7fdcac04dc884799eb6a25dc0b798289a8e26a8", "labels_vector_sha256": "71c622e9e8f405f3482b7cbc7d29a276342faf4f8ce3f5ca552702dd1e631b2e", "planned_active_tokens": 60852, "realized_active_tokens": 60852, "cumulative_start": 15864697, "cumulative_end": 15925549, "loss_sum": 17421.45835876465, "token_normalized_loss": 0.28629228881161917, "grad_norm_before_clip": 0.07240728288888931, "learning_rates_at_step": { "lora": 9.060741205862071e-05, "row_tokens": 9.060741205862071e-05 }, "learning_rates_after_step": { "lora": 9.0503677262657e-05, "row_tokens": 9.0503677262657e-05 } }, { "update_id": 243, "row_count": 13, "row_ids_sha256": "44ecfed932fe53b94d765cb27eb00d72b4d604c2ebe53f5bd4184a19df10b3fd", "input_ids_vector_sha256": "89d5da49789e22beab21888c78bdfbc5c5df27f3e800116ca437093d11a0f450", "labels_vector_sha256": "a1d85b986857ddd28685c3e0c03fab89401f049d6a3d47c67cf43144692df5a8", "planned_active_tokens": 68598, "realized_active_tokens": 68598, "cumulative_start": 15925549, "cumulative_end": 15994147, "loss_sum": 23191.62518310547, "token_normalized_loss": 0.3380801945115815, "grad_norm_before_clip": 0.0771583542227745, "learning_rates_at_step": { "lora": 9.0503677262657e-05, "row_tokens": 9.0503677262657e-05 }, "learning_rates_after_step": { "lora": 9.040507611024106e-05, "row_tokens": 9.040507611024106e-05 } }, { "update_id": 244, "row_count": 11, "row_ids_sha256": "8205a143e8895480cda5ae2759abd2449c06a1ccfb7d66790e467fff9d15f45b", "input_ids_vector_sha256": "9204227eb508ba5ee99820f0665ecdc70047b19ab8b655226e0e43c312e4fec0", "labels_vector_sha256": "50c4085186731d87b9bb417e934d66bc82e0b6cd7f1d74a219a9caefa29877ad", "planned_active_tokens": 64893, "realized_active_tokens": 64893, "cumulative_start": 15994147, "cumulative_end": 16059040, "loss_sum": 22460.374084472656, "token_normalized_loss": 0.34611397353293355, "grad_norm_before_clip": 0.08130306750535965, "learning_rates_at_step": { "lora": 9.040507611024106e-05, "row_tokens": 9.040507611024106e-05 }, "learning_rates_after_step": { "lora": 9.030533457334609e-05, "row_tokens": 9.030533457334609e-05 } }, { "update_id": 245, "row_count": 14, "row_ids_sha256": "c74a1e24094baef5358718b2b04f08c3a9abb86dc0a73fa9cae9abaaa5cd64b3", "input_ids_vector_sha256": "6fcbe785d6c133846368979189cd5526bf4e8d7bc6083e825ab96bf537fea3b1", "labels_vector_sha256": "4b5ead192312436c2e991be6c506d6d7867c66efe4f27aadd5401fe727cf6cf6", "planned_active_tokens": 65341, "realized_active_tokens": 65341, "cumulative_start": 16059040, "cumulative_end": 16124381, "loss_sum": 21431.277801513672, "token_normalized_loss": 0.32799127349617657, "grad_norm_before_clip": 0.07756909728050232, "learning_rates_at_step": { "lora": 9.030533457334609e-05, "row_tokens": 9.030533457334609e-05 }, "learning_rates_after_step": { "lora": 9.020763045501946e-05, "row_tokens": 9.020763045501946e-05 } }, { "update_id": 246, "row_count": 14, "row_ids_sha256": "451a845e3f8504d1c062a57b934c2d9371eba2cf81adfbfa43acb6a0d92b0819", "input_ids_vector_sha256": "a744b91c1214d6a09590beacbcfeab028607b745f45297f11e19a76d4b1177df", "labels_vector_sha256": "d752631f9875d7e716febd8aeecfe7ef166931738988296007178cd064c0b5df", "planned_active_tokens": 63716, "realized_active_tokens": 63716, "cumulative_start": 16124381, "cumulative_end": 16188097, "loss_sum": 19936.369750976562, "token_normalized_loss": 0.3128942455737423, "grad_norm_before_clip": 0.07698657363653183, "learning_rates_at_step": { "lora": 9.020763045501946e-05, "row_tokens": 9.020763045501946e-05 }, "learning_rates_after_step": { "lora": 9.010721897879382e-05, "row_tokens": 9.010721897879382e-05 } }, { "update_id": 247, "row_count": 13, "row_ids_sha256": "81f7d4c08140732ba18cf0af7811517bec11bf76723c247b52fa8aef849e1bab", "input_ids_vector_sha256": "5e51d947ca7966988ec2b81640d9c3e553b9bd825ed6c241920e399f90700283", "labels_vector_sha256": "159c200178bfb8ba8817b08e60b4f9d5f33e91e39c0d681bb014fb7a8c70500e", "planned_active_tokens": 65187, "realized_active_tokens": 65187, "cumulative_start": 16188097, "cumulative_end": 16253284, "loss_sum": 22952.530883789062, "token_normalized_loss": 0.35210288683002844, "grad_norm_before_clip": 0.08355046063661575, "learning_rates_at_step": { "lora": 9.010721897879382e-05, "row_tokens": 9.010721897879382e-05 }, "learning_rates_after_step": { "lora": 9.000273029575849e-05, "row_tokens": 9.000273029575849e-05 } }, { "update_id": 248, "row_count": 14, "row_ids_sha256": "e4feef7a161f4f2a8ce25033293ed23f6cd20b9ecd02b1e6739b380a1eb087f4", "input_ids_vector_sha256": "cb02fc34bda0a33e76a36d106d4f88e02122b5bedfaf01e9b346c2935870b737", "labels_vector_sha256": "f15f9ef25dd7d48d9cbb4758483d629fb4a869a43d867a4cad0820e96e080b37", "planned_active_tokens": 67522, "realized_active_tokens": 67522, "cumulative_start": 16253284, "cumulative_end": 16320806, "loss_sum": 22313.245880126953, "token_normalized_loss": 0.3304589005083818, "grad_norm_before_clip": 0.07984024286270142, "learning_rates_at_step": { "lora": 9.000273029575849e-05, "row_tokens": 9.000273029575849e-05 }, "learning_rates_after_step": { "lora": 8.990073011742914e-05, "row_tokens": 8.990073011742914e-05 } }, { "update_id": 249, "row_count": 14, "row_ids_sha256": "ec8ec43bf3fb896566b22786b0415067c63c077823c54391d8f2bf2a8084b805", "input_ids_vector_sha256": "83e86b732833df5d9fd1751a892b7c1ad909cddc1d2c757b0198a1203e0c2ee8", "labels_vector_sha256": "19f97bb8fa27ab00f0cd0386a7054f9bc08c15a9f16ec33bd303a4ce3584aa4f", "planned_active_tokens": 65612, "realized_active_tokens": 65612, "cumulative_start": 16320806, "cumulative_end": 16386418, "loss_sum": 20184.428314208984, "token_normalized_loss": 0.30763318164678694, "grad_norm_before_clip": 0.07683776319026947, "learning_rates_at_step": { "lora": 8.990073011742914e-05, "row_tokens": 8.990073011742914e-05 }, "learning_rates_after_step": { "lora": 8.979290959315824e-05, "row_tokens": 8.979290959315824e-05 } }, { "update_id": 250, "row_count": 14, "row_ids_sha256": "770880e9d0a3600994f7147c3e1c0d00c619c260a0909522dee5db74bae62aa1", "input_ids_vector_sha256": "32d227bf87e6ac910999ea05456dabad9328b56c565e769ccf7d0859a653f04b", "labels_vector_sha256": "88183a9f9f1c4ff7dd9a5e54e22a09a6d72316a8110b444913bc0ed6fe821a95", "planned_active_tokens": 69037, "realized_active_tokens": 69037, "cumulative_start": 16386418, "cumulative_end": 16455455, "loss_sum": 23675.944702148438, "token_normalized_loss": 0.3429457349269006, "grad_norm_before_clip": 0.0768950805068016, "learning_rates_at_step": { "lora": 8.979290959315824e-05, "row_tokens": 8.979290959315824e-05 }, "learning_rates_after_step": { "lora": 8.968931085544803e-05, "row_tokens": 8.968931085544803e-05 } }, { "update_id": 251, "row_count": 9, "row_ids_sha256": "2d60814612fc0f6aa40167eb330cfb2ef00d387569d94b0fb5cbb40b461f79f9", "input_ids_vector_sha256": "37159000b3849dcc0e224a822d78f213c68d3c0ac298e981c966f089aa0afb1f", "labels_vector_sha256": "4613879f01a09a84a096547aba259377a94908320c9b6bef2b32da7d72f08c97", "planned_active_tokens": 66030, "realized_active_tokens": 66030, "cumulative_start": 16455455, "cumulative_end": 16521485, "loss_sum": 25271.345581054688, "token_normalized_loss": 0.38272520946622274, "grad_norm_before_clip": 0.0813445895910263, "learning_rates_at_step": { "lora": 8.968931085544803e-05, "row_tokens": 8.968931085544803e-05 }, "learning_rates_after_step": { "lora": 8.958844131657485e-05, "row_tokens": 8.958844131657485e-05 } }, { "update_id": 252, "row_count": 11, "row_ids_sha256": "9ee6b7fa1e48e04026601fca9ad7cfd4dc2cb99bb4e4d65ba6151f06ea879301", "input_ids_vector_sha256": "c707fd151de5b7e0c684ec1e394eb02eb679cf4db0564e872336d975bd0fca4e", "labels_vector_sha256": "0dd0dd70af028340d0bbe3760ece7322318f2ecc632224867889ab5884e5a332", "planned_active_tokens": 64009, "realized_active_tokens": 64009, "cumulative_start": 16521485, "cumulative_end": 16585494, "loss_sum": 26827.617645263672, "token_normalized_loss": 0.41912258659350515, "grad_norm_before_clip": 0.08595157414674759, "learning_rates_at_step": { "lora": 8.958844131657485e-05, "row_tokens": 8.958844131657485e-05 }, "learning_rates_after_step": { "lora": 8.94804314330101e-05, "row_tokens": 8.94804314330101e-05 } }, { "update_id": 253, "row_count": 10, "row_ids_sha256": "f1a3d9330059b676ac4c869530bd50ee79d32543f13590ef407cf7713b5b1bd6", "input_ids_vector_sha256": "1ac759e59dde9a09c8df865cdc72ff1b49b77ea89169ca986be313ae840797d9", "labels_vector_sha256": "7594bda2dc3f0932e732ca90ad276114e1b5d12d93f4faa54b284754e190f2db", "planned_active_tokens": 68237, "realized_active_tokens": 68237, "cumulative_start": 16585494, "cumulative_end": 16653731, "loss_sum": 25543.172393798828, "token_normalized_loss": 0.3743302371704329, "grad_norm_before_clip": 0.07944438606500626, "learning_rates_at_step": { "lora": 8.94804314330101e-05, "row_tokens": 8.94804314330101e-05 }, "learning_rates_after_step": { "lora": 8.938503750766592e-05, "row_tokens": 8.938503750766592e-05 } }, { "update_id": 254, "row_count": 11, "row_ids_sha256": "2541e5670871a3d18f2a6a8dd04427d374678fce75d6336c497a411d5109566a", "input_ids_vector_sha256": "c3b5e0ccc536d3a0510a06f292e13e127e3e7f48652b88ca1984a34e314a6194", "labels_vector_sha256": "aec4a9dffda958d4c3b6bf0bc2039858f91ee266852725104a8a7cb1089feed2", "planned_active_tokens": 60010, "realized_active_tokens": 60010, "cumulative_start": 16653731, "cumulative_end": 16713741, "loss_sum": 19922.96173095703, "token_normalized_loss": 0.3319940298443098, "grad_norm_before_clip": 0.07639646530151367, "learning_rates_at_step": { "lora": 8.938503750766592e-05, "row_tokens": 8.938503750766592e-05 }, "learning_rates_after_step": { "lora": 8.92717062032199e-05, "row_tokens": 8.92717062032199e-05 } }, { "update_id": 255, "row_count": 15, "row_ids_sha256": "873619c44bc5691ee69634f0f6889b5461f633a65a3092393607ef3cf23e8b74", "input_ids_vector_sha256": "6c6a850d85a26446c58352e759de66e9c9fbbb2534d704a55122bb8eed3a993b", "labels_vector_sha256": "580e544b05060caf36554e4290eca332665ea788d5af77ebbcadc33203e14afb", "planned_active_tokens": 70986, "realized_active_tokens": 70986, "cumulative_start": 16713741, "cumulative_end": 16784727, "loss_sum": 23445.180389404297, "token_normalized_loss": 0.3302789337250204, "grad_norm_before_clip": 0.07086203992366791, "learning_rates_at_step": { "lora": 8.92717062032199e-05, "row_tokens": 8.92717062032199e-05 }, "learning_rates_after_step": { "lora": 8.917705838937048e-05, "row_tokens": 8.917705838937048e-05 } }, { "update_id": 256, "row_count": 12, "row_ids_sha256": "2c9ebb9c87ff9c189e0bf6f5bfe72d8be1353168cb04e666550855d428d85eda", "input_ids_vector_sha256": "8ecb8e1c047fdffb179214ec70bd277dfc3951499e37c8661d6555041c6d5d32", "labels_vector_sha256": "d2a246dd058fc18483aa793973873a594a06d40aaa9f1ebcdce948650fb3eed9", "planned_active_tokens": 59031, "realized_active_tokens": 59031, "cumulative_start": 16784727, "cumulative_end": 16843758, "loss_sum": 21326.892150878906, "token_normalized_loss": 0.3612829217001051, "grad_norm_before_clip": 0.08215050399303436, "learning_rates_at_step": { "lora": 8.917705838937048e-05, "row_tokens": 8.917705838937048e-05 }, "learning_rates_after_step": { "lora": 8.907009632728713e-05, "row_tokens": 8.907009632728713e-05 } }, { "update_id": 257, "row_count": 11, "row_ids_sha256": "29154608ff33ef88d71d41cdab2758b3ebee4d1b346b3241a2a46edd61dee36a", "input_ids_vector_sha256": "a3d078b769cdaad734ba2a4cd6d5bc4cbfa51e08278f3ddfbe0c33cedd4fe556", "labels_vector_sha256": "bac8d3af7f4e08d0abe99bb1f439c0a6683d3669d1544aa8dac1cd5524e3c7f8", "planned_active_tokens": 66439, "realized_active_tokens": 66439, "cumulative_start": 16843758, "cumulative_end": 16910197, "loss_sum": 26285.726593017578, "token_normalized_loss": 0.3956369992476946, "grad_norm_before_clip": 0.08022768795490265, "learning_rates_at_step": { "lora": 8.907009632728713e-05, "row_tokens": 8.907009632728713e-05 }, "learning_rates_after_step": { "lora": 8.895891367676668e-05, "row_tokens": 8.895891367676668e-05 } }, { "update_id": 258, "row_count": 15, "row_ids_sha256": "de0d033eba87409213f3a3189031a861ad00dfac5cb88d2f93757e932e52f307", "input_ids_vector_sha256": "4ab00d3371394587454d65d699430ba37575bf4782b290f09cf35367bffd87e8", "labels_vector_sha256": "53ab4594b0ed48353184b9a1db00f64d327d9a5a9a5a0eadc4f18405d5bf8dbf", "planned_active_tokens": 68759, "realized_active_tokens": 68759, "cumulative_start": 16910197, "cumulative_end": 16978956, "loss_sum": 23563.518829345703, "token_normalized_loss": 0.34269722988038953, "grad_norm_before_clip": 0.07540732622146606, "learning_rates_at_step": { "lora": 8.895891367676668e-05, "row_tokens": 8.895891367676668e-05 }, "learning_rates_after_step": { "lora": 8.885324088343288e-05, "row_tokens": 8.885324088343288e-05 } }, { "update_id": 259, "row_count": 12, "row_ids_sha256": "8f0b6dac569979bb82b847a86c081f64ff65c4c70394e02029661b3f48322bcd", "input_ids_vector_sha256": "366ba256d63a4d3c5fffdfca15ecad67c87f7e01c8e21f79267ede8660ea637b", "labels_vector_sha256": "88312cd31b7d4d22d74e984cbc1bbd15af40282a8dd383854aacbcbf6744425a", "planned_active_tokens": 65071, "realized_active_tokens": 65071, "cumulative_start": 16978956, "cumulative_end": 17044027, "loss_sum": 25602.839965820312, "token_normalized_loss": 0.39346006617111023, "grad_norm_before_clip": 0.08479096740484238, "learning_rates_at_step": { "lora": 8.885324088343288e-05, "row_tokens": 8.885324088343288e-05 }, "learning_rates_after_step": { "lora": 8.875191402626438e-05, "row_tokens": 8.875191402626438e-05 } }, { "update_id": 260, "row_count": 13, "row_ids_sha256": "7e2aa8373a18814f6a20952cae743c78fe763f214841dd729d902969a5c4c911", "input_ids_vector_sha256": "4ec245a932b6c884714dfeda4ddd7a8c44e11c2d05bacce7883c2afbb6b428e4", "labels_vector_sha256": "9da9788654db832f537e311e86e7c3b03f20d21e3c344b727aef64dbc31c1bb1", "planned_active_tokens": 62142, "realized_active_tokens": 62142, "cumulative_start": 17044027, "cumulative_end": 17106169, "loss_sum": 18908.049835205078, "token_normalized_loss": 0.3042716654630536, "grad_norm_before_clip": 0.07427813857793808, "learning_rates_at_step": { "lora": 8.875191402626438e-05, "row_tokens": 8.875191402626438e-05 }, "learning_rates_after_step": { "lora": 8.864402563546408e-05, "row_tokens": 8.864402563546408e-05 } }, { "update_id": 261, "row_count": 14, "row_ids_sha256": "a6e34015c0a6e6a48c39652937fc9d68e882cbb035053081b829f122036da023", "input_ids_vector_sha256": "5c0b1e8c082335c93851f4fe84bd02e1cb7ad13067310c04d6a7ad5a3c24715d", "labels_vector_sha256": "2304e0a0c963edd4d5882f563d0c2c95b12dfe8b3ad1bdb6d84ba993a9ef5009", "planned_active_tokens": 65898, "realized_active_tokens": 65898, "cumulative_start": 17106169, "cumulative_end": 17172067, "loss_sum": 23553.966583251953, "token_normalized_loss": 0.3574306744248984, "grad_norm_before_clip": 0.07747187465429306, "learning_rates_at_step": { "lora": 8.864402563546408e-05, "row_tokens": 8.864402563546408e-05 }, "learning_rates_after_step": { "lora": 8.853020703317487e-05, "row_tokens": 8.853020703317487e-05 } }, { "update_id": 262, "row_count": 14, "row_ids_sha256": "0c59eb6c7625569583322ff57a8371d057de7c6d76c7440102eeea774a111504", "input_ids_vector_sha256": "af839d64ad141905f05829d51d6f3aada8ad97fdb0e1317076a266f5d5102bcc", "labels_vector_sha256": "909b56a8489b855ede53ac3b4704b6256a656e214108bcf2eceec0e457f8b92f", "planned_active_tokens": 69225, "realized_active_tokens": 69225, "cumulative_start": 17172067, "cumulative_end": 17241292, "loss_sum": 22882.02374267578, "token_normalized_loss": 0.33054566619972237, "grad_norm_before_clip": 0.0749412253499031, "learning_rates_at_step": { "lora": 8.853020703317487e-05, "row_tokens": 8.853020703317487e-05 }, "learning_rates_after_step": { "lora": 8.842994587144056e-05, "row_tokens": 8.842994587144056e-05 } }, { "update_id": 263, "row_count": 12, "row_ids_sha256": "f485f9a059b4a57f4f345cd0e0f19c6938d028f8f23e270007fb62965ed9ab36", "input_ids_vector_sha256": "778f8d2b06062f13ed49fdbae4ebafc7d63a02b754299ede71a9602f2abfd2db", "labels_vector_sha256": "20617f212152960d5426aae1645581234d1762d55d2faaaea63d0c07f3093861", "planned_active_tokens": 60732, "realized_active_tokens": 60732, "cumulative_start": 17241292, "cumulative_end": 17302024, "loss_sum": 21776.54168701172, "token_normalized_loss": 0.35856783387689717, "grad_norm_before_clip": 0.0852949470281601, "learning_rates_at_step": { "lora": 8.842994587144056e-05, "row_tokens": 8.842994587144056e-05 }, "learning_rates_after_step": { "lora": 8.831900198243316e-05, "row_tokens": 8.831900198243316e-05 } }, { "update_id": 264, "row_count": 15, "row_ids_sha256": "2a0749144bd3a59ced15d731c3914b0029b02d068062ef7529bf26fdf7ff7bff", "input_ids_vector_sha256": "356aa1e1bd7f3c5c82810e8e4ebb8c1cfdaca67af326330801dd075d0137f10f", "labels_vector_sha256": "5525534a6d6f4f638bf35fd9be9ecc8d8c261a214e51affbffddb9bf2c49e670", "planned_active_tokens": 66937, "realized_active_tokens": 66937, "cumulative_start": 17302024, "cumulative_end": 17368961, "loss_sum": 21749.576202392578, "token_normalized_loss": 0.32492606783083466, "grad_norm_before_clip": 0.0726204663515091, "learning_rates_at_step": { "lora": 8.831900198243316e-05, "row_tokens": 8.831900198243316e-05 }, "learning_rates_after_step": { "lora": 8.820722878274617e-05, "row_tokens": 8.820722878274617e-05 } }, { "update_id": 265, "row_count": 12, "row_ids_sha256": "e23f8a8e2396339b5888245b890a65773eaa338a1171756fb92c5a2e8f06c43d", "input_ids_vector_sha256": "e0889b015a23d0a2ca402950f3ac0db3e25a001086309641098aa320729e3688", "labels_vector_sha256": "2e0542264130b6a13e43c49ab92f843b645a49a93763357e078bbf9a403eb26b", "planned_active_tokens": 67159, "realized_active_tokens": 67159, "cumulative_start": 17368961, "cumulative_end": 17436120, "loss_sum": 24632.693603515625, "token_normalized_loss": 0.3667817210428331, "grad_norm_before_clip": 0.079706110060215, "learning_rates_at_step": { "lora": 8.820722878274617e-05, "row_tokens": 8.820722878274617e-05 }, "learning_rates_after_step": { "lora": 8.809751327713071e-05, "row_tokens": 8.809751327713071e-05 } }, { "update_id": 266, "row_count": 10, "row_ids_sha256": "bf0ab852289608f7ff83154acddb968b0a02184641a521e15b933a139d816bca", "input_ids_vector_sha256": "b8986af21fffbea7ef90ab59ed3811c41d0d4ba19eafadb5ff9cc56a43efd9a5", "labels_vector_sha256": "55702efdff8fe87a4db0e7c7e76558a5256b90328637e056dd10a947fcade54d", "planned_active_tokens": 65655, "realized_active_tokens": 65655, "cumulative_start": 17436120, "cumulative_end": 17501775, "loss_sum": 27327.618408203125, "token_normalized_loss": 0.4162305751001923, "grad_norm_before_clip": 0.08307885378599167, "learning_rates_at_step": { "lora": 8.809751327713071e-05, "row_tokens": 8.809751327713071e-05 }, "learning_rates_after_step": { "lora": 8.799127371211151e-05, "row_tokens": 8.799127371211151e-05 } }, { "update_id": 267, "row_count": 14, "row_ids_sha256": "dc382a9a143617c4bf6ca7ce1b26be6a423367c2331d6d7437d2c77a84bbe1af", "input_ids_vector_sha256": "561e7bbefeeb2b65ef1f68d49c7fac5f94b720c0cc36aa0bb9fc0fe33d61bece", "labels_vector_sha256": "be489bca4c7c212f6126f5589ba74aafa16cd245ad23ccfbf515177c387d3ac2", "planned_active_tokens": 63326, "realized_active_tokens": 63326, "cumulative_start": 17501775, "cumulative_end": 17565101, "loss_sum": 21447.352752685547, "token_normalized_loss": 0.33868162765192095, "grad_norm_before_clip": 0.07885389775037766, "learning_rates_at_step": { "lora": 8.799127371211151e-05, "row_tokens": 8.799127371211151e-05 }, "learning_rates_after_step": { "lora": 8.787284355363607e-05, "row_tokens": 8.787284355363607e-05 } }, { "update_id": 268, "row_count": 13, "row_ids_sha256": "d8af879c5d4a7aaf787946dacaa66210b4570a69e1678f96bc80e1f1b1af7da3", "input_ids_vector_sha256": "5bc19a4ae52df07bc2fe77545f811c92f285efa5df81c32a11b2fe06bcc66154", "labels_vector_sha256": "3bcd6e1eef34dff064287c6a4eb9ea273c9953f96380fe4ac8e41de39e12246a", "planned_active_tokens": 70308, "realized_active_tokens": 70308, "cumulative_start": 17565101, "cumulative_end": 17635409, "loss_sum": 27293.468017578125, "token_normalized_loss": 0.38819861207228373, "grad_norm_before_clip": 0.08447875082492828, "learning_rates_at_step": { "lora": 8.787284355363607e-05, "row_tokens": 8.787284355363607e-05 }, "learning_rates_after_step": { "lora": 8.776907331915785e-05, "row_tokens": 8.776907331915785e-05 } }, { "update_id": 269, "row_count": 11, "row_ids_sha256": "199df5b433c17888110b9fc26f12a258f7cec1f6b6e8fbd02610887a736bdcc5", "input_ids_vector_sha256": "f9082c329c860b7573807b2102a59372afe0cf627fe7c4d57cdd50d6a9463d28", "labels_vector_sha256": "ce59f01d9ce1f10101a06147fa443f21fc6168eeb49bf1815167ad42ac658f9c", "planned_active_tokens": 61362, "realized_active_tokens": 61362, "cumulative_start": 17635409, "cumulative_end": 17696771, "loss_sum": 21179.87530517578, "token_normalized_loss": 0.3451627278311623, "grad_norm_before_clip": 0.07647533714771271, "learning_rates_at_step": { "lora": 8.776907331915785e-05, "row_tokens": 8.776907331915785e-05 }, "learning_rates_after_step": { "lora": 8.76596646978747e-05, "row_tokens": 8.76596646978747e-05 } }, { "update_id": 270, "row_count": 14, "row_ids_sha256": "51236af60cc712d2751993d7e0b6bb6afed35c033c5560f8cdd7dfda085cb497", "input_ids_vector_sha256": "de650544969f008bf7331105ee91d2b7bc59057faf8c00036015984d7e834b1f", "labels_vector_sha256": "722b6f0263920f09f9cf054f3d09f379d1a7ba3b56c3370fd0ab3bd01bc32174", "planned_active_tokens": 64454, "realized_active_tokens": 64454, "cumulative_start": 17696771, "cumulative_end": 17761225, "loss_sum": 20170.496948242188, "token_normalized_loss": 0.3129440678350791, "grad_norm_before_clip": 0.07369868457317352, "learning_rates_at_step": { "lora": 8.76596646978747e-05, "row_tokens": 8.76596646978747e-05 }, "learning_rates_after_step": { "lora": 8.753141979022416e-05, "row_tokens": 8.753141979022416e-05 } }, { "update_id": 271, "row_count": 14, "row_ids_sha256": "9fa575955bce72d0a1e11e8263291027860116d680a804fb1ca7f53cc360a9f9", "input_ids_vector_sha256": "8be86001ca34f25cd6c00a4b82e1d02fb9b87dac4730a7a450888f26ba4f30d3", "labels_vector_sha256": "eb7ff8925b3e4d9333fd4f67f6f54197abe80ae880e26449071f1274374854ce", "planned_active_tokens": 75239, "realized_active_tokens": 75239, "cumulative_start": 17761225, "cumulative_end": 17836464, "loss_sum": 28101.80743408203, "token_normalized_loss": 0.37350054405404154, "grad_norm_before_clip": 0.07216424494981766, "learning_rates_at_step": { "lora": 8.753141979022416e-05, "row_tokens": 8.753141979022416e-05 }, "learning_rates_after_step": { "lora": 8.743094530386358e-05, "row_tokens": 8.743094530386358e-05 } }, { "update_id": 272, "row_count": 12, "row_ids_sha256": "1efb04bdebef75baf752e3781645b8428a7aaf01aa5932a5fe0f7b6d0b4679e4", "input_ids_vector_sha256": "1dcca4853643b1978cc1245a3e88c03c23b66352e226b555203d3031e9a0ab20", "labels_vector_sha256": "9a694734c01b7f075262330495fe81a0b488d26a2e8a3ceb7be80cefff181b40", "planned_active_tokens": 58715, "realized_active_tokens": 58715, "cumulative_start": 17836464, "cumulative_end": 17895179, "loss_sum": 18877.25958251953, "token_normalized_loss": 0.3215065925661165, "grad_norm_before_clip": 0.08147791028022766, "learning_rates_at_step": { "lora": 8.743094530386358e-05, "row_tokens": 8.743094530386358e-05 }, "learning_rates_after_step": { "lora": 8.732370420216979e-05, "row_tokens": 8.732370420216979e-05 } }, { "update_id": 273, "row_count": 13, "row_ids_sha256": "3ef9e14c6c655bd602f69ddc38449127f8a2a6c2865179cc8378b574b387986d", "input_ids_vector_sha256": "85ff74e4f7d0fb220b8fe67f4d9a5706bb13abb8ecc9d5b8b051d37fe7b24562", "labels_vector_sha256": "393017c2b5dc5bc0601ca9fa91a36b6659441db1a7d831e7be32f374d70735e1", "planned_active_tokens": 62448, "realized_active_tokens": 62448, "cumulative_start": 17895179, "cumulative_end": 17957627, "loss_sum": 22113.411193847656, "token_normalized_loss": 0.35410919795426044, "grad_norm_before_clip": 0.0772833526134491, "learning_rates_at_step": { "lora": 8.732370420216979e-05, "row_tokens": 8.732370420216979e-05 }, "learning_rates_after_step": { "lora": 8.721192626408907e-05, "row_tokens": 8.721192626408907e-05 } }, { "update_id": 274, "row_count": 15, "row_ids_sha256": "30d63510054688a5f01cd3d7ad42cb7e8be865d50d2990053d28d5a0e9bb5b51", "input_ids_vector_sha256": "626d61728d633c7b3216695e84677471af3e1cb54abcc4161c57fdae1da483d7", "labels_vector_sha256": "a8d892b5b6a5127bb95dc8fe1d7869b38a6390b7b57c1133d858de966c48a996", "planned_active_tokens": 64850, "realized_active_tokens": 64850, "cumulative_start": 17957627, "cumulative_end": 18022477, "loss_sum": 20064.027404785156, "token_normalized_loss": 0.3093913246690078, "grad_norm_before_clip": 0.07148593664169312, "learning_rates_at_step": { "lora": 8.721192626408907e-05, "row_tokens": 8.721192626408907e-05 }, "learning_rates_after_step": { "lora": 8.708787171644355e-05, "row_tokens": 8.708787171644355e-05 } }, { "update_id": 275, "row_count": 16, "row_ids_sha256": "c40e977479f9d8d933724dfe9afe307d431a79e641f5a4de480e51372cbc18e6", "input_ids_vector_sha256": "87cdb82a11727672950b47e28170deb54fcd75e4ca999893261dcd43e788d773", "labels_vector_sha256": "a245312e7210e75e999ec2816c0a2be6dea738727c28af9dfc30002d45720a3f", "planned_active_tokens": 71690, "realized_active_tokens": 71690, "cumulative_start": 18022477, "cumulative_end": 18094167, "loss_sum": 24422.078155517578, "token_normalized_loss": 0.34066227026806495, "grad_norm_before_clip": 0.07282107323408127, "learning_rates_at_step": { "lora": 8.708787171644355e-05, "row_tokens": 8.708787171644355e-05 }, "learning_rates_after_step": { "lora": 8.69821106898304e-05, "row_tokens": 8.69821106898304e-05 } }, { "update_id": 276, "row_count": 14, "row_ids_sha256": "8bb771192ae3e2ba77e7810ddada29d4fda38196f261884b56551b51ac41d9d2", "input_ids_vector_sha256": "715afd79a9cd4371c856aae82dc5a23946cc4e42dc260fcde57504aa8731ce63", "labels_vector_sha256": "2c9ada642416f331bc496f03e5beab2f83fefe58f836a08cec49a5cfcd2abe94", "planned_active_tokens": 60887, "realized_active_tokens": 60887, "cumulative_start": 18094167, "cumulative_end": 18155054, "loss_sum": 17454.46270751953, "token_normalized_loss": 0.28666977692314505, "grad_norm_before_clip": 0.07272999733686447, "learning_rates_at_step": { "lora": 8.69821106898304e-05, "row_tokens": 8.69821106898304e-05 }, "learning_rates_after_step": { "lora": 8.686351565187012e-05, "row_tokens": 8.686351565187012e-05 } }, { "update_id": 277, "row_count": 17, "row_ids_sha256": "a104cbed1fa907262716764884f27688a07defb0eabad99e721756720c2aa49b", "input_ids_vector_sha256": "a0dc50f4dd8b0e0b56a0d4dc420f7f205a2f20013c4b54f2d42a89249c83c2a4", "labels_vector_sha256": "ffd92c3baa13f6850beba6ac74b78a367ba77e4cc72d3af5f470e06498ded1e8", "planned_active_tokens": 68026, "realized_active_tokens": 68026, "cumulative_start": 18155054, "cumulative_end": 18223080, "loss_sum": 22070.730438232422, "token_normalized_loss": 0.3244455125721404, "grad_norm_before_clip": 0.072530597448349, "learning_rates_at_step": { "lora": 8.686351565187012e-05, "row_tokens": 8.686351565187012e-05 }, "learning_rates_after_step": { "lora": 8.675559853291052e-05, "row_tokens": 8.675559853291052e-05 } }, { "update_id": 278, "row_count": 14, "row_ids_sha256": "18b71afc205721de2f1b41a199e1a498ec4ee6d047712c836906aff03fe715bf", "input_ids_vector_sha256": "402c3d2529d3953006a8190680f946a3208920eb38e6441d0ca7144d2d7643fc", "labels_vector_sha256": "d6d1db96a0dae68c2e490676609a9a2f6dd6b6a6e016c7e11b85d30e0cdbf134", "planned_active_tokens": 61675, "realized_active_tokens": 61675, "cumulative_start": 18223080, "cumulative_end": 18284755, "loss_sum": 18177.73193359375, "token_normalized_loss": 0.2947342024093028, "grad_norm_before_clip": 0.07652264833450317, "learning_rates_at_step": { "lora": 8.675559853291052e-05, "row_tokens": 8.675559853291052e-05 }, "learning_rates_after_step": { "lora": 8.663258955416056e-05, "row_tokens": 8.663258955416056e-05 } }, { "update_id": 279, "row_count": 16, "row_ids_sha256": "eae2fbbaccc027fe8a86f5d325e6c35cad1eb836ef69476d63d95413d0fc1a50", "input_ids_vector_sha256": "4cb1a46647fa13322640451159f5c5673b18cba46b2ba324efa9b37d6cddb8e0", "labels_vector_sha256": "6a2f1c5cf3f92cb0af93564090554c352fcca942ca7302a7ef30b4f8f5861e09", "planned_active_tokens": 70041, "realized_active_tokens": 70041, "cumulative_start": 18284755, "cumulative_end": 18354796, "loss_sum": 21627.621643066406, "token_normalized_loss": 0.30878516359084546, "grad_norm_before_clip": 0.07004176080226898, "learning_rates_at_step": { "lora": 8.663258955416056e-05, "row_tokens": 8.663258955416056e-05 }, "learning_rates_after_step": { "lora": 8.652364055405962e-05, "row_tokens": 8.652364055405962e-05 } }, { "update_id": 280, "row_count": 15, "row_ids_sha256": "b88310b20c19ac834ef593a99eb7a874f9324b148d16d5af65cf98efce90ef97", "input_ids_vector_sha256": "59ff7878df130255df22a4da9db2da22f37c8dc6fc4c2aff9ab9469506f51d0d", "labels_vector_sha256": "442227384dc50614914ceccd8117e04e80c92a065eb9ab44e53622806b94fe02", "planned_active_tokens": 61808, "realized_active_tokens": 61808, "cumulative_start": 18354796, "cumulative_end": 18416604, "loss_sum": 19934.052825927734, "token_normalized_loss": 0.3225157394823928, "grad_norm_before_clip": 0.07306966185569763, "learning_rates_at_step": { "lora": 8.652364055405962e-05, "row_tokens": 8.652364055405962e-05 }, "learning_rates_after_step": { "lora": 8.640756208978822e-05, "row_tokens": 8.640756208978822e-05 } }, { "update_id": 281, "row_count": 8, "row_ids_sha256": "e687f503a3bfc83eb511de09116df69a855c2098cb8f92336af02dd23911ac35", "input_ids_vector_sha256": "e7ce9fe7a86e2f530fbd88b3e01eab97c3f7b38e0137da555dcd72121dd6ee78", "labels_vector_sha256": "77d2aefaccdcbe2640df050dc2657af04cc2d419fcabd347df1ce078f81f39b6", "planned_active_tokens": 65621, "realized_active_tokens": 65621, "cumulative_start": 18416604, "cumulative_end": 18482225, "loss_sum": 25311.83966064453, "token_normalized_loss": 0.3857277344241101, "grad_norm_before_clip": 0.0790843814611435, "learning_rates_at_step": { "lora": 8.640756208978822e-05, "row_tokens": 8.640756208978822e-05 }, "learning_rates_after_step": { "lora": 8.628960069595421e-05, "row_tokens": 8.628960069595421e-05 } }, { "update_id": 282, "row_count": 13, "row_ids_sha256": "876c8c290d3d313d69ad9b05807e1e13a917e52307a0fae71a003c736fa7bc4b", "input_ids_vector_sha256": "9bcbae775a016ea2583181ab52c55190bf406cbef5b5626c4a2fed2ec888cbf7", "labels_vector_sha256": "8f7c859b6f14fd803a381b22eac4fa727c680c76266c8e5691335e6ef7a72d08", "planned_active_tokens": 66444, "realized_active_tokens": 66444, "cumulative_start": 18482225, "cumulative_end": 18548669, "loss_sum": 22671.26139831543, "token_normalized_loss": 0.3412085575569717, "grad_norm_before_clip": 0.07886805385351181, "learning_rates_at_step": { "lora": 8.628960069595421e-05, "row_tokens": 8.628960069595421e-05 }, "learning_rates_after_step": { "lora": 8.617017916638871e-05, "row_tokens": 8.617017916638871e-05 } }, { "update_id": 283, "row_count": 14, "row_ids_sha256": "e776ef27ef8bb9ef1e96f72e709c0a2f704328df7e8d9d6907cde9c38896f89a", "input_ids_vector_sha256": "cdeac25f8c64b2166295d465c3bd9f95287549ff412d7b37ab5fbb850d0c5bbb", "labels_vector_sha256": "8d5e4d6f6d76092aab8f07310ed597b3068d592c9d433037d960d87bc31d4949", "planned_active_tokens": 67022, "realized_active_tokens": 67022, "cumulative_start": 18548669, "cumulative_end": 18615691, "loss_sum": 21480.178100585938, "token_normalized_loss": 0.3204944361640348, "grad_norm_before_clip": 0.07340702414512634, "learning_rates_at_step": { "lora": 8.617017916638871e-05, "row_tokens": 8.617017916638871e-05 }, "learning_rates_after_step": { "lora": 8.605611296336417e-05, "row_tokens": 8.605611296336417e-05 } }, { "update_id": 284, "row_count": 16, "row_ids_sha256": "0f517d67ebe2d4b47baf45ef67a399616539afc607d44338ef00efe209255fff", "input_ids_vector_sha256": "3e050253541c3990ddcbd7bcdd285d6bcf3c4ce327a19b8414fcecea5640fa9f", "labels_vector_sha256": "2cc7d394ab93fedca94a18b5124a628d6db5e4a41d61779d65a5a7720fdb86c4", "planned_active_tokens": 63790, "realized_active_tokens": 63790, "cumulative_start": 18615691, "cumulative_end": 18679481, "loss_sum": 21178.752471923828, "token_normalized_loss": 0.3320074066769686, "grad_norm_before_clip": 0.08590386807918549, "learning_rates_at_step": { "lora": 8.605611296336417e-05, "row_tokens": 8.605611296336417e-05 }, "learning_rates_after_step": { "lora": 8.593991635618781e-05, "row_tokens": 8.593991635618781e-05 } }, { "update_id": 285, "row_count": 16, "row_ids_sha256": "d7155380ac4432d362c0e9b5f51c4450cd4f960ea7764524223d4976425f5ea2", "input_ids_vector_sha256": "740be823880707ea9298655319d28bae9ba9383e61467bf9a1d728c69bbd8db4", "labels_vector_sha256": "09c70089163588fc5dbc42e4d64bdfe32caf7b3d087fdcee6589ddda7a3a2831", "planned_active_tokens": 64757, "realized_active_tokens": 64757, "cumulative_start": 18679481, "cumulative_end": 18744238, "loss_sum": 18892.933135986328, "token_normalized_loss": 0.29175121046352254, "grad_norm_before_clip": 0.0716482549905777, "learning_rates_at_step": { "lora": 8.593991635618781e-05, "row_tokens": 8.593991635618781e-05 }, "learning_rates_after_step": { "lora": 8.582100257040331e-05, "row_tokens": 8.582100257040331e-05 } }, { "update_id": 286, "row_count": 11, "row_ids_sha256": "72135a8149a74800c8917f9b6af335bcf478147adf3bd5da0f43e65040397de4", "input_ids_vector_sha256": "ac74b0410b5f0d32e0edf6a5765b7edd7e4dd43ca4be9927faef70c7289c4eb0", "labels_vector_sha256": "c2e9bf42457df67e74446d958d5e262a89066d1733c3f0391f521affdf86a7e7", "planned_active_tokens": 66040, "realized_active_tokens": 66040, "cumulative_start": 18744238, "cumulative_end": 18810278, "loss_sum": 23167.584716796875, "token_normalized_loss": 0.3508113978921392, "grad_norm_before_clip": 0.0784575417637825, "learning_rates_at_step": { "lora": 8.582100257040331e-05, "row_tokens": 8.582100257040331e-05 }, "learning_rates_after_step": { "lora": 8.570151539131632e-05, "row_tokens": 8.570151539131632e-05 } }, { "update_id": 287, "row_count": 15, "row_ids_sha256": "31f1b89d8aaf8b8f33f7658421109603b2357621c8b02ed79817e22831f03458", "input_ids_vector_sha256": "a492e0d744c5f6a3028d78d231f436199bf75e2183d5659e2e149df959622e5c", "labels_vector_sha256": "eb10b822659c3ae0d03c1dda6b4d2aa32ca3c50e6674ee73decb68d8d6255961", "planned_active_tokens": 66126, "realized_active_tokens": 66126, "cumulative_start": 18810278, "cumulative_end": 18876404, "loss_sum": 21313.002471923828, "token_normalized_loss": 0.32230896276689697, "grad_norm_before_clip": 0.07600311189889908, "learning_rates_at_step": { "lora": 8.570151539131632e-05, "row_tokens": 8.570151539131632e-05 }, "learning_rates_after_step": { "lora": 8.557599396052972e-05, "row_tokens": 8.557599396052972e-05 } }, { "update_id": 288, "row_count": 16, "row_ids_sha256": "63ca5a4970b9689dd3844f93bf2fb0537a9e31a37b101e50e3b3117a8e8a35ef", "input_ids_vector_sha256": "250d93f1579c8099b16972a24b9ac3fb1ecdca569542e42d791b16ec58f11fc4", "labels_vector_sha256": "01fec880398997989df0cf76f0b4e5fcb5d2451cfc9cb9770b215bc1d911e541", "planned_active_tokens": 69218, "realized_active_tokens": 69218, "cumulative_start": 18876404, "cumulative_end": 18945622, "loss_sum": 21674.15525817871, "token_normalized_loss": 0.3131288863905156, "grad_norm_before_clip": 0.07048475742340088, "learning_rates_at_step": { "lora": 8.557599396052972e-05, "row_tokens": 8.557599396052972e-05 }, "learning_rates_after_step": { "lora": 8.546427747559478e-05, "row_tokens": 8.546427747559478e-05 } }, { "update_id": 289, "row_count": 10, "row_ids_sha256": "85ee7e5f08263945f84a52efd36d86dd13f949ac3bc575d3e189f52db049f139", "input_ids_vector_sha256": "385bb4ab6d0136b9c24f3d2817c84cdac0ce0ba1bb4534cb5faeb7ea85b27228", "labels_vector_sha256": "99917da39295d7b8b40844725c926182b6d7f0c5b5ade79b679a07f6421cae9b", "planned_active_tokens": 61395, "realized_active_tokens": 61395, "cumulative_start": 18945622, "cumulative_end": 19007017, "loss_sum": 22644.077758789062, "token_normalized_loss": 0.3688260894012389, "grad_norm_before_clip": 0.08086851239204407, "learning_rates_at_step": { "lora": 8.546427747559478e-05, "row_tokens": 8.546427747559478e-05 }, "learning_rates_after_step": { "lora": 8.534659918616299e-05, "row_tokens": 8.534659918616299e-05 } }, { "update_id": 290, "row_count": 15, "row_ids_sha256": "003fc455e4a9535068a275f56dbb6ddb2e1ad6193df80cb123731984a0006185", "input_ids_vector_sha256": "5d6516b5591fe1877063fe1dbc73d4323be4e72be32633700df16fb3634ec115", "labels_vector_sha256": "43d71cb3e6c3799e4d4ba0263bfbac6e4ddc9443eaf700b353ca25c4cde751cb", "planned_active_tokens": 64460, "realized_active_tokens": 64460, "cumulative_start": 19007017, "cumulative_end": 19071477, "loss_sum": 22903.63363647461, "token_normalized_loss": 0.35531544580320523, "grad_norm_before_clip": 0.07714825123548508, "learning_rates_at_step": { "lora": 8.534659918616299e-05, "row_tokens": 8.534659918616299e-05 }, "learning_rates_after_step": { "lora": 8.522414658139159e-05, "row_tokens": 8.522414658139159e-05 } }, { "update_id": 291, "row_count": 14, "row_ids_sha256": "c3e2ee01b432e07862ae8c90f8712c791ba49750fff16ba6ac3c197c43dea3a1", "input_ids_vector_sha256": "ec77b248a00f886e0a89a91200e01b5d3b4e2ece084e60a9cf486d13a768f460", "labels_vector_sha256": "9ebeccab289a687fd03a91ffab1618cd47f46fef67e599dfe44f870b51f7ae84", "planned_active_tokens": 66848, "realized_active_tokens": 66848, "cumulative_start": 19071477, "cumulative_end": 19138325, "loss_sum": 21071.51463317871, "token_normalized_loss": 0.31521533378977246, "grad_norm_before_clip": 0.07311566919088364, "learning_rates_at_step": { "lora": 8.522414658139159e-05, "row_tokens": 8.522414658139159e-05 }, "learning_rates_after_step": { "lora": 8.509963251576723e-05, "row_tokens": 8.509963251576723e-05 } }, { "update_id": 292, "row_count": 15, "row_ids_sha256": "dd6f85b95012e9afeafd4e07817672b485294d72be77ce355c804c09bf49182d", "input_ids_vector_sha256": "ad049765bd90b16eac3c192cdf3fbca572737152b54dc750593c6692e130edcb", "labels_vector_sha256": "f26005cc0e072c7acc59cea6f17fd0d3e7d26669dd3f718ecf134fe1cbabc7e0", "planned_active_tokens": 67739, "realized_active_tokens": 67739, "cumulative_start": 19138325, "cumulative_end": 19206064, "loss_sum": 23023.418548583984, "token_normalized_loss": 0.3398842402247447, "grad_norm_before_clip": 0.07985446602106094, "learning_rates_at_step": { "lora": 8.509963251576723e-05, "row_tokens": 8.509963251576723e-05 }, "learning_rates_after_step": { "lora": 8.497499082482596e-05, "row_tokens": 8.497499082482596e-05 } }, { "update_id": 293, "row_count": 12, "row_ids_sha256": "fda928d6c62450de72e7e7d861991e40328322879973e3c33cb9afef9d283c6f", "input_ids_vector_sha256": "846206550cf1042be7ecea4454d31e5b99811d45df110cc9f67f039086461e8d", "labels_vector_sha256": "bbe4808324e4613e311ea59bdda42eb0334f1b1909d00c3fc41cb1995baf25af", "planned_active_tokens": 67575, "realized_active_tokens": 67575, "cumulative_start": 19206064, "cumulative_end": 19273639, "loss_sum": 21946.513671875, "token_normalized_loss": 0.3247726773492416, "grad_norm_before_clip": 0.07437458634376526, "learning_rates_at_step": { "lora": 8.497499082482596e-05, "row_tokens": 8.497499082482596e-05 }, "learning_rates_after_step": { "lora": 8.486148717486281e-05, "row_tokens": 8.486148717486281e-05 } }, { "update_id": 294, "row_count": 14, "row_ids_sha256": "43c98d06b3b6026b7a16286cbd8c9a4592c5999588fcc237b1f86a8c9391e1c0", "input_ids_vector_sha256": "74428422f3ed9ee5a04763049d0761590e716c62be2ac76e14412f39fd6931b4", "labels_vector_sha256": "9e2911e7d958d21b40af54a66376a6af233ad40aa52f414f830c608465f3beea", "planned_active_tokens": 61336, "realized_active_tokens": 61336, "cumulative_start": 19273639, "cumulative_end": 19334975, "loss_sum": 18861.3436126709, "token_normalized_loss": 0.3075085367919476, "grad_norm_before_clip": 0.07406052201986313, "learning_rates_at_step": { "lora": 8.486148717486281e-05, "row_tokens": 8.486148717486281e-05 }, "learning_rates_after_step": { "lora": 8.473631668598153e-05, "row_tokens": 8.473631668598153e-05 } }, { "update_id": 295, "row_count": 12, "row_ids_sha256": "c191d3c9ffbe2f5c5a98b979b9b5ffde3f03a1addbcc55944d8aa9a928e146b3", "input_ids_vector_sha256": "a711462b8c2360f68238844f2ad8c67890b6ac496963b7bcf97e7469f271c672", "labels_vector_sha256": "1404d155ad260151aabd849af1f945533a99e2e5eafff0b0a81df5b91bd76716", "planned_active_tokens": 67422, "realized_active_tokens": 67422, "cumulative_start": 19334975, "cumulative_end": 19402397, "loss_sum": 24087.594360351562, "token_normalized_loss": 0.35726609059878917, "grad_norm_before_clip": 0.08016841113567352, "learning_rates_at_step": { "lora": 8.473631668598153e-05, "row_tokens": 8.473631668598153e-05 }, "learning_rates_after_step": { "lora": 8.461190882506091e-05, "row_tokens": 8.461190882506091e-05 } }, { "update_id": 296, "row_count": 12, "row_ids_sha256": "2d6855454fde4a1769ead096abb3a0833ac6329914e108f671edcf347fadf199", "input_ids_vector_sha256": "8a45b9679fba2822d9d507d03d7b842426387db7a434a2d96145263d81774ed5", "labels_vector_sha256": "7eff96c8e81889a3f2fa3319981f12b445ef166ac4997cdd6b34e9fa4e1e6b7d", "planned_active_tokens": 66787, "realized_active_tokens": 66787, "cumulative_start": 19402397, "cumulative_end": 19469184, "loss_sum": 21494.522979736328, "token_normalized_loss": 0.3218369290391293, "grad_norm_before_clip": 0.07412362843751907, "learning_rates_at_step": { "lora": 8.461190882506091e-05, "row_tokens": 8.461190882506091e-05 }, "learning_rates_after_step": { "lora": 8.449260085590216e-05, "row_tokens": 8.449260085590216e-05 } }, { "update_id": 297, "row_count": 11, "row_ids_sha256": "226d81088c7b89506cf68a4de253943dd5e8296fdec266bbe7c96c9a7b7b4c1c", "input_ids_vector_sha256": "57baa10d7967d0d36046f7f5cdc15be07595da944da42c7aa7d04f6ba24d7ff2", "labels_vector_sha256": "0602a51d33d03997d8ad3a54a25be9527e326fb6974e8e6d710626994bf11253", "planned_active_tokens": 63842, "realized_active_tokens": 63842, "cumulative_start": 19469184, "cumulative_end": 19533026, "loss_sum": 21110.001708984375, "token_normalized_loss": 0.330660093809473, "grad_norm_before_clip": 0.07614696025848389, "learning_rates_at_step": { "lora": 8.449260085590216e-05, "row_tokens": 8.449260085590216e-05 }, "learning_rates_after_step": { "lora": 8.436367795244783e-05, "row_tokens": 8.436367795244783e-05 } }, { "update_id": 298, "row_count": 14, "row_ids_sha256": "83416d6b4476f527b3643c8707b62eae57e3d2d20dc205db75de7a2cba7e7e9f", "input_ids_vector_sha256": "c1452f5932199e831d3232340a428932e72982df888a3964bee78ac5df6abcd2", "labels_vector_sha256": "fedfd9975b34de79e3b6255641e66978cea840c405209c35f1e2150cb02d9c0c", "planned_active_tokens": 68762, "realized_active_tokens": 68762, "cumulative_start": 19533026, "cumulative_end": 19601788, "loss_sum": 21700.206329345703, "token_normalized_loss": 0.3155842809887104, "grad_norm_before_clip": 0.07253316789865494, "learning_rates_at_step": { "lora": 8.436367795244783e-05, "row_tokens": 8.436367795244783e-05 }, "learning_rates_after_step": { "lora": 8.424326286173422e-05, "row_tokens": 8.424326286173422e-05 } }, { "update_id": 299, "row_count": 13, "row_ids_sha256": "a6d20ec88e2984e869ed7eb5abe91b0e51bbcea2ad71fd05ff6ed28efc70f98b", "input_ids_vector_sha256": "7fa5586bda02c7180a75b33d8f697fd64c534c05e9b8749d6386629d2332ad66", "labels_vector_sha256": "b4add6c91277231a39441f84da39adb0c036abb86bc5b6dd45542cede682f104", "planned_active_tokens": 64016, "realized_active_tokens": 64016, "cumulative_start": 19601788, "cumulative_end": 19665804, "loss_sum": 21493.904327392578, "token_normalized_loss": 0.3357583155366249, "grad_norm_before_clip": 0.0793546587228775, "learning_rates_at_step": { "lora": 8.424326286173422e-05, "row_tokens": 8.424326286173422e-05 }, "learning_rates_after_step": { "lora": 8.412755578231538e-05, "row_tokens": 8.412755578231538e-05 } }, { "update_id": 300, "row_count": 11, "row_ids_sha256": "28179229205ccc5c6e017ab54856660cc94090f7c80712af6cf97664b826e4a1", "input_ids_vector_sha256": "5a2cb3d7dedb36fc94eb86fabeb317cbed903d575d0dfbdf3a2903a838ae9021", "labels_vector_sha256": "4309564d60a3d868009d13adebbf80f7bba2452359cdfc8251137632cc9ff123", "planned_active_tokens": 61326, "realized_active_tokens": 61326, "cumulative_start": 19665804, "cumulative_end": 19727130, "loss_sum": 20873.26821899414, "token_normalized_loss": 0.34036572121113623, "grad_norm_before_clip": 0.07707320898771286, "learning_rates_at_step": { "lora": 8.412755578231538e-05, "row_tokens": 8.412755578231538e-05 }, "learning_rates_after_step": { "lora": 8.399816715069697e-05, "row_tokens": 8.399816715069697e-05 } }, { "update_id": 301, "row_count": 12, "row_ids_sha256": "d8ed649359c4f0bad36ff3a5926a5faaed77ea827b7f4e9961671d8a3c793d1c", "input_ids_vector_sha256": "eb1c983234adedaed45ab9fdd28d4a60e07262a7003d7ee3fd0c8a9345b4bc20", "labels_vector_sha256": "ed980ff526a0276b7f93182679a41f12f04e33e046de72d6da521fcf84b80a11", "planned_active_tokens": 68363, "realized_active_tokens": 68363, "cumulative_start": 19727130, "cumulative_end": 19795493, "loss_sum": 25334.15023803711, "token_normalized_loss": 0.37058277486413865, "grad_norm_before_clip": 0.08093686401844025, "learning_rates_at_step": { "lora": 8.399816715069697e-05, "row_tokens": 8.399816715069697e-05 }, "learning_rates_after_step": { "lora": 8.387446808230652e-05, "row_tokens": 8.387446808230652e-05 } }, { "update_id": 302, "row_count": 15, "row_ids_sha256": "ab29c561a3216c028b1a26c2aba015d135c7496c0b5fa12dfc3e63a570f0860c", "input_ids_vector_sha256": "c96d82ba0d72a0244a67862572bb9e703fb89c37521a742fdc3ed636d352969a", "labels_vector_sha256": "451715bbc6065f2b4cbadc51b98f5ef7056e7d373be63145e5381f0c1f315c1c", "planned_active_tokens": 65148, "realized_active_tokens": 65148, "cumulative_start": 19795493, "cumulative_end": 19860641, "loss_sum": 22149.164642333984, "token_normalized_loss": 0.3399822656464356, "grad_norm_before_clip": 0.07874935865402222, "learning_rates_at_step": { "lora": 8.387446808230652e-05, "row_tokens": 8.387446808230652e-05 }, "learning_rates_after_step": { "lora": 8.374594539848784e-05, "row_tokens": 8.374594539848784e-05 } }, { "update_id": 303, "row_count": 14, "row_ids_sha256": "864106a08e19dcf67ba23a9a45afc2aebce943ceaf2d6b92250e5355c5b272f5", "input_ids_vector_sha256": "14e46ea864dee929abe9fe00f2d5b64af4341132876d14d1658a29156f9b70c5", "labels_vector_sha256": "013ae69678a8e24eb2ffafde5c087e974f08a3450eeb92682699e0b1db39ae15", "planned_active_tokens": 67475, "realized_active_tokens": 67475, "cumulative_start": 19860641, "cumulative_end": 19928116, "loss_sum": 24000.421096801758, "token_normalized_loss": 0.3556935323720157, "grad_norm_before_clip": 0.08083237707614899, "learning_rates_at_step": { "lora": 8.374594539848784e-05, "row_tokens": 8.374594539848784e-05 }, "learning_rates_after_step": { "lora": 8.362586067576087e-05, "row_tokens": 8.362586067576087e-05 } }, { "update_id": 304, "row_count": 15, "row_ids_sha256": "cc4e18a0532cc9a69ecc920522f8c1dab0f25de6453ebd85fa2b23b376b4a68b", "input_ids_vector_sha256": "b5f75b50a5f38cfacfdfddd7628de13236a41febf2587af5f32e02c2aa00b84e", "labels_vector_sha256": "8322c89fa983a61edf8902c36c6ec2a4e890fe331b33e05fe0f9babc5a5daf32", "planned_active_tokens": 62851, "realized_active_tokens": 62851, "cumulative_start": 19928116, "cumulative_end": 19990967, "loss_sum": 16250.35092163086, "token_normalized_loss": 0.25855357785287203, "grad_norm_before_clip": 0.0716802105307579, "learning_rates_at_step": { "lora": 8.362586067576087e-05, "row_tokens": 8.362586067576087e-05 }, "learning_rates_after_step": { "lora": 8.350482969888844e-05, "row_tokens": 8.350482969888844e-05 } }, { "update_id": 305, "row_count": 15, "row_ids_sha256": "c4d316f33f86e0e9ef82ef9b44e79f6a6dea9a747f52fdbf3e9b9e8fb0188305", "input_ids_vector_sha256": "0088d0b7f8a0415eca2d091225f980d843850059e754a37356832d75a32b3dab", "labels_vector_sha256": "0ac7a0091d5353cfb9369ed7c5603258e37791aa1f8d5ceef73eb7a64e8adaed", "planned_active_tokens": 63159, "realized_active_tokens": 63159, "cumulative_start": 19990967, "cumulative_end": 20054126, "loss_sum": 17975.382095336914, "token_normalized_loss": 0.28460523591787257, "grad_norm_before_clip": 0.07486092299222946, "learning_rates_at_step": { "lora": 8.350482969888844e-05, "row_tokens": 8.350482969888844e-05 }, "learning_rates_after_step": { "lora": 8.33777782930042e-05, "row_tokens": 8.33777782930042e-05 } }, { "update_id": 306, "row_count": 13, "row_ids_sha256": "19053bd74545c68ea2073c782d071152c9a6dda7fa00e5623bd021744d0b261d", "input_ids_vector_sha256": "f20ee33533fcad53f9dc395cf9e873187eccaff1dc03f08450c62cb754b11683", "labels_vector_sha256": "e20117c30406708f086b8363cc5c8c0338611cfe91a8915e754a95006da70bb4", "planned_active_tokens": 66101, "realized_active_tokens": 66101, "cumulative_start": 20054126, "cumulative_end": 20120227, "loss_sum": 22221.609497070312, "token_normalized_loss": 0.33617660091481694, "grad_norm_before_clip": 0.07884159684181213, "learning_rates_at_step": { "lora": 8.33777782930042e-05, "row_tokens": 8.33777782930042e-05 }, "learning_rates_after_step": { "lora": 8.323495625878835e-05, "row_tokens": 8.323495625878835e-05 } }, { "update_id": 307, "row_count": 18, "row_ids_sha256": "60516aa5ee63fbc8ae55d59e2ae8990262656135b9ad5c31322e2dbd9e07ebd0", "input_ids_vector_sha256": "aaef4b74cdf6a2937150a40b4b4a3bcf9f407111d02e14adfb62413e3b091a5a", "labels_vector_sha256": "e8b9017b7d08b46687dddd56cf991da1f42efef93ec2b398399ef84f84af7b99", "planned_active_tokens": 74065, "realized_active_tokens": 74065, "cumulative_start": 20120227, "cumulative_end": 20194292, "loss_sum": 20326.052520751953, "token_normalized_loss": 0.27443532735775267, "grad_norm_before_clip": 0.0646844431757927, "learning_rates_at_step": { "lora": 8.323495625878835e-05, "row_tokens": 8.323495625878835e-05 }, "learning_rates_after_step": { "lora": 8.311850165198258e-05, "row_tokens": 8.311850165198258e-05 } }, { "update_id": 308, "row_count": 15, "row_ids_sha256": "529e5d7d66c96a5d15e02d09b81f85ac5cc24a91d4cd7c6c860c456ac8d5fc96", "input_ids_vector_sha256": "5045b2bc33e3d91daa3ff4747ca50e559cb5ac1cbcbb8f92a5944153305e8332", "labels_vector_sha256": "0c311f240ad227268dadf1ccde6e8dd45c7db9e346b255a6e190becfcb4efb62", "planned_active_tokens": 60205, "realized_active_tokens": 60205, "cumulative_start": 20194292, "cumulative_end": 20254497, "loss_sum": 16474.27749633789, "token_normalized_loss": 0.2736363673505172, "grad_norm_before_clip": 0.07410047203302383, "learning_rates_at_step": { "lora": 8.311850165198258e-05, "row_tokens": 8.311850165198258e-05 }, "learning_rates_after_step": { "lora": 8.299426895972424e-05, "row_tokens": 8.299426895972424e-05 } }, { "update_id": 309, "row_count": 12, "row_ids_sha256": "20a968193225174614f66da313f5d616ff88b9bc0616a41f4456a3e3cbbfe5d6", "input_ids_vector_sha256": "fbe9126be77590636a8a6c6284189850d1e60e7137f3fb3a22986ffc2f9e9316", "labels_vector_sha256": "193e1400411b56d828244823be13255937672b828a718d1d3deb71920f8a96ed", "planned_active_tokens": 64044, "realized_active_tokens": 64044, "cumulative_start": 20254497, "cumulative_end": 20318541, "loss_sum": 21653.959411621094, "token_normalized_loss": 0.33811066472458146, "grad_norm_before_clip": 0.08049635589122772, "learning_rates_at_step": { "lora": 8.299426895972424e-05, "row_tokens": 8.299426895972424e-05 }, "learning_rates_after_step": { "lora": 8.286810018349164e-05, "row_tokens": 8.286810018349164e-05 } }, { "update_id": 310, "row_count": 13, "row_ids_sha256": "475643d8059e5062edcf5dee803514ba2f895c0fd366aa522bc86b9185367cdf", "input_ids_vector_sha256": "6c4ab769702e375018a56c0ae84655ff3123e9804f9fc8b6a303d21f426d55e7", "labels_vector_sha256": "3ee8fb98e5259baf2124d3bdd83108bc1d43e63c715e5d22e0bf99b838af7e51", "planned_active_tokens": 64852, "realized_active_tokens": 64852, "cumulative_start": 20318541, "cumulative_end": 20383393, "loss_sum": 23268.63949584961, "token_normalized_loss": 0.3587960201050023, "grad_norm_before_clip": 0.0793871134519577, "learning_rates_at_step": { "lora": 8.286810018349164e-05, "row_tokens": 8.286810018349164e-05 }, "learning_rates_after_step": { "lora": 8.27365318225337e-05, "row_tokens": 8.27365318225337e-05 } }, { "update_id": 311, "row_count": 19, "row_ids_sha256": "f75800debeac6e5fcbf7b76a83f8eeafef0fa19be02c83d109592d0009880cfd", "input_ids_vector_sha256": "b0430e720eed60fffd1ee7d43c1a6b73d0c84894cce95c8e33fb540958fc8cc5", "labels_vector_sha256": "db4f2d6c90c6e6b90cddd4ef124bfa405d7b6a96cffc22b4b4d90e03d4ce3834", "planned_active_tokens": 67426, "realized_active_tokens": 67426, "cumulative_start": 20383393, "cumulative_end": 20450819, "loss_sum": 17646.31170654297, "token_normalized_loss": 0.2617137559182358, "grad_norm_before_clip": 0.06689967215061188, "learning_rates_at_step": { "lora": 8.27365318225337e-05, "row_tokens": 8.27365318225337e-05 }, "learning_rates_after_step": { "lora": 8.261213102626051e-05, "row_tokens": 8.261213102626051e-05 } }, { "update_id": 312, "row_count": 11, "row_ids_sha256": "734c9259589b2f32d409f45cbc761689af4d0ed5a0e127a6bdef1cbd1c183f66", "input_ids_vector_sha256": "9d8b29556ff1e6471f3196eb75a5172117fb6896b983c544db63747e3b4e3a99", "labels_vector_sha256": "c0128760405dfd3d638d5145652d4d1c98404337235e3d169640229ef56b203a", "planned_active_tokens": 63566, "realized_active_tokens": 63566, "cumulative_start": 20450819, "cumulative_end": 20514385, "loss_sum": 22436.31671142578, "token_normalized_loss": 0.35296096516102604, "grad_norm_before_clip": 0.08236130326986313, "learning_rates_at_step": { "lora": 8.261213102626051e-05, "row_tokens": 8.261213102626051e-05 }, "learning_rates_after_step": { "lora": 8.248545181113344e-05, "row_tokens": 8.248545181113344e-05 } }, { "update_id": 313, "row_count": 16, "row_ids_sha256": "170e8d73e89d20a3ba6f5ab9cfb5bf196a694d040582a6ee9cd7a53dfc3302d9", "input_ids_vector_sha256": "e022504b9d4a02639db0fe9d60a78d384cf02c429f8878c51fcc9329945b74f8", "labels_vector_sha256": "481b5657ea471cf94bc6c3a9a7ab87aecebc88c9da8cf0cdd6004483a2bc5c92", "planned_active_tokens": 64546, "realized_active_tokens": 64546, "cumulative_start": 20514385, "cumulative_end": 20578931, "loss_sum": 21702.85809326172, "token_normalized_loss": 0.3362386219635875, "grad_norm_before_clip": 0.07786848396062851, "learning_rates_at_step": { "lora": 8.248545181113344e-05, "row_tokens": 8.248545181113344e-05 }, "learning_rates_after_step": { "lora": 8.23513381336757e-05, "row_tokens": 8.23513381336757e-05 } }, { "update_id": 314, "row_count": 14, "row_ids_sha256": "74e7c620f999aef8e976a3fe93dbbd72de2c6606dd59766469164a024ad06414", "input_ids_vector_sha256": "a31330f469ed149e56a6b3ae0c95d29f47771da53c81c1cfceec668e59a43755", "labels_vector_sha256": "80cb2e8ede81a3e12fa166fb189e9658b3814a61d477bb01dfe58625da64acf9", "planned_active_tokens": 68134, "realized_active_tokens": 68134, "cumulative_start": 20578931, "cumulative_end": 20647065, "loss_sum": 21069.43832397461, "token_normalized_loss": 0.3092353057794142, "grad_norm_before_clip": 0.07526332139968872, "learning_rates_at_step": { "lora": 8.23513381336757e-05, "row_tokens": 8.23513381336757e-05 }, "learning_rates_after_step": { "lora": 8.222348956485265e-05, "row_tokens": 8.222348956485265e-05 } }, { "update_id": 315, "row_count": 16, "row_ids_sha256": "9da193ae899c6bfa6c8db6174f31d24d4e45f4dd3a26c831b0443b9cedacec8b", "input_ids_vector_sha256": "4ba5e58bc0a1692dde534fc135efafc5bda7490cbe175b5485dd3821d43e9a10", "labels_vector_sha256": "5a0f08026de6c4293ec83b182314531a1a7dc1128116b530d46b1c0fddbecfcf", "planned_active_tokens": 64762, "realized_active_tokens": 64762, "cumulative_start": 20647065, "cumulative_end": 20711827, "loss_sum": 18421.120391845703, "token_normalized_loss": 0.2844433524573933, "grad_norm_before_clip": 0.07389324903488159, "learning_rates_at_step": { "lora": 8.222348956485265e-05, "row_tokens": 8.222348956485265e-05 }, "learning_rates_after_step": { "lora": 8.209626293338391e-05, "row_tokens": 8.209626293338391e-05 } }, { "update_id": 316, "row_count": 13, "row_ids_sha256": "2f346126fbdf6f23b048783fccd835cd700c219fd2d805319fc3932ff9f19347", "input_ids_vector_sha256": "7a926b87d1b75ae6e0b655f05f2ef67994b2cc0a4b302918cfd712c223839a9b", "labels_vector_sha256": "65e967f2f4b2c927d83cc1b0daedebcfc852bada6fe349a804d65f2e1ac86d6e", "planned_active_tokens": 64266, "realized_active_tokens": 64266, "cumulative_start": 20711827, "cumulative_end": 20776093, "loss_sum": 19503.819732666016, "token_normalized_loss": 0.30348582038194405, "grad_norm_before_clip": 0.07409650832414627, "learning_rates_at_step": { "lora": 8.209626293338391e-05, "row_tokens": 8.209626293338391e-05 }, "learning_rates_after_step": { "lora": 8.196715706726475e-05, "row_tokens": 8.196715706726475e-05 } }, { "update_id": 317, "row_count": 17, "row_ids_sha256": "9597b66c01dcfd631bf5a7381f543fbdf9c5c2d13e6d2c2508c5e7d0a33982bf", "input_ids_vector_sha256": "e845811f64282caf094440ad1bacee44a64f2b70bd6cebd1db46506f9133e51c", "labels_vector_sha256": "148f7f411438fc02770b464c1d7000e2a02e0bb53b6934f918e4f26b875f18b2", "planned_active_tokens": 65033, "realized_active_tokens": 65033, "cumulative_start": 20776093, "cumulative_end": 20841126, "loss_sum": 17176.954650878906, "token_normalized_loss": 0.26412674566572214, "grad_norm_before_clip": 0.07087138295173645, "learning_rates_at_step": { "lora": 8.196715706726475e-05, "row_tokens": 8.196715706726475e-05 }, "learning_rates_after_step": { "lora": 8.183741060095707e-05, "row_tokens": 8.183741060095707e-05 } }, { "update_id": 318, "row_count": 17, "row_ids_sha256": "9ca781f2f9fe3ca2ea439323ecf3c6a240c29d1abcbc2fa72f84cf7807535365", "input_ids_vector_sha256": "4d94640f7d68992906bcc273ce1282064a36816594fa9820b67d7c6ace9da2e8", "labels_vector_sha256": "27e7c7714bdd9e349fcb4e8b5b17925339bdb1e35017e07d63423e4dd2b0df29", "planned_active_tokens": 65173, "realized_active_tokens": 65173, "cumulative_start": 20841126, "cumulative_end": 20906299, "loss_sum": 18196.93911743164, "token_normalized_loss": 0.27920978192551577, "grad_norm_before_clip": 0.0725213959813118, "learning_rates_at_step": { "lora": 8.183741060095707e-05, "row_tokens": 8.183741060095707e-05 }, "learning_rates_after_step": { "lora": 8.170040309788045e-05, "row_tokens": 8.170040309788045e-05 } }, { "update_id": 319, "row_count": 13, "row_ids_sha256": "3fb35c3ed39c6982319d9890c850a745460260571877dbdc43b5a6017553b566", "input_ids_vector_sha256": "46cb203f948a988c24182f1310c43e2277e379a7cce690f57f913d1c4d1bfd09", "labels_vector_sha256": "f34b54adfe89f90820b1e762623f382fa791a90c4ce23926f5e3b3ac04ef9533", "planned_active_tokens": 68624, "realized_active_tokens": 68624, "cumulative_start": 20906299, "cumulative_end": 20974923, "loss_sum": 23628.013397216797, "token_normalized_loss": 0.34431122343810905, "grad_norm_before_clip": 0.08004917204380035, "learning_rates_at_step": { "lora": 8.170040309788045e-05, "row_tokens": 8.170040309788045e-05 }, "learning_rates_after_step": { "lora": 8.157496604097612e-05, "row_tokens": 8.157496604097612e-05 } }, { "update_id": 320, "row_count": 17, "row_ids_sha256": "820d5b570ab2817ac48bf09a61791aeba44e7f08c5ee865ce1dbcd3b183377c7", "input_ids_vector_sha256": "c8521f88b55d30c26b47480eb2bfafd04c20acd2318d0c134e17045dd90c2133", "labels_vector_sha256": "2c867ad23af80efb555794619b591c8214268d835fe5cc6ffc0610c5bb4b2d3d", "planned_active_tokens": 62654, "realized_active_tokens": 62654, "cumulative_start": 20974923, "cumulative_end": 21037577, "loss_sum": 17329.504959106445, "token_normalized_loss": 0.2765905602053571, "grad_norm_before_clip": 0.07551660388708115, "learning_rates_at_step": { "lora": 8.157496604097612e-05, "row_tokens": 8.157496604097612e-05 }, "learning_rates_after_step": { "lora": 8.144045734553578e-05, "row_tokens": 8.144045734553578e-05 } }, { "update_id": 321, "row_count": 15, "row_ids_sha256": "b2c1760f63a27f722d42941e7b00fc109c3f29d3b23e5168317b10afbc7f26d3", "input_ids_vector_sha256": "75ef0f3549eeea883f204b084d795af051870c4840508adc47a1ab3f651a291d", "labels_vector_sha256": "4b963f55004da73568929b8ebac8515a59152871a79d119f0554fd67117952c9", "planned_active_tokens": 67002, "realized_active_tokens": 67002, "cumulative_start": 21037577, "cumulative_end": 21104579, "loss_sum": 19367.934448242188, "token_normalized_loss": 0.28906501967466924, "grad_norm_before_clip": 0.0764603391289711, "learning_rates_at_step": { "lora": 8.144045734553578e-05, "row_tokens": 8.144045734553578e-05 }, "learning_rates_after_step": { "lora": 8.130977840515413e-05, "row_tokens": 8.130977840515413e-05 } }, { "update_id": 322, "row_count": 11, "row_ids_sha256": "51759fa650bda039c31b1b2336b4cfd417738fcd30e49970e1d5aa78b72747f4", "input_ids_vector_sha256": "f16370591a152c8beec032c6bfe3dd54f4edcbf2d29664e714d39b487f75127e", "labels_vector_sha256": "199925821c86c1880e6a3ab4ef356a7df998b14d46bb8e119004f4154e21715a", "planned_active_tokens": 64915, "realized_active_tokens": 64915, "cumulative_start": 21104579, "cumulative_end": 21169494, "loss_sum": 23998.77960205078, "token_normalized_loss": 0.36969544176308683, "grad_norm_before_clip": 0.08465296030044556, "learning_rates_at_step": { "lora": 8.130977840515413e-05, "row_tokens": 8.130977840515413e-05 }, "learning_rates_after_step": { "lora": 8.116731533953742e-05, "row_tokens": 8.116731533953742e-05 } }, { "update_id": 323, "row_count": 13, "row_ids_sha256": "dd4f26d6257a0331daa52f2403d24e80b910ccdcac1ea930f40a5747bb6f1aa8", "input_ids_vector_sha256": "ad5bbf0399c9496fafe49fb9a40d0e880877686b0994df726e18ebabdbcb3746", "labels_vector_sha256": "b3693d3ce5844bc13c25381c531d074500a52879751931a12a42d7116b7f0e9a", "planned_active_tokens": 70570, "realized_active_tokens": 70570, "cumulative_start": 21169494, "cumulative_end": 21240064, "loss_sum": 24862.27589416504, "token_normalized_loss": 0.3523065877024945, "grad_norm_before_clip": 0.07668176293373108, "learning_rates_at_step": { "lora": 8.116731533953742e-05, "row_tokens": 8.116731533953742e-05 }, "learning_rates_after_step": { "lora": 8.104118815019459e-05, "row_tokens": 8.104118815019459e-05 } }, { "update_id": 324, "row_count": 9, "row_ids_sha256": "03b585102391915275a39b12727f1a28ddafae8cd28c6cdc8bbf20db2f71f445", "input_ids_vector_sha256": "78a02670c200a3a49ea19eb95e30096f52154c8dca4ddb9b188d108016461aeb", "labels_vector_sha256": "b6d295f861657bb48fe9630375d2be6ff9647cd9d0920d05a3878dd43ac7f50a", "planned_active_tokens": 62307, "realized_active_tokens": 62307, "cumulative_start": 21240064, "cumulative_end": 21302371, "loss_sum": 23541.47933959961, "token_normalized_loss": 0.3778304097388674, "grad_norm_before_clip": 0.08126434683799744, "learning_rates_at_step": { "lora": 8.104118815019459e-05, "row_tokens": 8.104118815019459e-05 }, "learning_rates_after_step": { "lora": 8.091221082665575e-05, "row_tokens": 8.091221082665575e-05 } }, { "update_id": 325, "row_count": 11, "row_ids_sha256": "ea47243d5bfcb8f5c0a201c5c0c6601aad685ab66118ebfef013adab6640f9f1", "input_ids_vector_sha256": "a4753c22f5c4217c637f40969a55abb7e88740155bb9f84580a6061468534b22", "labels_vector_sha256": "be65286885319c9b12319422bc3950b7b027372d971a7685800938a463a868de", "planned_active_tokens": 63551, "realized_active_tokens": 63551, "cumulative_start": 21302371, "cumulative_end": 21365922, "loss_sum": 22502.91717529297, "token_normalized_loss": 0.35409225937110306, "grad_norm_before_clip": 0.08133471757173538, "learning_rates_at_step": { "lora": 8.091221082665575e-05, "row_tokens": 8.091221082665575e-05 }, "learning_rates_after_step": { "lora": 8.07808255874057e-05, "row_tokens": 8.07808255874057e-05 } }, { "update_id": 326, "row_count": 14, "row_ids_sha256": "97d97345f9e02cca23b755a79965b2c5b1dc70b80f9de73e244755a6427c7570", "input_ids_vector_sha256": "c2e52e5a32d77f08a05e3ed9ec34978d3e3c60715e0ae0cfc0348c3678320130", "labels_vector_sha256": "9112b59c3e96df8787870fc2eade6c0ba9348ed51579ae3de447aa668da84ba3", "planned_active_tokens": 64569, "realized_active_tokens": 64569, "cumulative_start": 21365922, "cumulative_end": 21430491, "loss_sum": 21531.62631225586, "token_normalized_loss": 0.3334669316894463, "grad_norm_before_clip": 0.07779253274202347, "learning_rates_at_step": { "lora": 8.07808255874057e-05, "row_tokens": 8.07808255874057e-05 }, "learning_rates_after_step": { "lora": 8.064317079984015e-05, "row_tokens": 8.064317079984015e-05 } }, { "update_id": 327, "row_count": 15, "row_ids_sha256": "0dba54de9830d9149100194cd59cf108882d77458bf3084d68c947cc833f2f3a", "input_ids_vector_sha256": "ac22f74edceed7eb4c54e2d5ce9bc9557aa9711d5afa38c8fa9b475287f7d6d5", "labels_vector_sha256": "7b6205da69a7a11591ab2637b42071ffa619c88e3016dbbd583a7371a2cd025e", "planned_active_tokens": 67470, "realized_active_tokens": 67470, "cumulative_start": 21430491, "cumulative_end": 21497961, "loss_sum": 23314.70391845703, "token_normalized_loss": 0.3455566017260565, "grad_norm_before_clip": 0.07736548036336899, "learning_rates_at_step": { "lora": 8.064317079984015e-05, "row_tokens": 8.064317079984015e-05 }, "learning_rates_after_step": { "lora": 8.051163028354896e-05, "row_tokens": 8.051163028354896e-05 } }, { "update_id": 328, "row_count": 13, "row_ids_sha256": "afc5eacd82c2ef6eeef7e79686b63971be3864fe2aa99bc2cec23ed379c1988d", "input_ids_vector_sha256": "5cb4c594c08e50a50f708c01c1df8b093f6dedef39dca61694834d8c4e515f48", "labels_vector_sha256": "13b7265715fc96597f1075c7ee064e294936922f701cdc1ff7d5ef5ed60f00a4", "planned_active_tokens": 64303, "realized_active_tokens": 64303, "cumulative_start": 21497961, "cumulative_end": 21562264, "loss_sum": 20003.27325439453, "token_normalized_loss": 0.3110783828809625, "grad_norm_before_clip": 0.07560630887746811, "learning_rates_at_step": { "lora": 8.051163028354896e-05, "row_tokens": 8.051163028354896e-05 }, "learning_rates_after_step": { "lora": 8.037757156983045e-05, "row_tokens": 8.037757156983045e-05 } }, { "update_id": 329, "row_count": 15, "row_ids_sha256": "24ec900415ffda81df41be8c0d491b81d8fca581297fe2fd49ff44bfc21a0651", "input_ids_vector_sha256": "5cc2531a25ace59a40cc64a0ca72edac2e2356009d5eec7ba4ef074f35acb4c0", "labels_vector_sha256": "959df39e123998854f24f3375a1e370728f8584aecf85768de57d9f2705ac72d", "planned_active_tokens": 65365, "realized_active_tokens": 65365, "cumulative_start": 21562264, "cumulative_end": 21627629, "loss_sum": 18146.892639160156, "token_normalized_loss": 0.2776239981513066, "grad_norm_before_clip": 0.07231023162603378, "learning_rates_at_step": { "lora": 8.037757156983045e-05, "row_tokens": 8.037757156983045e-05 }, "learning_rates_after_step": { "lora": 8.024143426790205e-05, "row_tokens": 8.024143426790205e-05 } }, { "update_id": 330, "row_count": 14, "row_ids_sha256": "295368f054fa8516d20be84d22bea32e55847050215cd9b7dd090edd0552f9dd", "input_ids_vector_sha256": "110930e5caa3b209d629d0d842c49e61e5e5fcd5337a2cef4f7f0f62c3e26a1b", "labels_vector_sha256": "6466f148e1e94cb61553078440958528fff161234ed0fcd91893726fa8742ae2", "planned_active_tokens": 66206, "realized_active_tokens": 66206, "cumulative_start": 21627629, "cumulative_end": 21693835, "loss_sum": 21170.506240844727, "token_normalized_loss": 0.31976718486005384, "grad_norm_before_clip": 0.0729069709777832, "learning_rates_at_step": { "lora": 8.024143426790205e-05, "row_tokens": 8.024143426790205e-05 }, "learning_rates_after_step": { "lora": 8.01066455455562e-05, "row_tokens": 8.01066455455562e-05 } }, { "update_id": 331, "row_count": 12, "row_ids_sha256": "e458031d67721b26ad56b1ef6aed89ac7cda96b4b578c5c1f379af6d9acda75f", "input_ids_vector_sha256": "af88c8d459ac64bc0622d10e16ed1c58f302dd38ca656f905db351f1a88eb85e", "labels_vector_sha256": "6aa81df27efbcfe02e724141f635160161ecb0261bd6635e548df6fef32bbd78", "planned_active_tokens": 65381, "realized_active_tokens": 65381, "cumulative_start": 21693835, "cumulative_end": 21759216, "loss_sum": 23572.454132080078, "token_normalized_loss": 0.36053982245729, "grad_norm_before_clip": 0.07641074806451797, "learning_rates_at_step": { "lora": 8.01066455455562e-05, "row_tokens": 8.01066455455562e-05 }, "learning_rates_after_step": { "lora": 7.996283055445937e-05, "row_tokens": 7.996283055445937e-05 } }, { "update_id": 332, "row_count": 14, "row_ids_sha256": "f9c8f09abd2768206a7a595a7a2587f3d427d4c15547bbba1316f7303943fdd9", "input_ids_vector_sha256": "94c4f1a3954d121346c30542a9308192a8992078e4e7dfcc14f05297892091d2", "labels_vector_sha256": "638aac853d143cf3b09857d1ce523a5e99dcfcce5c117104d16d084ab6ec4dfe", "planned_active_tokens": 69576, "realized_active_tokens": 69576, "cumulative_start": 21759216, "cumulative_end": 21828792, "loss_sum": 24372.344787597656, "token_normalized_loss": 0.35029816010689974, "grad_norm_before_clip": 0.08071631193161011, "learning_rates_at_step": { "lora": 7.996283055445937e-05, "row_tokens": 7.996283055445937e-05 }, "learning_rates_after_step": { "lora": 7.983589207432752e-05, "row_tokens": 7.983589207432752e-05 } }, { "update_id": 333, "row_count": 11, "row_ids_sha256": "6aae4413b4038f1b2d25d0e3932406b3838f1489b6f1d152621d96c2139dcf30", "input_ids_vector_sha256": "efec80e202f450a0e258a05b605fb7a156a72f5c0999e2e9aed08a88b1234dfa", "labels_vector_sha256": "ad8d4e989afc7561877ffc7f6075bb23451a085a76a317d87525615d081b9490", "planned_active_tokens": 61256, "realized_active_tokens": 61256, "cumulative_start": 21828792, "cumulative_end": 21890048, "loss_sum": 21341.894470214844, "token_normalized_loss": 0.3484049639254088, "grad_norm_before_clip": 0.08226091414690018, "learning_rates_at_step": { "lora": 7.983589207432752e-05, "row_tokens": 7.983589207432752e-05 }, "learning_rates_after_step": { "lora": 7.967321283073514e-05, "row_tokens": 7.967321283073514e-05 } }, { "update_id": 334, "row_count": 13, "row_ids_sha256": "272afe39a6f589a94a1573d23be5123e83dadce981c01d9a7410d9b5af34210f", "input_ids_vector_sha256": "7b6b30826f1f5412b0e40555885ab4551b4c3072cf4c13ac35bae8c34eb4c6d5", "labels_vector_sha256": "93e9fa8270f43df494856ee030ae8f06accbb3f08fd2b4d62908e672cb148efb", "planned_active_tokens": 78293, "realized_active_tokens": 78293, "cumulative_start": 21890048, "cumulative_end": 21968341, "loss_sum": 28689.89520263672, "token_normalized_loss": 0.36644266029704725, "grad_norm_before_clip": 0.07657735049724579, "learning_rates_at_step": { "lora": 7.967321283073514e-05, "row_tokens": 7.967321283073514e-05 }, "learning_rates_after_step": { "lora": 7.955675000875415e-05, "row_tokens": 7.955675000875415e-05 } }, { "update_id": 335, "row_count": 11, "row_ids_sha256": "82bc0b139e292dac70da81a838b6aee60619250e2ec7db7ed511d3561867b1d6", "input_ids_vector_sha256": "8edcc2c610aa8ccc2a427d1a14688201fa65cc8cb8cf27b05d1bbac20b69d1cd", "labels_vector_sha256": "8e87a35b6fbb4fedab9ce41af6bc82be92f0452fc0f1d613c1415f7cb79be22d", "planned_active_tokens": 55907, "realized_active_tokens": 55907, "cumulative_start": 21968341, "cumulative_end": 22024248, "loss_sum": 19116.975036621094, "token_normalized_loss": 0.34194242289196514, "grad_norm_before_clip": 0.08278504759073257, "learning_rates_at_step": { "lora": 7.955675000875415e-05, "row_tokens": 7.955675000875415e-05 }, "learning_rates_after_step": { "lora": 7.942426012985093e-05, "row_tokens": 7.942426012985093e-05 } }, { "update_id": 336, "row_count": 11, "row_ids_sha256": "ee46d591f729979b7702798c8c5d7f1e2469304a8a5fcaae05d27a3756d5b799", "input_ids_vector_sha256": "630418ff6ff379cf83ec5d14c27922e65e3370e58524dd8732696322d8dbc19b", "labels_vector_sha256": "3ede2dd2e11a585e4531bf0f06fa8e4c54f649942d37ab0af40ef7cd4f1f0992", "planned_active_tokens": 63457, "realized_active_tokens": 63457, "cumulative_start": 22024248, "cumulative_end": 22087705, "loss_sum": 21568.963836669922, "token_normalized_loss": 0.33989888958932696, "grad_norm_before_clip": 0.07912958413362503, "learning_rates_at_step": { "lora": 7.942426012985093e-05, "row_tokens": 7.942426012985093e-05 }, "learning_rates_after_step": { "lora": 7.928669469750128e-05, "row_tokens": 7.928669469750128e-05 } }, { "update_id": 337, "row_count": 14, "row_ids_sha256": "e5c03f5c489dae755e598f327eff4ff675a00931f972a463d705017acf28b36e", "input_ids_vector_sha256": "7b3e89ea285e55dc358b7c18c487f30f39fc91b341eab45f31a5fa2fc2d21e76", "labels_vector_sha256": "c3492d9373448cc9b77fd01a119a041a1634269fb04e28999dbf99d2147001be", "planned_active_tokens": 65728, "realized_active_tokens": 65728, "cumulative_start": 22087705, "cumulative_end": 22153433, "loss_sum": 21425.448150634766, "token_normalized_loss": 0.32597139956540233, "grad_norm_before_clip": 0.07656750082969666, "learning_rates_at_step": { "lora": 7.928669469750128e-05, "row_tokens": 7.928669469750128e-05 }, "learning_rates_after_step": { "lora": 7.914259366644921e-05, "row_tokens": 7.914259366644921e-05 } }, { "update_id": 338, "row_count": 12, "row_ids_sha256": "1eaee09b2f7aca3480afa7b94472a93a51d69ad2383b2be0233216b2791f0c43", "input_ids_vector_sha256": "1919a31fca7713bb3928823241b5bc04fc93651bef5bf3ffe8e154e2b725b1f6", "labels_vector_sha256": "5095378854b3a0aa7c6f1ac547ed948bb831a00f749e5d677643241dfd096569", "planned_active_tokens": 68678, "realized_active_tokens": 68678, "cumulative_start": 22153433, "cumulative_end": 22222111, "loss_sum": 25906.410385131836, "token_normalized_loss": 0.3772155622634881, "grad_norm_before_clip": 0.083070769906044, "learning_rates_at_step": { "lora": 7.914259366644921e-05, "row_tokens": 7.914259366644921e-05 }, "learning_rates_after_step": { "lora": 7.899980795294429e-05, "row_tokens": 7.899980795294429e-05 } }, { "update_id": 339, "row_count": 16, "row_ids_sha256": "ea4b02baf1d50b6218fbe207370ccb7b3c813eb41e5f05ac2ca233de1a84d463", "input_ids_vector_sha256": "42009fb7c8c9a3a1aa86702dba30cdf7855e9a316d8e468cfb1cedf8048f5bda", "labels_vector_sha256": "120f8d98c201ef044069b0760ba8cfd0ad2b6114ed8b0f5f8e34cfda125bdbc1", "planned_active_tokens": 67879, "realized_active_tokens": 67879, "cumulative_start": 22222111, "cumulative_end": 22289990, "loss_sum": 23256.585479736328, "token_normalized_loss": 0.3426182689747393, "grad_norm_before_clip": 0.07368559390306473, "learning_rates_at_step": { "lora": 7.899980795294429e-05, "row_tokens": 7.899980795294429e-05 }, "learning_rates_after_step": { "lora": 7.887384514012284e-05, "row_tokens": 7.887384514012284e-05 } }, { "update_id": 340, "row_count": 13, "row_ids_sha256": "98cf4693a3e96ea2ad28a8827c60863f0953ef892f5ef1edb88d6ef6d1593922", "input_ids_vector_sha256": "9bf48d8a5702b07fc9567a9ae699b3c7fbfd2ea8b24862fdeb40d78019274d5b", "labels_vector_sha256": "98b4440e4303130a325db4dc4228703631500131c8ace41f4b8019a15c677696", "planned_active_tokens": 59741, "realized_active_tokens": 59741, "cumulative_start": 22289990, "cumulative_end": 22349731, "loss_sum": 18522.406677246094, "token_normalized_loss": 0.3100451394728259, "grad_norm_before_clip": 0.07824495434761047, "learning_rates_at_step": { "lora": 7.887384514012284e-05, "row_tokens": 7.887384514012284e-05 }, "learning_rates_after_step": { "lora": 7.87357763040868e-05, "row_tokens": 7.87357763040868e-05 } }, { "update_id": 341, "row_count": 12, "row_ids_sha256": "98f27fe318b4379b0cccfc5aaa84280c4fb6d151385b189ca1c82e37d33f6476", "input_ids_vector_sha256": "3710e906c4a1921987d7a96c8479633b7ae4e1c913e22fc840ac619254cfe2b7", "labels_vector_sha256": "2b9b14dc36d56b83e7fca0d7d06db4f9c5fa9daf228acfbe05a8aba62fb2a056", "planned_active_tokens": 65333, "realized_active_tokens": 65333, "cumulative_start": 22349731, "cumulative_end": 22415064, "loss_sum": 20192.807556152344, "token_normalized_loss": 0.3090751619572397, "grad_norm_before_clip": 0.07514039427042007, "learning_rates_at_step": { "lora": 7.87357763040868e-05, "row_tokens": 7.87357763040868e-05 }, "learning_rates_after_step": { "lora": 7.860025104018636e-05, "row_tokens": 7.860025104018636e-05 } }, { "update_id": 342, "row_count": 16, "row_ids_sha256": "fd6281e21f60be3633a375435a28ca9f7e6ff739978d6d5aeceaefb32e96fd0f", "input_ids_vector_sha256": "c6caed4db91f428d4de041ee8ce59ba2caf3989c2c6438cf7d7d6a80acb9d317", "labels_vector_sha256": "98b651ddb6181b9c7e872a70169b3fa59ae80f460f6b4ab926e83bcff7b62f9a", "planned_active_tokens": 63979, "realized_active_tokens": 63979, "cumulative_start": 22415064, "cumulative_end": 22479043, "loss_sum": 21781.55389404297, "token_normalized_loss": 0.3404484892549582, "grad_norm_before_clip": 0.0813271626830101, "learning_rates_at_step": { "lora": 7.860025104018636e-05, "row_tokens": 7.860025104018636e-05 }, "learning_rates_after_step": { "lora": 7.846048874648575e-05, "row_tokens": 7.846048874648575e-05 } }, { "update_id": 343, "row_count": 14, "row_ids_sha256": "8d9ecff5959c75fa5483291e5cb61658b4a3ba318fef409297c4c22eb8422979", "input_ids_vector_sha256": "5580ab8c50d68096171d4e56ab9be3355f0ccfbf93539fd1d1ca7b0d8c03bf50", "labels_vector_sha256": "50424291aa8ec045bede71dcc53c8c9d7f5156c2ead9ab9277f867d19a7819d5", "planned_active_tokens": 65825, "realized_active_tokens": 65825, "cumulative_start": 22479043, "cumulative_end": 22544868, "loss_sum": 18989.65704345703, "token_normalized_loss": 0.28848700407834454, "grad_norm_before_clip": 0.0705757811665535, "learning_rates_at_step": { "lora": 7.846048874648575e-05, "row_tokens": 7.846048874648575e-05 }, "learning_rates_after_step": { "lora": 7.831975536306007e-05, "row_tokens": 7.831975536306007e-05 } }, { "update_id": 344, "row_count": 13, "row_ids_sha256": "cc1a7a8940fc189acaf700fac4fc7b6c2f63963d5a5959816b77f535e9d547f1", "input_ids_vector_sha256": "b997a439cbee26854aa513f336ee339835b3ee0ac057040fcffcd3987f4cbbec", "labels_vector_sha256": "bc0af05aa90da8673725c917fa80fbbfb6f8999ab0100cbbfef666f6620f9dca", "planned_active_tokens": 66126, "realized_active_tokens": 66126, "cumulative_start": 22544868, "cumulative_end": 22610994, "loss_sum": 20841.88458251953, "token_normalized_loss": 0.31518441433807476, "grad_norm_before_clip": 0.076276496052742, "learning_rates_at_step": { "lora": 7.831975536306007e-05, "row_tokens": 7.831975536306007e-05 }, "learning_rates_after_step": { "lora": 7.816794489126968e-05, "row_tokens": 7.816794489126968e-05 } }, { "update_id": 345, "row_count": 15, "row_ids_sha256": "d641aae8fe20f114307e8a8460b02b864974a8de0cb17cfc1f0b2d06ba1e9273", "input_ids_vector_sha256": "ca6f960934440e80742c8192d36334667fb94fbabcbf6c3ebc8c39a8219a5f59", "labels_vector_sha256": "2ccee6191e1855281e9c02eb728eae0c01d9414522617084e6228b0eb8fef2e4", "planned_active_tokens": 71157, "realized_active_tokens": 71157, "cumulative_start": 22610994, "cumulative_end": 22682151, "loss_sum": 21347.57305908203, "token_normalized_loss": 0.30000664810323696, "grad_norm_before_clip": 0.07001359015703201, "learning_rates_at_step": { "lora": 7.816794489126968e-05, "row_tokens": 7.816794489126968e-05 }, "learning_rates_after_step": { "lora": 7.803445395921258e-05, "row_tokens": 7.803445395921258e-05 } }, { "update_id": 346, "row_count": 14, "row_ids_sha256": "bff1fd34d1c9fb8bee4bcaf93e5727d49879e3081049250af81830cd47276ac2", "input_ids_vector_sha256": "62641c6f4864033014dcbaee906226710085b1ca31984acfb94779b1c63a7c68", "labels_vector_sha256": "6c81bc46e9cf21843911eb0c11c9ef264168796180bededdb757965f565ff25c", "planned_active_tokens": 62423, "realized_active_tokens": 62423, "cumulative_start": 22682151, "cumulative_end": 22744574, "loss_sum": 19500.9248046875, "token_normalized_loss": 0.3123996732724717, "grad_norm_before_clip": 0.07649737596511841, "learning_rates_at_step": { "lora": 7.803445395921258e-05, "row_tokens": 7.803445395921258e-05 }, "learning_rates_after_step": { "lora": 7.787843310535598e-05, "row_tokens": 7.787843310535598e-05 } }, { "update_id": 347, "row_count": 12, "row_ids_sha256": "8fc22ecce552b0df9581d665ec23587867e4ce95d2ddd4c3780cb2880e1e2e10", "input_ids_vector_sha256": "39c84365a8a519f2a95f50b7e085f76c2893716fdf2438672a0f31c8297ed759", "labels_vector_sha256": "c42652fad74f92fd32a1e1b12ec7ae76b5e7ecda0b4bf0defda3a1cde9afb3a1", "planned_active_tokens": 72786, "realized_active_tokens": 72786, "cumulative_start": 22744574, "cumulative_end": 22817360, "loss_sum": 23188.290618896484, "token_normalized_loss": 0.31858174125376426, "grad_norm_before_clip": 0.07029154151678085, "learning_rates_at_step": { "lora": 7.787843310535598e-05, "row_tokens": 7.787843310535598e-05 }, "learning_rates_after_step": { "lora": 7.775755089226397e-05, "row_tokens": 7.775755089226397e-05 } }, { "update_id": 348, "row_count": 14, "row_ids_sha256": "54e62417e15b20d5e4ccde0627dda01258336530d98390462953ffe314ac4587", "input_ids_vector_sha256": "b6eef724737f728c4b427fedc1d622954a578e13e60c5084486b3fe90c2f448d", "labels_vector_sha256": "b833935bf7e903b22f4ea2d6ba3e057b60a5e082c34cd4bf62bb8d30990ee3eb", "planned_active_tokens": 56267, "realized_active_tokens": 56267, "cumulative_start": 22817360, "cumulative_end": 22873627, "loss_sum": 18125.080078125, "token_normalized_loss": 0.3221262921094958, "grad_norm_before_clip": 0.08056473731994629, "learning_rates_at_step": { "lora": 7.775755089226397e-05, "row_tokens": 7.775755089226397e-05 }, "learning_rates_after_step": { "lora": 7.761387287488022e-05, "row_tokens": 7.761387287488022e-05 } }, { "update_id": 349, "row_count": 14, "row_ids_sha256": "79ed73cebc88d74076bc2a592cb0b33d5e33db548d6a66b83f51cc0a89f931f3", "input_ids_vector_sha256": "8cce57493788a9845134fe378ccbf32899929ef914ca30a52ab3754774c09a78", "labels_vector_sha256": "1a475c38dbefec5fac29a5dfa44195f3bea67f176e47d545f0c291d64a1906b4", "planned_active_tokens": 66736, "realized_active_tokens": 66736, "cumulative_start": 22873627, "cumulative_end": 22940363, "loss_sum": 23344.347564697266, "token_normalized_loss": 0.3498014199936656, "grad_norm_before_clip": 0.07429955899715424, "learning_rates_at_step": { "lora": 7.761387287488022e-05, "row_tokens": 7.761387287488022e-05 }, "learning_rates_after_step": { "lora": 7.746545450367924e-05, "row_tokens": 7.746545450367924e-05 } }, { "update_id": 350, "row_count": 15, "row_ids_sha256": "39fc351b9667fb3cfc33bbf518763b7ccc31c75ec59d15c8c28cce1156682c4d", "input_ids_vector_sha256": "40f93ccb9e504d1d87f90a2c09344682c24d2fa8a25fa401e4426ce8fa1451b8", "labels_vector_sha256": "a50a10d2b1a47bfe736aeab3712de3cda484a12534c31cb0f2086cfacd020386", "planned_active_tokens": 68778, "realized_active_tokens": 68778, "cumulative_start": 22940363, "cumulative_end": 23009141, "loss_sum": 21743.380615234375, "token_normalized_loss": 0.3161385997736831, "grad_norm_before_clip": 0.07233492285013199, "learning_rates_at_step": { "lora": 7.746545450367924e-05, "row_tokens": 7.746545450367924e-05 }, "learning_rates_after_step": { "lora": 7.73316376169175e-05, "row_tokens": 7.73316376169175e-05 } }, { "update_id": 351, "row_count": 15, "row_ids_sha256": "cac47e215386c7ccbc0030bc619407f7387775d40c514855ff84b61fe96d9cc4", "input_ids_vector_sha256": "b61443de4e5ac52a34e53f8c8e8cde759896b427c93419adb1d1ddf6b4cb6f90", "labels_vector_sha256": "5852dd706e153d6c99388a502ba6cce6ad4391f3a037e71fdc8c8376b0a58b71", "planned_active_tokens": 61874, "realized_active_tokens": 61874, "cumulative_start": 23009141, "cumulative_end": 23071015, "loss_sum": 19720.061157226562, "token_normalized_loss": 0.318713210027258, "grad_norm_before_clip": 0.07635567337274551, "learning_rates_at_step": { "lora": 7.73316376169175e-05, "row_tokens": 7.73316376169175e-05 }, "learning_rates_after_step": { "lora": 7.718520395425309e-05, "row_tokens": 7.718520395425309e-05 } }, { "update_id": 352, "row_count": 13, "row_ids_sha256": "c157eb640fe5193ba368a7d93047227e3e69101bb4b4e810ce041fe92dbbf6af", "input_ids_vector_sha256": "0e234993a9741c3690d84c7cf6e2fa2625d28534f63a80c43084898d36e470d8", "labels_vector_sha256": "c441d101fcf32520637e8ec3af52a045a82effc5b099cca48f795a2b2b1ba0f8", "planned_active_tokens": 67560, "realized_active_tokens": 67560, "cumulative_start": 23071015, "cumulative_end": 23138575, "loss_sum": 24593.085540771484, "token_normalized_loss": 0.3640184360682576, "grad_norm_before_clip": 0.07822605967521667, "learning_rates_at_step": { "lora": 7.718520395425309e-05, "row_tokens": 7.718520395425309e-05 }, "learning_rates_after_step": { "lora": 7.704319684253347e-05, "row_tokens": 7.704319684253347e-05 } }, { "update_id": 353, "row_count": 14, "row_ids_sha256": "26bc9726833adf593d34f3d79b22455eab21482d092f1bf962a254fa84ff6166", "input_ids_vector_sha256": "c040223aaa00aa40addd0c934c47dd46ee9fd5a04744ac61fabbb84d5a9aa026", "labels_vector_sha256": "e59f61c167e5b27afd6dba56bb918dccd0fd58200703b1879bfa10233c4bdcea", "planned_active_tokens": 65372, "realized_active_tokens": 65372, "cumulative_start": 23138575, "cumulative_end": 23203947, "loss_sum": 19534.540405273438, "token_normalized_loss": 0.2988212140560704, "grad_norm_before_clip": 0.07422839850187302, "learning_rates_at_step": { "lora": 7.704319684253347e-05, "row_tokens": 7.704319684253347e-05 }, "learning_rates_after_step": { "lora": 7.690791100559129e-05, "row_tokens": 7.690791100559129e-05 } }, { "update_id": 354, "row_count": 13, "row_ids_sha256": "d254e3859091d84ce250f95a24f41d5ba6553c1194530f91cd39ecfc45ef118a", "input_ids_vector_sha256": "b80c2d8379d9f31ed11067f5d8fdfb87cb6ac2e88f9b0a6909888cfc607ae528", "labels_vector_sha256": "4afe2c6f88ac84f5e4cb66affc71228ed3a069a12a462e6812d71181ae8c8281", "planned_active_tokens": 62146, "realized_active_tokens": 62146, "cumulative_start": 23203947, "cumulative_end": 23266093, "loss_sum": 19486.975463867188, "token_normalized_loss": 0.31356765461762925, "grad_norm_before_clip": 0.07953789085149765, "learning_rates_at_step": { "lora": 7.690791100559129e-05, "row_tokens": 7.690791100559129e-05 }, "learning_rates_after_step": { "lora": 7.676328036212304e-05, "row_tokens": 7.676328036212304e-05 } }, { "update_id": 355, "row_count": 14, "row_ids_sha256": "92110e7bc79ae4ab4afaf48518767b9c73fea6f3aa4548b2bab5c9cbad7e22d3", "input_ids_vector_sha256": "118d5fa34234a2680e4def748f2b51d85f9ee8f22e233e4bba375ae3538490fb", "labels_vector_sha256": "7c0be216a5412f5ed11ccfa01cb637aa559bb49de464d9794b44ec4c9dc12e2f", "planned_active_tokens": 66298, "realized_active_tokens": 66298, "cumulative_start": 23266093, "cumulative_end": 23332391, "loss_sum": 23163.262481689453, "token_normalized_loss": 0.34938101423405615, "grad_norm_before_clip": 0.07917486131191254, "learning_rates_at_step": { "lora": 7.676328036212304e-05, "row_tokens": 7.676328036212304e-05 }, "learning_rates_after_step": { "lora": 7.662334914574786e-05, "row_tokens": 7.662334914574786e-05 } }, { "update_id": 356, "row_count": 13, "row_ids_sha256": "c3807882a5566dfb05b565f052d2f267f06520a5c09d64d61712749e5e2b4d1c", "input_ids_vector_sha256": "f15b2bb6a5216451b5205c8d828cc112b98b17cc9086c7802b9947d84d43a6fa", "labels_vector_sha256": "551d5492268cd1a31133a994a242955fe136eecab14feef0ea91c8b9dccafa6f", "planned_active_tokens": 64007, "realized_active_tokens": 64007, "cumulative_start": 23332391, "cumulative_end": 23396398, "loss_sum": 18119.47006225586, "token_normalized_loss": 0.28308575721805207, "grad_norm_before_clip": 0.07086814194917679, "learning_rates_at_step": { "lora": 7.662334914574786e-05, "row_tokens": 7.662334914574786e-05 }, "learning_rates_after_step": { "lora": 7.647352240247585e-05, "row_tokens": 7.647352240247585e-05 } }, { "update_id": 357, "row_count": 12, "row_ids_sha256": "b8753278106be1c35ac9baa0d18ad1c1d8f140d4f87d2f8e77c9f0263eee6e8b", "input_ids_vector_sha256": "f311f340a226ee7f2c94c671b57c0373e24bfe3b3ee91db9457179f60b1eab9a", "labels_vector_sha256": "2f40d9084cb0e823def121a18da1d5854d386f366ee4e5164b8457fd03b77573", "planned_active_tokens": 68386, "realized_active_tokens": 68386, "cumulative_start": 23396398, "cumulative_end": 23464784, "loss_sum": 26189.844665527344, "token_normalized_loss": 0.38297085171712547, "grad_norm_before_clip": 0.08243854343891144, "learning_rates_at_step": { "lora": 7.647352240247585e-05, "row_tokens": 7.647352240247585e-05 }, "learning_rates_after_step": { "lora": 7.63344533879269e-05, "row_tokens": 7.63344533879269e-05 } }, { "update_id": 358, "row_count": 15, "row_ids_sha256": "73c70fdac3fee060d57a59b5d6478a97c7607ea94aca09f36b15531dbd237e80", "input_ids_vector_sha256": "470e825123b2170069cc509c7d4bc3ce0d326882f23ec8c90eb84305921a5e13", "labels_vector_sha256": "ac0e8e51409e43f184d29a2544c580c1980db6a38b42cc7870e429e4c9f3c116", "planned_active_tokens": 63341, "realized_active_tokens": 63341, "cumulative_start": 23464784, "cumulative_end": 23528125, "loss_sum": 21033.944885253906, "token_normalized_loss": 0.33207472072202693, "grad_norm_before_clip": 0.08173419535160065, "learning_rates_at_step": { "lora": 7.63344533879269e-05, "row_tokens": 7.63344533879269e-05 }, "learning_rates_after_step": { "lora": 7.618891108330901e-05, "row_tokens": 7.618891108330901e-05 } }, { "update_id": 359, "row_count": 14, "row_ids_sha256": "7867b936a02bdbdc843ba4c53a6282d2058d8ff66a8e24b91647aa155775d85f", "input_ids_vector_sha256": "6f49c18651afb36f889e017d64edb12fb919791c1d61ad0d1ed87b2fd44df75f", "labels_vector_sha256": "571a1b72ed67a37819fcba741b2cec1a86c20084ce400e9fd0ef23aeb65d2cb5", "planned_active_tokens": 66152, "realized_active_tokens": 66152, "cumulative_start": 23528125, "cumulative_end": 23594277, "loss_sum": 19776.353515625, "token_normalized_loss": 0.2989532216051669, "grad_norm_before_clip": 0.07231839001178741, "learning_rates_at_step": { "lora": 7.618891108330901e-05, "row_tokens": 7.618891108330901e-05 }, "learning_rates_after_step": { "lora": 7.604413717211621e-05, "row_tokens": 7.604413717211621e-05 } }, { "update_id": 360, "row_count": 12, "row_ids_sha256": "d8ecb778985e9f42571c76e8a82829377ee1b27b8b4d78123e3c7472bf185c1b", "input_ids_vector_sha256": "f8291dc764adfad3845665475e2d5188d40727231371bd20f3ea40275625c01e", "labels_vector_sha256": "1af60c50f689990a5de749c67a6e76ff9d82084640cd6d6f2d102d074f2b12d4", "planned_active_tokens": 65665, "realized_active_tokens": 65665, "cumulative_start": 23594277, "cumulative_end": 23659942, "loss_sum": 17939.24252319336, "token_normalized_loss": 0.27319336820518325, "grad_norm_before_clip": 0.06726082414388657, "learning_rates_at_step": { "lora": 7.604413717211621e-05, "row_tokens": 7.604413717211621e-05 }, "learning_rates_after_step": { "lora": 7.590088973509809e-05, "row_tokens": 7.590088973509809e-05 } }, { "update_id": 361, "row_count": 16, "row_ids_sha256": "d8327e4807468c5c9a1eb13cd2d772f58e02e67dbd8a0ab5f7cda70f257784c6", "input_ids_vector_sha256": "2ac276caaf7c3a6b5905d48467d67fb09cfedcb88ed1e43d9cc786c0faf59dc3", "labels_vector_sha256": "d180e020758f0da456ae8ebd2c2ee7d33372d7934e9c87063c5ab6e9a95175ed", "planned_active_tokens": 64839, "realized_active_tokens": 64839, "cumulative_start": 23659942, "cumulative_end": 23724781, "loss_sum": 21940.821899414062, "token_normalized_loss": 0.33838927033751387, "grad_norm_before_clip": 0.07769034802913666, "learning_rates_at_step": { "lora": 7.590088973509809e-05, "row_tokens": 7.590088973509809e-05 }, "learning_rates_after_step": { "lora": 7.57536481005825e-05, "row_tokens": 7.57536481005825e-05 } }, { "update_id": 362, "row_count": 14, "row_ids_sha256": "e9ddd370dcae6e8b282e7d3e83382178aa6d95f9fdd25628d21713210a6b4f62", "input_ids_vector_sha256": "4f6d858e256ce65044400a7e956810cf6a7a793bf893ba00ad347e257ddfc940", "labels_vector_sha256": "9644829268592dea221ec49eeb9d36c52680a90e17fc0a7085f37bb0e6399c13", "planned_active_tokens": 66510, "realized_active_tokens": 66510, "cumulative_start": 23724781, "cumulative_end": 23791291, "loss_sum": 23545.387084960938, "token_normalized_loss": 0.35401273620449464, "grad_norm_before_clip": 0.07961998134851456, "learning_rates_at_step": { "lora": 7.57536481005825e-05, "row_tokens": 7.57536481005825e-05 }, "learning_rates_after_step": { "lora": 7.560609963173646e-05, "row_tokens": 7.560609963173646e-05 } }, { "update_id": 363, "row_count": 14, "row_ids_sha256": "acc8e8279a66775a0715ed18c77e338bb4aa278c6d1f1cdffa5b56369f57d3b4", "input_ids_vector_sha256": "ffb3c38c87fe54f5096d0a51a6a3fe0b31727552716c364f3f340c891ba587f6", "labels_vector_sha256": "4ab1eea3176bc7cf281a1b8234ee9fdd8e54913ed2fb2c4a284123ae75438c8d", "planned_active_tokens": 66511, "realized_active_tokens": 66511, "cumulative_start": 23791291, "cumulative_end": 23857802, "loss_sum": 21020.239532470703, "token_normalized_loss": 0.31604155000632533, "grad_norm_before_clip": 0.07329832017421722, "learning_rates_at_step": { "lora": 7.560609963173646e-05, "row_tokens": 7.560609963173646e-05 }, "learning_rates_after_step": { "lora": 7.54656534702755e-05, "row_tokens": 7.54656534702755e-05 } }, { "update_id": 364, "row_count": 16, "row_ids_sha256": "9edbc65149ce647de4fc8dad3e4f1f7004a44aff335bdca1f079a9c64f5e11a8", "input_ids_vector_sha256": "047e98eb12a2270548a966b3166bc275096f5ccbd2eb6b0f93bbd028cc6d2185", "labels_vector_sha256": "7eb3c6a4858f64a2c86ab2c38e45c2fbc26a3022e789ea285fafab0c015c4cdd", "planned_active_tokens": 63183, "realized_active_tokens": 63183, "cumulative_start": 23857802, "cumulative_end": 23920985, "loss_sum": 18061.603912353516, "token_normalized_loss": 0.2858617652272528, "grad_norm_before_clip": 0.07449634373188019, "learning_rates_at_step": { "lora": 7.54656534702755e-05, "row_tokens": 7.54656534702755e-05 }, "learning_rates_after_step": { "lora": 7.531696755759208e-05, "row_tokens": 7.531696755759208e-05 } }, { "update_id": 365, "row_count": 16, "row_ids_sha256": "e7162a9b4116f1c73c6c454fe66c06a35cb50df92309b8a3f02546eff61dde69", "input_ids_vector_sha256": "584f11dd8da09262591372d44215d6632f982fd74b1e82517c02563f65c095b1", "labels_vector_sha256": "bc6981efc8984f5a839335ab27081464f482f33dd7db0abe7e0782a5f804bceb", "planned_active_tokens": 66757, "realized_active_tokens": 66757, "cumulative_start": 23920985, "cumulative_end": 23987742, "loss_sum": 21682.49432373047, "token_normalized_loss": 0.3247973144948166, "grad_norm_before_clip": 0.0747913345694542, "learning_rates_at_step": { "lora": 7.531696755759208e-05, "row_tokens": 7.531696755759208e-05 }, "learning_rates_after_step": { "lora": 7.517167944670893e-05, "row_tokens": 7.517167944670893e-05 } }, { "update_id": 366, "row_count": 17, "row_ids_sha256": "d5942949d8afcef6df1d7426819f3daf18f12d836cbf36922273f1933b8b16fe", "input_ids_vector_sha256": "92de40feebdafbf085b81b91a722b5655b98c03cb7c305671fef0dfa96137e81", "labels_vector_sha256": "5edd88a35c0e305a8f3f20134b8caff68dde62be0d9d9a84ddd817da22940206", "planned_active_tokens": 65101, "realized_active_tokens": 65101, "cumulative_start": 23987742, "cumulative_end": 24052843, "loss_sum": 16635.98257446289, "token_normalized_loss": 0.2555411218639175, "grad_norm_before_clip": 0.06550362706184387, "learning_rates_at_step": { "lora": 7.517167944670893e-05, "row_tokens": 7.517167944670893e-05 }, "learning_rates_after_step": { "lora": 7.500875726853946e-05, "row_tokens": 7.500875726853946e-05 } }, { "update_id": 367, "row_count": 19, "row_ids_sha256": "2a0223ad174fcf10734102832022a3268293a5c635367779baf557068f7fdd46", "input_ids_vector_sha256": "90edfbc7e69131117672518f28c3507cf6de6f2ab9d06bfb96b13467d6964ea5", "labels_vector_sha256": "3ec2475108b0d258bf7627101c9ba650a46f738f83ac021e3f44caae791205e4", "planned_active_tokens": 72851, "realized_active_tokens": 72851, "cumulative_start": 24052843, "cumulative_end": 24125694, "loss_sum": 22351.344635009766, "token_normalized_loss": 0.30680902986931907, "grad_norm_before_clip": 0.06940589100122452, "learning_rates_at_step": { "lora": 7.500875726853946e-05, "row_tokens": 7.500875726853946e-05 }, "learning_rates_after_step": { "lora": 7.487174230946937e-05, "row_tokens": 7.487174230946937e-05 } }, { "update_id": 368, "row_count": 14, "row_ids_sha256": "7cc9a2175bb861d6582d186f9ef26bd74a48bc9085cfc3676b029fe66d5505fa", "input_ids_vector_sha256": "33c30934d53a6da8078eef0ecf06729fb80d87cafa4e593d0ce1c33bcb3abb89", "labels_vector_sha256": "e7e9874a1ef805902fdbc945879169241e50762e008edd93bcdd41b945a11cc2", "planned_active_tokens": 61144, "realized_active_tokens": 61144, "cumulative_start": 24125694, "cumulative_end": 24186838, "loss_sum": 21479.10971069336, "token_normalized_loss": 0.35128728429107287, "grad_norm_before_clip": 0.08095572888851166, "learning_rates_at_step": { "lora": 7.487174230946937e-05, "row_tokens": 7.487174230946937e-05 }, "learning_rates_after_step": { "lora": 7.473036669478963e-05, "row_tokens": 7.473036669478963e-05 } }, { "update_id": 369, "row_count": 12, "row_ids_sha256": "6a6e0034eb7d1fbc617d3c716cd89b9aadfb2f57518baa523f9b725f1402e4da", "input_ids_vector_sha256": "4c4b89a9c974560186fa551b2b0ff954a599eacae50cf1b8702aa4beb33d8d4c", "labels_vector_sha256": "8df8554cdaf177ed90bed8eb11aa3a4856006488caefa004291cf8fec39a88fc", "planned_active_tokens": 62974, "realized_active_tokens": 62974, "cumulative_start": 24186838, "cumulative_end": 24249812, "loss_sum": 20092.652862548828, "token_normalized_loss": 0.31906267447754355, "grad_norm_before_clip": 0.07960733026266098, "learning_rates_at_step": { "lora": 7.473036669478963e-05, "row_tokens": 7.473036669478963e-05 }, "learning_rates_after_step": { "lora": 7.457812035686448e-05, "row_tokens": 7.457812035686448e-05 } }, { "update_id": 370, "row_count": 17, "row_ids_sha256": "5dfeae91ba93dc148a921ba1f94b779a0d65688d8c3422eb979c6ebe0f0e6da6", "input_ids_vector_sha256": "464923610a202d92adf0b2d64818b3cd768c455365afd574e80c9fe1d622db26", "labels_vector_sha256": "cf7d008635730dfa3cf337c4f5719a5ce304d5825f523e4b0932218408fee06b", "planned_active_tokens": 67686, "realized_active_tokens": 67686, "cumulative_start": 24249812, "cumulative_end": 24317498, "loss_sum": 20670.77621459961, "token_normalized_loss": 0.30539219653398947, "grad_norm_before_clip": 0.07640156894922256, "learning_rates_at_step": { "lora": 7.457812035686448e-05, "row_tokens": 7.457812035686448e-05 }, "learning_rates_after_step": { "lora": 7.442067056914494e-05, "row_tokens": 7.442067056914494e-05 } }, { "update_id": 371, "row_count": 14, "row_ids_sha256": "39665617e875598503def5096b375c420b15a9efad87d9003e4f8bf26f9a9fcd", "input_ids_vector_sha256": "fa48640c56c43d364f128f2809f767206e7ef9d9954c5c36ac8ff67dff7d8e1a", "labels_vector_sha256": "18f69247149147344dd47531e10c1f482206544a735150fb69945d70539be7cd", "planned_active_tokens": 69859, "realized_active_tokens": 69859, "cumulative_start": 24317498, "cumulative_end": 24387357, "loss_sum": 22593.726654052734, "token_normalized_loss": 0.3234189818642227, "grad_norm_before_clip": 0.07221725583076477, "learning_rates_at_step": { "lora": 7.442067056914494e-05, "row_tokens": 7.442067056914494e-05 }, "learning_rates_after_step": { "lora": 7.42812903950483e-05, "row_tokens": 7.42812903950483e-05 } }, { "update_id": 372, "row_count": 13, "row_ids_sha256": "109781930bd737a359b30dda1df1fc24d97cee9656d654fd12c1f4445e6dc013", "input_ids_vector_sha256": "59a57364bd2f9cecc50d8d46e31a6b2798bd18d6223bbc4ac2896b58ee1f4442", "labels_vector_sha256": "d46fd1b03e0993500cd743248c720849d26c26e6bc7ee07f9dfeb11aea18fcbb", "planned_active_tokens": 61724, "realized_active_tokens": 61724, "cumulative_start": 24387357, "cumulative_end": 24449081, "loss_sum": 17872.915466308594, "token_normalized_loss": 0.2895618473577311, "grad_norm_before_clip": 0.0746670663356781, "learning_rates_at_step": { "lora": 7.42812903950483e-05, "row_tokens": 7.42812903950483e-05 }, "learning_rates_after_step": { "lora": 7.413676315491202e-05, "row_tokens": 7.413676315491202e-05 } }, { "update_id": 373, "row_count": 16, "row_ids_sha256": "234260bab8c2ec156128396eb2c12113cd2c7afe66688c4ed183f8c5d13a0072", "input_ids_vector_sha256": "3bd5122af08709c40c65d2e9ed93ee89f6dd8dd08ac24ab935c41da0d3e610bf", "labels_vector_sha256": "8173ed10dfd100b2fa27689cd4e1d05624c5e39c455b06c79e007379290acdcd", "planned_active_tokens": 63888, "realized_active_tokens": 63888, "cumulative_start": 24449081, "cumulative_end": 24512969, "loss_sum": 20075.697677612305, "token_normalized_loss": 0.3142326834086574, "grad_norm_before_clip": 0.07530319690704346, "learning_rates_at_step": { "lora": 7.413676315491202e-05, "row_tokens": 7.413676315491202e-05 }, "learning_rates_after_step": { "lora": 7.399067270281019e-05, "row_tokens": 7.399067270281019e-05 } }, { "update_id": 374, "row_count": 17, "row_ids_sha256": "3b854dc32c14f43800b32ff74feb027fe734ef10c46ea94cc7f4c619bf5beb4c", "input_ids_vector_sha256": "25d8f5edc29d5d9b18c2f5acd5cf818db6d421c2c0a9ac57093ff0904ebdee1e", "labels_vector_sha256": "12ac9a284509973776a68f04d0a92d0421df7ea64532d3e2e6190e2e420855cb", "planned_active_tokens": 64461, "realized_active_tokens": 64461, "cumulative_start": 24512969, "cumulative_end": 24577430, "loss_sum": 17923.470626831055, "token_normalized_loss": 0.27805138962831877, "grad_norm_before_clip": 0.07191217690706253, "learning_rates_at_step": { "lora": 7.399067270281019e-05, "row_tokens": 7.399067270281019e-05 }, "learning_rates_after_step": { "lora": 7.384354303925765e-05, "row_tokens": 7.384354303925765e-05 } }, { "update_id": 375, "row_count": 12, "row_ids_sha256": "17505f3f8f1bf9b290c0f089dad2127d98a7c9708d97dd92c846625642d5f86e", "input_ids_vector_sha256": "6951d56fb7bc57aa3f1887914c19d3e6e93df1654c1d8805922f97ead296ca23", "labels_vector_sha256": "fedce2dac214f638a8986b463ed92b90fdd547a413afc4302bc6c4994ceef770", "planned_active_tokens": 64801, "realized_active_tokens": 64801, "cumulative_start": 24577430, "cumulative_end": 24642231, "loss_sum": 21338.069610595703, "token_normalized_loss": 0.3292861161185121, "grad_norm_before_clip": 0.07909315079450607, "learning_rates_at_step": { "lora": 7.384354303925765e-05, "row_tokens": 7.384354303925765e-05 }, "learning_rates_after_step": { "lora": 7.368933812652608e-05, "row_tokens": 7.368933812652608e-05 } }, { "update_id": 376, "row_count": 15, "row_ids_sha256": "430dadb819f6e95a677477aef45efdee9aa1f314150f4f9d22f5d7098ed8bde8", "input_ids_vector_sha256": "c85a2482831d673ef7b5b41e64fc529b11ef56341bf7f0bc5ae0a79127739c58", "labels_vector_sha256": "d096626126da41ca555bd42c9b703ea9b3f99f2e3d25b84aa97dddaf54205493", "planned_active_tokens": 67791, "realized_active_tokens": 67791, "cumulative_start": 24642231, "cumulative_end": 24710022, "loss_sum": 18681.54800415039, "token_normalized_loss": 0.27557563694517545, "grad_norm_before_clip": 0.07409324496984482, "learning_rates_at_step": { "lora": 7.368933812652608e-05, "row_tokens": 7.368933812652608e-05 }, "learning_rates_after_step": { "lora": 7.354045582026955e-05, "row_tokens": 7.354045582026955e-05 } }, { "update_id": 377, "row_count": 14, "row_ids_sha256": "db6b305457608436b1bbb4e3b95383523e3e921757d0d69f103bb340aee2c4a0", "input_ids_vector_sha256": "7397e055e050d8da7ce4b3d61e1a13bd13a7dc1ebce69582868f099e5744b10c", "labels_vector_sha256": "d55e0f2328b1a0bb0cebae36d1862d32f04102cbb30dcacb553012d6741a9c94", "planned_active_tokens": 65330, "realized_active_tokens": 65330, "cumulative_start": 24710022, "cumulative_end": 24775352, "loss_sum": 18481.454162597656, "token_normalized_loss": 0.282893833806791, "grad_norm_before_clip": 0.07440079748630524, "learning_rates_at_step": { "lora": 7.354045582026955e-05, "row_tokens": 7.354045582026955e-05 }, "learning_rates_after_step": { "lora": 7.338711391623755e-05, "row_tokens": 7.338711391623755e-05 } }, { "update_id": 378, "row_count": 16, "row_ids_sha256": "5a5e54a5996b09dcbef3929c34eb249338c1af2134bb63370af20184658d09bb", "input_ids_vector_sha256": "06d4a5f2290276c71291be3a966fe1041ffbef8c151d07e501c9ab4b966940a2", "labels_vector_sha256": "6f99ddbca68dfb66a0c736594cce75ae13ee9724cbca41682171dd8b052afe02", "planned_active_tokens": 67164, "realized_active_tokens": 67164, "cumulative_start": 24775352, "cumulative_end": 24842516, "loss_sum": 18623.12892150879, "token_normalized_loss": 0.277278436684962, "grad_norm_before_clip": 0.07357297092676163, "learning_rates_at_step": { "lora": 7.338711391623755e-05, "row_tokens": 7.338711391623755e-05 }, "learning_rates_after_step": { "lora": 7.324650866482673e-05, "row_tokens": 7.324650866482673e-05 } }, { "update_id": 379, "row_count": 16, "row_ids_sha256": "f924131f4f03e408b6d00d485a5398b231485f5abbd6f68ba6a31007e6e6119f", "input_ids_vector_sha256": "a60492a9f4476e0e3ec81ea52b6e2e1a0ba06618f1c6662c8a810f0c329a8753", "labels_vector_sha256": "078f7b7928e94f3c19de8a2f20f728f444dcd604b21f922ad27c5151c8542f6f", "planned_active_tokens": 61477, "realized_active_tokens": 61477, "cumulative_start": 24842516, "cumulative_end": 24903993, "loss_sum": 17923.063842773438, "token_normalized_loss": 0.29154096398284624, "grad_norm_before_clip": 0.07759573310613632, "learning_rates_at_step": { "lora": 7.324650866482673e-05, "row_tokens": 7.324650866482673e-05 }, "learning_rates_after_step": { "lora": 7.309421496823194e-05, "row_tokens": 7.309421496823194e-05 } }, { "update_id": 380, "row_count": 15, "row_ids_sha256": "9ccc2e1d85e876c3108f7e2b458c90b46e13619dd6e5652da1b5af3767c3bb54", "input_ids_vector_sha256": "b2f6b6844ea23a88d0f19c81836bb44aae547d14a89c068adcab2db03b79cf46", "labels_vector_sha256": "93ff87b5030052d7b6df55fb1175e1c69dc8e6dcb1f80fbe9862bf6a458a8a59", "planned_active_tokens": 66472, "realized_active_tokens": 66472, "cumulative_start": 24903993, "cumulative_end": 24970465, "loss_sum": 19700.185424804688, "token_normalized_loss": 0.2963681764472964, "grad_norm_before_clip": 0.07539989054203033, "learning_rates_at_step": { "lora": 7.309421496823194e-05, "row_tokens": 7.309421496823194e-05 }, "learning_rates_after_step": { "lora": 7.294239962108149e-05, "row_tokens": 7.294239962108149e-05 } }, { "update_id": 381, "row_count": 19, "row_ids_sha256": "b51a58ca3bdc67976961a13f5102b9f9a811f7c86167d8c65075b0cbe145255f", "input_ids_vector_sha256": "42d1a36b47d155910ffd5f92441e4e37ba439c615e9f93f02d24964899486c66", "labels_vector_sha256": "0dc9746b167cae0d633f7a9e605413baf767c665e2e7b9df6e2a4ae6b811101e", "planned_active_tokens": 66145, "realized_active_tokens": 66145, "cumulative_start": 24970465, "cumulative_end": 25036610, "loss_sum": 18055.82649230957, "token_normalized_loss": 0.27297341435194755, "grad_norm_before_clip": 0.07383882254362106, "learning_rates_at_step": { "lora": 7.294239962108149e-05, "row_tokens": 7.294239962108149e-05 }, "learning_rates_after_step": { "lora": 7.279108680313211e-05, "row_tokens": 7.279108680313211e-05 } }, { "update_id": 382, "row_count": 12, "row_ids_sha256": "c75248eb94ba3e82cc04f1d1131cff544fd6a1e98a89022b6c33afe02ee59473", "input_ids_vector_sha256": "cbc8e251531a871376ae47d2693469ccf3ab43aebd6251a31fc0821cbfac9077", "labels_vector_sha256": "5c23879d397f4212c8577daa61242acaf6e24829608dbc5b5fd50323fdecef16", "planned_active_tokens": 65810, "realized_active_tokens": 65810, "cumulative_start": 25036610, "cumulative_end": 25102420, "loss_sum": 20259.699188232422, "token_normalized_loss": 0.30785137803118706, "grad_norm_before_clip": 0.07742486149072647, "learning_rates_at_step": { "lora": 7.279108680313211e-05, "row_tokens": 7.279108680313211e-05 }, "learning_rates_after_step": { "lora": 7.264108452486302e-05, "row_tokens": 7.264108452486302e-05 } }, { "update_id": 383, "row_count": 14, "row_ids_sha256": "329904fb1a6b0d39fddcff1cfb31c1dc76a83ef3b66b2ff80e3f3dd597e9304e", "input_ids_vector_sha256": "d1efab7aa51f6334568af4e1daaf59484ad8e31dadbaa30e0d60c932e3db5d95", "labels_vector_sha256": "b23bded77ed4a8444d95af2bb7cf82855a7cbc97208986eed69a1a91bee20cb6", "planned_active_tokens": 65127, "realized_active_tokens": 65127, "cumulative_start": 25102420, "cumulative_end": 25167547, "loss_sum": 18782.943634033203, "token_normalized_loss": 0.2884048648645447, "grad_norm_before_clip": 0.07343890517950058, "learning_rates_at_step": { "lora": 7.264108452486302e-05, "row_tokens": 7.264108452486302e-05 }, "learning_rates_after_step": { "lora": 7.248901970956822e-05, "row_tokens": 7.248901970956822e-05 } }, { "update_id": 384, "row_count": 15, "row_ids_sha256": "be12a8c83620f988acff18aedc821209c3104ddedecfeb396a42999d6e50e72b", "input_ids_vector_sha256": "0e7116349aec5e7dd40d0403657d48c9ea92095f4f6fd2098aa3d04ab3116851", "labels_vector_sha256": "eac1ccc5ef3e05bb0c7a71075619e3843251bb680085a65a7ef958b8f973a26b", "planned_active_tokens": 65909, "realized_active_tokens": 65909, "cumulative_start": 25167547, "cumulative_end": 25233456, "loss_sum": 19394.61117553711, "token_normalized_loss": 0.29426347199224856, "grad_norm_before_clip": 0.07557607442140579, "learning_rates_at_step": { "lora": 7.248901970956822e-05, "row_tokens": 7.248901970956822e-05 }, "learning_rates_after_step": { "lora": 7.233968681960366e-05, "row_tokens": 7.233968681960366e-05 } }, { "update_id": 385, "row_count": 15, "row_ids_sha256": "674097316bd4968cd9cacabfceee54e629dd439ebc6e33a72888cf817c9cb1f6", "input_ids_vector_sha256": "66776620539a3d32914fcaf13fcab4ae5237f0187aa58151b51ba887679b7667", "labels_vector_sha256": "558f7ab419ef9928da0c11b3eafa82146a0662e4cc3770c09775eb831728085d", "planned_active_tokens": 64615, "realized_active_tokens": 64615, "cumulative_start": 25233456, "cumulative_end": 25298071, "loss_sum": 19000.544021606445, "token_normalized_loss": 0.29405778877360433, "grad_norm_before_clip": 0.07612800598144531, "learning_rates_at_step": { "lora": 7.233968681960366e-05, "row_tokens": 7.233968681960366e-05 }, "learning_rates_after_step": { "lora": 7.218572085996681e-05, "row_tokens": 7.218572085996681e-05 } }, { "update_id": 386, "row_count": 18, "row_ids_sha256": "50c2b6a22158e71f7a481a5854654529193aeb8365b5959f82b5db8d3d6c5896", "input_ids_vector_sha256": "f331e2dd41763e231b00ed5716c8ab90d6222fa5d2935b8e9c71662d2ab0ef0c", "labels_vector_sha256": "cfafba35e2d84e82ffd9b2d1914fbb5f3d65f24bf035ad4d3069f1838bd68616", "planned_active_tokens": 66507, "realized_active_tokens": 66507, "cumulative_start": 25298071, "cumulative_end": 25364578, "loss_sum": 18552.51072692871, "token_normalized_loss": 0.27895575994900856, "grad_norm_before_clip": 0.0789385735988617, "learning_rates_at_step": { "lora": 7.218572085996681e-05, "row_tokens": 7.218572085996681e-05 }, "learning_rates_after_step": { "lora": 7.203713687010225e-05, "row_tokens": 7.203713687010225e-05 } }, { "update_id": 387, "row_count": 16, "row_ids_sha256": "9765387e6180cca8e2d644151a28afdf661cdcdd67fda5faf2b0873e959e338c", "input_ids_vector_sha256": "0c703809eb1bdf0d39b6a8263bcd396ad0898304c05ccce0ba030f29fe43a2fe", "labels_vector_sha256": "1cfe76635738e3c0c3602c97ff1773f694e6039a2442dba099ab0299af3436ce", "planned_active_tokens": 64075, "realized_active_tokens": 64075, "cumulative_start": 25364578, "cumulative_end": 25428653, "loss_sum": 18755.96759033203, "token_normalized_loss": 0.292718963563512, "grad_norm_before_clip": 0.0730370283126831, "learning_rates_at_step": { "lora": 7.203713687010225e-05, "row_tokens": 7.203713687010225e-05 }, "learning_rates_after_step": { "lora": 7.188174151524218e-05, "row_tokens": 7.188174151524218e-05 } }, { "update_id": 388, "row_count": 17, "row_ids_sha256": "9de48aa3e63bf1278ff79458483910908caa6286f7858f3cbf1cf7dd81be9c2c", "input_ids_vector_sha256": "dc420dfb8d8a4af3d0508a840b82922be82a2080a9fc3d9b89763b9e6773a231", "labels_vector_sha256": "38fd86ec4576d31b115e9fca0d43139ed51acb62604cced338ea82f99d7292c6", "planned_active_tokens": 66901, "realized_active_tokens": 66901, "cumulative_start": 25428653, "cumulative_end": 25495554, "loss_sum": 19061.982666015625, "token_normalized_loss": 0.2849282173064024, "grad_norm_before_clip": 0.07228204607963562, "learning_rates_at_step": { "lora": 7.188174151524218e-05, "row_tokens": 7.188174151524218e-05 }, "learning_rates_after_step": { "lora": 7.17335658732239e-05, "row_tokens": 7.17335658732239e-05 } }, { "update_id": 389, "row_count": 14, "row_ids_sha256": "f7f17562768f643e020d6679cb51c716b4f8393e0d77797fdf0203e239b76fd4", "input_ids_vector_sha256": "9f4c3f49574b6162643e872283281eb8b04b90bbde91ddb55f162985dd22a16e", "labels_vector_sha256": "4c0d047b1517364952ee5b1ac96e5895a9372d4c28331a3f57130ab8cde7f7de", "planned_active_tokens": 63688, "realized_active_tokens": 63688, "cumulative_start": 25495554, "cumulative_end": 25559242, "loss_sum": 19804.50112915039, "token_normalized_loss": 0.31096126631626664, "grad_norm_before_clip": 0.08240894973278046, "learning_rates_at_step": { "lora": 7.17335658732239e-05, "row_tokens": 7.17335658732239e-05 }, "learning_rates_after_step": { "lora": 7.157985810321698e-05, "row_tokens": 7.157985810321698e-05 } }, { "update_id": 390, "row_count": 13, "row_ids_sha256": "41e0a73c69e836a37e57731875f1055f0ddd47bba073e4f79378d0e6d50c96fa", "input_ids_vector_sha256": "8ad6d08093e01d3f0efac41368477f4ff300ee7d5390f120716211c60c6e79c7", "labels_vector_sha256": "1883e2bbe55cd4ffccdccc6e2a578596641f0850c80403d2c2725a510c5009da", "planned_active_tokens": 65959, "realized_active_tokens": 65959, "cumulative_start": 25559242, "cumulative_end": 25625201, "loss_sum": 20930.174682617188, "token_normalized_loss": 0.3173209824681573, "grad_norm_before_clip": 0.07578996568918228, "learning_rates_at_step": { "lora": 7.157985810321698e-05, "row_tokens": 7.157985810321698e-05 }, "learning_rates_after_step": { "lora": 7.142278061679964e-05, "row_tokens": 7.142278061679964e-05 } }, { "update_id": 391, "row_count": 12, "row_ids_sha256": "a0b0e9063bbaa855cd3bedbe85f3e7a54ede0d3d85cb6c4a5cdc3e7f992c804f", "input_ids_vector_sha256": "2693b1db7101866ae78492f3b11f0fe14d0ee68fd06552d8e76bdb5aa5b61d92", "labels_vector_sha256": "c6509ddfcbd7e8a1ec758dcfcc9552087972007240a18d1ce6de7f24119346b8", "planned_active_tokens": 67294, "realized_active_tokens": 67294, "cumulative_start": 25625201, "cumulative_end": 25692495, "loss_sum": 27195.493072509766, "token_normalized_loss": 0.40412953714312966, "grad_norm_before_clip": 0.08360560238361359, "learning_rates_at_step": { "lora": 7.142278061679964e-05, "row_tokens": 7.142278061679964e-05 }, "learning_rates_after_step": { "lora": 7.125789235371173e-05, "row_tokens": 7.125789235371173e-05 } }, { "update_id": 392, "row_count": 14, "row_ids_sha256": "3313cc203ebc5033dc554a0f3b834fdbfca29efd9ce4c2940825204d44d9e0df", "input_ids_vector_sha256": "c2294a422cfeebc7c2352d546e3848fdb4544b1aa4faf91a93d5c8be952eab50", "labels_vector_sha256": "cd46525c72415ed9bec71ddb505482197a11ca0c344b952a04f75d00c161536b", "planned_active_tokens": 70521, "realized_active_tokens": 70521, "cumulative_start": 25692495, "cumulative_end": 25763016, "loss_sum": 24413.424224853516, "token_normalized_loss": 0.34618658590850265, "grad_norm_before_clip": 0.07375374436378479, "learning_rates_at_step": { "lora": 7.125789235371173e-05, "row_tokens": 7.125789235371173e-05 }, "learning_rates_after_step": { "lora": 7.112111426117291e-05, "row_tokens": 7.112111426117291e-05 } }, { "update_id": 393, "row_count": 15, "row_ids_sha256": "1456cc9d279a4e3ea27f2b213ff7d803f1b205ab27ffbf094d11a029a0871117", "input_ids_vector_sha256": "d5500e699851cd7ad8db3c56925dacfa92636de16b3e8ecc8daf3e481011fed0", "labels_vector_sha256": "6454c08d34cf3067d91f3b56f0389efc56c9f0c49dd0aea760ce0aa648ee2052", "planned_active_tokens": 58407, "realized_active_tokens": 58407, "cumulative_start": 25763016, "cumulative_end": 25821423, "loss_sum": 20176.78546142578, "token_normalized_loss": 0.3454514948794799, "grad_norm_before_clip": 0.08221946656703949, "learning_rates_at_step": { "lora": 7.112111426117291e-05, "row_tokens": 7.112111426117291e-05 }, "learning_rates_after_step": { "lora": 7.095190090833253e-05, "row_tokens": 7.095190090833253e-05 } }, { "update_id": 394, "row_count": 15, "row_ids_sha256": "93420e6f20700a6b613db4f18ecb2883269aece31972daeeef758b09a521c5e3", "input_ids_vector_sha256": "ec4600d1bcb17a7931858e193acc833fe4b10a9528b1cb37e64f9408aae79d7c", "labels_vector_sha256": "ec02e897c58c424714add0972b4dea06ad757153e501342d7fdc7db749717e3a", "planned_active_tokens": 72144, "realized_active_tokens": 72144, "cumulative_start": 25821423, "cumulative_end": 25893567, "loss_sum": 26321.538543701172, "token_normalized_loss": 0.3648472297585547, "grad_norm_before_clip": 0.07762578129768372, "learning_rates_at_step": { "lora": 7.095190090833253e-05, "row_tokens": 7.095190090833253e-05 }, "learning_rates_after_step": { "lora": 7.080896489491016e-05, "row_tokens": 7.080896489491016e-05 } }, { "update_id": 395, "row_count": 13, "row_ids_sha256": "a3198af343a674fe5fb6cbddbf68e6d25dc41aa3e7637e5d6f8fa5b4cde2a06d", "input_ids_vector_sha256": "a8875872ac3165f628dc3b4100916946c40d608b2ce24d7ad363dedc82edca4c", "labels_vector_sha256": "a5ffe57d8bc4c15c5e89ad585130c9f30e37c489bc4448fef78e292316f72a93", "planned_active_tokens": 60844, "realized_active_tokens": 60844, "cumulative_start": 25893567, "cumulative_end": 25954411, "loss_sum": 19754.182098388672, "token_normalized_loss": 0.324669352744538, "grad_norm_before_clip": 0.07741805166006088, "learning_rates_at_step": { "lora": 7.080896489491016e-05, "row_tokens": 7.080896489491016e-05 }, "learning_rates_after_step": { "lora": 7.065607330793718e-05, "row_tokens": 7.065607330793718e-05 } }, { "update_id": 396, "row_count": 14, "row_ids_sha256": "68e88b401d2e175d9f39898ed8c4a2e79d76b885b0b35ae2484ef9290450f24e", "input_ids_vector_sha256": "c23b39e22606cc4453a10321c91fc1e5576c7dca3a48a2e2213ed3ec26570edc", "labels_vector_sha256": "53e88f86df355918ee96f4f42c4d93c8d6f3211cb0d9454505059b02212ea86b", "planned_active_tokens": 64985, "realized_active_tokens": 64985, "cumulative_start": 25954411, "cumulative_end": 26019396, "loss_sum": 20541.796356201172, "token_normalized_loss": 0.3161005825375267, "grad_norm_before_clip": 0.07508455961942673, "learning_rates_at_step": { "lora": 7.065607330793718e-05, "row_tokens": 7.065607330793718e-05 }, "learning_rates_after_step": { "lora": 7.049372318534186e-05, "row_tokens": 7.049372318534186e-05 } }, { "update_id": 397, "row_count": 15, "row_ids_sha256": "9daf0250fc998835705c3aec50388fb16d7f862060f84494473b947eed5914a5", "input_ids_vector_sha256": "aa1b280bc6b9a8fbced901258581833f134ec5746930c55e17c26fd4851bde60", "labels_vector_sha256": "df652a6c5c56ebeb8fc1e4b25e5f66cd9809b87d65c3e52f25ce07b09042b44b", "planned_active_tokens": 68897, "realized_active_tokens": 68897, "cumulative_start": 26019396, "cumulative_end": 26088293, "loss_sum": 20413.055633544922, "token_normalized_loss": 0.29628366450708915, "grad_norm_before_clip": 0.07106852531433105, "learning_rates_at_step": { "lora": 7.049372318534186e-05, "row_tokens": 7.049372318534186e-05 }, "learning_rates_after_step": { "lora": 7.034856008640778e-05, "row_tokens": 7.034856008640778e-05 } }, { "update_id": 398, "row_count": 14, "row_ids_sha256": "11ddc2f64b80656598b90e6ed4022432c827123a620d8744107c558118fc5b69", "input_ids_vector_sha256": "a75183f1e4df01bd8c6c3f5d40ade85e3a8c5039e04d98f0263e6198a09dbaeb", "labels_vector_sha256": "fe93a3f99f5df41f1069001b2306c38c962675fea2338027963f7da2cef933df", "planned_active_tokens": 61510, "realized_active_tokens": 61510, "cumulative_start": 26088293, "cumulative_end": 26149803, "loss_sum": 18746.17352294922, "token_normalized_loss": 0.3047662741497191, "grad_norm_before_clip": 0.07513578981161118, "learning_rates_at_step": { "lora": 7.034856008640778e-05, "row_tokens": 7.034856008640778e-05 }, "learning_rates_after_step": { "lora": 7.018816044171035e-05, "row_tokens": 7.018816044171035e-05 } }, { "update_id": 399, "row_count": 13, "row_ids_sha256": "864e4f64173de280f397fc927ab104e119c1a236a3f14c49e68809cf6da91ff8", "input_ids_vector_sha256": "345a44fa559d3b4f8e254381397acd4b46870d8e95c7672e322fab1b0f9ad691", "labels_vector_sha256": "406bb2f98599175c085c8eb8d847db3c7c2e4ea2ed1ba0f74a632e8ee399b460", "planned_active_tokens": 67865, "realized_active_tokens": 67865, "cumulative_start": 26149803, "cumulative_end": 26217668, "loss_sum": 21672.55258178711, "token_normalized_loss": 0.3193480082780094, "grad_norm_before_clip": 0.07206572592258453, "learning_rates_at_step": { "lora": 7.018816044171035e-05, "row_tokens": 7.018816044171035e-05 }, "learning_rates_after_step": { "lora": 7.002266036739064e-05, "row_tokens": 7.002266036739064e-05 } }, { "update_id": 400, "row_count": 11, "row_ids_sha256": "76cdcc721a425f447acc3ca56eaa95a0b10e6e055bf408d5f9f952b177cc0cef", "input_ids_vector_sha256": "852716df1e4bb06a9143b130639ef5805e82d0f3caa6d94f7bbacf6ba80f5456", "labels_vector_sha256": "482794659a88d3b1aa340dba0dbeb22e3f28f496f050b1307ac67619c52f11bd", "planned_active_tokens": 69913, "realized_active_tokens": 69913, "cumulative_start": 26217668, "cumulative_end": 26287581, "loss_sum": 22955.737670898438, "token_normalized_loss": 0.32834719824493924, "grad_norm_before_clip": 0.07001377642154694, "learning_rates_at_step": { "lora": 7.002266036739064e-05, "row_tokens": 7.002266036739064e-05 }, "learning_rates_after_step": { "lora": 6.987385826453401e-05, "row_tokens": 6.987385826453401e-05 } }, { "update_id": 401, "row_count": 7, "row_ids_sha256": "de48416445da06f9b01fa2455e721f9c5cdddfd5119dc8ba04d51fe19b23285f", "input_ids_vector_sha256": "7c4576ae2f5387d75638a70cbe23d33e2536f171f9e138bbbf377c5d33e9f0e5", "labels_vector_sha256": "b1fa1378da34186ad582c2646f22a7568a21580f726e0b838f1d86ce6f7a3de3", "planned_active_tokens": 62765, "realized_active_tokens": 62765, "cumulative_start": 26287581, "cumulative_end": 26350346, "loss_sum": 18768.050415039062, "token_normalized_loss": 0.29902095777963933, "grad_norm_before_clip": 0.07593585550785065, "learning_rates_at_step": { "lora": 6.987385826453401e-05, "row_tokens": 6.987385826453401e-05 }, "learning_rates_after_step": { "lora": 6.972874539849264e-05, "row_tokens": 6.972874539849264e-05 } }, { "update_id": 402, "row_count": 14, "row_ids_sha256": "4b62dfbcc12176e4a21724e2300b4ff627d1bd91f8d73929ab422a59d2a63911", "input_ids_vector_sha256": "b805f0b21aa21b93cf47959a94b828330ad3b21689e91c7e226ad44291edcc16", "labels_vector_sha256": "85836a4c0641c0551985861c3f28130a59274088ac1962c18c51fc039b26af76", "planned_active_tokens": 61124, "realized_active_tokens": 61124, "cumulative_start": 26350346, "cumulative_end": 26411470, "loss_sum": 20410.579513549805, "token_normalized_loss": 0.3339208741828055, "grad_norm_before_clip": 0.07687288522720337, "learning_rates_at_step": { "lora": 6.972874539849264e-05, "row_tokens": 6.972874539849264e-05 }, "learning_rates_after_step": { "lora": 6.956979871758981e-05, "row_tokens": 6.956979871758981e-05 } }, { "update_id": 403, "row_count": 8, "row_ids_sha256": "fe98d063382b3a3e0190f80bd375b704953f305a33188ac94eb2531f8b432d31", "input_ids_vector_sha256": "e7d8319e16c6bc92a24e2d0629988e48155dd4252aaf4aa3f3788a04c6235a72", "labels_vector_sha256": "7a6a0f1c408652cd4160353127eee5a7577804ab9a0067a72b4f57bb50f5a404", "planned_active_tokens": 66856, "realized_active_tokens": 66856, "cumulative_start": 26411470, "cumulative_end": 26478326, "loss_sum": 22511.154174804688, "token_normalized_loss": 0.33671105323089456, "grad_norm_before_clip": 0.07999046891927719, "learning_rates_at_step": { "lora": 6.956979871758981e-05, "row_tokens": 6.956979871758981e-05 }, "learning_rates_after_step": { "lora": 6.941229316654869e-05, "row_tokens": 6.941229316654869e-05 } }, { "update_id": 404, "row_count": 12, "row_ids_sha256": "95d299fe9cc274af3661b38274c233e7b8c0d970514f40a342971f19c6fe5b3b", "input_ids_vector_sha256": "ae1a664519438dbdffbf401254cd4d9969fc6da65a585e973ae184e22f292029", "labels_vector_sha256": "76ddd620fa291b97def7a2130476e84b12e716621dcc029c216227fb40b415e6", "planned_active_tokens": 66153, "realized_active_tokens": 66153, "cumulative_start": 26478326, "cumulative_end": 26544479, "loss_sum": 22592.781616210938, "token_normalized_loss": 0.3415231601924469, "grad_norm_before_clip": 0.07295792549848557, "learning_rates_at_step": { "lora": 6.941229316654869e-05, "row_tokens": 6.941229316654869e-05 }, "learning_rates_after_step": { "lora": 6.924223811594229e-05, "row_tokens": 6.924223811594229e-05 } }, { "update_id": 405, "row_count": 10, "row_ids_sha256": "cd7a723b71b439b54d15988b0584475258a4c25388905e43fda9a2caf23f6547", "input_ids_vector_sha256": "8dff4929cc8d5d6bf5f5bc54515d234c2efca894209e58a939ef451f67db0719", "labels_vector_sha256": "fbed2cf5cafeb1f7ae5d6075ac75cc40e3c31cd5d63bb03d0595c28f69ea02e4", "planned_active_tokens": 71317, "realized_active_tokens": 71317, "cumulative_start": 26544479, "cumulative_end": 26615796, "loss_sum": 24375.476959228516, "token_normalized_loss": 0.34179055427497673, "grad_norm_before_clip": 0.07022076845169067, "learning_rates_at_step": { "lora": 6.924223811594229e-05, "row_tokens": 6.924223811594229e-05 }, "learning_rates_after_step": { "lora": 6.909365143652985e-05, "row_tokens": 6.909365143652985e-05 } }, { "update_id": 406, "row_count": 7, "row_ids_sha256": "9558f508281721b13d4137b3c4be7f7e2e06172764e12ec813d4b861132387d7", "input_ids_vector_sha256": "75bed6b8679d3c822338a072b557229d171aa8d585af382ea7eae985e6ed61e0", "labels_vector_sha256": "2e2da76f443c1dbce792b544e2c509dbe5a6ef0bc3bfd98cb481add5af8a4db3", "planned_active_tokens": 62224, "realized_active_tokens": 62224, "cumulative_start": 26615796, "cumulative_end": 26678020, "loss_sum": 24150.899963378906, "token_normalized_loss": 0.3881283743150377, "grad_norm_before_clip": 0.0848962590098381, "learning_rates_at_step": { "lora": 6.909365143652985e-05, "row_tokens": 6.909365143652985e-05 }, "learning_rates_after_step": { "lora": 6.8931038892145e-05, "row_tokens": 6.8931038892145e-05 } }, { "update_id": 407, "row_count": 9, "row_ids_sha256": "8130fed70934793feea1fe37f547dffabed426b1ffb3ff56e7a1df5aaa5c9936", "input_ids_vector_sha256": "e808f7ec7557d3c68d905dc7af2dd1332dc9bad64aa7f88b42589b380bf4ef8c", "labels_vector_sha256": "84bab45a080b667fb230e953f2dc571659da14caa63d4a91e3beff5815f05c1d", "planned_active_tokens": 68003, "realized_active_tokens": 68003, "cumulative_start": 26678020, "cumulative_end": 26746023, "loss_sum": 25605.100830078125, "token_normalized_loss": 0.37652898886928704, "grad_norm_before_clip": 0.07714151591062546, "learning_rates_at_step": { "lora": 6.8931038892145e-05, "row_tokens": 6.8931038892145e-05 }, "learning_rates_after_step": { "lora": 6.87700854135513e-05, "row_tokens": 6.87700854135513e-05 } }, { "update_id": 408, "row_count": 12, "row_ids_sha256": "bb9e5013a9868e1518a6eda1d999f6f0159de044fad9e7ac8ec1016794de5f59", "input_ids_vector_sha256": "d6d0c096367ac4de4a834e02151955520290a007075b159aa91a82d6ffe633eb", "labels_vector_sha256": "48d57ed93e0299cd8cfe7433ed7b6201ea0d02412346b3d618a540726069a87e", "planned_active_tokens": 67213, "realized_active_tokens": 67213, "cumulative_start": 26746023, "cumulative_end": 26813236, "loss_sum": 23936.048767089844, "token_normalized_loss": 0.3561223091825963, "grad_norm_before_clip": 0.07639163732528687, "learning_rates_at_step": { "lora": 6.87700854135513e-05, "row_tokens": 6.87700854135513e-05 }, "learning_rates_after_step": { "lora": 6.862963939695591e-05, "row_tokens": 6.862963939695591e-05 } }, { "update_id": 409, "row_count": 8, "row_ids_sha256": "a8feb9090645c9995323841a2dbc689e299cb0ea46ebb413c3a0c63e8c97fa53", "input_ids_vector_sha256": "d036178e064066e9c2d1dc56e89db954de164d38b5f5759f4d1643d9eed0dbbb", "labels_vector_sha256": "3ff65c789dfc9c2b50d1d20a23dd3b78ef4f313c6d2aa1743d00fef52d92def7", "planned_active_tokens": 58572, "realized_active_tokens": 58572, "cumulative_start": 26813236, "cumulative_end": 26871808, "loss_sum": 19818.708862304688, "token_normalized_loss": 0.33836489896716326, "grad_norm_before_clip": 0.08082553744316101, "learning_rates_at_step": { "lora": 6.862963939695591e-05, "row_tokens": 6.862963939695591e-05 }, "learning_rates_after_step": { "lora": 6.846357556608347e-05, "row_tokens": 6.846357556608347e-05 } }, { "update_id": 410, "row_count": 11, "row_ids_sha256": "1f04de428bb2f65e18d24ce09731da165b9df54ffb43b173f5190c96fb36bfef", "input_ids_vector_sha256": "23db3e9c827c09b83f015ceb35a829af130d5d8c80ec32f05fe8172c3b3b7dbb", "labels_vector_sha256": "add86cadce2cd1e019d0df73c9e4ea8da3c22d176e58712061b93e1b9395f41d", "planned_active_tokens": 69164, "realized_active_tokens": 69164, "cumulative_start": 26871808, "cumulative_end": 26940972, "loss_sum": 24567.269409179688, "token_normalized_loss": 0.3552031318197283, "grad_norm_before_clip": 0.07660488039255142, "learning_rates_at_step": { "lora": 6.846357556608347e-05, "row_tokens": 6.846357556608347e-05 }, "learning_rates_after_step": { "lora": 6.831726639147568e-05, "row_tokens": 6.831726639147568e-05 } }, { "update_id": 411, "row_count": 7, "row_ids_sha256": "20a0c2466e00923ddada990c71ae094e8cbd2d51679e4d298c92c09d31e9e066", "input_ids_vector_sha256": "e2f1a6d000ecba2548a8aca0e081acfe34545c3a570d826f8db20edb3cf69b7e", "labels_vector_sha256": "5fd1cf4d0352596900b74c18dae90dcaf60dfb643ac7e0e59acfc38fee55321c", "planned_active_tokens": 60855, "realized_active_tokens": 60855, "cumulative_start": 26940972, "cumulative_end": 27001827, "loss_sum": 24416.083740234375, "token_normalized_loss": 0.4012173813200949, "grad_norm_before_clip": 0.08455216884613037, "learning_rates_at_step": { "lora": 6.831726639147568e-05, "row_tokens": 6.831726639147568e-05 }, "learning_rates_after_step": { "lora": 6.815087118239543e-05, "row_tokens": 6.815087118239543e-05 } }, { "update_id": 412, "row_count": 14, "row_ids_sha256": "ce25d3281266d9e2ce1fd3a0755613eb48bd7effeab8ec7535a0934a4fe6a2b7", "input_ids_vector_sha256": "8fa45b0c5838e301f16173a5f1fcf0b85ac49ea77625fc324c4369f66bd077e2", "labels_vector_sha256": "589362a9d912db92870d9109988767dea379ed198696c0e9c13c1f9bac97ad25", "planned_active_tokens": 69118, "realized_active_tokens": 69118, "cumulative_start": 27001827, "cumulative_end": 27070945, "loss_sum": 22151.98663330078, "token_normalized_loss": 0.32049519131486415, "grad_norm_before_clip": 0.07203658670186996, "learning_rates_at_step": { "lora": 6.815087118239543e-05, "row_tokens": 6.815087118239543e-05 }, "learning_rates_after_step": { "lora": 6.798703767910221e-05, "row_tokens": 6.798703767910221e-05 } }, { "update_id": 413, "row_count": 10, "row_ids_sha256": "873e451b31617534747a6d105ce92cfd60538ed4d23e2e0c9669ec8cb8dbc4a8", "input_ids_vector_sha256": "a97668f25ffff25453151f9bd7f5a3d41d10b46662feea0c9e5878a11092056a", "labels_vector_sha256": "b937f8782620355fe86bb54421f5fa3e232351ede9e5ab778933e6c4825177ae", "planned_active_tokens": 67960, "realized_active_tokens": 67960, "cumulative_start": 27070945, "cumulative_end": 27138905, "loss_sum": 20808.685302734375, "token_normalized_loss": 0.3061901898577748, "grad_norm_before_clip": 0.06941313296556473, "learning_rates_at_step": { "lora": 6.798703767910221e-05, "row_tokens": 6.798703767910221e-05 }, "learning_rates_after_step": { "lora": 6.781497398217344e-05, "row_tokens": 6.781497398217344e-05 } }, { "update_id": 414, "row_count": 8, "row_ids_sha256": "5ff5b305b6c3be65c8b4185dea2605dfc5e7fddb15ee11459e4767a1c20adfff", "input_ids_vector_sha256": "60217b2b7d5f9ffae7dba479cc1a623d45900e95529e15348995cd69a6060bad", "labels_vector_sha256": "984ef8194423eca75d856524f0875bbeb4cf77959ba02f2c143092389638c63e", "planned_active_tokens": 71275, "realized_active_tokens": 71275, "cumulative_start": 27138905, "cumulative_end": 27210180, "loss_sum": 29230.01220703125, "token_normalized_loss": 0.4101018899618555, "grad_norm_before_clip": 0.07790534943342209, "learning_rates_at_step": { "lora": 6.781497398217344e-05, "row_tokens": 6.781497398217344e-05 }, "learning_rates_after_step": { "lora": 6.768611128187228e-05, "row_tokens": 6.768611128187228e-05 } }, { "update_id": 415, "row_count": 9, "row_ids_sha256": "ec17f5eb7be81f5b22f0e0a6ad30aa1a79ed877fe8c3737f9a724729b79b9b7b", "input_ids_vector_sha256": "4f41e99684287841f95d44b5d2e6edc033a6184cf6ee7a227207ea42c88a3f7c", "labels_vector_sha256": "b43729b58c0426beb7bae80578d81b6c2dea0e41f8842edd7b0d3f16680d7d07", "planned_active_tokens": 53314, "realized_active_tokens": 53314, "cumulative_start": 27210180, "cumulative_end": 27263494, "loss_sum": 19129.62826538086, "token_normalized_loss": 0.3588105988179626, "grad_norm_before_clip": 0.08770277351140976, "learning_rates_at_step": { "lora": 6.768611128187228e-05, "row_tokens": 6.768611128187228e-05 }, "learning_rates_after_step": { "lora": 6.752232203018544e-05, "row_tokens": 6.752232203018544e-05 } }, { "update_id": 416, "row_count": 9, "row_ids_sha256": "03964df55a1e7b60f78ec6d5496abf4246ee2d4feabd1b38b39ea4cb5c83ec46", "input_ids_vector_sha256": "7729a50480ebd093d623ea35ec26bc87abbb65c62df0d1c1a4cd7663479fcb4d", "labels_vector_sha256": "d86d2f3c1a04e0d65aad65c8487f5c9251b957ac292c143b553664f7199cd585", "planned_active_tokens": 67684, "realized_active_tokens": 67684, "cumulative_start": 27263494, "cumulative_end": 27331178, "loss_sum": 23960.91131591797, "token_normalized_loss": 0.3540114549364395, "grad_norm_before_clip": 0.07600689679384232, "learning_rates_at_step": { "lora": 6.752232203018544e-05, "row_tokens": 6.752232203018544e-05 }, "learning_rates_after_step": { "lora": 6.73582429791704e-05, "row_tokens": 6.73582429791704e-05 } }, { "update_id": 417, "row_count": 10, "row_ids_sha256": "1e5daf6e618b76187cd81c35c6c0e0f6fe0e572b809dd03eb551174012172c05", "input_ids_vector_sha256": "dcfd169ef50027f44aabe6fe1b50b19a815d627db7fbd41066f97954f7ef5e89", "labels_vector_sha256": "94e60959676531acacbea9a41da7ca3a6ecf89def599f67e15e4578be35762dd", "planned_active_tokens": 67715, "realized_active_tokens": 67715, "cumulative_start": 27331178, "cumulative_end": 27398893, "loss_sum": 22666.295532226562, "token_normalized_loss": 0.33473079129035754, "grad_norm_before_clip": 0.07357332110404968, "learning_rates_at_step": { "lora": 6.73582429791704e-05, "row_tokens": 6.73582429791704e-05 }, "learning_rates_after_step": { "lora": 6.719893040308954e-05, "row_tokens": 6.719893040308954e-05 } }, { "update_id": 418, "row_count": 15, "row_ids_sha256": "adb578e15877d49fd54b1cac089a56089bad506f480f847894cea9f0eac8223a", "input_ids_vector_sha256": "31cd445bb846b8200db776d33fd28aa78b3ac5d7255c04afd78543422d8dc683", "labels_vector_sha256": "5fcc7dae780dec45e55c429b495b4378cf29c2ca41d4fb890c088daea295f640", "planned_active_tokens": 65664, "realized_active_tokens": 65664, "cumulative_start": 27398893, "cumulative_end": 27464557, "loss_sum": 24045.35073852539, "token_normalized_loss": 0.366187724453664, "grad_norm_before_clip": 0.07736260443925858, "learning_rates_at_step": { "lora": 6.719893040308954e-05, "row_tokens": 6.719893040308954e-05 }, "learning_rates_after_step": { "lora": 6.703611131767285e-05, "row_tokens": 6.703611131767285e-05 } }, { "update_id": 419, "row_count": 12, "row_ids_sha256": "29b986897ddb0e0eb697a4ab0c2ece182a46507431a967b50ce8b1c813ff5c39", "input_ids_vector_sha256": "22ce7c835ed92bc0ced87296598162e025b228551bf78edbb1ecccd6c5e726ca", "labels_vector_sha256": "aa4b45d94e1d4e97d5eef84c05a964eccc2d9363018aae0999d4953b5b015240", "planned_active_tokens": 67025, "realized_active_tokens": 67025, "cumulative_start": 27464557, "cumulative_end": 27531582, "loss_sum": 24082.48696899414, "token_normalized_loss": 0.3593060345989428, "grad_norm_before_clip": 0.07843484729528427, "learning_rates_at_step": { "lora": 6.703611131767285e-05, "row_tokens": 6.703611131767285e-05 }, "learning_rates_after_step": { "lora": 6.687266411510765e-05, "row_tokens": 6.687266411510765e-05 } }, { "update_id": 420, "row_count": 11, "row_ids_sha256": "992a2b49cec86255ee28a2141ef6639661673ec5c92411b893f611ba22c20de4", "input_ids_vector_sha256": "dde21b8c8f63048cc8b11148ce7b4de7026bc14cccfabf11cdc345c0c3597b66", "labels_vector_sha256": "ab84afd8fa975525cc329290b0c24c0fe207b36a001070f720e000c6b6ab8da1", "planned_active_tokens": 67199, "realized_active_tokens": 67199, "cumulative_start": 27531582, "cumulative_end": 27598781, "loss_sum": 25194.79052734375, "token_normalized_loss": 0.3749280573720405, "grad_norm_before_clip": 0.07665132731199265, "learning_rates_at_step": { "lora": 6.687266411510765e-05, "row_tokens": 6.687266411510765e-05 }, "learning_rates_after_step": { "lora": 6.673203917730231e-05, "row_tokens": 6.673203917730231e-05 } }, { "update_id": 421, "row_count": 7, "row_ids_sha256": "2ed3671860b92ded6c9a2253e346de729c37e39fc6f321e626c9a1442c527fb2", "input_ids_vector_sha256": "246b234c7c78e4a7ede7e06731503477081bc532bb66e32629d866e4ba9397e9", "labels_vector_sha256": "ec23852f024adc90b653f83c2a654f242ddb893355a0cd2b0a55515c1ecfbed7", "planned_active_tokens": 57749, "realized_active_tokens": 57749, "cumulative_start": 27598781, "cumulative_end": 27656530, "loss_sum": 22391.088928222656, "token_normalized_loss": 0.3877311975657181, "grad_norm_before_clip": 0.08766704052686691, "learning_rates_at_step": { "lora": 6.673203917730231e-05, "row_tokens": 6.673203917730231e-05 }, "learning_rates_after_step": { "lora": 6.656053044295971e-05, "row_tokens": 6.656053044295971e-05 } }, { "update_id": 422, "row_count": 10, "row_ids_sha256": "da1b89ba1ac36bd20df139d2bd95302ae7b0697e5d8778af38712298efe1df71", "input_ids_vector_sha256": "4633267afff609f1534dedd57ec7b0199b196f23e94e77382dc854b7d0790f08", "labels_vector_sha256": "ad763c6bf71166441048c1ca0cdc36f2d51534d2598bfec9180c797b3365b7f7", "planned_active_tokens": 70349, "realized_active_tokens": 70349, "cumulative_start": 27656530, "cumulative_end": 27726879, "loss_sum": 24300.705932617188, "token_normalized_loss": 0.345430723004125, "grad_norm_before_clip": 0.07640378177165985, "learning_rates_at_step": { "lora": 6.656053044295971e-05, "row_tokens": 6.656053044295971e-05 }, "learning_rates_after_step": { "lora": 6.63807343148488e-05, "row_tokens": 6.63807343148488e-05 } }, { "update_id": 423, "row_count": 8, "row_ids_sha256": "a4436b2d71d2c236dbe1786be0c019f9dae12d6c9c53545e097c59a3af44f07f", "input_ids_vector_sha256": "a7b5163d6b5ab41f6496c77dc09bc9e02dfbfbd5870aca536e086b51d30dd6fd", "labels_vector_sha256": "6b1477a623fc83fc9aa348a825de8a9866e3a547b0564196d03faf7b573bb92c", "planned_active_tokens": 73652, "realized_active_tokens": 73652, "cumulative_start": 27726879, "cumulative_end": 27800531, "loss_sum": 24326.717529296875, "token_normalized_loss": 0.3302926944183033, "grad_norm_before_clip": 0.07538799196481705, "learning_rates_at_step": { "lora": 6.63807343148488e-05, "row_tokens": 6.63807343148488e-05 }, "learning_rates_after_step": { "lora": 6.622790704090778e-05, "row_tokens": 6.622790704090778e-05 } }, { "update_id": 424, "row_count": 9, "row_ids_sha256": "8c5a68dfa8ec8a7bab231e4c124cc8cf458010fb47e522fff56ef758fe656a2c", "input_ids_vector_sha256": "b2fbe2bbddad8ed1c0a775546196c24ad6e4798db90feef620e89a4d0bbcc88d", "labels_vector_sha256": "d3f3c5007006e0f60a0d31131521dbf7a36c94be38f7379380fa913f53bbcf77", "planned_active_tokens": 62528, "realized_active_tokens": 62528, "cumulative_start": 27800531, "cumulative_end": 27863059, "loss_sum": 24712.351989746094, "token_normalized_loss": 0.39522057301922486, "grad_norm_before_clip": 0.08446253091096878, "learning_rates_at_step": { "lora": 6.622790704090778e-05, "row_tokens": 6.622790704090778e-05 }, "learning_rates_after_step": { "lora": 6.608969647861752e-05, "row_tokens": 6.608969647861752e-05 } }, { "update_id": 425, "row_count": 6, "row_ids_sha256": "45e762937e4a38cac3216d57deb2f60eca2e5bb7f3e91ce8bdb5271e85f3a087", "input_ids_vector_sha256": "5fa53c63f81bb6e65deb5a22d44a298c02150c74bc544acf091f0bab17790a28", "labels_vector_sha256": "302a1ce5ec16247105edd8322011893b8f3845478e54c0b69ee1dfd2f4b4c768", "planned_active_tokens": 56488, "realized_active_tokens": 56488, "cumulative_start": 27863059, "cumulative_end": 27919547, "loss_sum": 19576.162872314453, "token_normalized_loss": 0.34655436326856065, "grad_norm_before_clip": 0.07974737137556076, "learning_rates_at_step": { "lora": 6.608969647861752e-05, "row_tokens": 6.608969647861752e-05 }, "learning_rates_after_step": { "lora": 6.591181874648836e-05, "row_tokens": 6.591181874648836e-05 } }, { "update_id": 426, "row_count": 10, "row_ids_sha256": "3d4a93960f7c477b3a0f1e2b31a37da2020149791fd749d2abb24e534ed00754", "input_ids_vector_sha256": "46de14dfde2a4d544512d70f22f139082f31d728ce944bc384c56d150d9ecd01", "labels_vector_sha256": "3c525cc720606dc8abdf61c3c2e101bc022b27fd05657fc83eb492afcc4a315b", "planned_active_tokens": 72618, "realized_active_tokens": 72618, "cumulative_start": 27919547, "cumulative_end": 27992165, "loss_sum": 29527.03482055664, "token_normalized_loss": 0.40660765678697625, "grad_norm_before_clip": 0.07658307999372482, "learning_rates_at_step": { "lora": 6.591181874648836e-05, "row_tokens": 6.591181874648836e-05 }, "learning_rates_after_step": { "lora": 6.577133585176433e-05, "row_tokens": 6.577133585176433e-05 } }, { "update_id": 427, "row_count": 9, "row_ids_sha256": "e489c7209b7ddec1bf0169d55481f4a89683d651e1fe6033f5a9901cc9b3545b", "input_ids_vector_sha256": "8e645192c1ed6d124e85e353af9f526b2f01e9b78b0716876d2be0e50eca9814", "labels_vector_sha256": "68ca097752771c983ea6690eb08bad5ca502ce22f18522ce129a06c0707959e8", "planned_active_tokens": 57287, "realized_active_tokens": 57287, "cumulative_start": 27992165, "cumulative_end": 28049452, "loss_sum": 20812.63885498047, "token_normalized_loss": 0.36330474374605876, "grad_norm_before_clip": 0.08694317936897278, "learning_rates_at_step": { "lora": 6.577133585176433e-05, "row_tokens": 6.577133585176433e-05 }, "learning_rates_after_step": { "lora": 6.560595470056667e-05, "row_tokens": 6.560595470056667e-05 } }, { "update_id": 428, "row_count": 8, "row_ids_sha256": "bc21ab3d1d316fc7acaadf4c098f4fd3331632c101f6099bf68fb4b859ca0af2", "input_ids_vector_sha256": "6dacd576b507c96d9677735812c1aecd98e7c845c7044221801dacf5a7c93c36", "labels_vector_sha256": "71af13344f68c91a0ce3a657482af3086b1adac0f68afffd48a284f357196737", "planned_active_tokens": 67368, "realized_active_tokens": 67368, "cumulative_start": 28049452, "cumulative_end": 28116820, "loss_sum": 25484.058837890625, "token_normalized_loss": 0.3782813626334554, "grad_norm_before_clip": 0.08358398824930191, "learning_rates_at_step": { "lora": 6.560595470056667e-05, "row_tokens": 6.560595470056667e-05 }, "learning_rates_after_step": { "lora": 6.543270666239876e-05, "row_tokens": 6.543270666239876e-05 } }, { "update_id": 429, "row_count": 9, "row_ids_sha256": "e24904e27b11b33510d616bc7402398bf1c7abd91df30cd81c222d126b33f6b0", "input_ids_vector_sha256": "ed0c7c8d5f413bcc9084deba5faf6dde34ca6d8d55d13d35da54f272e8774f81", "labels_vector_sha256": "72dbbb0ec861325652fb1b598460b580fa2cdd8281e1d8732b43812f7a580160", "planned_active_tokens": 70490, "realized_active_tokens": 70490, "cumulative_start": 28116820, "cumulative_end": 28187310, "loss_sum": 26582.912872314453, "token_normalized_loss": 0.3771160855768826, "grad_norm_before_clip": 0.07691210508346558, "learning_rates_at_step": { "lora": 6.543270666239876e-05, "row_tokens": 6.543270666239876e-05 }, "learning_rates_after_step": { "lora": 6.52803721486086e-05, "row_tokens": 6.52803721486086e-05 } }, { "update_id": 430, "row_count": 7, "row_ids_sha256": "c5be8ed902cc65ac6b490ff370df2bab2e418d7bcda3b547d698c1bcd2281148", "input_ids_vector_sha256": "802695f1f03d0eb37cc3bdcff0989bc45cb30c383002546d06b47634d1e0ac50", "labels_vector_sha256": "9ba290c6c0b51644dd8138cfb57629dacd2a07be116dd9403e1e9f60744b5b6f", "planned_active_tokens": 61912, "realized_active_tokens": 61912, "cumulative_start": 28187310, "cumulative_end": 28249222, "loss_sum": 21591.6708984375, "token_normalized_loss": 0.348747753237458, "grad_norm_before_clip": 0.08112620562314987, "learning_rates_at_step": { "lora": 6.52803721486086e-05, "row_tokens": 6.52803721486086e-05 }, "learning_rates_after_step": { "lora": 6.511253512824274e-05, "row_tokens": 6.511253512824274e-05 } }, { "update_id": 431, "row_count": 10, "row_ids_sha256": "56e62905a25a38d03f2693c3d24696bae3913aebeba24b8c2409f4e184feef19", "input_ids_vector_sha256": "531f1ef3f4ab940afcbd8f181e1b96bceb9242ad15b774bbc6817a58383a1310", "labels_vector_sha256": "505a8507871b43523a2254f3b7f3b2e8ea4fe49c59bfa2f716e8f6c911ddc4e5", "planned_active_tokens": 68139, "realized_active_tokens": 68139, "cumulative_start": 28249222, "cumulative_end": 28317361, "loss_sum": 25550.841064453125, "token_normalized_loss": 0.3749811571119788, "grad_norm_before_clip": 0.07739800959825516, "learning_rates_at_step": { "lora": 6.511253512824274e-05, "row_tokens": 6.511253512824274e-05 }, "learning_rates_after_step": { "lora": 6.496412407779913e-05, "row_tokens": 6.496412407779913e-05 } }, { "update_id": 432, "row_count": 8, "row_ids_sha256": "6841e393eb443852ff07332f015454feab901f5017c0ba684067e5a5f61ff468", "input_ids_vector_sha256": "2e65a319778725b79edcb17b8d4cf530f3514baad1f2cf6a5abefdabc8a1bfac", "labels_vector_sha256": "340c9029e97a69a4066cf30d21336547a34a6f33cbfadb474b9957986cd6e348", "planned_active_tokens": 60189, "realized_active_tokens": 60189, "cumulative_start": 28317361, "cumulative_end": 28377550, "loss_sum": 21760.043334960938, "token_normalized_loss": 0.36152857390820475, "grad_norm_before_clip": 0.08350375294685364, "learning_rates_at_step": { "lora": 6.496412407779913e-05, "row_tokens": 6.496412407779913e-05 }, "learning_rates_after_step": { "lora": 6.479332005150926e-05, "row_tokens": 6.479332005150926e-05 } }, { "update_id": 433, "row_count": 9, "row_ids_sha256": "8a1c175bc81e6eacffb0c77158b2b84a3ddeb0e89a4ba38e2a75da374aa910e2", "input_ids_vector_sha256": "da79b3247a049543be152d6bcc40e97b858eb1076c762ed42e74eecf6b779657", "labels_vector_sha256": "cfa0e4a3ab6a2fdf2e8d0316b30c269a865af511653d063f9e95ac5ee37c7856", "planned_active_tokens": 69198, "realized_active_tokens": 69198, "cumulative_start": 28377550, "cumulative_end": 28446748, "loss_sum": 27461.254150390625, "token_normalized_loss": 0.39685040247392445, "grad_norm_before_clip": 0.08015251159667969, "learning_rates_at_step": { "lora": 6.479332005150926e-05, "row_tokens": 6.479332005150926e-05 }, "learning_rates_after_step": { "lora": 6.463099225776491e-05, "row_tokens": 6.463099225776491e-05 } }, { "update_id": 434, "row_count": 9, "row_ids_sha256": "f92735510cdd31d869bfac7ba1c81ad65db8c8e0f1e6cabf598759a9e0634ba8", "input_ids_vector_sha256": "0027ce0dd08666db2a25c6fdde00cddccbd93e210540200a565a5a47804f0972", "labels_vector_sha256": "279e5165b882dfec08fc26ed83f36df140141175d04391554fc5607400b26f6e", "planned_active_tokens": 65693, "realized_active_tokens": 65693, "cumulative_start": 28446748, "cumulative_end": 28512441, "loss_sum": 23396.292724609375, "token_normalized_loss": 0.35614590176440986, "grad_norm_before_clip": 0.07859253138303757, "learning_rates_at_step": { "lora": 6.463099225776491e-05, "row_tokens": 6.463099225776491e-05 }, "learning_rates_after_step": { "lora": 6.447736277859223e-05, "row_tokens": 6.447736277859223e-05 } }, { "update_id": 435, "row_count": 8, "row_ids_sha256": "caa991e6cc3f1c454e5c0abaaddcfe0f2414ab5dc42a84df1c4928ae0ff29358", "input_ids_vector_sha256": "99e6ce487583275df259a44ac5cf1f1cb215cdd80c33f11249dfc01216e44aae", "labels_vector_sha256": "d305db01cdef92cd8accae179b3a61d17a9fa416b5d7ba08e27bc251efade2b1", "planned_active_tokens": 62110, "realized_active_tokens": 62110, "cumulative_start": 28512441, "cumulative_end": 28574551, "loss_sum": 21769.197204589844, "token_normalized_loss": 0.350494239326837, "grad_norm_before_clip": 0.07773597538471222, "learning_rates_at_step": { "lora": 6.447736277859223e-05, "row_tokens": 6.447736277859223e-05 }, "learning_rates_after_step": { "lora": 6.431123760539765e-05, "row_tokens": 6.431123760539765e-05 } }, { "update_id": 436, "row_count": 11, "row_ids_sha256": "2bff9f4a16ff47043f97acad2a650404e0e1f868f05345639e667ef4bffe2c5c", "input_ids_vector_sha256": "b097a3aba92087a9d16bdf56d12e52404ce007f6558ad45e30003c5368e24127", "labels_vector_sha256": "8b282c6b7dc095fe9ec5e895eb75f01e376ad98d8a424381e070bd0acdb773d5", "planned_active_tokens": 67094, "realized_active_tokens": 67094, "cumulative_start": 28574551, "cumulative_end": 28641645, "loss_sum": 21458.135803222656, "token_normalized_loss": 0.3198219781682812, "grad_norm_before_clip": 0.07335489243268967, "learning_rates_at_step": { "lora": 6.431123760539765e-05, "row_tokens": 6.431123760539765e-05 }, "learning_rates_after_step": { "lora": 6.415444763109053e-05, "row_tokens": 6.415444763109053e-05 } }, { "update_id": 437, "row_count": 10, "row_ids_sha256": "f0afa690ac9850551156801b80c0ab33d7681341552caa280c3c88781e2e42f7", "input_ids_vector_sha256": "e8f263adcd1b494184616397c28f26a2c71c56553a90aa02afe4068df96c134c", "labels_vector_sha256": "c360562953de7602150756782f405ac6e6d616c25bf48728b3552286d16bdbdb", "planned_active_tokens": 63260, "realized_active_tokens": 63260, "cumulative_start": 28641645, "cumulative_end": 28704905, "loss_sum": 23124.53646850586, "token_normalized_loss": 0.3655475255849804, "grad_norm_before_clip": 0.08313468843698502, "learning_rates_at_step": { "lora": 6.415444763109053e-05, "row_tokens": 6.415444763109053e-05 }, "learning_rates_after_step": { "lora": 6.397554077913108e-05, "row_tokens": 6.397554077913108e-05 } }, { "update_id": 438, "row_count": 9, "row_ids_sha256": "eb79ee43891b3ac7e2c2d97d245e45ca406ede3b17f87bef36d00d07cfa066bf", "input_ids_vector_sha256": "f5d267c7deec8800d0173254a884ae844ff4f765cc05350457928747108e6218", "labels_vector_sha256": "2f478fe736bde1ac3836bea716f2e968fff2f11312d7ef77f3bdd3bdd53d8433", "planned_active_tokens": 72109, "realized_active_tokens": 72109, "cumulative_start": 28704905, "cumulative_end": 28777014, "loss_sum": 27177.056884765625, "token_normalized_loss": 0.3768885560022414, "grad_norm_before_clip": 0.08321016281843185, "learning_rates_at_step": { "lora": 6.397554077913108e-05, "row_tokens": 6.397554077913108e-05 }, "learning_rates_after_step": { "lora": 6.3814072903865e-05, "row_tokens": 6.3814072903865e-05 } }, { "update_id": 439, "row_count": 7, "row_ids_sha256": "681fe06473d5d68fc5ec94e2874f636ee42905081bf57e764359bceed8fa9ff7", "input_ids_vector_sha256": "7e1d212b0dfe31a8802afc4853549b988d9cea668577597352269b2fb3ec66ff", "labels_vector_sha256": "d3b2a18f0f15d34d2a8edb3373fcacd45df4a7913e4119c81c282322d503b45e", "planned_active_tokens": 65013, "realized_active_tokens": 65013, "cumulative_start": 28777014, "cumulative_end": 28842027, "loss_sum": 24652.838012695312, "token_normalized_loss": 0.379198591246294, "grad_norm_before_clip": 0.08501264452934265, "learning_rates_at_step": { "lora": 6.3814072903865e-05, "row_tokens": 6.3814072903865e-05 }, "learning_rates_after_step": { "lora": 6.36476932826257e-05, "row_tokens": 6.36476932826257e-05 } }, { "update_id": 440, "row_count": 13, "row_ids_sha256": "560be087e597e6098b343a10f85b19c2617f665354a09ddf00414cddaa5f09ee", "input_ids_vector_sha256": "eda7db9f22724b887dda6f589deeecb40f500a2df1606dca6de7ca40dc383769", "labels_vector_sha256": "e213bb6f5d2b2a29258932f7594592ffc3e00619183531ddd96b26bc50bda0e7", "planned_active_tokens": 66925, "realized_active_tokens": 66925, "cumulative_start": 28842027, "cumulative_end": 28908952, "loss_sum": 21557.025146484375, "token_normalized_loss": 0.3221072117517277, "grad_norm_before_clip": 0.07094620913267136, "learning_rates_at_step": { "lora": 6.36476932826257e-05, "row_tokens": 6.36476932826257e-05 }, "learning_rates_after_step": { "lora": 6.350315041236123e-05, "row_tokens": 6.350315041236123e-05 } }, { "update_id": 441, "row_count": 7, "row_ids_sha256": "409baf10158b6db29726bce166758f1237cbfe16576382a883f8e0a5b40c6c2e", "input_ids_vector_sha256": "3022ff780d1c7a1ceec473cf7b3635d0717eacc8f23ff37af1e866d0770fd207", "labels_vector_sha256": "9d4f6c6537ca798d9a0160c585eb187bd4ba18f81377b5c262a850c279a95f6c", "planned_active_tokens": 58088, "realized_active_tokens": 58088, "cumulative_start": 28908952, "cumulative_end": 28967040, "loss_sum": 22508.174072265625, "token_normalized_loss": 0.38748405991367624, "grad_norm_before_clip": 0.08385802060365677, "learning_rates_at_step": { "lora": 6.350315041236123e-05, "row_tokens": 6.350315041236123e-05 }, "learning_rates_after_step": { "lora": 6.330434238503854e-05, "row_tokens": 6.330434238503854e-05 } }, { "update_id": 442, "row_count": 10, "row_ids_sha256": "edd0c03d4b1a4a20793e1b3f1f654ee34a9d70efdd6022824a4f7e7941d7c63f", "input_ids_vector_sha256": "5adfb8cb859828256b6ad47bef5d868006819c95fa3c34f0dcae9b33f8a66aae", "labels_vector_sha256": "81dd6218e77bfd441624c62b482cf339abf61fc78a4b8f2d184be2edc8921ba3", "planned_active_tokens": 79816, "realized_active_tokens": 79816, "cumulative_start": 28967040, "cumulative_end": 29046856, "loss_sum": 29745.512329101562, "token_normalized_loss": 0.37267605904958356, "grad_norm_before_clip": 0.07300790399312973, "learning_rates_at_step": { "lora": 6.330434238503854e-05, "row_tokens": 6.330434238503854e-05 }, "learning_rates_after_step": { "lora": 6.315416702960771e-05, "row_tokens": 6.315416702960771e-05 } }, { "update_id": 443, "row_count": 10, "row_ids_sha256": "e55e337d82c10fc8c5903b60854a252d8327ac211c27c9a87c1ff7abaddadfe1", "input_ids_vector_sha256": "a6aa1befe9f0bb7c826119a4b6bc367bb56597333bfdb748844c7061c36b3db3", "labels_vector_sha256": "920267c9aff5476965fde8aa30be82f745342c6d15027f147a8df6bc6f7efd83", "planned_active_tokens": 60231, "realized_active_tokens": 60231, "cumulative_start": 29046856, "cumulative_end": 29107087, "loss_sum": 21460.863815307617, "token_normalized_loss": 0.3563092728878421, "grad_norm_before_clip": 0.08047520369291306, "learning_rates_at_step": { "lora": 6.315416702960771e-05, "row_tokens": 6.315416702960771e-05 }, "learning_rates_after_step": { "lora": 6.300640548900583e-05, "row_tokens": 6.300640548900583e-05 } }, { "update_id": 444, "row_count": 11, "row_ids_sha256": "7a8ca982bb0991d75ac976fa74bf3f7b4387711efb1ab27399cfab8664ac599f", "input_ids_vector_sha256": "76f4d9e2ef832c465316ffb4c6360c533c66538bd2f14591dbba7d0a58777bb9", "labels_vector_sha256": "218665e16597b12a4cfac800eff8b616d091b290b4a0d5cc84e208a82d0de2d6", "planned_active_tokens": 59213, "realized_active_tokens": 59213, "cumulative_start": 29107087, "cumulative_end": 29166300, "loss_sum": 20243.910186767578, "token_normalized_loss": 0.3418828667145319, "grad_norm_before_clip": 0.07703737169504166, "learning_rates_at_step": { "lora": 6.300640548900583e-05, "row_tokens": 6.300640548900583e-05 }, "learning_rates_after_step": { "lora": 6.283804561047407e-05, "row_tokens": 6.283804561047407e-05 } }, { "update_id": 445, "row_count": 9, "row_ids_sha256": "6166190d7a6ece31e0dd0fe6c9c0a35f80ae8f1ed58e07e4dd6d7cfd49c41e72", "input_ids_vector_sha256": "9c2d7290c0df95dc0e9e03b335085fab69f5cf85f3c48387b784ea2abc023f4c", "labels_vector_sha256": "5d02d1d5e229bfcc9b7ca9e9d361057071d7d00f9fe0f7c08d73e034dd04b1ba", "planned_active_tokens": 67408, "realized_active_tokens": 67408, "cumulative_start": 29166300, "cumulative_end": 29233708, "loss_sum": 26470.354461669922, "token_normalized_loss": 0.3926886194764705, "grad_norm_before_clip": 0.07417728751897812, "learning_rates_at_step": { "lora": 6.283804561047407e-05, "row_tokens": 6.283804561047407e-05 }, "learning_rates_after_step": { "lora": 6.266563552475665e-05, "row_tokens": 6.266563552475665e-05 } }, { "update_id": 446, "row_count": 16, "row_ids_sha256": "fb033a2e21c4e219688d9e167b1b781e98c4c75933c7cf9b1ddc7b9585c15cf4", "input_ids_vector_sha256": "1bf8ad5c5b56324c787f7a85ecae60487cbd131e78cf8837bbd2a812682cceda", "labels_vector_sha256": "7ba02a9d2c4c1b3c0779bf450d754520616fbfdb11e5fb78161f67a0aa70aa82", "planned_active_tokens": 68965, "realized_active_tokens": 68965, "cumulative_start": 29233708, "cumulative_end": 29302673, "loss_sum": 25220.717742919922, "token_normalized_loss": 0.3657031500459642, "grad_norm_before_clip": 0.07369814813137054, "learning_rates_at_step": { "lora": 6.266563552475665e-05, "row_tokens": 6.266563552475665e-05 }, "learning_rates_after_step": { "lora": 6.251151894893127e-05, "row_tokens": 6.251151894893127e-05 } }, { "update_id": 447, "row_count": 11, "row_ids_sha256": "bf165ccc0bd7ee0efb695475c26397a4ba660284bb315bfebbeaabfce96e2f4d", "input_ids_vector_sha256": "c2470f6879cc7f31b932e963844794e9335f3613882c6ea8a47b32f13d883548", "labels_vector_sha256": "32a14a97f2f5b9418f54ac8a472ac7a59848b69de0381a24079245730cd09ea1", "planned_active_tokens": 61593, "realized_active_tokens": 61593, "cumulative_start": 29302673, "cumulative_end": 29364266, "loss_sum": 20565.673767089844, "token_normalized_loss": 0.3338962831342822, "grad_norm_before_clip": 0.07447916269302368, "learning_rates_at_step": { "lora": 6.251151894893127e-05, "row_tokens": 6.251151894893127e-05 }, "learning_rates_after_step": { "lora": 6.235753851113821e-05, "row_tokens": 6.235753851113821e-05 } }, { "update_id": 448, "row_count": 16, "row_ids_sha256": "fc284fedf69907e712f8a7826e404c2f50d15e37218bd6e47c9ac908ca2eeed3", "input_ids_vector_sha256": "35909dd9801064ec09e8801e1e8318c47c671d6bf1f730f0f542f3c879f39955", "labels_vector_sha256": "e8403a7c75cd3ec6f0434a21d13559b864d6b9a1013b45964a16f829adb50058", "planned_active_tokens": 61488, "realized_active_tokens": 61488, "cumulative_start": 29364266, "cumulative_end": 29425754, "loss_sum": 20363.733642578125, "token_normalized_loss": 0.3311822411296208, "grad_norm_before_clip": 0.0693831518292427, "learning_rates_at_step": { "lora": 6.235753851113821e-05, "row_tokens": 6.235753851113821e-05 }, "learning_rates_after_step": { "lora": 6.217107906913233e-05, "row_tokens": 6.217107906913233e-05 } }, { "update_id": 449, "row_count": 13, "row_ids_sha256": "d6b91a1dd7075a0445320ef3eb64b283b960faae3511e6091069cf664c4cea42", "input_ids_vector_sha256": "9d01200114d2d771c5db63fc4c9ae177b74ead448b42cadc048b72f899fdf3e5", "labels_vector_sha256": "e0a9143ae3604c3b94a75cc39b177d94bf0f805b781189b1df150c00977b986b", "planned_active_tokens": 74391, "realized_active_tokens": 74391, "cumulative_start": 29425754, "cumulative_end": 29500145, "loss_sum": 27182.42562866211, "token_normalized_loss": 0.36539938471941646, "grad_norm_before_clip": 0.06780946999788284, "learning_rates_at_step": { "lora": 6.217107906913233e-05, "row_tokens": 6.217107906913233e-05 }, "learning_rates_after_step": { "lora": 6.201238747827478e-05, "row_tokens": 6.201238747827478e-05 } }, { "update_id": 450, "row_count": 9, "row_ids_sha256": "13c6ee1223813b0cafd56609d029dbf63f9dc6a542a92cd2d84f2e84c647d469", "input_ids_vector_sha256": "c66d9711b2212754fcca77faefe7b508faf98aff2730a223074dee4f178152cf", "labels_vector_sha256": "6563e71e7c0c3ef1c183849475c2eccee1f7b184af8c76e353cb6329e52523d3", "planned_active_tokens": 63256, "realized_active_tokens": 63256, "cumulative_start": 29500145, "cumulative_end": 29563401, "loss_sum": 19609.650512695312, "token_normalized_loss": 0.31000459265042546, "grad_norm_before_clip": 0.06845173239707947, "learning_rates_at_step": { "lora": 6.201238747827478e-05, "row_tokens": 6.201238747827478e-05 }, "learning_rates_after_step": { "lora": 6.185895752880264e-05, "row_tokens": 6.185895752880264e-05 } }, { "update_id": 451, "row_count": 13, "row_ids_sha256": "ec07dc71eef3bbdb88ecb82c5aa17e825bcad7d9d26152e81fdf881eebf6079f", "input_ids_vector_sha256": "0d9688e13a2a90913209ac2afc7be91dd4846ffafd2306784a0828437b3c2603", "labels_vector_sha256": "88e11db19fa68912fdaeefa80f82c91b2c9f403eedb7628ebf91dcf32bf63769", "planned_active_tokens": 61110, "realized_active_tokens": 61110, "cumulative_start": 29563401, "cumulative_end": 29624511, "loss_sum": 19565.614654541016, "token_normalized_loss": 0.3201704247183933, "grad_norm_before_clip": 0.07137469947338104, "learning_rates_at_step": { "lora": 6.185895752880264e-05, "row_tokens": 6.185895752880264e-05 }, "learning_rates_after_step": { "lora": 6.169038472357216e-05, "row_tokens": 6.169038472357216e-05 } }, { "update_id": 452, "row_count": 12, "row_ids_sha256": "924b4490f2c19410e34460b302bd570328da91716a792fd17a87844960001ebc", "input_ids_vector_sha256": "664a67a8383f442d3952916ef0abcf2ad06409b69d9993bc34fa27e395858012", "labels_vector_sha256": "24340be2fb9e8b8a619bf010f669281593ff9d96639acee5660d143d3aded731", "planned_active_tokens": 67087, "realized_active_tokens": 67087, "cumulative_start": 29624511, "cumulative_end": 29691598, "loss_sum": 23855.258895874023, "token_normalized_loss": 0.3555869079832758, "grad_norm_before_clip": 0.07294759154319763, "learning_rates_at_step": { "lora": 6.169038472357216e-05, "row_tokens": 6.169038472357216e-05 }, "learning_rates_after_step": { "lora": 6.152885144443522e-05, "row_tokens": 6.152885144443522e-05 } }, { "update_id": 453, "row_count": 14, "row_ids_sha256": "94fb2f93c5637ce76f70b49343060bc318a1a3a900441413ae26868cb1a58902", "input_ids_vector_sha256": "2a9d1c4c33c0ab0006a4d91e2e92d3b7e8c494603c495b5198ec8f3f65547921", "labels_vector_sha256": "83814110ec672dbd0900d7b6b40a5489ee7d60798e80de4e654c14f9163a6dc2", "planned_active_tokens": 64233, "realized_active_tokens": 64233, "cumulative_start": 29691598, "cumulative_end": 29755831, "loss_sum": 23390.871154785156, "token_normalized_loss": 0.36415660415651074, "grad_norm_before_clip": 0.07413329929113388, "learning_rates_at_step": { "lora": 6.152885144443522e-05, "row_tokens": 6.152885144443522e-05 }, "learning_rates_after_step": { "lora": 6.136414949959e-05, "row_tokens": 6.136414949959e-05 } }, { "update_id": 454, "row_count": 12, "row_ids_sha256": "4bfbe8a91b3d1097f82b4abc47afb8c072959a3481e1a37627eca4910a206141", "input_ids_vector_sha256": "ced02187586aae0d9243cf1a7ea5198a8a7cac3a3294bbb960a71d66646aa593", "labels_vector_sha256": "27930f0fe65d8add05678ae5ea633fdbe65aa785f642ad779023a5ce415fc34d", "planned_active_tokens": 65441, "realized_active_tokens": 65441, "cumulative_start": 29755831, "cumulative_end": 29821272, "loss_sum": 21165.880401611328, "token_normalized_loss": 0.3234345502301513, "grad_norm_before_clip": 0.06886682659387589, "learning_rates_at_step": { "lora": 6.136414949959e-05, "row_tokens": 6.136414949959e-05 }, "learning_rates_after_step": { "lora": 6.120439722878782e-05, "row_tokens": 6.120439722878782e-05 } }, { "update_id": 455, "row_count": 13, "row_ids_sha256": "c88799a34a7a5bc71bb793e0a8203b56431b64e3e05d248d18824702d43701a8", "input_ids_vector_sha256": "a2d125aa858b79f5aec4a56635df8316b9e7d1e9b7249d7c496f29c369fac643", "labels_vector_sha256": "fd635cfa9c7875175062414dd015f04dd6122f0829552b6a4670a5d2cdbcd84e", "planned_active_tokens": 63425, "realized_active_tokens": 63425, "cumulative_start": 29821272, "cumulative_end": 29884697, "loss_sum": 23231.116943359375, "token_normalized_loss": 0.36627697190948955, "grad_norm_before_clip": 0.0746873989701271, "learning_rates_at_step": { "lora": 6.120439722878782e-05, "row_tokens": 6.120439722878782e-05 }, "learning_rates_after_step": { "lora": 6.1033988939618655e-05, "row_tokens": 6.1033988939618655e-05 } }, { "update_id": 456, "row_count": 14, "row_ids_sha256": "8ea1084d648409e1cc54969e44a108e0bdc138cd9bcc1f94778d73b28eccff5f", "input_ids_vector_sha256": "d53a9133bcabaababfa1cd0d25dfe17198470801dc22eb8bb343a49e56750109", "labels_vector_sha256": "751efd73a3af86ab4c68d227166e416d43aeb38e05346085db95bd639a83efe3", "planned_active_tokens": 67603, "realized_active_tokens": 67603, "cumulative_start": 29884697, "cumulative_end": 29952300, "loss_sum": 22545.62384033203, "token_normalized_loss": 0.33350034525586186, "grad_norm_before_clip": 0.07071583718061447, "learning_rates_at_step": { "lora": 6.1033988939618655e-05, "row_tokens": 6.1033988939618655e-05 }, "learning_rates_after_step": { "lora": 6.087133729094472e-05, "row_tokens": 6.087133729094472e-05 } }, { "update_id": 457, "row_count": 9, "row_ids_sha256": "2a49f5ffdb35d6d8bce94099064a3a1761a3dff97864222dfd4374a9e599f043", "input_ids_vector_sha256": "0d99f7c68bc4ffd684b40662d1b29e4a71eed3aac5b5f1b08d5cd09569d48bf6", "labels_vector_sha256": "cc596127af70537d56b5731b3ea19264014d378097baea98e47841bca1abd7b3", "planned_active_tokens": 64476, "realized_active_tokens": 64476, "cumulative_start": 29952300, "cumulative_end": 30016776, "loss_sum": 25384.83152770996, "token_normalized_loss": 0.3937097761602761, "grad_norm_before_clip": 0.07861973345279694, "learning_rates_at_step": { "lora": 6.087133729094472e-05, "row_tokens": 6.087133729094472e-05 }, "learning_rates_after_step": { "lora": 6.069519960428105e-05, "row_tokens": 6.069519960428105e-05 } }, { "update_id": 458, "row_count": 10, "row_ids_sha256": "097e4ea804756903f3c287addc552c928cd46245ce8185c5616a8fe293f1cc82", "input_ids_vector_sha256": "d437334880b29245713777a076fce18cc3c059bdd309f21883eae7ebb6712b06", "labels_vector_sha256": "a265c0e65f5f18d910bd61a7ba9d2ee78d18bf06eae2a43f51c0230dc0fd96f9", "planned_active_tokens": 69768, "realized_active_tokens": 69768, "cumulative_start": 30016776, "cumulative_end": 30086544, "loss_sum": 29000.172393798828, "token_normalized_loss": 0.4156658123179513, "grad_norm_before_clip": 0.07525432109832764, "learning_rates_at_step": { "lora": 6.069519960428105e-05, "row_tokens": 6.069519960428105e-05 }, "learning_rates_after_step": { "lora": 6.054119737950513e-05, "row_tokens": 6.054119737950513e-05 } }, { "update_id": 459, "row_count": 13, "row_ids_sha256": "9ae6041f783118170202a4941cefdc1a5f8190c0c0c4f1cefbd451d6441f9399", "input_ids_vector_sha256": "ce8e15b2bdce7f522e176feb70b696ef9d4db2dbac31035b5f64c607b3b465f6", "labels_vector_sha256": "f8dd0f7605ef1c4852114f6aa62dff9e41cc9e3956f6cbfaf993a69a5f653e0f", "planned_active_tokens": 60955, "realized_active_tokens": 60955, "cumulative_start": 30086544, "cumulative_end": 30147499, "loss_sum": 23158.573150634766, "token_normalized_loss": 0.3799290156777092, "grad_norm_before_clip": 0.07493582367897034, "learning_rates_at_step": { "lora": 6.054119737950513e-05, "row_tokens": 6.054119737950513e-05 }, "learning_rates_after_step": { "lora": 6.036205138544204e-05, "row_tokens": 6.036205138544204e-05 } }, { "update_id": 460, "row_count": 14, "row_ids_sha256": "37a503497c82c4d5278688959f6776f06510a3385ebf20872a94dfdb67a399be", "input_ids_vector_sha256": "66380d0fe734868958d01e2c58ce0517c35fbc86c41b71fcb0ba8be931e937df", "labels_vector_sha256": "f01b53744e08ba98f93f65c6cc6f00043242f2162383e217d88a6f0a6a268918", "planned_active_tokens": 70855, "realized_active_tokens": 70855, "cumulative_start": 30147499, "cumulative_end": 30218354, "loss_sum": 26121.83676147461, "token_normalized_loss": 0.36866610347152085, "grad_norm_before_clip": 0.07494378089904785, "learning_rates_at_step": { "lora": 6.036205138544204e-05, "row_tokens": 6.036205138544204e-05 }, "learning_rates_after_step": { "lora": 6.0210155677314214e-05, "row_tokens": 6.0210155677314214e-05 } }, { "update_id": 461, "row_count": 8, "row_ids_sha256": "171da653b2fbc2326580f8cf43f8d014efa0a37b094de4cc150f140c24b75e1c", "input_ids_vector_sha256": "145ff07f4ac9e91fb061ab9928ec00f7de0a6a18c78b48967256cf49d2f00fe1", "labels_vector_sha256": "3fba88ddf2a03641759e56a4a6020206bc6ed0c641f8aae9b3941bba99799838", "planned_active_tokens": 60034, "realized_active_tokens": 60034, "cumulative_start": 30218354, "cumulative_end": 30278388, "loss_sum": 22408.242553710938, "token_normalized_loss": 0.3732591956842945, "grad_norm_before_clip": 0.07872529327869415, "learning_rates_at_step": { "lora": 6.0210155677314214e-05, "row_tokens": 6.0210155677314214e-05 }, "learning_rates_after_step": { "lora": 6.00348654773321e-05, "row_tokens": 6.00348654773321e-05 } }, { "update_id": 462, "row_count": 8, "row_ids_sha256": "5c9a9813dec2aa024552db9dad0452383a3de3fd7c5fa1ef6ad6c0f21224a508", "input_ids_vector_sha256": "02d39d2fe00a6d7f90b1d58d85aeaccb1345382cc05d55f86adca916fbf92014", "labels_vector_sha256": "eac6983a952d6a8a11a4333d60eef4d0ae4bd03fe5e037cfcb4e970a033d632d", "planned_active_tokens": 69232, "realized_active_tokens": 69232, "cumulative_start": 30278388, "cumulative_end": 30347620, "loss_sum": 26081.746337890625, "token_normalized_loss": 0.3767296385759566, "grad_norm_before_clip": 0.07414054125547409, "learning_rates_at_step": { "lora": 6.00348654773321e-05, "row_tokens": 6.00348654773321e-05 }, "learning_rates_after_step": { "lora": 5.987547305283304e-05, "row_tokens": 5.987547305283304e-05 } }, { "update_id": 463, "row_count": 13, "row_ids_sha256": "0652d8380ef4a64208938b047bc0e2e223861756b2c35327680ae711ae674bc0", "input_ids_vector_sha256": "c4a32638873381a9908ccab444d23798348469e43813ce47b9854c1d8d005f0e", "labels_vector_sha256": "a08c89fd3c313089a5e5c0e442fbd6fb8399f9ef7f6f18ed46f02829c9c9c984", "planned_active_tokens": 62909, "realized_active_tokens": 62909, "cumulative_start": 30347620, "cumulative_end": 30410529, "loss_sum": 22523.032592773438, "token_normalized_loss": 0.3580256019452453, "grad_norm_before_clip": 0.07657027244567871, "learning_rates_at_step": { "lora": 5.987547305283304e-05, "row_tokens": 5.987547305283304e-05 }, "learning_rates_after_step": { "lora": 5.97113171189817e-05, "row_tokens": 5.97113171189817e-05 } }, { "update_id": 464, "row_count": 13, "row_ids_sha256": "4a27cc3a06d585e1e818d2e0dc8d82b118047d2c737542c4fe61029da6551ffe", "input_ids_vector_sha256": "1ddb7ab6eec3d4b2762edaffa73a9e55d44b320f12e5a83538a366756193a7b6", "labels_vector_sha256": "185e54d9e7215ace6a64b2ec1f0a4a3ccab880d1af2c229694ca3dff09cafe78", "planned_active_tokens": 64746, "realized_active_tokens": 64746, "cumulative_start": 30410529, "cumulative_end": 30475275, "loss_sum": 23334.41876220703, "token_normalized_loss": 0.36039938779549363, "grad_norm_before_clip": 0.08204953372478485, "learning_rates_at_step": { "lora": 5.97113171189817e-05, "row_tokens": 5.97113171189817e-05 }, "learning_rates_after_step": { "lora": 5.951685971956027e-05, "row_tokens": 5.951685971956027e-05 } }, { "update_id": 465, "row_count": 13, "row_ids_sha256": "7527ed5ce737ee1c59d22ef5ca9e15049f789716db1201f18c9f72df23faf490", "input_ids_vector_sha256": "c27c6bdd164f5777b8b1d6636ae947a87af249ee81f3791bf081003a8b787a1a", "labels_vector_sha256": "e31f2f346bb9b1811d24d36a728aff7a56983e1c1551a09c7dd6e8c695cfad34", "planned_active_tokens": 76642, "realized_active_tokens": 76642, "cumulative_start": 30475275, "cumulative_end": 30551917, "loss_sum": 32350.163482666016, "token_normalized_loss": 0.4220944584257459, "grad_norm_before_clip": 0.07076806575059891, "learning_rates_at_step": { "lora": 5.951685971956027e-05, "row_tokens": 5.951685971956027e-05 }, "learning_rates_after_step": { "lora": 5.937665922681697e-05, "row_tokens": 5.937665922681697e-05 } }, { "update_id": 466, "row_count": 9, "row_ids_sha256": "ab4bd585707f000b9bba106a3064e8a09ba957452834923d39662c2f4a04cc21", "input_ids_vector_sha256": "d8d37e294f09ef2a33cbb8e9afe38c2e80dc11a80362c8a98f05a252799f5c5e", "labels_vector_sha256": "7ed81834d4d49645690a4268ac4d4d90ffc191328d4041b780f662922314c485", "planned_active_tokens": 55221, "realized_active_tokens": 55221, "cumulative_start": 30551917, "cumulative_end": 30607138, "loss_sum": 20400.96417236328, "token_normalized_loss": 0.3694421356433835, "grad_norm_before_clip": 0.07949185371398926, "learning_rates_at_step": { "lora": 5.937665922681697e-05, "row_tokens": 5.937665922681697e-05 }, "learning_rates_after_step": { "lora": 5.9207977800274475e-05, "row_tokens": 5.9207977800274475e-05 } }, { "update_id": 467, "row_count": 12, "row_ids_sha256": "c532859a2e80bd8977028af4691d336cd978f6e6ec291970272d54f1a70ef3e9", "input_ids_vector_sha256": "d53f9501bcc00bc71ccadb30890bb33ae9499e9c6552284228eec54cc819fa85", "labels_vector_sha256": "b0711df56a8bf3674e5dd1d5e5c0e8d4713ebe5d640d7f3e753a704756f0a1da", "planned_active_tokens": 66399, "realized_active_tokens": 66399, "cumulative_start": 30607138, "cumulative_end": 30673537, "loss_sum": 22926.88687133789, "token_normalized_loss": 0.34528964097859743, "grad_norm_before_clip": 0.07344604283571243, "learning_rates_at_step": { "lora": 5.9207977800274475e-05, "row_tokens": 5.9207977800274475e-05 }, "learning_rates_after_step": { "lora": 5.904636623219547e-05, "row_tokens": 5.904636623219547e-05 } }, { "update_id": 468, "row_count": 13, "row_ids_sha256": "7ac2855c6da41f14f289c67596072d9c3d9d31251b9d872dba9ce6cc47e87716", "input_ids_vector_sha256": "2f38fe2519612303d496ce2a2df816b785c2f9684da6106529beeb9729806740", "labels_vector_sha256": "c6acd533d560f2d832a64422f96d6e9432db08fbf98124e626b039bbc8c211ca", "planned_active_tokens": 63576, "realized_active_tokens": 63576, "cumulative_start": 30673537, "cumulative_end": 30737113, "loss_sum": 21843.81216430664, "token_normalized_loss": 0.3435858211322927, "grad_norm_before_clip": 0.07186270505189896, "learning_rates_at_step": { "lora": 5.904636623219547e-05, "row_tokens": 5.904636623219547e-05 }, "learning_rates_after_step": { "lora": 5.8877779514414733e-05, "row_tokens": 5.8877779514414733e-05 } }, { "update_id": 469, "row_count": 13, "row_ids_sha256": "392fe187966a45fb85eb7094e8afdedc60794577b7bae13ddf5c73665d8f4aab", "input_ids_vector_sha256": "750c1fdff32b5c3c0b67a4f47561bfa4c64538c13c70e47a376cb81d0963d225", "labels_vector_sha256": "b8b3ba9dc93b50173dcf9e7ad4a0b3fce502a8327e0a0b1116eaf5915eaf0f67", "planned_active_tokens": 66279, "realized_active_tokens": 66279, "cumulative_start": 30737113, "cumulative_end": 30803392, "loss_sum": 22953.226837158203, "token_normalized_loss": 0.34631220804716734, "grad_norm_before_clip": 0.069864921271801, "learning_rates_at_step": { "lora": 5.8877779514414733e-05, "row_tokens": 5.8877779514414733e-05 }, "learning_rates_after_step": { "lora": 5.8707079763269244e-05, "row_tokens": 5.8707079763269244e-05 } }, { "update_id": 470, "row_count": 13, "row_ids_sha256": "8d995dd5896d962437dd61c88ba84fd6db0af70664232a9013aa1d3f2c7edc6d", "input_ids_vector_sha256": "1009a95c96a6e4d15ffae8d3c9d8da8ea526a7dcc28401bc334e1563bc337520", "labels_vector_sha256": "f498fcc5e78eadfda21429bd1abad6f0b183cb733a5492216b11a3b7b9fc0b45", "planned_active_tokens": 67068, "realized_active_tokens": 67068, "cumulative_start": 30803392, "cumulative_end": 30870460, "loss_sum": 22214.80891418457, "token_normalized_loss": 0.3312281403081137, "grad_norm_before_clip": 0.07130637019872665, "learning_rates_at_step": { "lora": 5.8707079763269244e-05, "row_tokens": 5.8707079763269244e-05 }, "learning_rates_after_step": { "lora": 5.8540835289284516e-05, "row_tokens": 5.8540835289284516e-05 } }, { "update_id": 471, "row_count": 7, "row_ids_sha256": "2faf225ef1968e594fed636c190bdce113f7e8e29374fbdf8e69808ffca818ab", "input_ids_vector_sha256": "9a0be41e353cd859ef64d1ee461a33135659dbdfe998542c40a313e42b4879c9", "labels_vector_sha256": "97fab38d11ec9bd05879147721e1e6da2f4c06a318fe5f53c2dcf0d12675f9c1", "planned_active_tokens": 65278, "realized_active_tokens": 65278, "cumulative_start": 30870460, "cumulative_end": 30935738, "loss_sum": 26445.312744140625, "token_normalized_loss": 0.40511830546494415, "grad_norm_before_clip": 0.07728447765111923, "learning_rates_at_step": { "lora": 5.8540835289284516e-05, "row_tokens": 5.8540835289284516e-05 }, "learning_rates_after_step": { "lora": 5.836167459185222e-05, "row_tokens": 5.836167459185222e-05 } }, { "update_id": 472, "row_count": 12, "row_ids_sha256": "1df11d1819829f3b829969783553facc423451b74c225709099a3ab61034d7d0", "input_ids_vector_sha256": "bd348e4311df964e2c1706071054ad3a8b05c92196f02193fb712ff1fb220ee5", "labels_vector_sha256": "cedff8b92d8d0974f763c7688e74af7d862f12198d3836a2c086e68a7e5c45e3", "planned_active_tokens": 70307, "realized_active_tokens": 70307, "cumulative_start": 30935738, "cumulative_end": 31006045, "loss_sum": 25636.822265625, "token_normalized_loss": 0.36464110637098723, "grad_norm_before_clip": 0.06951422989368439, "learning_rates_at_step": { "lora": 5.836167459185222e-05, "row_tokens": 5.836167459185222e-05 }, "learning_rates_after_step": { "lora": 5.818672407856249e-05, "row_tokens": 5.818672407856249e-05 } }, { "update_id": 473, "row_count": 11, "row_ids_sha256": "3d2900fc037f38405c8bcc2decdf89b57174819b870a74eb86519071d8661816", "input_ids_vector_sha256": "789d6767c9c6df2c8df66345815e630a42e6738246e19a5b09d41ba7386cc436", "labels_vector_sha256": "7fd24555c779777d3df0c003ca3f2bc82bcfef60925ec02b0189c2a3ee398854", "planned_active_tokens": 68613, "realized_active_tokens": 68613, "cumulative_start": 31006045, "cumulative_end": 31074658, "loss_sum": 20034.354690551758, "token_normalized_loss": 0.2919906532370215, "grad_norm_before_clip": 0.06585735082626343, "learning_rates_at_step": { "lora": 5.818672407856249e-05, "row_tokens": 5.818672407856249e-05 }, "learning_rates_after_step": { "lora": 5.804317658627184e-05, "row_tokens": 5.804317658627184e-05 } }, { "update_id": 474, "row_count": 10, "row_ids_sha256": "08a1fd407e3fc67edc662f7a288922576012c2731e518d514262bdb27ec788cb", "input_ids_vector_sha256": "54832f3ce51f4a32f007770e75fa06f16284a779a27cb7a063cdd8f63a9c5716", "labels_vector_sha256": "849d5020d15a56ea19dd914e94b9fe6bd9d08829865c8cfc69c860b369386246", "planned_active_tokens": 56267, "realized_active_tokens": 56267, "cumulative_start": 31074658, "cumulative_end": 31130925, "loss_sum": 17623.288208007812, "token_normalized_loss": 0.31320824298448136, "grad_norm_before_clip": 0.07666800916194916, "learning_rates_at_step": { "lora": 5.804317658627184e-05, "row_tokens": 5.804317658627184e-05 }, "learning_rates_after_step": { "lora": 5.787856193002298e-05, "row_tokens": 5.787856193002298e-05 } }, { "update_id": 475, "row_count": 9, "row_ids_sha256": "3ce0252eb13d40620a2422588d8b3f71b4d430b4565820f816e43792abc98dcf", "input_ids_vector_sha256": "471d6eb57c3c505afbc76dddf8e915a5a32dccc19d6c6c5d5568401869b18e97", "labels_vector_sha256": "3bc4797d433d787bbc680d4010beb86f9a5ebd7e0dc121e840e44de26b879164", "planned_active_tokens": 64492, "realized_active_tokens": 64492, "cumulative_start": 31130925, "cumulative_end": 31195417, "loss_sum": 25555.89273071289, "token_normalized_loss": 0.39626454026410857, "grad_norm_before_clip": 0.08053337037563324, "learning_rates_at_step": { "lora": 5.787856193002298e-05, "row_tokens": 5.787856193002298e-05 }, "learning_rates_after_step": { "lora": 5.7709310039949496e-05, "row_tokens": 5.7709310039949496e-05 } }, { "update_id": 476, "row_count": 11, "row_ids_sha256": "321b1c4bb6b9719729056db1f2ce56c80e6ae5e5016d39acf4de129ede18e6fb", "input_ids_vector_sha256": "1931bb45cb42e0cdf88d8c91b54b59d58d782bda12f9602a16f4e24b58d013e7", "labels_vector_sha256": "df0112b935f36c74f17eee802259d779608895f83f91280f097efd442f2cad69", "planned_active_tokens": 66273, "realized_active_tokens": 66273, "cumulative_start": 31195417, "cumulative_end": 31261690, "loss_sum": 23952.342742919922, "token_normalized_loss": 0.3614193222416357, "grad_norm_before_clip": 0.07683751732110977, "learning_rates_at_step": { "lora": 5.7709310039949496e-05, "row_tokens": 5.7709310039949496e-05 }, "learning_rates_after_step": { "lora": 5.7534612962325186e-05, "row_tokens": 5.7534612962325186e-05 } }, { "update_id": 477, "row_count": 15, "row_ids_sha256": "6dfa54f11f2410928b4628583fbe2fa21fb6ff90bf1530dad5220ec0a214ec44", "input_ids_vector_sha256": "9638bba038f1901b07fb3fbda7f0848896104e5ec74e4c46f6368e07e6db7416", "labels_vector_sha256": "167d1bdc088241ea4096333c6daa1727043686c8758964a40e9188da9824f78f", "planned_active_tokens": 68368, "realized_active_tokens": 68368, "cumulative_start": 31261690, "cumulative_end": 31330058, "loss_sum": 23395.247100830078, "token_normalized_loss": 0.3421958679620594, "grad_norm_before_clip": 0.0732937753200531, "learning_rates_at_step": { "lora": 5.7534612962325186e-05, "row_tokens": 5.7534612962325186e-05 }, "learning_rates_after_step": { "lora": 5.735225968960936e-05, "row_tokens": 5.735225968960936e-05 } }, { "update_id": 478, "row_count": 11, "row_ids_sha256": "fe5752a482cc71c162cb7c2890bf6148166f9011e46714e9e2213e62f8104020", "input_ids_vector_sha256": "9418b25e3beac9b0e6376d703593a005e0ae961f96d484689d19151093b80db0", "labels_vector_sha256": "143124f71566b30d9598ae392ea5bc7bb30b331bd6b4545dd92fc5252fdc90fe", "planned_active_tokens": 71325, "realized_active_tokens": 71325, "cumulative_start": 31330058, "cumulative_end": 31401383, "loss_sum": 24512.22900390625, "token_normalized_loss": 0.34366952686864705, "grad_norm_before_clip": 0.07117975503206253, "learning_rates_at_step": { "lora": 5.735225968960936e-05, "row_tokens": 5.735225968960936e-05 }, "learning_rates_after_step": { "lora": 5.720547344161309e-05, "row_tokens": 5.720547344161309e-05 } }, { "update_id": 479, "row_count": 11, "row_ids_sha256": "95e8c899dc52822b9041fecb20a17ab61d1814c555af472a1f19cc98041a2fe9", "input_ids_vector_sha256": "a66bc49d1ae8d19e2080cd36b02b44be49d3f75fcc3e9c43259e76ad2c9a4747", "labels_vector_sha256": "78c78ac9cbd9b8f7c205efa4c2a43f9b406bd104ef0d25b9b462c9729e6924d1", "planned_active_tokens": 57385, "realized_active_tokens": 57385, "cumulative_start": 31401383, "cumulative_end": 31458768, "loss_sum": 21346.318572998047, "token_normalized_loss": 0.3719842915918454, "grad_norm_before_clip": 0.08085338026285172, "learning_rates_at_step": { "lora": 5.720547344161309e-05, "row_tokens": 5.720547344161309e-05 }, "learning_rates_after_step": { "lora": 5.704139996831709e-05, "row_tokens": 5.704139996831709e-05 } }, { "update_id": 480, "row_count": 10, "row_ids_sha256": "3faee94f3b4927fae1e601104283d5702524fff9397fe08dc4459c4f8bae3e80", "input_ids_vector_sha256": "382287e88fc27ef16a132ee46f4ce3b925bdeb7fda58c7e5f9e7c9b9834129ba", "labels_vector_sha256": "90ecf53ea01bbf2f5189c72f14a17de568e6dc46a70027d9aba4eaa4525c3e4d", "planned_active_tokens": 64114, "realized_active_tokens": 64114, "cumulative_start": 31458768, "cumulative_end": 31522882, "loss_sum": 22172.093658447266, "token_normalized_loss": 0.3458229662545975, "grad_norm_before_clip": 0.07216928154230118, "learning_rates_at_step": { "lora": 5.704139996831709e-05, "row_tokens": 5.704139996831709e-05 }, "learning_rates_after_step": { "lora": 5.686734343842414e-05, "row_tokens": 5.686734343842414e-05 } }, { "update_id": 481, "row_count": 10, "row_ids_sha256": "3bb7e6510bd9ba35bedec40cd0b439847e5cd883b71c156f3eed78151a9fd735", "input_ids_vector_sha256": "d432ba03450f0c5c76576cf80b190aa02eb76e3de6cc32b6c8749d49c84c920e", "labels_vector_sha256": "41e6734bd9b57ba9fd128107141b33933d3fad03ff39fa215496a315935c2233", "planned_active_tokens": 67982, "realized_active_tokens": 67982, "cumulative_start": 31522882, "cumulative_end": 31590864, "loss_sum": 25936.210235595703, "token_normalized_loss": 0.38151584589443827, "grad_norm_before_clip": 0.0719958022236824, "learning_rates_at_step": { "lora": 5.686734343842414e-05, "row_tokens": 5.686734343842414e-05 }, "learning_rates_after_step": { "lora": 5.670372226614752e-05, "row_tokens": 5.670372226614752e-05 } }, { "update_id": 482, "row_count": 12, "row_ids_sha256": "41f0e813945f1310150aec9b13c60f241192ca87fa3c935b4f1bdb0dbe93e2af", "input_ids_vector_sha256": "653e1ef2b11e81f6755ea6176ecea8e4de7b27bb273cb768cb89686ecf29afa3", "labels_vector_sha256": "988e7cb0438ac8980c3ae151204bbf1b4d2ffe2415389aac068d38c8c8265511", "planned_active_tokens": 63876, "realized_active_tokens": 63876, "cumulative_start": 31590864, "cumulative_end": 31654740, "loss_sum": 22492.83123779297, "token_normalized_loss": 0.3521327452845039, "grad_norm_before_clip": 0.07578583806753159, "learning_rates_at_step": { "lora": 5.670372226614752e-05, "row_tokens": 5.670372226614752e-05 }, "learning_rates_after_step": { "lora": 5.651812433292531e-05, "row_tokens": 5.651812433292531e-05 } }, { "update_id": 483, "row_count": 12, "row_ids_sha256": "51a5f0dffb6bc92ac7c401944201ba4cafd3b626e5024a52fe5eb1130d6b74a7", "input_ids_vector_sha256": "48d93fd2b1005298bbde5c027b60471e0a7ef5c74a0be44e478fe11c946b0033", "labels_vector_sha256": "e9c17818cd7c01b6b4013d6f3efe0f5a02a514e7c6cdea986ac153e7a6ac320a", "planned_active_tokens": 72421, "realized_active_tokens": 72421, "cumulative_start": 31654740, "cumulative_end": 31727161, "loss_sum": 28558.91094970703, "token_normalized_loss": 0.39434571394632817, "grad_norm_before_clip": 0.07744176685810089, "learning_rates_at_step": { "lora": 5.651812433292531e-05, "row_tokens": 5.651812433292531e-05 }, "learning_rates_after_step": { "lora": 5.636615861021894e-05, "row_tokens": 5.636615861021894e-05 } }, { "update_id": 484, "row_count": 15, "row_ids_sha256": "259b9f1ed7f92f9666006721d261659e9abdae81fd9a097fbd20015db955e60a", "input_ids_vector_sha256": "306c5028f06994ea1f2166ac61d949a5e9a7d576a1df593c13534df9c7b54a21", "labels_vector_sha256": "5d6e786195ebab5b88e78a5b27cddb1abe9820fc8a8e3a50767a803386c8c8c3", "planned_active_tokens": 59271, "realized_active_tokens": 59271, "cumulative_start": 31727161, "cumulative_end": 31786432, "loss_sum": 20504.185317993164, "token_normalized_loss": 0.34593958796027, "grad_norm_before_clip": 0.07412072271108627, "learning_rates_at_step": { "lora": 5.636615861021894e-05, "row_tokens": 5.636615861021894e-05 }, "learning_rates_after_step": { "lora": 5.6187870024714215e-05, "row_tokens": 5.6187870024714215e-05 } }, { "update_id": 485, "row_count": 12, "row_ids_sha256": "3925f3e320d8189f0cd9cf2ba9adc6bbe53c151aa1952d695924924899b5890d", "input_ids_vector_sha256": "e8a756ccbc0360737ec66704287da82a7fc5f0491bb80db122fd20cbc56c4623", "labels_vector_sha256": "0c76440d0f3bd89db4294a2b8a1180635afbfb1dc6e444557f3d0e8af81184c8", "planned_active_tokens": 69508, "realized_active_tokens": 69508, "cumulative_start": 31786432, "cumulative_end": 31855940, "loss_sum": 24201.83090209961, "token_normalized_loss": 0.3481877036038961, "grad_norm_before_clip": 0.07536614686250687, "learning_rates_at_step": { "lora": 5.6187870024714215e-05, "row_tokens": 5.6187870024714215e-05 }, "learning_rates_after_step": { "lora": 5.6029819170773445e-05, "row_tokens": 5.6029819170773445e-05 } }, { "update_id": 486, "row_count": 8, "row_ids_sha256": "1048b73ac04a76754cd3d2679dc606b7a9fc928b2a5ca7aadeefc354843f32f9", "input_ids_vector_sha256": "cfe55e943a5ccf3438a3064deab37671628cc37146c7cf32d7cab738e21e4a43", "labels_vector_sha256": "232026f0ee2115a52ed59e860dfecb949957181e1342fad4f7f817bfbcfd2569", "planned_active_tokens": 61592, "realized_active_tokens": 61592, "cumulative_start": 31855940, "cumulative_end": 31917532, "loss_sum": 25744.669921875, "token_normalized_loss": 0.4179872373339882, "grad_norm_before_clip": 0.08261585235595703, "learning_rates_at_step": { "lora": 5.6029819170773445e-05, "row_tokens": 5.6029819170773445e-05 }, "learning_rates_after_step": { "lora": 5.5858971789958914e-05, "row_tokens": 5.5858971789958914e-05 } }, { "update_id": 487, "row_count": 9, "row_ids_sha256": "b96e64545802c7d990fbd6f4b4a9bbc8f8a013d20b6c4f8573f061c41581d658", "input_ids_vector_sha256": "09cb481ce3e839d8cb6d5d882bd29dfd767de5010f106af8ed14f4daa3ca4fc1", "labels_vector_sha256": "257c41c8fa57bad49e761421a31f8c04de418b2bd1657cc5889b95d674844d08", "planned_active_tokens": 66552, "realized_active_tokens": 66552, "cumulative_start": 31917532, "cumulative_end": 31984084, "loss_sum": 21776.128173828125, "token_normalized_loss": 0.3272047147167347, "grad_norm_before_clip": 0.07310928404331207, "learning_rates_at_step": { "lora": 5.5858971789958914e-05, "row_tokens": 5.5858971789958914e-05 }, "learning_rates_after_step": { "lora": 5.5688625268361846e-05, "row_tokens": 5.5688625268361846e-05 } }, { "update_id": 488, "row_count": 12, "row_ids_sha256": "55c10f357ade801bb7f18abab92446035eeb8741d1a09012b04b018c1716a99d", "input_ids_vector_sha256": "a23c921dac6d85d5f376f014d1f47b0b2bc1689de21bb9419b3ff592f077e4b8", "labels_vector_sha256": "d1eda4ca37ddd5c2f984f3ae5f71e0f48525d54a7260be04c4ef5f9c5aa3accf", "planned_active_tokens": 66330, "realized_active_tokens": 66330, "cumulative_start": 31984084, "cumulative_end": 32050414, "loss_sum": 25825.22802734375, "token_normalized_loss": 0.38934461069416176, "grad_norm_before_clip": 0.07806864380836487, "learning_rates_at_step": { "lora": 5.5688625268361846e-05, "row_tokens": 5.5688625268361846e-05 }, "learning_rates_after_step": { "lora": 5.5515367191385926e-05, "row_tokens": 5.5515367191385926e-05 } }, { "update_id": 489, "row_count": 11, "row_ids_sha256": "426629cb83360f7528957e2c8a7d59d54140d3d7249a1d9553b228c97d52b50a", "input_ids_vector_sha256": "91225b3cfb408845866d1f48f6ac387f8f8310d4fe460ae8d0bcbc3acaab1621", "labels_vector_sha256": "23b8d3c685cb210046668bacf8a88aa08c5afcc0479c030e6b6964032dd78dda", "planned_active_tokens": 67437, "realized_active_tokens": 67437, "cumulative_start": 32050414, "cumulative_end": 32117851, "loss_sum": 25343.169982910156, "token_normalized_loss": 0.37580512156398055, "grad_norm_before_clip": 0.07955316454172134, "learning_rates_at_step": { "lora": 5.5515367191385926e-05, "row_tokens": 5.5515367191385926e-05 }, "learning_rates_after_step": { "lora": 5.5357018502636135e-05, "row_tokens": 5.5357018502636135e-05 } }, { "update_id": 490, "row_count": 9, "row_ids_sha256": "f8bcfee80c7274d428bd9e03318af24549b5465040bc31cef515e0f35fa22c1d", "input_ids_vector_sha256": "8ac4fba349e9a57bc293ac06458064893578eb1c8947215dede7d98491bf7885", "labels_vector_sha256": "e4e94b38dc14103009107c9c4226311d57963aeeded9c8c384b6a0d630a4f3e8", "planned_active_tokens": 61611, "realized_active_tokens": 61611, "cumulative_start": 32117851, "cumulative_end": 32179462, "loss_sum": 23170.406799316406, "token_normalized_loss": 0.3760758111265262, "grad_norm_before_clip": 0.08066105097532272, "learning_rates_at_step": { "lora": 5.5357018502636135e-05, "row_tokens": 5.5357018502636135e-05 }, "learning_rates_after_step": { "lora": 5.5165020813037984e-05, "row_tokens": 5.5165020813037984e-05 } }, { "update_id": 491, "row_count": 12, "row_ids_sha256": "93f11a1365657b0a9ae3b6dd7023b7a5ea5b7adece4b24d9c2046c2e929d374e", "input_ids_vector_sha256": "465fb95fe123150a6a069242af6c9f680f37eddd455a1170be7036ffdcd115fb", "labels_vector_sha256": "f3deb3f835b73bf7a65c215e8435902bf9f263f12ea1af4002488dd81aa47e0e", "planned_active_tokens": 74675, "realized_active_tokens": 74675, "cumulative_start": 32179462, "cumulative_end": 32254137, "loss_sum": 28138.78630065918, "token_normalized_loss": 0.3768166896639997, "grad_norm_before_clip": 0.0717359408736229, "learning_rates_at_step": { "lora": 5.5165020813037984e-05, "row_tokens": 5.5165020813037984e-05 }, "learning_rates_after_step": { "lora": 5.500478414333603e-05, "row_tokens": 5.500478414333603e-05 } }, { "update_id": 492, "row_count": 10, "row_ids_sha256": "52f2bd8595af78d12bd0c51575ed133b0dce463ad8665e2e17b00418cc119c66", "input_ids_vector_sha256": "736b62212edbe4f114bed5c1500bb50cecfcf0d72b957ab5499425141e16b4dd", "labels_vector_sha256": "9d2bc6880a62a4a005afe0b1cb762d198791cbf2b4e64ce0e87f4cbf48e66274", "planned_active_tokens": 62299, "realized_active_tokens": 62299, "cumulative_start": 32254137, "cumulative_end": 32316436, "loss_sum": 24550.979064941406, "token_normalized_loss": 0.39408303608310574, "grad_norm_before_clip": 0.08166775852441788, "learning_rates_at_step": { "lora": 5.500478414333603e-05, "row_tokens": 5.500478414333603e-05 }, "learning_rates_after_step": { "lora": 5.4844539281849786e-05, "row_tokens": 5.4844539281849786e-05 } }, { "update_id": 493, "row_count": 7, "row_ids_sha256": "830758da34309319658c0069839d22e1fc153372d6a19951faf3542d57837585", "input_ids_vector_sha256": "00ac68f0f5f62d1f6d8b4e90fcd768824cbf7bfa484b2da2a02b17a5cbc09b07", "labels_vector_sha256": "5e2a5132f00c95b67c123d5bdc1b5e85ef42f634cd9508e7533e59a74d189977", "planned_active_tokens": 62282, "realized_active_tokens": 62282, "cumulative_start": 32316436, "cumulative_end": 32378718, "loss_sum": 30026.8935546875, "token_normalized_loss": 0.48211190319333835, "grad_norm_before_clip": 0.08938008546829224, "learning_rates_at_step": { "lora": 5.4844539281849786e-05, "row_tokens": 5.4844539281849786e-05 }, "learning_rates_after_step": { "lora": 5.4681806500913166e-05, "row_tokens": 5.4681806500913166e-05 } }, { "update_id": 494, "row_count": 8, "row_ids_sha256": "8a33a19664cf00d31037cc2cc1aa8bf9bed8db8b3768b378ebb7c377afa6d164", "input_ids_vector_sha256": "3f423e01a52f4ea66f143edb686eb3e2dee760f66851e85177373dd19931a0db", "labels_vector_sha256": "a50efdf6849ea91e4efe98b22e8288849dc218b57b6bbf0ef581179f4f5dcc21", "planned_active_tokens": 63229, "realized_active_tokens": 63229, "cumulative_start": 32378718, "cumulative_end": 32441947, "loss_sum": 28746.41162109375, "token_normalized_loss": 0.4546396688401485, "grad_norm_before_clip": 0.08721411228179932, "learning_rates_at_step": { "lora": 5.4681806500913166e-05, "row_tokens": 5.4681806500913166e-05 }, "learning_rates_after_step": { "lora": 5.4512707448282284e-05, "row_tokens": 5.4512707448282284e-05 } }, { "update_id": 495, "row_count": 8, "row_ids_sha256": "adc3fb22e7db06ab1fee09b44109cd9c8bd254443ef3ea99d652261cbf281ed9", "input_ids_vector_sha256": "685005ae19f107fd778317bbcf0d5001bc1fc7c6254c279db6e86f755e52d7cb", "labels_vector_sha256": "263e423c3feee9b4aa45340476efbe47399ef8096168c7907dbd4c76c2593bfd", "planned_active_tokens": 65682, "realized_active_tokens": 65682, "cumulative_start": 32441947, "cumulative_end": 32507629, "loss_sum": 29465.351318359375, "token_normalized_loss": 0.4486061830997743, "grad_norm_before_clip": 0.08956004679203033, "learning_rates_at_step": { "lora": 5.4512707448282284e-05, "row_tokens": 5.4512707448282284e-05 }, "learning_rates_after_step": { "lora": 5.4323975607956145e-05, "row_tokens": 5.4323975607956145e-05 } }, { "update_id": 496, "row_count": 11, "row_ids_sha256": "9d765c81e5c4c24cfe472ef950a15ea90299ff3a29ee7b6ad7133c0967cbceb4", "input_ids_vector_sha256": "5e96393045b9e35b85ca763699801f01e8f6139a3564a4ed86fb4011fa061411", "labels_vector_sha256": "9c7740c9bc090a4e9c2698b38ca526b09a479c0b93ba497be3e8445428432011", "planned_active_tokens": 73284, "realized_active_tokens": 73284, "cumulative_start": 32507629, "cumulative_end": 32580913, "loss_sum": 28969.152770996094, "token_normalized_loss": 0.3952998303994882, "grad_norm_before_clip": 0.07874112576246262, "learning_rates_at_step": { "lora": 5.4323975607956145e-05, "row_tokens": 5.4323975607956145e-05 }, "learning_rates_after_step": { "lora": 5.417793378962419e-05, "row_tokens": 5.417793378962419e-05 } }, { "update_id": 497, "row_count": 7, "row_ids_sha256": "b92c1b5075582835e6b6758c20cbeef359cb9c1d7b2f82518712f30b59de5bae", "input_ids_vector_sha256": "878f3114bfce8681c2b70610bff467aaa614bbc715e5600c6b3c6e6901c848c0", "labels_vector_sha256": "7b33f8ec649dabbd1ef61405f5dd75eaaf44298e8c31567b944d1d5b18898d43", "planned_active_tokens": 56691, "realized_active_tokens": 56691, "cumulative_start": 32580913, "cumulative_end": 32637604, "loss_sum": 21860.13818359375, "token_normalized_loss": 0.3856015625689042, "grad_norm_before_clip": 0.08694815635681152, "learning_rates_at_step": { "lora": 5.417793378962419e-05, "row_tokens": 5.417793378962419e-05 }, "learning_rates_after_step": { "lora": 5.400748447365902e-05, "row_tokens": 5.400748447365902e-05 } }, { "update_id": 498, "row_count": 8, "row_ids_sha256": "3797fcbad26f519e6a700929006abfde0e7c52111b27454a5f46c8c3edb3c3bd", "input_ids_vector_sha256": "04edda7c4a9fa2243bd9b6bfd776f240dbc29924f314649ba4b558699207d54c", "labels_vector_sha256": "f7ebf7bea4bda9d1356e6f566dde0eee826042826b1cc6340103e027234cf755", "planned_active_tokens": 66148, "realized_active_tokens": 66148, "cumulative_start": 32637604, "cumulative_end": 32703752, "loss_sum": 27013.788208007812, "token_normalized_loss": 0.4083840510371865, "grad_norm_before_clip": 0.0871722549200058, "learning_rates_at_step": { "lora": 5.400748447365902e-05, "row_tokens": 5.400748447365902e-05 }, "learning_rates_after_step": { "lora": 5.3824913555448105e-05, "row_tokens": 5.3824913555448105e-05 } }, { "update_id": 499, "row_count": 12, "row_ids_sha256": "fc032255083a611e03fc142e3f04b976f2c803d75463a9ea631edd595f7a9eec", "input_ids_vector_sha256": "7535b687e47f34151132d3b66643e36e378d9c426277edc2d03d1b203f484219", "labels_vector_sha256": "9b6ea391a3616df823a53c805b95f4596d8132e047ad59ab5bf1ee65f839ab91", "planned_active_tokens": 70832, "realized_active_tokens": 70832, "cumulative_start": 32703752, "cumulative_end": 32774584, "loss_sum": 26648.50457763672, "token_normalized_loss": 0.3762212640845482, "grad_norm_before_clip": 0.07971841841936111, "learning_rates_at_step": { "lora": 5.3824913555448105e-05, "row_tokens": 5.3824913555448105e-05 }, "learning_rates_after_step": { "lora": 5.366845840888004e-05, "row_tokens": 5.366845840888004e-05 } }, { "update_id": 500, "row_count": 8, "row_ids_sha256": "8513f91605bc6f0750ebdbd558360d1e3d85b1aa6115dd66248813850e62f926", "input_ids_vector_sha256": "c3d322d13f353688ec3c0e0de069bd6c81329c71182d3a9eaa0b6512dec6b5ce", "labels_vector_sha256": "c8363c9cfe9b698d67830e64cf492d686581273a0afa9e9eb22bcba66e238473", "planned_active_tokens": 60684, "realized_active_tokens": 60684, "cumulative_start": 32774584, "cumulative_end": 32835268, "loss_sum": 26571.641799926758, "token_normalized_loss": 0.4378689901774233, "grad_norm_before_clip": 0.08964687585830688, "learning_rates_at_step": { "lora": 5.366845840888004e-05, "row_tokens": 5.366845840888004e-05 }, "learning_rates_after_step": { "lora": 5.3502491541871466e-05, "row_tokens": 5.3502491541871466e-05 } }, { "update_id": 501, "row_count": 9, "row_ids_sha256": "1ccee3c758c829f85d59f3556ed1176e95254cb74d619d35c83facfae97855f7", "input_ids_vector_sha256": "2facf9ecfd740a919022f289d936e9aafec6fef650499b057146829368813d3b", "labels_vector_sha256": "967c5ef5689ebeea6db52a76f012b45a59489d774a6a74ad4a9771e5986910d2", "planned_active_tokens": 64358, "realized_active_tokens": 64358, "cumulative_start": 32835268, "cumulative_end": 32899626, "loss_sum": 26451.25177001953, "token_normalized_loss": 0.4110017677681024, "grad_norm_before_clip": 0.08442199975252151, "learning_rates_at_step": { "lora": 5.3502491541871466e-05, "row_tokens": 5.3502491541871466e-05 }, "learning_rates_after_step": { "lora": 5.33194106445974e-05, "row_tokens": 5.33194106445974e-05 } }, { "update_id": 502, "row_count": 10, "row_ids_sha256": "52f207f783c93cf27e58d4acfbcda8f82d407881e3aa87447e1ce8965ad4ceeb", "input_ids_vector_sha256": "1d4fdc8e2e5d2d0d1b174e10a106374becd8c8e173a1f070eb0bf299fe4343da", "labels_vector_sha256": "21c11e7f199800ef4aef1f9b1a95c74a4020db34877b0bfa61310d4d9ce57dc3", "planned_active_tokens": 70977, "realized_active_tokens": 70977, "cumulative_start": 32899626, "cumulative_end": 32970603, "loss_sum": 27969.269287109375, "token_normalized_loss": 0.39406102381207114, "grad_norm_before_clip": 0.07586026936769485, "learning_rates_at_step": { "lora": 5.33194106445974e-05, "row_tokens": 5.33194106445974e-05 }, "learning_rates_after_step": { "lora": 5.315583111986592e-05, "row_tokens": 5.315583111986592e-05 } }, { "update_id": 503, "row_count": 7, "row_ids_sha256": "c8d267a882f9f51d42926786ae32e54d1f297c76f4235b1e7f5f3647d28b25ea", "input_ids_vector_sha256": "b699bb94f58a6f88e311868c5b1c0d8c1ced84c5b1026613dae10dbae79c5e60", "labels_vector_sha256": "3cf4e5a580f7a95e5ead09975603c83e5db18e9aacd8986ff45825d43b6fa3d9", "planned_active_tokens": 63402, "realized_active_tokens": 63402, "cumulative_start": 32970603, "cumulative_end": 33034005, "loss_sum": 25062.204711914062, "token_normalized_loss": 0.3952904437070449, "grad_norm_before_clip": 0.08236682415008545, "learning_rates_at_step": { "lora": 5.315583111986592e-05, "row_tokens": 5.315583111986592e-05 }, "learning_rates_after_step": { "lora": 5.2992127346016304e-05, "row_tokens": 5.2992127346016304e-05 } }, { "update_id": 504, "row_count": 9, "row_ids_sha256": "de8555cbb2389c7f5e5d52fec2579c24c824cbb15fdd6c0f5a34bd6829a41303", "input_ids_vector_sha256": "576be725762a4d4199e5920b7ede0abcbb9ae37ed235e4dd81ff681903ea0e21", "labels_vector_sha256": "432f3508a5e24de5bbb7de5f461ad6689ee09fb2796297d196de1e64403c9126", "planned_active_tokens": 63437, "realized_active_tokens": 63437, "cumulative_start": 33034005, "cumulative_end": 33097442, "loss_sum": 23879.458374023438, "token_normalized_loss": 0.37642792651013507, "grad_norm_before_clip": 0.08681229501962662, "learning_rates_at_step": { "lora": 5.2992127346016304e-05, "row_tokens": 5.2992127346016304e-05 }, "learning_rates_after_step": { "lora": 5.281119700640327e-05, "row_tokens": 5.281119700640327e-05 } }, { "update_id": 505, "row_count": 11, "row_ids_sha256": "805e7f4494c05af524b773e51076972a9398534d7d017f693cbd927a0960a4ed", "input_ids_vector_sha256": "007c0f0db06d9236c5c8e295649e03290a652b1caef54e3f8f1968d4f9357d94", "labels_vector_sha256": "760e1a93b62a997dfce9c45089d4e847084aef6563f1b13ecff5cea684b3d865", "planned_active_tokens": 70098, "realized_active_tokens": 70098, "cumulative_start": 33097442, "cumulative_end": 33167540, "loss_sum": 24444.1171875, "token_normalized_loss": 0.34871347524180435, "grad_norm_before_clip": 0.0767119824886322, "learning_rates_at_step": { "lora": 5.281119700640327e-05, "row_tokens": 5.281119700640327e-05 }, "learning_rates_after_step": { "lora": 5.263949865219519e-05, "row_tokens": 5.263949865219519e-05 } }, { "update_id": 506, "row_count": 8, "row_ids_sha256": "ad3898fe7075d33be9f25b4bdbaa5a2ee054c2622403152ed758fd0036dac6ce", "input_ids_vector_sha256": "fe0790f05327e202f4ac24df7fbcecdf198697b57bc895a353c8f4db0729cc8d", "labels_vector_sha256": "d0f3f7dcdb5834f8a057c36af8d8fabe7f9ffeaf927ba4717ef1381b22fadd45", "planned_active_tokens": 66508, "realized_active_tokens": 66508, "cumulative_start": 33167540, "cumulative_end": 33234048, "loss_sum": 26779.793701171875, "token_normalized_loss": 0.4026552249529662, "grad_norm_before_clip": 0.0818929523229599, "learning_rates_at_step": { "lora": 5.263949865219519e-05, "row_tokens": 5.263949865219519e-05 }, "learning_rates_after_step": { "lora": 5.2479430740168357e-05, "row_tokens": 5.2479430740168357e-05 } }, { "update_id": 507, "row_count": 8, "row_ids_sha256": "1842741689e1e740c6dcbfb5bd6ce2d4def886edf5e4761cb7be90976fca66c0", "input_ids_vector_sha256": "7d4186fcedf99e16f159cd996e82581d4d0059c59b5671e69d87ffd2f29d240d", "labels_vector_sha256": "e4a2b0a045f0eb081b35bd28863f6e4c297f5e0a124b013ba80b08533ba7a552", "planned_active_tokens": 61992, "realized_active_tokens": 61992, "cumulative_start": 33234048, "cumulative_end": 33296040, "loss_sum": 22985.999755859375, "token_normalized_loss": 0.37078977538810454, "grad_norm_before_clip": 0.08428304642438889, "learning_rates_at_step": { "lora": 5.2479430740168357e-05, "row_tokens": 5.2479430740168357e-05 }, "learning_rates_after_step": { "lora": 5.2307929586676975e-05, "row_tokens": 5.2307929586676975e-05 } }, { "update_id": 508, "row_count": 10, "row_ids_sha256": "1b76b910a0a7037f0772a95dc29f2e1cf8ad1c5afc55d220a1c78df8759a123d", "input_ids_vector_sha256": "47ecaa05bf46adb1b7a7cc95cf9dc33000dfc9c43b1e4c6aa6b6f4eb69fcef11", "labels_vector_sha256": "ac544518c0ac3efa1650b427f96d58d57b4ba89311080ed5cfbb9cbdccd6121f", "planned_active_tokens": 66409, "realized_active_tokens": 66409, "cumulative_start": 33296040, "cumulative_end": 33362449, "loss_sum": 21949.224731445312, "token_normalized_loss": 0.3305158145950897, "grad_norm_before_clip": 0.07667544484138489, "learning_rates_at_step": { "lora": 5.2307929586676975e-05, "row_tokens": 5.2307929586676975e-05 }, "learning_rates_after_step": { "lora": 5.2139472523582935e-05, "row_tokens": 5.2139472523582935e-05 } }, { "update_id": 509, "row_count": 9, "row_ids_sha256": "f9c1cba53b99d408481ec23d53ba9f59415fb9a6710aa60ab97479b7c27f37fc", "input_ids_vector_sha256": "444547e0acc8de924a1cfece182be749f64c9ce63936541bf5b5bebd9cca7fd5", "labels_vector_sha256": "0c40c8d4cb31e0626d36d4782a51c80c0e10fd9cc3dea39bc9df2bf73dd13e0b", "planned_active_tokens": 65220, "realized_active_tokens": 65220, "cumulative_start": 33362449, "cumulative_end": 33427669, "loss_sum": 25409.039428710938, "token_normalized_loss": 0.3895896876527283, "grad_norm_before_clip": 0.08275716751813889, "learning_rates_at_step": { "lora": 5.2139472523582935e-05, "row_tokens": 5.2139472523582935e-05 }, "learning_rates_after_step": { "lora": 5.198097614049083e-05, "row_tokens": 5.198097614049083e-05 } }, { "update_id": 510, "row_count": 9, "row_ids_sha256": "a04e275c577c74f99fb99ed0a55605ee95be0356bc5b996d06f1dad930cd4d02", "input_ids_vector_sha256": "57fc3b80d4a34389a8902f4699657031bd4be77b9b12ba0ddeb1b3049128e2fd", "labels_vector_sha256": "b266f7ef5d71650cdbd144e0cba0cc6092fb4292b9ee10b70144d5d608319a7b", "planned_active_tokens": 61355, "realized_active_tokens": 61355, "cumulative_start": 33427669, "cumulative_end": 33489024, "loss_sum": 23663.124084472656, "token_normalized_loss": 0.38567556164082234, "grad_norm_before_clip": 0.08731621503829956, "learning_rates_at_step": { "lora": 5.198097614049083e-05, "row_tokens": 5.198097614049083e-05 }, "learning_rates_after_step": { "lora": 5.1802407215761074e-05, "row_tokens": 5.1802407215761074e-05 } }, { "update_id": 511, "row_count": 9, "row_ids_sha256": "15ca2f265f0707fff4ea4a643fbeeee827aa0133b8745140834db9e3a2ffb6c5", "input_ids_vector_sha256": "3e3d0e46d09b2b087f53caa005813eabdc0251212c2939c16a86643c80ba8033", "labels_vector_sha256": "2a141f468479ded833eb9f466e8d54e3b5fb3cf570d546c27cbcbc7fa6bc2685", "planned_active_tokens": 69116, "realized_active_tokens": 69116, "cumulative_start": 33489024, "cumulative_end": 33558140, "loss_sum": 27687.737365722656, "token_normalized_loss": 0.4005980867776297, "grad_norm_before_clip": 0.08565796911716461, "learning_rates_at_step": { "lora": 5.1802407215761074e-05, "row_tokens": 5.1802407215761074e-05 }, "learning_rates_after_step": { "lora": 5.163591914833657e-05, "row_tokens": 5.163591914833657e-05 } }, { "update_id": 512, "row_count": 11, "row_ids_sha256": "31f6e1945d1da61c1221b94079dc6731998a8fd459d6cfe0428d146f6a6c8727", "input_ids_vector_sha256": "8a6adddf60bc781143da5536d65a6238ef23ae3642075b5b6fc367254b803686", "labels_vector_sha256": "5f3cfed5e922de6e9a3a02bdd9e37477c6dc3f874dbd988a974a2fd9f7897f37", "planned_active_tokens": 64432, "realized_active_tokens": 64432, "cumulative_start": 33558140, "cumulative_end": 33622572, "loss_sum": 24835.128143310547, "token_normalized_loss": 0.3854471092517778, "grad_norm_before_clip": 0.08456744998693466, "learning_rates_at_step": { "lora": 5.163591914833657e-05, "row_tokens": 5.163591914833657e-05 }, "learning_rates_after_step": { "lora": 5.1472449527323444e-05, "row_tokens": 5.1472449527323444e-05 } }, { "update_id": 513, "row_count": 8, "row_ids_sha256": "be1f1649a9f9f2a14333574eee376082999a43197aa932289d06dbb438d09909", "input_ids_vector_sha256": "3f73586002cd437e42514c2266e2d0f5ad1168bab4330c1fe18137ed906ac5a3", "labels_vector_sha256": "24c73ebc3eec86f5cc68b5121aeefaa0445dbad702a84baf34841f986af0e8da", "planned_active_tokens": 63257, "realized_active_tokens": 63257, "cumulative_start": 33622572, "cumulative_end": 33685829, "loss_sum": 24883.734130859375, "token_normalized_loss": 0.3933751858428217, "grad_norm_before_clip": 0.08275662362575531, "learning_rates_at_step": { "lora": 5.1472449527323444e-05, "row_tokens": 5.1472449527323444e-05 }, "learning_rates_after_step": { "lora": 5.1301337046427235e-05, "row_tokens": 5.1301337046427235e-05 } }, { "update_id": 514, "row_count": 11, "row_ids_sha256": "3f668da78bd44ae7307a17575fb0b9336791530ec7a1a81d64e3c43c106eb781", "input_ids_vector_sha256": "e998494e56352e148b2af6c50b6554ee4cad654863c39f952cc5d40a709b6f73", "labels_vector_sha256": "53ed15510b8ccf537aab1bbd8b32f8e51817175b00a34d04fe5ff9b822c50beb", "planned_active_tokens": 66208, "realized_active_tokens": 66208, "cumulative_start": 33685829, "cumulative_end": 33752037, "loss_sum": 25441.181640625, "token_normalized_loss": 0.3842614433395511, "grad_norm_before_clip": 0.08378835022449493, "learning_rates_at_step": { "lora": 5.1301337046427235e-05, "row_tokens": 5.1301337046427235e-05 }, "learning_rates_after_step": { "lora": 5.1130248084863274e-05, "row_tokens": 5.1130248084863274e-05 } }, { "update_id": 515, "row_count": 9, "row_ids_sha256": "2393a441ecd9eeaa3933cefbbbe7e849cc129c06a0b36c63932fc90c4ff12131", "input_ids_vector_sha256": "b9c11a7afdb33470957c031cfcf39a6a9b6626175355cb1c9b70e5b87c84dd54", "labels_vector_sha256": "230f715c4eb0452b80272ce687d1829d09567aa50460f2ebcbaa8885d57cbe9e", "planned_active_tokens": 66193, "realized_active_tokens": 66193, "cumulative_start": 33752037, "cumulative_end": 33818230, "loss_sum": 27077.610717773438, "token_normalized_loss": 0.4090706074324088, "grad_norm_before_clip": 0.08551423996686935, "learning_rates_at_step": { "lora": 5.1130248084863274e-05, "row_tokens": 5.1130248084863274e-05 }, "learning_rates_after_step": { "lora": 5.096184460865815e-05, "row_tokens": 5.096184460865815e-05 } }, { "update_id": 516, "row_count": 12, "row_ids_sha256": "2f2c5d3f48e738d58b9a50be6b88a8637a7325691f6c328034647fd525c1f378", "input_ids_vector_sha256": "7a2f60101f07ca62d6cf81be2dc3ac82386838c257681970cebb229ccbdb2866", "labels_vector_sha256": "432bf180dc79fcae150e2818607c479b43b9efeccf52b9d32cdc2a7c09c2d05d", "planned_active_tokens": 65149, "realized_active_tokens": 65149, "cumulative_start": 33818230, "cumulative_end": 33883379, "loss_sum": 22556.779418945312, "token_normalized_loss": 0.34623370149879984, "grad_norm_before_clip": 0.07985607534646988, "learning_rates_at_step": { "lora": 5.096184460865815e-05, "row_tokens": 5.096184460865815e-05 }, "learning_rates_after_step": { "lora": 5.079353362216711e-05, "row_tokens": 5.079353362216711e-05 } }, { "update_id": 517, "row_count": 9, "row_ids_sha256": "b763ecc7594374b9cffad267e3fc4103fa6f73bfa4b6bad9b40da8014b48a44b", "input_ids_vector_sha256": "5d005191ec0af078b1ceee6f890504c1706a26565982de7767b96fdd58151b37", "labels_vector_sha256": "e621dc1a6d6085aaa0c74061f847139cc9f8877d7a40637c07e471ac897c814f", "planned_active_tokens": 65109, "realized_active_tokens": 65109, "cumulative_start": 33883379, "cumulative_end": 33948488, "loss_sum": 24636.485473632812, "token_normalized_loss": 0.3783883253257278, "grad_norm_before_clip": 0.08041095733642578, "learning_rates_at_step": { "lora": 5.079353362216711e-05, "row_tokens": 5.079353362216711e-05 }, "learning_rates_after_step": { "lora": 5.061785339253879e-05, "row_tokens": 5.061785339253879e-05 } }, { "update_id": 518, "row_count": 8, "row_ids_sha256": "e2577d6c72765f65b5e0f63995f4b52ea6d92bc27700ccff71ba1990bb041a85", "input_ids_vector_sha256": "ffea4c4cce196639e30668102a42cd130e0b2d93b1ddd460bd15ab176d860318", "labels_vector_sha256": "6aa3b68c975b3b40c35d66338f07d2638e1a5b0b055ac7e7cc84fe8b96ea7146", "planned_active_tokens": 67956, "realized_active_tokens": 67956, "cumulative_start": 33948488, "cumulative_end": 34016444, "loss_sum": 28425.744018554688, "token_normalized_loss": 0.4182963096496952, "grad_norm_before_clip": 0.08060774952173233, "learning_rates_at_step": { "lora": 5.061785339253879e-05, "row_tokens": 5.061785339253879e-05 }, "learning_rates_after_step": { "lora": 5.0439631877105296e-05, "row_tokens": 5.0439631877105296e-05 } }, { "update_id": 519, "row_count": 11, "row_ids_sha256": "ea5152a66a49f7594e8def38eeec49aa310850181e9174878db1e8475c0cb0d4", "input_ids_vector_sha256": "0521c93a1ccb2743f6fda8b148f3eeb3b465aecac5d36eb319a404541a2ca400", "labels_vector_sha256": "702eb7777c5784d3aafadca95fe400f07e34172bd577af6fe64074c69cff27e2", "planned_active_tokens": 68936, "realized_active_tokens": 68936, "cumulative_start": 34016444, "cumulative_end": 34085380, "loss_sum": 23157.00079345703, "token_normalized_loss": 0.3359202853872727, "grad_norm_before_clip": 0.07496102154254913, "learning_rates_at_step": { "lora": 5.0439631877105296e-05, "row_tokens": 5.0439631877105296e-05 }, "learning_rates_after_step": { "lora": 5.026487442066145e-05, "row_tokens": 5.026487442066145e-05 } }, { "update_id": 520, "row_count": 7, "row_ids_sha256": "530858366212107226904d86a347c41613897711235e5b505e328bd3564b6a60", "input_ids_vector_sha256": "90d84b34a7bb8e2cc8383d176feedaf06111a5fd58c28bc01310fc989200d2f2", "labels_vector_sha256": "6b93bc21374f0d0f4cf69c3f2e7aa3333cb838a9326e89ac6d595bdf7b56044d", "planned_active_tokens": 67594, "realized_active_tokens": 67594, "cumulative_start": 34085380, "cumulative_end": 34152974, "loss_sum": 28621.361450195312, "token_normalized_loss": 0.423430503449941, "grad_norm_before_clip": 0.08354004472494125, "learning_rates_at_step": { "lora": 5.026487442066145e-05, "row_tokens": 5.026487442066145e-05 }, "learning_rates_after_step": { "lora": 5.010907290124775e-05, "row_tokens": 5.010907290124775e-05 } }, { "update_id": 521, "row_count": 11, "row_ids_sha256": "be7000c6384d44cefebe83eacf49d4d2fd73a33f2c5fa754e1144d8a2b7f5ab4", "input_ids_vector_sha256": "0c5fe4f9ed971413dc82987db9be988781f58e5cffcc3a578d03ec05341eee95", "labels_vector_sha256": "b0c4b19f842330c19af30b4e0820b200cefe2270f3ba9e9ee82bdf0d6db3add2", "planned_active_tokens": 60261, "realized_active_tokens": 60261, "cumulative_start": 34152974, "cumulative_end": 34213235, "loss_sum": 20889.000427246094, "token_normalized_loss": 0.3466421139251936, "grad_norm_before_clip": 0.08067072182893753, "learning_rates_at_step": { "lora": 5.010907290124775e-05, "row_tokens": 5.010907290124775e-05 }, "learning_rates_after_step": { "lora": 4.99351591558245e-05, "row_tokens": 4.99351591558245e-05 } }, { "update_id": 522, "row_count": 10, "row_ids_sha256": "943f54624884c64323531d72dad1f56b8e4b21781d390d5af2c44592bf4f153f", "input_ids_vector_sha256": "50ebeab33055e6257ed23b14e9f6b78a1c80f3959473caa12c398a187aed4a7a", "labels_vector_sha256": "a0e0da8ea0a319112e636791a609679fc0559d36d6a9593958be683207987dff", "planned_active_tokens": 67266, "realized_active_tokens": 67266, "cumulative_start": 34213235, "cumulative_end": 34280501, "loss_sum": 25897.411743164062, "token_normalized_loss": 0.3850000259144897, "grad_norm_before_clip": 0.0816662386059761, "learning_rates_at_step": { "lora": 4.99351591558245e-05, "row_tokens": 4.99351591558245e-05 }, "learning_rates_after_step": { "lora": 4.977820149067782e-05, "row_tokens": 4.977820149067782e-05 } }, { "update_id": 523, "row_count": 11, "row_ids_sha256": "e10763fff25c3f39765bfdbb148917a6838bcdcc29089e3087e5bfcc7a92a011", "input_ids_vector_sha256": "8031b0a1bc27fad6d9e0548fdf5517d5d83a98c4949e6ae1621e759aeab73d61", "labels_vector_sha256": "b2632663ee68861026e5e33176a5c63d431686f897c197a03c1c188670f6371c", "planned_active_tokens": 60708, "realized_active_tokens": 60708, "cumulative_start": 34280501, "cumulative_end": 34341209, "loss_sum": 22198.497680664062, "token_normalized_loss": 0.3656601713227921, "grad_norm_before_clip": 0.08062628656625748, "learning_rates_at_step": { "lora": 4.977820149067782e-05, "row_tokens": 4.977820149067782e-05 }, "learning_rates_after_step": { "lora": 4.958760758698229e-05, "row_tokens": 4.958760758698229e-05 } }, { "update_id": 524, "row_count": 11, "row_ids_sha256": "e41ee493a2b2f55e66d880cbbe42378ddb6babff56f117751cf314ad7e4f1092", "input_ids_vector_sha256": "6a52942d79ed60961f3dd801c368a5cf2c9faf22be0ff08eeac07e0a53171c24", "labels_vector_sha256": "620ff6a61bd102af30893042bd34f772b7d94820a0612f791ce3ddd33e7971c0", "planned_active_tokens": 73719, "realized_active_tokens": 73719, "cumulative_start": 34341209, "cumulative_end": 34414928, "loss_sum": 25534.67645263672, "token_normalized_loss": 0.3463784974380651, "grad_norm_before_clip": 0.07400960475206375, "learning_rates_at_step": { "lora": 4.958760758698229e-05, "row_tokens": 4.958760758698229e-05 }, "learning_rates_after_step": { "lora": 4.943266561716639e-05, "row_tokens": 4.943266561716639e-05 } }, { "update_id": 525, "row_count": 9, "row_ids_sha256": "245bb36cfbdc988c6fc93e072a9a64687ef747d408d14bb166bf3b7feb50ed41", "input_ids_vector_sha256": "a230ecf697ffad5ad559c8e6521f4cc7e9de796229b5e05a4d334d2090881fd5", "labels_vector_sha256": "a1465a0a2f4183951a2cfa0b8ed0f36b576aa3325f662239111d6907d7bd2b37", "planned_active_tokens": 59931, "realized_active_tokens": 59931, "cumulative_start": 34414928, "cumulative_end": 34474859, "loss_sum": 23833.542053222656, "token_normalized_loss": 0.39768303637888, "grad_norm_before_clip": 0.08422190696001053, "learning_rates_at_step": { "lora": 4.943266561716639e-05, "row_tokens": 4.943266561716639e-05 }, "learning_rates_after_step": { "lora": 4.925600318885446e-05, "row_tokens": 4.925600318885446e-05 } }, { "update_id": 526, "row_count": 12, "row_ids_sha256": "1f40f2b8e8f1a6a08cc91edaa80d9e9d03307dbd336811492938d666351cc6de", "input_ids_vector_sha256": "64fea584671e16de9a95d048dda48db140e9043498f158cfb77774e619a4508a", "labels_vector_sha256": "8baec3f64eb0a43e5a947bfbf20a9a5da247972e92731ca2e11a738125d8dbd6", "planned_active_tokens": 68335, "realized_active_tokens": 68335, "cumulative_start": 34474859, "cumulative_end": 34543194, "loss_sum": 23999.291900634766, "token_normalized_loss": 0.3512005838974869, "grad_norm_before_clip": 0.07561564445495605, "learning_rates_at_step": { "lora": 4.925600318885446e-05, "row_tokens": 4.925600318885446e-05 }, "learning_rates_after_step": { "lora": 4.90952505919425e-05, "row_tokens": 4.90952505919425e-05 } }, { "update_id": 527, "row_count": 12, "row_ids_sha256": "24d1b7468c9c38fd7fecf33437627dc68528f869eacac6c2666ba61635d09629", "input_ids_vector_sha256": "4896b5bd14db55f1ec5ad8d94bc1c463d8ce41aa18c4f8b0d0e75fefe5f48732", "labels_vector_sha256": "d1b7c95045dc4247ba322d59e70f8012eb1d3d0b8cd95d945f2e59c09189ea3e", "planned_active_tokens": 62184, "realized_active_tokens": 62184, "cumulative_start": 34543194, "cumulative_end": 34605378, "loss_sum": 21465.720947265625, "token_normalized_loss": 0.34519685043203435, "grad_norm_before_clip": 0.07906069606542587, "learning_rates_at_step": { "lora": 4.90952505919425e-05, "row_tokens": 4.90952505919425e-05 }, "learning_rates_after_step": { "lora": 4.89269259166805e-05, "row_tokens": 4.89269259166805e-05 } }, { "update_id": 528, "row_count": 12, "row_ids_sha256": "3c4cd48019bd448c7a54639c97a8033b5f0a3f83b1d8141d9fe84ea2dc76fa93", "input_ids_vector_sha256": "24105dd00c40bb4fc9643a56c38770bd5e96b413fad8bed3f1cdf1c8a6c7e2af", "labels_vector_sha256": "8e663b7bab6682e709195fea660a2586acdda37c13a3adc2714018d166971950", "planned_active_tokens": 65117, "realized_active_tokens": 65117, "cumulative_start": 34605378, "cumulative_end": 34670495, "loss_sum": 22874.84893798828, "token_normalized_loss": 0.3512884337114468, "grad_norm_before_clip": 0.07699145376682281, "learning_rates_at_step": { "lora": 4.89269259166805e-05, "row_tokens": 4.89269259166805e-05 }, "learning_rates_after_step": { "lora": 4.875498195314795e-05, "row_tokens": 4.875498195314795e-05 } }, { "update_id": 529, "row_count": 12, "row_ids_sha256": "45b594fb3adb0517202c556f51b65c91dc1fcc7998efb4dd5726939d603a9247", "input_ids_vector_sha256": "7cdbeb9610a7f9047f6c5375ea4a6d27fc7009de617afeed2ed963c5d6d0fee8", "labels_vector_sha256": "eae068bcb94a2180776444b7ca8bf1d7aa75841119dcc77785bd101cfa156e55", "planned_active_tokens": 66522, "realized_active_tokens": 66522, "cumulative_start": 34670495, "cumulative_end": 34737017, "loss_sum": 23909.705017089844, "token_normalized_loss": 0.3594255286535258, "grad_norm_before_clip": 0.07852213084697723, "learning_rates_at_step": { "lora": 4.875498195314795e-05, "row_tokens": 4.875498195314795e-05 }, "learning_rates_after_step": { "lora": 4.859170023164058e-05, "row_tokens": 4.859170023164058e-05 } }, { "update_id": 530, "row_count": 10, "row_ids_sha256": "2f5809f6fd1c1b04ae56d8cb4150d68ea4ab44587fbf4d546752d60cd7734e2e", "input_ids_vector_sha256": "8782fb25113b404b041f85309f2008f6a11201b7e5433f141f853c012503fd98", "labels_vector_sha256": "932dfc5d95b49a3a65f81e20c87c13202f80c98e639570e381dbaf1b4059e48d", "planned_active_tokens": 63176, "realized_active_tokens": 63176, "cumulative_start": 34737017, "cumulative_end": 34800193, "loss_sum": 26061.774047851562, "token_normalized_loss": 0.4125264981615101, "grad_norm_before_clip": 0.08721365034580231, "learning_rates_at_step": { "lora": 4.859170023164058e-05, "row_tokens": 4.859170023164058e-05 }, "learning_rates_after_step": { "lora": 4.8416755641374056e-05, "row_tokens": 4.8416755641374056e-05 } }, { "update_id": 531, "row_count": 12, "row_ids_sha256": "cc161e88163596c17c9620d2ddd54ad1073db4bce71e99a25c30dd4be8b5171d", "input_ids_vector_sha256": "5445ffea8465ef2c99b8d238ecb6d87907f84bd91292365792e300e3735237a3", "labels_vector_sha256": "122856d5946df458f1e1cec7e998099d76a0b7bf7c819199c5c12832e1e45dcf", "planned_active_tokens": 67695, "realized_active_tokens": 67695, "cumulative_start": 34800193, "cumulative_end": 34867888, "loss_sum": 24376.494201660156, "token_normalized_loss": 0.36009297882650354, "grad_norm_before_clip": 0.07703524827957153, "learning_rates_at_step": { "lora": 4.8416755641374056e-05, "row_tokens": 4.8416755641374056e-05 }, "learning_rates_after_step": { "lora": 4.8249954147310733e-05, "row_tokens": 4.8249954147310733e-05 } }, { "update_id": 532, "row_count": 10, "row_ids_sha256": "bd9c0e137c5d6b8eccde32e892c4a18a8b3a7e79fd7efe9909331cf0f7e7166f", "input_ids_vector_sha256": "5a77acb8bfabef54bf72324c7dcb4e2ad57057199cc2d853f551a5b516c916c9", "labels_vector_sha256": "1333f3bd9c07e98f79c8817ec844aace87f8adbea9cdf20116931b5ffb0b63a3", "planned_active_tokens": 64551, "realized_active_tokens": 64551, "cumulative_start": 34867888, "cumulative_end": 34932439, "loss_sum": 21162.390625, "token_normalized_loss": 0.32783985724465925, "grad_norm_before_clip": 0.08049342036247253, "learning_rates_at_step": { "lora": 4.8249954147310733e-05, "row_tokens": 4.8249954147310733e-05 }, "learning_rates_after_step": { "lora": 4.808385937949344e-05, "row_tokens": 4.808385937949344e-05 } }, { "update_id": 533, "row_count": 9, "row_ids_sha256": "37c55f83fc758aabe421933d5259abfe260df41069c5d74056ce6f0de6068449", "input_ids_vector_sha256": "fabe8a86d5b0a598fabbe41d3ee58a6e9c1cb67226d1a241a7b6a9e0a8f2c910", "labels_vector_sha256": "064dc21b1c06c6b8e5bcfe67c91a8ecd29eaa46626ab75b16edfeadcb7708b69", "planned_active_tokens": 64285, "realized_active_tokens": 64285, "cumulative_start": 34932439, "cumulative_end": 34996724, "loss_sum": 23648.243896484375, "token_normalized_loss": 0.3678656591193027, "grad_norm_before_clip": 0.08237971365451813, "learning_rates_at_step": { "lora": 4.808385937949344e-05, "row_tokens": 4.808385937949344e-05 }, "learning_rates_after_step": { "lora": 4.7907184290501744e-05, "row_tokens": 4.7907184290501744e-05 } }, { "update_id": 534, "row_count": 10, "row_ids_sha256": "288aef74d6b8b6b6428a5a3493b755b324b40d5c0c5da9a957c311dd787df0c6", "input_ids_vector_sha256": "01223c7a329d97d75bef902bfab111e3ba72e660a9f2dcd34ca11c655814c774", "labels_vector_sha256": "83fcb27ac39756adb97a1196abd538bb99ffc28423ed1a52a9b7998f7ba8219d", "planned_active_tokens": 68389, "realized_active_tokens": 68389, "cumulative_start": 34996724, "cumulative_end": 35065113, "loss_sum": 24604.572814941406, "token_normalized_loss": 0.3597738351919374, "grad_norm_before_clip": 0.08349286764860153, "learning_rates_at_step": { "lora": 4.7907184290501744e-05, "row_tokens": 4.7907184290501744e-05 }, "learning_rates_after_step": { "lora": 4.7740727148819144e-05, "row_tokens": 4.7740727148819144e-05 } }, { "update_id": 535, "row_count": 11, "row_ids_sha256": "84a9ebed3efeaa1830b6c0456db38007890c7fbbcfc3d112d9b232c4c5ee11e1", "input_ids_vector_sha256": "1d8e36d446db8347c0ce88f9ceefe91df499e140e03f2639cb5e049c78fd427e", "labels_vector_sha256": "db321f8facd65c9ff11696c35c28d2c380e197317c88aee70153871ecc50e42d", "planned_active_tokens": 64443, "realized_active_tokens": 64443, "cumulative_start": 35065113, "cumulative_end": 35129556, "loss_sum": 21598.047912597656, "token_normalized_loss": 0.3351496347562599, "grad_norm_before_clip": 0.07596445828676224, "learning_rates_at_step": { "lora": 4.7740727148819144e-05, "row_tokens": 4.7740727148819144e-05 }, "learning_rates_after_step": { "lora": 4.7557643785354215e-05, "row_tokens": 4.7557643785354215e-05 } }, { "update_id": 536, "row_count": 10, "row_ids_sha256": "0adcfa2d626800589a666188b601d9cbb40dcd05446261ba00d268ad8e5e7922", "input_ids_vector_sha256": "04565e1e5d5092b04db8e34ed31012412d48ae89a3d4380eac21271d017a0d46", "labels_vector_sha256": "611c1f879d9f02718464f6778140010574315fc59f5ebf868025c80d762c7046", "planned_active_tokens": 70891, "realized_active_tokens": 70891, "cumulative_start": 35129556, "cumulative_end": 35200447, "loss_sum": 26144.0830078125, "token_normalized_loss": 0.368792695939012, "grad_norm_before_clip": 0.08033650368452072, "learning_rates_at_step": { "lora": 4.7557643785354215e-05, "row_tokens": 4.7557643785354215e-05 }, "learning_rates_after_step": { "lora": 4.739861293886877e-05, "row_tokens": 4.739861293886877e-05 } }, { "update_id": 537, "row_count": 10, "row_ids_sha256": "764dbabf347af9db8d3a46fcb1f3443cb53db8034552125ae2bfe9ba15d8a992", "input_ids_vector_sha256": "0fdaad0d449fb7e0cc25e9be07a3c158376e74ac8f484e7f89a8fdaf83ff08d8", "labels_vector_sha256": "4bda368d5ca7b1ddc3212f35d5e0a035c60b17dadc3816a4436971a1a10a070d", "planned_active_tokens": 61588, "realized_active_tokens": 61588, "cumulative_start": 35200447, "cumulative_end": 35262035, "loss_sum": 22257.24188232422, "token_normalized_loss": 0.36138926223167206, "grad_norm_before_clip": 0.08157128095626831, "learning_rates_at_step": { "lora": 4.739861293886877e-05, "row_tokens": 4.739861293886877e-05 }, "learning_rates_after_step": { "lora": 4.7231004306538655e-05, "row_tokens": 4.7231004306538655e-05 } }, { "update_id": 538, "row_count": 10, "row_ids_sha256": "4c1fb9dbc8b2344462464866e58a80eb62433dba3a154c320aff7c665e7365b6", "input_ids_vector_sha256": "4e8e090f138afe60d32fc2ac2d84a413eb6e0cb6865eca64eb0afd39530c97d0", "labels_vector_sha256": "33aae204d7f80f76264877374cf27122c047691fff52e484aee5e396bab35ef4", "planned_active_tokens": 64921, "realized_active_tokens": 64921, "cumulative_start": 35262035, "cumulative_end": 35326956, "loss_sum": 21984.49090576172, "token_normalized_loss": 0.33863450818320295, "grad_norm_before_clip": 0.07825275510549545, "learning_rates_at_step": { "lora": 4.7231004306538655e-05, "row_tokens": 4.7231004306538655e-05 }, "learning_rates_after_step": { "lora": 4.706517163835271e-05, "row_tokens": 4.706517163835271e-05 } }, { "update_id": 539, "row_count": 11, "row_ids_sha256": "ac4ff893a2ce70e15448ea42c92b2aae3156cff49e83c22fa456ba4ba7fc1ecd", "input_ids_vector_sha256": "19cd6e27380c5006f9c0b53fe74eab5bfa05d99d5d5ada3260b0b385c3553d98", "labels_vector_sha256": "ace153338d85925e0654558556e9bbf457e13f5a473fb0a4cb68cadc75ed4c8e", "planned_active_tokens": 64245, "realized_active_tokens": 64245, "cumulative_start": 35326956, "cumulative_end": 35391201, "loss_sum": 22071.954010009766, "token_normalized_loss": 0.34355909424873166, "grad_norm_before_clip": 0.08327807486057281, "learning_rates_at_step": { "lora": 4.706517163835271e-05, "row_tokens": 4.706517163835271e-05 }, "learning_rates_after_step": { "lora": 4.6877778123557855e-05, "row_tokens": 4.6877778123557855e-05 } }, { "update_id": 540, "row_count": 9, "row_ids_sha256": "332907b314c1b12cc995bc4639db9ce6b71788c11b8335e098627787cfc773f9", "input_ids_vector_sha256": "4a9c73fc7e188e55067e120af5df263aff79182e18b3f66e99896ed1fece765d", "labels_vector_sha256": "ef0ea16bb9612cf0c6edc62526efa0d67f46eb2825f97e065093ce0fef99bcc4", "planned_active_tokens": 72613, "realized_active_tokens": 72613, "cumulative_start": 35391201, "cumulative_end": 35463814, "loss_sum": 26662.71112060547, "token_normalized_loss": 0.3671892239764983, "grad_norm_before_clip": 0.08063008636236191, "learning_rates_at_step": { "lora": 4.6877778123557855e-05, "row_tokens": 4.6877778123557855e-05 }, "learning_rates_after_step": { "lora": 4.672775143414735e-05, "row_tokens": 4.672775143414735e-05 } }, { "update_id": 541, "row_count": 11, "row_ids_sha256": "24be62eed43fd49b768e7517d4d2ee01ab8fa7e67e31687f0a2ab0f689f02584", "input_ids_vector_sha256": "cdc5addda337ae5a7fd1559f64178a247c7058b23c9978920eb9fac3f5e25891", "labels_vector_sha256": "2b4d5da0d595ac5f4df5c4e6bf32e65a75366003752ef7b3fb4147de94d428d1", "planned_active_tokens": 58146, "realized_active_tokens": 58146, "cumulative_start": 35463814, "cumulative_end": 35521960, "loss_sum": 21097.77166748047, "token_normalized_loss": 0.36284132472535463, "grad_norm_before_clip": 0.08546759933233261, "learning_rates_at_step": { "lora": 4.672775143414735e-05, "row_tokens": 4.672775143414735e-05 }, "learning_rates_after_step": { "lora": 4.654511273869639e-05, "row_tokens": 4.654511273869639e-05 } }, { "update_id": 542, "row_count": 9, "row_ids_sha256": "a4c81e24e352c8a1fc6f747d35a432ef476d84039054b4e2ad262a9577195caf", "input_ids_vector_sha256": "759e406107747f6812b4a693aebcfa7932dafeebd690466f657c388cd1eaae57", "labels_vector_sha256": "580e63dac51760e5ebd0e7a878055360d1db391f1715361ed80847bce5e2520a", "planned_active_tokens": 70801, "realized_active_tokens": 70801, "cumulative_start": 35521960, "cumulative_end": 35592761, "loss_sum": 27598.937622070312, "token_normalized_loss": 0.38980999734566335, "grad_norm_before_clip": 0.07894737273454666, "learning_rates_at_step": { "lora": 4.654511273869639e-05, "row_tokens": 4.654511273869639e-05 }, "learning_rates_after_step": { "lora": 4.638133933085478e-05, "row_tokens": 4.638133933085478e-05 } }, { "update_id": 543, "row_count": 12, "row_ids_sha256": "c92531b3fd670d46d84707da87cef14422fbfcbf3242f3761684b04900c19f8f", "input_ids_vector_sha256": "dd50270c2f1a10ca6a1ff28041c2eecbbdda1ac0841a0420a5d938a95f88ff04", "labels_vector_sha256": "4860967c06d5139746e8e7b1234f210e6e540fc0d6dc38e7e08b4b87e150d021", "planned_active_tokens": 63503, "realized_active_tokens": 63503, "cumulative_start": 35592761, "cumulative_end": 35656264, "loss_sum": 23190.482666015625, "token_normalized_loss": 0.36518719849480535, "grad_norm_before_clip": 0.07985240966081619, "learning_rates_at_step": { "lora": 4.638133933085478e-05, "row_tokens": 4.638133933085478e-05 }, "learning_rates_after_step": { "lora": 4.6209656843137374e-05, "row_tokens": 4.6209656843137374e-05 } }, { "update_id": 544, "row_count": 12, "row_ids_sha256": "ab329012c2e75ec16f880cfd51794b886f6d2c15551cbff4aa8b3bce98f3d5df", "input_ids_vector_sha256": "128cd6d13017c04d87fd47fb5950881d7be5823b8968dfbae8d9ad84470ab67f", "labels_vector_sha256": "23653922ebaa8276edabbeebe259685f96317bb5257b3e22c95a389ce0bcddb0", "planned_active_tokens": 66586, "realized_active_tokens": 66586, "cumulative_start": 35656264, "cumulative_end": 35722850, "loss_sum": 21226.878540039062, "token_normalized_loss": 0.3187889126849347, "grad_norm_before_clip": 0.07647187262773514, "learning_rates_at_step": { "lora": 4.6209656843137374e-05, "row_tokens": 4.6209656843137374e-05 }, "learning_rates_after_step": { "lora": 4.604931327225352e-05, "row_tokens": 4.604931327225352e-05 } }, { "update_id": 545, "row_count": 10, "row_ids_sha256": "d599930611b7aa2fd1266a60b93b8862ce14c074b302a5533ac17ffb69b4c0ac", "input_ids_vector_sha256": "77f6adb4ec1d4e06ae5e06feda84f7b5838b77b6636fca3bdcc24cecea72f307", "labels_vector_sha256": "d8fc645b8f8e49d5fc453b9aeb62c4a227d32d639660c68ae439dae6f894087b", "planned_active_tokens": 62204, "realized_active_tokens": 62204, "cumulative_start": 35722850, "cumulative_end": 35785054, "loss_sum": 19824.065063476562, "token_normalized_loss": 0.3186943775878812, "grad_norm_before_clip": 0.08160311728715897, "learning_rates_at_step": { "lora": 4.604931327225352e-05, "row_tokens": 4.604931327225352e-05 }, "learning_rates_after_step": { "lora": 4.5884686870325824e-05, "row_tokens": 4.5884686870325824e-05 } }, { "update_id": 546, "row_count": 12, "row_ids_sha256": "86d9b40c07d0c4297cc23d504ca218b8994b98170b2315ed8c7f2832de4e25fa", "input_ids_vector_sha256": "3e9e05398929fa110037f5373dbefa6185ef733a6c6b45025004306bfa6a344e", "labels_vector_sha256": "80e34c0e1cb15129c9373079d3c6827220eacaf3bbee6ad8aa3a0cb3a912c56b", "planned_active_tokens": 63882, "realized_active_tokens": 63882, "cumulative_start": 35785054, "cumulative_end": 35848936, "loss_sum": 17925.896362304688, "token_normalized_loss": 0.2806095044348124, "grad_norm_before_clip": 0.07216978073120117, "learning_rates_at_step": { "lora": 4.5884686870325824e-05, "row_tokens": 4.5884686870325824e-05 }, "learning_rates_after_step": { "lora": 4.569846243487447e-05, "row_tokens": 4.569846243487447e-05 } }, { "update_id": 547, "row_count": 10, "row_ids_sha256": "1e25db58ed41aa4aeee8de14a7d4c6a23245cf3921dd5dbe988d03a020a764a0", "input_ids_vector_sha256": "88593bf861d1a48811d35ccbf0b3d35f9e696ae4b1c8cad3ee99ba119c7e2376", "labels_vector_sha256": "fec2e78c8807515c8fa6a5ec7f7c9a42dc9d2ab5779e3158666173ade72562ff", "planned_active_tokens": 72284, "realized_active_tokens": 72284, "cumulative_start": 35848936, "cumulative_end": 35921220, "loss_sum": 23874.688903808594, "token_normalized_loss": 0.33029009052914327, "grad_norm_before_clip": 0.07209910452365875, "learning_rates_at_step": { "lora": 4.569846243487447e-05, "row_tokens": 4.569846243487447e-05 }, "learning_rates_after_step": { "lora": 4.5541775241203294e-05, "row_tokens": 4.5541775241203294e-05 } }, { "update_id": 548, "row_count": 8, "row_ids_sha256": "bac354c01445ee6d6a4f5cfd970f4f18f82103926eadafb49f56b571e4fb6a1d", "input_ids_vector_sha256": "5549dbef5734e0ee6eb1d301497cc5dc9cb6d0e235224dc5e9aef1eb25fd0aa1", "labels_vector_sha256": "0ae0d851dc6906db5ce2ec9ed2a9e15714dd9e1d440b015b4dcbb14ff91622a9", "planned_active_tokens": 60837, "realized_active_tokens": 60837, "cumulative_start": 35921220, "cumulative_end": 35982057, "loss_sum": 19385.711791992188, "token_normalized_loss": 0.31865002863376213, "grad_norm_before_clip": 0.08199416100978851, "learning_rates_at_step": { "lora": 4.5541775241203294e-05, "row_tokens": 4.5541775241203294e-05 }, "learning_rates_after_step": { "lora": 4.536630827768361e-05, "row_tokens": 4.536630827768361e-05 } }, { "update_id": 549, "row_count": 12, "row_ids_sha256": "80e1e025f3f968e050e2895571157b224f40015d76ee30dc1922949315c7260b", "input_ids_vector_sha256": "e248deaacedc3e028e4d71318a617ad1d0bcac2ecd4e98290fb9e49710036c7c", "labels_vector_sha256": "92f3e937c2bd2c859275ce3261bf245a9e585801632b08beffac6b35ae09e389", "planned_active_tokens": 68149, "realized_active_tokens": 68149, "cumulative_start": 35982057, "cumulative_end": 36050206, "loss_sum": 22447.57992553711, "token_normalized_loss": 0.3293897184923786, "grad_norm_before_clip": 0.07779020816087723, "learning_rates_at_step": { "lora": 4.536630827768361e-05, "row_tokens": 4.536630827768361e-05 }, "learning_rates_after_step": { "lora": 4.5206095465042386e-05, "row_tokens": 4.5206095465042386e-05 } }, { "update_id": 550, "row_count": 8, "row_ids_sha256": "7e431c240355be988bb913d0478e66e465abf5fad421ea3436a83eed87316a74", "input_ids_vector_sha256": "ac73935a7580270f21adc354650b7e916ba259476fe32f8b81221f402a132e36", "labels_vector_sha256": "0b0f645e908cccaacea446b9b28d1b5de70781b69fdb9ac29a078f2375d65185", "planned_active_tokens": 62244, "realized_active_tokens": 62244, "cumulative_start": 36050206, "cumulative_end": 36112450, "loss_sum": 19441.541748046875, "token_normalized_loss": 0.3123440291119927, "grad_norm_before_clip": 0.07674456387758255, "learning_rates_at_step": { "lora": 4.5206095465042386e-05, "row_tokens": 4.5206095465042386e-05 }, "learning_rates_after_step": { "lora": 4.5036114826226896e-05, "row_tokens": 4.5036114826226896e-05 } }, { "update_id": 551, "row_count": 12, "row_ids_sha256": "51c057149005b6e7365a196b9a833b02b5a73f7051a326d4b1d28295b290bb06", "input_ids_vector_sha256": "f8355c5e2df6feaa9ea2d0b0419978241de7424e6601b29feb8569aab00abdc2", "labels_vector_sha256": "82a2e8b831a7cd4d7c03e077d3c2c22ddfcc1c324efb30ffe4acb8f73d15d363", "planned_active_tokens": 66060, "realized_active_tokens": 66060, "cumulative_start": 36112450, "cumulative_end": 36178510, "loss_sum": 21149.780029296875, "token_normalized_loss": 0.3201601578761259, "grad_norm_before_clip": 0.07579418271780014, "learning_rates_at_step": { "lora": 4.5036114826226896e-05, "row_tokens": 4.5036114826226896e-05 }, "learning_rates_after_step": { "lora": 4.4870361013893295e-05, "row_tokens": 4.4870361013893295e-05 } }, { "update_id": 552, "row_count": 8, "row_ids_sha256": "3b8619feb1430ae3ac6cde5d852b80aa3e1081ac240986c0092030d5093f313e", "input_ids_vector_sha256": "e50d2e2fe807168b5bdd3e538210bf2c9a35494631d692cd292b43631f00d012", "labels_vector_sha256": "3d4345e9fc423884479cad0414f1c7da6ed9863315b583bf70f2bbcc46745a3f", "planned_active_tokens": 64439, "realized_active_tokens": 64439, "cumulative_start": 36178510, "cumulative_end": 36242949, "loss_sum": 21539.058471679688, "token_normalized_loss": 0.33425500817330633, "grad_norm_before_clip": 0.07901498675346375, "learning_rates_at_step": { "lora": 4.4870361013893295e-05, "row_tokens": 4.4870361013893295e-05 }, "learning_rates_after_step": { "lora": 4.470064067650613e-05, "row_tokens": 4.470064067650613e-05 } }, { "update_id": 553, "row_count": 11, "row_ids_sha256": "2e71989651cbd546b241334544e70b743d43ff4512d71ce35e1557f3d0b6908d", "input_ids_vector_sha256": "05cdd4b98220b6fa66105453e181cce28da248846c299330758e372303b6f284", "labels_vector_sha256": "c12e96e6a64d3056a50e8a1e06f21ce58f7ff1b343183510ab2f21f1e2dc9926", "planned_active_tokens": 66004, "realized_active_tokens": 66004, "cumulative_start": 36242949, "cumulative_end": 36308953, "loss_sum": 23033.44842529297, "token_normalized_loss": 0.34897049308061584, "grad_norm_before_clip": 0.07968780398368835, "learning_rates_at_step": { "lora": 4.470064067650613e-05, "row_tokens": 4.470064067650613e-05 }, "learning_rates_after_step": { "lora": 4.453234414611037e-05, "row_tokens": 4.453234414611037e-05 } }, { "update_id": 554, "row_count": 11, "row_ids_sha256": "1fdd3b3e722cd7a9c40734d458827da6f92d49d414a9420c62123f11514d9080", "input_ids_vector_sha256": "e79b8878956056be422dc0e8cee92454b3d348e5c734ff83f2006f5b7ac1f1ec", "labels_vector_sha256": "65a338c076f9918bc381221db80989633bf4b8cabb38ebdc7f5910d6df81ba3c", "planned_active_tokens": 65474, "realized_active_tokens": 65474, "cumulative_start": 36308953, "cumulative_end": 36374427, "loss_sum": 24328.116302490234, "token_normalized_loss": 0.3715691160230051, "grad_norm_before_clip": 0.07973860949277878, "learning_rates_at_step": { "lora": 4.453234414611037e-05, "row_tokens": 4.453234414611037e-05 }, "learning_rates_after_step": { "lora": 4.436535624866103e-05, "row_tokens": 4.436535624866103e-05 } }, { "update_id": 555, "row_count": 9, "row_ids_sha256": "e0d8c22725303929299cc1ea6abcb1eeff909634636cb59c55ec35297e62793d", "input_ids_vector_sha256": "316aeafceb323504106014bd345a82a312255d2fae639f53b9587891452b0ccc", "labels_vector_sha256": "574dc6135507a2899c5612e3dd27148c657fd7b99c27c864487ca58d3e449fc7", "planned_active_tokens": 64989, "realized_active_tokens": 64989, "cumulative_start": 36374427, "cumulative_end": 36439416, "loss_sum": 26199.225952148438, "token_normalized_loss": 0.4031332371962707, "grad_norm_before_clip": 0.08466144651174545, "learning_rates_at_step": { "lora": 4.436535624866103e-05, "row_tokens": 4.436535624866103e-05 }, "learning_rates_after_step": { "lora": 4.4191385447861756e-05, "row_tokens": 4.4191385447861756e-05 } }, { "update_id": 556, "row_count": 11, "row_ids_sha256": "3675f89185c2c710e528da3343949100cfa50804bfbd96071e4a1558e98818d1", "input_ids_vector_sha256": "ffd2e09ad26cbc31d6d34f5cf7357af68c425f785875343ae20e901de80c37fa", "labels_vector_sha256": "568e31f312583586f8bbac504ae77754a32ff3d47f8d7748dfc3b094def43c26", "planned_active_tokens": 67733, "realized_active_tokens": 67733, "cumulative_start": 36439416, "cumulative_end": 36507149, "loss_sum": 24597.772415161133, "token_normalized_loss": 0.3631578760007844, "grad_norm_before_clip": 0.08526677638292313, "learning_rates_at_step": { "lora": 4.4191385447861756e-05, "row_tokens": 4.4191385447861756e-05 }, "learning_rates_after_step": { "lora": 4.4017095733959845e-05, "row_tokens": 4.4017095733959845e-05 } }, { "update_id": 557, "row_count": 11, "row_ids_sha256": "ce911f8c968f7a854379209b84be4c8255bc5b738f1868b5966629b5d1a494a9", "input_ids_vector_sha256": "1d363d681cfd7f1b4d0193d190316a53c2ac275c1ba11ba0ad20f955e488c42d", "labels_vector_sha256": "d1cc07929a128e7be3043e16569a643ac0788ee6fe60b183008c294ffa7645f0", "planned_active_tokens": 67885, "realized_active_tokens": 67885, "cumulative_start": 36507149, "cumulative_end": 36575034, "loss_sum": 22772.34359741211, "token_normalized_loss": 0.33545471897196893, "grad_norm_before_clip": 0.0805547907948494, "learning_rates_at_step": { "lora": 4.4017095733959845e-05, "row_tokens": 4.4017095733959845e-05 }, "learning_rates_after_step": { "lora": 4.3847765029232084e-05, "row_tokens": 4.3847765029232084e-05 } }, { "update_id": 558, "row_count": 10, "row_ids_sha256": "efb56ae9e0595663e254c07c79f9b8326da650a9a4cdf5203a3230ba28ad5287", "input_ids_vector_sha256": "898a263528703cb23342939e316d05a14c50c41ef9c2e575087908da98d3e590", "labels_vector_sha256": "4eef049e0bdec09537725a23fe6118cc1a107ae2015de7037a63957c2dbd10fd", "planned_active_tokens": 65981, "realized_active_tokens": 65981, "cumulative_start": 36575034, "cumulative_end": 36641015, "loss_sum": 24445.88214111328, "token_normalized_loss": 0.3704988124022564, "grad_norm_before_clip": 0.08373767882585526, "learning_rates_at_step": { "lora": 4.3847765029232084e-05, "row_tokens": 4.3847765029232084e-05 }, "learning_rates_after_step": { "lora": 4.3685164003599946e-05, "row_tokens": 4.3685164003599946e-05 } }, { "update_id": 559, "row_count": 10, "row_ids_sha256": "dff663fedcbdf10f99b5784af86fae52ebb061f5eb71f9e69fd7ce5d3137aa46", "input_ids_vector_sha256": "c750e27729a7feafdb1f534322e0b70f0d6c493124b32ac0b9e8eb9456abeae4", "labels_vector_sha256": "cff7b3a0cc2121aaa68d879b75a56a63f3bd83cef33df999d9dcee90935ea021", "planned_active_tokens": 63385, "realized_active_tokens": 63385, "cumulative_start": 36641015, "cumulative_end": 36704400, "loss_sum": 22494.192016601562, "token_normalized_loss": 0.3548819439394425, "grad_norm_before_clip": 0.08539954572916031, "learning_rates_at_step": { "lora": 4.3685164003599946e-05, "row_tokens": 4.3685164003599946e-05 }, "learning_rates_after_step": { "lora": 4.351938521417122e-05, "row_tokens": 4.351938521417122e-05 } }, { "update_id": 560, "row_count": 11, "row_ids_sha256": "67e6f2b76d126ae59c430da3cde0538337c6da17acb86b311e386b9e6c6515b3", "input_ids_vector_sha256": "564232544046815016e4745d2cc7352627ff513deaf3b2a9a35397042d55832b", "labels_vector_sha256": "a9090d34b9be3bfd06057736c82b54c7f2536ba2ae3099e2a6ba00c08ccc41b9", "planned_active_tokens": 64651, "realized_active_tokens": 64651, "cumulative_start": 36704400, "cumulative_end": 36769051, "loss_sum": 21569.079803466797, "token_normalized_loss": 0.33362329745041525, "grad_norm_before_clip": 0.08700492978096008, "learning_rates_at_step": { "lora": 4.351938521417122e-05, "row_tokens": 4.351938521417122e-05 }, "learning_rates_after_step": { "lora": 4.3343428911361616e-05, "row_tokens": 4.3343428911361616e-05 } }, { "update_id": 561, "row_count": 7, "row_ids_sha256": "781ed107ed64d328e806edecda6eb73e05dbdc9dc151e333231cd61fa3749501", "input_ids_vector_sha256": "1b6b69d3c3219912686dfba312f0f750bb125b5931823d51c63a48adc8fc179e", "labels_vector_sha256": "05f52e7b45de066d3c2a1a4bff518e5e7d9a3802979496a36da056fa166a8440", "planned_active_tokens": 68651, "realized_active_tokens": 68651, "cumulative_start": 36769051, "cumulative_end": 36837702, "loss_sum": 27323.736083984375, "token_normalized_loss": 0.3980092946058233, "grad_norm_before_clip": 0.08738640695810318, "learning_rates_at_step": { "lora": 4.3343428911361616e-05, "row_tokens": 4.3343428911361616e-05 }, "learning_rates_after_step": { "lora": 4.318520879675303e-05, "row_tokens": 4.318520879675303e-05 } }, { "update_id": 562, "row_count": 10, "row_ids_sha256": "af33370d7e45db69dc580d5e31a53dd72fd5e07305a041b6372f21e11d980a47", "input_ids_vector_sha256": "183399fe83a6d609902ed4775e05938c886f9344b7a76adf26031b131534014b", "labels_vector_sha256": "fe852bcd71ee3ba19b6c023727048b1a0080c64000ee130bd0d771ff5cc9b55e", "planned_active_tokens": 61759, "realized_active_tokens": 61759, "cumulative_start": 36837702, "cumulative_end": 36899461, "loss_sum": 21787.460998535156, "token_normalized_loss": 0.3527819588810563, "grad_norm_before_clip": 0.08695206791162491, "learning_rates_at_step": { "lora": 4.318520879675303e-05, "row_tokens": 4.318520879675303e-05 }, "learning_rates_after_step": { "lora": 4.3010135675661044e-05, "row_tokens": 4.3010135675661044e-05 } }, { "update_id": 563, "row_count": 12, "row_ids_sha256": "0e46d2c1c1be4ab18f5106809fe9c114db50765eeaf4c5e57af5de3ed1dabfdb", "input_ids_vector_sha256": "2d1fcaa98ffdfd43a1f0166314b8e5ff50e3d89d7ebb6e509726e0536aa3027f", "labels_vector_sha256": "1839e34a01011574ae53b086b89914b7a9579725f0286a2f24179cb94fb8a413", "planned_active_tokens": 68369, "realized_active_tokens": 68369, "cumulative_start": 36899461, "cumulative_end": 36967830, "loss_sum": 20969.226196289062, "token_normalized_loss": 0.3067066389195258, "grad_norm_before_clip": 0.0762452557682991, "learning_rates_at_step": { "lora": 4.3010135675661044e-05, "row_tokens": 4.3010135675661044e-05 }, "learning_rates_after_step": { "lora": 4.2853276806949627e-05, "row_tokens": 4.2853276806949627e-05 } }, { "update_id": 564, "row_count": 9, "row_ids_sha256": "abd74096f5fe409e9d395e4c0059449d28367b7c0c74f55488aa8be4b885cc5e", "input_ids_vector_sha256": "135f8f26fab7be44d655cfd464e66d3020b200abe9e8502d99115fb22eeacb27", "labels_vector_sha256": "4e2a4e3fc19b40067945f535417c48439bb017b1b7222c859ac46fb3132458e2", "planned_active_tokens": 61285, "realized_active_tokens": 61285, "cumulative_start": 36967830, "cumulative_end": 37029115, "loss_sum": 20130.148071289062, "token_normalized_loss": 0.32846778283901545, "grad_norm_before_clip": 0.08262897282838821, "learning_rates_at_step": { "lora": 4.2853276806949627e-05, "row_tokens": 4.2853276806949627e-05 }, "learning_rates_after_step": { "lora": 4.268390078303458e-05, "row_tokens": 4.268390078303458e-05 } }, { "update_id": 565, "row_count": 11, "row_ids_sha256": "5fcf7f02a75ae9098920486f5df4dc81273fcbd9ab90352f5a416c673b083258", "input_ids_vector_sha256": "e9aa8c14ba3d7482479cb305b37f7eec43e3665d4a76579c78c7fe6b4175516b", "labels_vector_sha256": "f4a80d7098bc9257aa8a9c149f9d02790fc0715a139632e1776c6fd5e7fe7794", "planned_active_tokens": 66207, "realized_active_tokens": 66207, "cumulative_start": 37029115, "cumulative_end": 37095322, "loss_sum": 23071.327514648438, "token_normalized_loss": 0.3484726315140157, "grad_norm_before_clip": 0.08208145201206207, "learning_rates_at_step": { "lora": 4.268390078303458e-05, "row_tokens": 4.268390078303458e-05 }, "learning_rates_after_step": { "lora": 4.252052334497218e-05, "row_tokens": 4.252052334497218e-05 } }, { "update_id": 566, "row_count": 11, "row_ids_sha256": "3f2dc849c8eea686f25e90dec8a154872973ae53e068507b809f61f2bdc66083", "input_ids_vector_sha256": "51b797c0abdd2df8feae7e80b9741338d41a3dbb1eeffcc8e003890bc8510ac4", "labels_vector_sha256": "0bcf246ae67a4feb944c72c3379fa58cf74b7d2e61f65cd257c3c3bfdfb6eeae", "planned_active_tokens": 63894, "realized_active_tokens": 63894, "cumulative_start": 37095322, "cumulative_end": 37159216, "loss_sum": 21529.930114746094, "token_normalized_loss": 0.3369632534314035, "grad_norm_before_clip": 0.08031861484050751, "learning_rates_at_step": { "lora": 4.252052334497218e-05, "row_tokens": 4.252052334497218e-05 }, "learning_rates_after_step": { "lora": 4.2349319672326246e-05, "row_tokens": 4.2349319672326246e-05 } }, { "update_id": 567, "row_count": 11, "row_ids_sha256": "0af808352b041618552e016b85258121b13ee26a794d5fd721bdd609167a016b", "input_ids_vector_sha256": "5dfb50a302e5bfcdf3ae1e6ec50e60fdaa335ee5847fa3f36ce6cc2367f1b20b", "labels_vector_sha256": "bc9e1c9d20f0b85544281149917ae0c7e8165e260f6b5ab047391b9c670bfb7d", "planned_active_tokens": 66989, "realized_active_tokens": 66989, "cumulative_start": 37159216, "cumulative_end": 37226205, "loss_sum": 21779.170776367188, "token_normalized_loss": 0.3251156275861289, "grad_norm_before_clip": 0.0803389623761177, "learning_rates_at_step": { "lora": 4.2349319672326246e-05, "row_tokens": 4.2349319672326246e-05 }, "learning_rates_after_step": { "lora": 4.21789841051509e-05, "row_tokens": 4.21789841051509e-05 } }, { "update_id": 568, "row_count": 12, "row_ids_sha256": "0fcc62d49c51cd3ef76684cf400aad6cafeefe62747541e02bd3191e8b15863b", "input_ids_vector_sha256": "102a5ae81e36d276e49488f8eeb99e229e4434a08ec410267488aa44db401afb", "labels_vector_sha256": "ee2dc701a48f093090146ef6293a0e1f9ea862a55ec5a3bdb53dba1c5f0b7997", "planned_active_tokens": 66685, "realized_active_tokens": 66685, "cumulative_start": 37226205, "cumulative_end": 37292890, "loss_sum": 23771.57650756836, "token_normalized_loss": 0.3564756168189002, "grad_norm_before_clip": 0.0841187983751297, "learning_rates_at_step": { "lora": 4.21789841051509e-05, "row_tokens": 4.21789841051509e-05 }, "learning_rates_after_step": { "lora": 4.200897888964567e-05, "row_tokens": 4.200897888964567e-05 } }, { "update_id": 569, "row_count": 10, "row_ids_sha256": "091a56f4be4f50eefc3c620e49d785eaa01bda737519594c57d613ceb2341853", "input_ids_vector_sha256": "a7ac25b1409aa12cdb508d73494634483cd9c69da80d000a6be361a61c4cd291", "labels_vector_sha256": "3828fe1d16179837c680a74240ea443719149d8c8fe9ce7db4ea53d7e7385691", "planned_active_tokens": 66592, "realized_active_tokens": 66592, "cumulative_start": 37292890, "cumulative_end": 37359482, "loss_sum": 24303.47918701172, "token_normalized_loss": 0.3649609440625258, "grad_norm_before_clip": 0.083185113966465, "learning_rates_at_step": { "lora": 4.200897888964567e-05, "row_tokens": 4.200897888964567e-05 }, "learning_rates_after_step": { "lora": 4.1834443872869646e-05, "row_tokens": 4.1834443872869646e-05 } }, { "update_id": 570, "row_count": 12, "row_ids_sha256": "263b817256bf40d68243ed0ce089fbd4c9dcec1859319f2b37f292da1209764c", "input_ids_vector_sha256": "bd10a62a5e650e18783f37837f171e902a1b6c01e2ad1930e339cb9672974713", "labels_vector_sha256": "dc90ebd1dcceb9e452c4f895d79d1a4f2e8666c7b932ab692505b8bec575a7f6", "planned_active_tokens": 68405, "realized_active_tokens": 68405, "cumulative_start": 37359482, "cumulative_end": 37427887, "loss_sum": 16936.739959716797, "token_normalized_loss": 0.24759505825183534, "grad_norm_before_clip": 0.06792952865362167, "learning_rates_at_step": { "lora": 4.1834443872869646e-05, "row_tokens": 4.1834443872869646e-05 }, "learning_rates_after_step": { "lora": 4.1672777914135394e-05, "row_tokens": 4.1672777914135394e-05 } }, { "update_id": 571, "row_count": 11, "row_ids_sha256": "b010da684e57b34b405bd20af6d3f7518615607bed12144d404828c38db088e9", "input_ids_vector_sha256": "f1b0ec3f54a6f64e62051b5fe8d3cec9c9059438df457541d6d491e8622b7931", "labels_vector_sha256": "10db5a1c0707ee37b5071b26aca96b9c2bff3322a8d36287b4eb18ee731314c5", "planned_active_tokens": 63397, "realized_active_tokens": 63397, "cumulative_start": 37427887, "cumulative_end": 37491284, "loss_sum": 22735.536743164062, "token_normalized_loss": 0.3586216499702519, "grad_norm_before_clip": 0.0856681764125824, "learning_rates_at_step": { "lora": 4.1672777914135394e-05, "row_tokens": 4.1672777914135394e-05 }, "learning_rates_after_step": { "lora": 4.1499562736114777e-05, "row_tokens": 4.1499562736114777e-05 } }, { "update_id": 572, "row_count": 11, "row_ids_sha256": "11b367e4c5421903c6ac91f5cb11cf52df7e0dcee64ba5e43e4efc58e2329cb4", "input_ids_vector_sha256": "1fb5e37f9054805310f0acd4e865f415523923f0c297c44a3e128810aeaf1718", "labels_vector_sha256": "cef8f4eeffd4c71e707261282855cb8ca87fe8464861b25b07e919076149762d", "planned_active_tokens": 67965, "realized_active_tokens": 67965, "cumulative_start": 37491284, "cumulative_end": 37559249, "loss_sum": 22309.73291015625, "token_normalized_loss": 0.32825326138683514, "grad_norm_before_clip": 0.08263617753982544, "learning_rates_at_step": { "lora": 4.1499562736114777e-05, "row_tokens": 4.1499562736114777e-05 }, "learning_rates_after_step": { "lora": 4.134379315825549e-05, "row_tokens": 4.134379315825549e-05 } }, { "update_id": 573, "row_count": 10, "row_ids_sha256": "98bc63bae9594a25dd0eeb6bf7134862c0c7c5381e4e83ffa902fe82c6d85cc3", "input_ids_vector_sha256": "b7ce6dec9c08caeb8daf9e706954551a523464dbe5cc567875121bfdc74d5505", "labels_vector_sha256": "83e73b75a2217115e52744ef8c39cbd3ffbae346973f76c8f342662a821a26d4", "planned_active_tokens": 61155, "realized_active_tokens": 61155, "cumulative_start": 37559249, "cumulative_end": 37620404, "loss_sum": 21123.57891845703, "token_normalized_loss": 0.3454104965817518, "grad_norm_before_clip": 0.08783494681119919, "learning_rates_at_step": { "lora": 4.134379315825549e-05, "row_tokens": 4.134379315825549e-05 }, "learning_rates_after_step": { "lora": 4.1174586367995855e-05, "row_tokens": 4.1174586367995855e-05 } }, { "update_id": 574, "row_count": 13, "row_ids_sha256": "f20b986a0fe05e9006681ba367cdac371e47c0b80256c865a1229ab217bcf949", "input_ids_vector_sha256": "118ac995fab2d93d622c69e3b9a143a82c33402628dd4bc506eed8af0e7a7000", "labels_vector_sha256": "c4fb0e72ab84dc81cbc49d6dda0aa1ce318f3f65b2a1561a9908d0ac4dc4d114", "planned_active_tokens": 66469, "realized_active_tokens": 66469, "cumulative_start": 37620404, "cumulative_end": 37686873, "loss_sum": 23152.196807861328, "token_normalized_loss": 0.3483157081927113, "grad_norm_before_clip": 0.08729422837495804, "learning_rates_at_step": { "lora": 4.1174586367995855e-05, "row_tokens": 4.1174586367995855e-05 }, "learning_rates_after_step": { "lora": 4.099588564246574e-05, "row_tokens": 4.099588564246574e-05 } }, { "update_id": 575, "row_count": 10, "row_ids_sha256": "9ada3a615216e68d94c7b2d5fdcde0c62cad7e54e3df8a1c4cc4ef2da5995ad6", "input_ids_vector_sha256": "c0bc2d6da99a30def507938ff24d63a4a1cbf79e04474b1c73277dfa8a895263", "labels_vector_sha256": "b6315eb488e8a3bc68f07947e70d9b29d9cf896d9d155f9805a524c9c67c6baa", "planned_active_tokens": 70243, "realized_active_tokens": 70243, "cumulative_start": 37686873, "cumulative_end": 37757116, "loss_sum": 23522.41815185547, "token_normalized_loss": 0.3348720605876097, "grad_norm_before_clip": 0.08281811326742172, "learning_rates_at_step": { "lora": 4.099588564246574e-05, "row_tokens": 4.099588564246574e-05 }, "learning_rates_after_step": { "lora": 4.0847267016370186e-05, "row_tokens": 4.0847267016370186e-05 } }, { "update_id": 576, "row_count": 11, "row_ids_sha256": "7ad86f91943814908c45fb972efd8b0b183c37a398921b1a7cea172f075db04a", "input_ids_vector_sha256": "49e95cbfb6bd2148848a4252b695ed652e6040446607edea23c887454b1cc7f6", "labels_vector_sha256": "4637c3f715f3eb323d82a16b40b08aa5eb9d42d04b5542881a235283375b27e4", "planned_active_tokens": 58454, "realized_active_tokens": 58454, "cumulative_start": 37757116, "cumulative_end": 37815570, "loss_sum": 18038.306182861328, "token_normalized_loss": 0.3085897660187725, "grad_norm_before_clip": 0.0845009833574295, "learning_rates_at_step": { "lora": 4.0847267016370186e-05, "row_tokens": 4.0847267016370186e-05 }, "learning_rates_after_step": { "lora": 4.068195110139644e-05, "row_tokens": 4.068195110139644e-05 } }, { "update_id": 577, "row_count": 13, "row_ids_sha256": "750b2cd4f39dafb74a46af6b1e95c76124ecde8efba71e51c37c74491aa3155c", "input_ids_vector_sha256": "979c8c6abf79444625ffa996d617a0f1ccc90e1534f0bd36d09a6862ea0299ad", "labels_vector_sha256": "7dae04a91c17bfe679c3340a308750f8b57a591f958baab7e42238c808e8f52c", "planned_active_tokens": 65060, "realized_active_tokens": 65060, "cumulative_start": 37815570, "cumulative_end": 37880630, "loss_sum": 18733.076416015625, "token_normalized_loss": 0.2879353891179776, "grad_norm_before_clip": 0.07888417690992355, "learning_rates_at_step": { "lora": 4.068195110139644e-05, "row_tokens": 4.068195110139644e-05 }, "learning_rates_after_step": { "lora": 4.051517945256134e-05, "row_tokens": 4.051517945256134e-05 } }, { "update_id": 578, "row_count": 9, "row_ids_sha256": "9f88d87398f71dc6b2c63c9d6ad3acf6d841030e421995f4e799dcb8414bea37", "input_ids_vector_sha256": "5f2b21002b5d1d8532146fc5d0762c347e6d364c448d86de0659cc4c2dffb21a", "labels_vector_sha256": "75fad81e794d660eda881639c7eec456a0a9fd50599f8ace4de39171b590830a", "planned_active_tokens": 65675, "realized_active_tokens": 65675, "cumulative_start": 37880630, "cumulative_end": 37946305, "loss_sum": 23561.608947753906, "token_normalized_loss": 0.3587606996232037, "grad_norm_before_clip": 0.08696142584085464, "learning_rates_at_step": { "lora": 4.051517945256134e-05, "row_tokens": 4.051517945256134e-05 }, "learning_rates_after_step": { "lora": 4.0338981393885895e-05, "row_tokens": 4.0338981393885895e-05 } }, { "update_id": 579, "row_count": 10, "row_ids_sha256": "b3ad3c4c26108f637ad94a0213ac7cc6bc8ad5c9981571ea6fa89fd285eb20b3", "input_ids_vector_sha256": "0aa2b57b8f3a5389c3da2fdc5d733ba7b6faf5160561ca1810b528996a580c45", "labels_vector_sha256": "2d6f257f0aa49873dfa1f4ba81eec0a37cef1f30fb3ace990875dc3581dd7af9", "planned_active_tokens": 69434, "realized_active_tokens": 69434, "cumulative_start": 37946305, "cumulative_end": 38015739, "loss_sum": 22772.659790039062, "token_normalized_loss": 0.3279756285110906, "grad_norm_before_clip": 0.08362986147403717, "learning_rates_at_step": { "lora": 4.0338981393885895e-05, "row_tokens": 4.0338981393885895e-05 }, "learning_rates_after_step": { "lora": 4.018286114069039e-05, "row_tokens": 4.018286114069039e-05 } }, { "update_id": 580, "row_count": 11, "row_ids_sha256": "0d06c220707eaf073a6bd3fea55f0f75bd9633739db0eb505c5ada1b39415bb1", "input_ids_vector_sha256": "23fb79c8a05a1370df6c7fe3df3c3ecb9d333a6c56f8435b6d6e2bbb1667a1fc", "labels_vector_sha256": "3ccc027a664889c11676454e355b27ca0f0d0691d6ea515d04f58cb1299219f5", "planned_active_tokens": 61563, "realized_active_tokens": 61563, "cumulative_start": 38015739, "cumulative_end": 38077302, "loss_sum": 19517.278106689453, "token_normalized_loss": 0.3170293537788843, "grad_norm_before_clip": 0.08936969935894012, "learning_rates_at_step": { "lora": 4.018286114069039e-05, "row_tokens": 4.018286114069039e-05 }, "learning_rates_after_step": { "lora": 4.0013549945166024e-05, "row_tokens": 4.0013549945166024e-05 } }, { "update_id": 581, "row_count": 9, "row_ids_sha256": "5775733985ad1c6b1657c2d64bba9f15fc878eea6590adf442d123c334c61a5e", "input_ids_vector_sha256": "e03431b46f0883a6b91813f73296ba71a5177f35378a42d9573a71c1627a3527", "labels_vector_sha256": "7dc979fa464d7200eca334428bb4fa920b241dd73f505edda5d80a91a14497d6", "planned_active_tokens": 66809, "realized_active_tokens": 66809, "cumulative_start": 38077302, "cumulative_end": 38144111, "loss_sum": 20451.95343017578, "token_normalized_loss": 0.30612572303395924, "grad_norm_before_clip": 0.08048615604639053, "learning_rates_at_step": { "lora": 4.0013549945166024e-05, "row_tokens": 4.0013549945166024e-05 }, "learning_rates_after_step": { "lora": 3.9838684750525494e-05, "row_tokens": 3.9838684750525494e-05 } }, { "update_id": 582, "row_count": 14, "row_ids_sha256": "b0c52e3034f72757d4ea4c99ff728efba7405e0550aa835607265b0098268b52", "input_ids_vector_sha256": "c2ddb01e2e9d1a24b471f7f64ce4fa518bd8b3b6c2a89fb10335c5ef09ee5db8", "labels_vector_sha256": "5b0ae58d3ab5efb693828205c103836d53e944a62ec8306a73a19845e8878aec", "planned_active_tokens": 69050, "realized_active_tokens": 69050, "cumulative_start": 38144111, "cumulative_end": 38213161, "loss_sum": 21686.355407714844, "token_normalized_loss": 0.3140674208213591, "grad_norm_before_clip": 0.08077353239059448, "learning_rates_at_step": { "lora": 3.9838684750525494e-05, "row_tokens": 3.9838684750525494e-05 }, "learning_rates_after_step": { "lora": 3.9685613762014706e-05, "row_tokens": 3.9685613762014706e-05 } }, { "update_id": 583, "row_count": 9, "row_ids_sha256": "0165b5d7b32c7f42b8e542c2d2d1ea7e722d6c029af009fb91db83d6e2e7d127", "input_ids_vector_sha256": "369b88f3cebdfa1a5cfeb4f47460f0340874629183847c2d376deb05ba3bc184", "labels_vector_sha256": "8dcd2e35bea041fb528aa1f234c09118dcb947d0b6f329c25fd215c68a84c8b6", "planned_active_tokens": 60486, "realized_active_tokens": 60486, "cumulative_start": 38213161, "cumulative_end": 38273647, "loss_sum": 21093.779052734375, "token_normalized_loss": 0.34873820475373435, "grad_norm_before_clip": 0.08746706694364548, "learning_rates_at_step": { "lora": 3.9685613762014706e-05, "row_tokens": 3.9685613762014706e-05 }, "learning_rates_after_step": { "lora": 3.950421865419478e-05, "row_tokens": 3.950421865419478e-05 } }, { "update_id": 584, "row_count": 8, "row_ids_sha256": "2f2d7bf175720e4e488c67f026ec218364bc141d16c6a850c10930e6f7da5102", "input_ids_vector_sha256": "5293a59799e40963e00b390ddc48b188adc6da54d821c9b9bbe81ff340a8ecd4", "labels_vector_sha256": "922b84458c7d2ce881306f5f8cd33c2e8f5646db53b1ab5deb323532b05f0d0d", "planned_active_tokens": 71730, "realized_active_tokens": 71730, "cumulative_start": 38273647, "cumulative_end": 38345377, "loss_sum": 28953.179931640625, "token_normalized_loss": 0.4036411533757232, "grad_norm_before_clip": 0.08694781363010406, "learning_rates_at_step": { "lora": 3.950421865419478e-05, "row_tokens": 3.950421865419478e-05 }, "learning_rates_after_step": { "lora": 3.935312331558928e-05, "row_tokens": 3.935312331558928e-05 } }, { "update_id": 585, "row_count": 9, "row_ids_sha256": "4cbe69188847f2c32e0baf53119e2a8acc853daccbf2e26d6e8da5397c2690e4", "input_ids_vector_sha256": "40c9366525586c5ad0e6e604a3efb22f0bdcc81c09cd0371a88b6c2e7aa70277", "labels_vector_sha256": "2d4bf9ea3fc40b696f94efeff29dc28ebb5f99d911a7444d52066434f4cbe4d5", "planned_active_tokens": 59792, "realized_active_tokens": 59792, "cumulative_start": 38345377, "cumulative_end": 38405169, "loss_sum": 23416.682189941406, "token_normalized_loss": 0.39163570694978267, "grad_norm_before_clip": 0.10169295221567154, "learning_rates_at_step": { "lora": 3.935312331558928e-05, "row_tokens": 3.935312331558928e-05 }, "learning_rates_after_step": { "lora": 3.915487450393672e-05, "row_tokens": 3.915487450393672e-05 } }, { "update_id": 586, "row_count": 10, "row_ids_sha256": "b2f42db1409d4a4433cf52341c15cdce0e5aabea4754d9f46bd1dab17731305e", "input_ids_vector_sha256": "57861cdd8b07392167435c4bf739766043888b69aa5e19c825cd2c7fdb8853b9", "labels_vector_sha256": "33cd7d908c60b0ed9ca57fbc354ae58fb56d6bb941510df64b8fb7bc621d59cd", "planned_active_tokens": 78513, "realized_active_tokens": 78513, "cumulative_start": 38405169, "cumulative_end": 38483682, "loss_sum": 30859.30108642578, "token_normalized_loss": 0.39304702516049295, "grad_norm_before_clip": 0.08145732432603836, "learning_rates_at_step": { "lora": 3.915487450393672e-05, "row_tokens": 3.915487450393672e-05 }, "learning_rates_after_step": { "lora": 3.901364914566806e-05, "row_tokens": 3.901364914566806e-05 } }, { "update_id": 587, "row_count": 9, "row_ids_sha256": "4eb95b72ed6d72886b1e380ecd520f5c708deb00caa7fa228620293293b6a87b", "input_ids_vector_sha256": "49e55f763dd0c966daf612cc89b1070fa96b633faac7f1022b9c2527add12617", "labels_vector_sha256": "236ac0537045ead1b80dde66edfeae880a19aec3e290a09011238f6122c0dc7e", "planned_active_tokens": 55973, "realized_active_tokens": 55973, "cumulative_start": 38483682, "cumulative_end": 38539655, "loss_sum": 19779.86737060547, "token_normalized_loss": 0.353382298083102, "grad_norm_before_clip": 0.09346528351306915, "learning_rates_at_step": { "lora": 3.901364914566806e-05, "row_tokens": 3.901364914566806e-05 }, "learning_rates_after_step": { "lora": 3.884357849433433e-05, "row_tokens": 3.884357849433433e-05 } }, { "update_id": 588, "row_count": 12, "row_ids_sha256": "b45c7e594db5bfc8167da2fc01561886e5f7bf5653abdcfd160842925326395c", "input_ids_vector_sha256": "404ec5de1bd31251898392af33a7f6572765f44cd98b016e1b299e5b5246b87f", "labels_vector_sha256": "3ac44561878a95ba7bbe83f1724b8b7b9580467996246639101c2348139ee23b", "planned_active_tokens": 67454, "realized_active_tokens": 67454, "cumulative_start": 38539655, "cumulative_end": 38607109, "loss_sum": 23596.64859008789, "token_normalized_loss": 0.34981837385607806, "grad_norm_before_clip": 0.08370468765497208, "learning_rates_at_step": { "lora": 3.884357849433433e-05, "row_tokens": 3.884357849433433e-05 }, "learning_rates_after_step": { "lora": 3.8685457040235844e-05, "row_tokens": 3.8685457040235844e-05 } }, { "update_id": 589, "row_count": 11, "row_ids_sha256": "5fda0b415cf191487b0d18273b5cd4119515d85a696f65e2d6ecf8365ea27e46", "input_ids_vector_sha256": "26a91d814dd068c5d4c4137ea29d1d6a1f10b3aea5a668aa716690880659dd81", "labels_vector_sha256": "27379d51e4bcfaad4c1ca1b4863c4b61feb298a7bd3bceef1bc3b45b4592dac6", "planned_active_tokens": 62763, "realized_active_tokens": 62763, "cumulative_start": 38607109, "cumulative_end": 38669872, "loss_sum": 21365.12286376953, "token_normalized_loss": 0.3404095225494245, "grad_norm_before_clip": 0.08352304250001907, "learning_rates_at_step": { "lora": 3.8685457040235844e-05, "row_tokens": 3.8685457040235844e-05 }, "learning_rates_after_step": { "lora": 3.8529432726600514e-05, "row_tokens": 3.8529432726600514e-05 } }, { "update_id": 590, "row_count": 10, "row_ids_sha256": "0bc68ffef829afb59efdd7e659b19662fb1b7fbf6644761a065ce46a1f7a2df4", "input_ids_vector_sha256": "a14fae0d47896e6971969bf88adf43cc8e1fd22ee5ebb7b99bbf692e47ef7b88", "labels_vector_sha256": "7838be6c865df6bf8c5dbabd001091d8cd6af51b6fcd30f6e3a29a8166d8c434", "planned_active_tokens": 61977, "realized_active_tokens": 61977, "cumulative_start": 38669872, "cumulative_end": 38731849, "loss_sum": 21563.62518310547, "token_normalized_loss": 0.3479294767914786, "grad_norm_before_clip": 0.08709447830915451, "learning_rates_at_step": { "lora": 3.8529432726600514e-05, "row_tokens": 3.8529432726600514e-05 }, "learning_rates_after_step": { "lora": 3.835370715025324e-05, "row_tokens": 3.835370715025324e-05 } }, { "update_id": 591, "row_count": 12, "row_ids_sha256": "b82b98b410d0817fcdb3b6fec0d8cde46cce20537514ebedb47c7ebcd8cfff3d", "input_ids_vector_sha256": "4b2828b10ff4734a30aa526bfaa3e0037da4c1f190ca9eb3c8aae7b4f926d928", "labels_vector_sha256": "2b550dd929f5790488b53ab3eb72d682b45582b8eff8c8832d78ed553666d728", "planned_active_tokens": 69859, "realized_active_tokens": 69859, "cumulative_start": 38731849, "cumulative_end": 38801708, "loss_sum": 22853.74072265625, "token_normalized_loss": 0.3271409656974227, "grad_norm_before_clip": 0.08564954996109009, "learning_rates_at_step": { "lora": 3.835370715025324e-05, "row_tokens": 3.835370715025324e-05 }, "learning_rates_after_step": { "lora": 3.819368441169272e-05, "row_tokens": 3.819368441169272e-05 } }, { "update_id": 592, "row_count": 12, "row_ids_sha256": "7ebdd1faa27105f4473948bd36bf364959771640e001bfe2fbde0b17c78a97bf", "input_ids_vector_sha256": "bae57b2cdbe90c39d71333343ee2c34c94b154f09232011e7855d4bbab63d280", "labels_vector_sha256": "b95d165ce435c52da6eb4b8d5a1c42cf11630bb0b9ae835494a756bb0d92c0ac", "planned_active_tokens": 63669, "realized_active_tokens": 63669, "cumulative_start": 38801708, "cumulative_end": 38865377, "loss_sum": 22138.343322753906, "token_normalized_loss": 0.3477099266951563, "grad_norm_before_clip": 0.08699849247932434, "learning_rates_at_step": { "lora": 3.819368441169272e-05, "row_tokens": 3.819368441169272e-05 }, "learning_rates_after_step": { "lora": 3.803027019150947e-05, "row_tokens": 3.803027019150947e-05 } }, { "update_id": 593, "row_count": 12, "row_ids_sha256": "b2cf2466dde61aa0d28734cde948a59f0bdaae3da8087caaf72452c2dd19fecf", "input_ids_vector_sha256": "37f36c376855e6c76c2b29c51da77e5be8dd82cbc492ea0f2a98ec2b5357986b", "labels_vector_sha256": "e1dfa22a59c3d30b68c4a1993feb23e70be822064eeedeaba281a71e6c6d3765", "planned_active_tokens": 65071, "realized_active_tokens": 65071, "cumulative_start": 38865377, "cumulative_end": 38930448, "loss_sum": 20891.393127441406, "token_normalized_loss": 0.32105535687850817, "grad_norm_before_clip": 0.09951600432395935, "learning_rates_at_step": { "lora": 3.803027019150947e-05, "row_tokens": 3.803027019150947e-05 }, "learning_rates_after_step": { "lora": 3.7867987242377646e-05, "row_tokens": 3.7867987242377646e-05 } }, { "update_id": 594, "row_count": 11, "row_ids_sha256": "47b187003c901eae6c2b0b77705ef0a0ea3a3ffd54ab22f2e0e4ea8d64ee2cae", "input_ids_vector_sha256": "75eaf79da6360bb483de13b7c8f63f7547e07b6b4ba5d6d21289846f2c61925f", "labels_vector_sha256": "2285dedae5ec1d9ccd68ec1c5f1ebf3d9810652ef1d3801a6e8f13da34cf36e4", "planned_active_tokens": 64674, "realized_active_tokens": 64674, "cumulative_start": 38930448, "cumulative_end": 38995122, "loss_sum": 24602.22705078125, "token_normalized_loss": 0.3804036715029417, "grad_norm_before_clip": 0.09218152612447739, "learning_rates_at_step": { "lora": 3.7867987242377646e-05, "row_tokens": 3.7867987242377646e-05 }, "learning_rates_after_step": { "lora": 3.769335755457375e-05, "row_tokens": 3.769335755457375e-05 } }, { "update_id": 595, "row_count": 12, "row_ids_sha256": "dccff0cb0abeb6f55000f475b0ae74d054bf51b79975ff579f53551a38024da5", "input_ids_vector_sha256": "dd210e7f3eecaeea63cabf7991dcb3ae596e53051efc3ca877206409e23ff25e", "labels_vector_sha256": "6e2d457c84a3050067d79167f1904d6aa24209468456c396c8984111b35ed14e", "planned_active_tokens": 69655, "realized_active_tokens": 69655, "cumulative_start": 38995122, "cumulative_end": 39064777, "loss_sum": 24330.1826171875, "token_normalized_loss": 0.34929556553280455, "grad_norm_before_clip": 0.08463875204324722, "learning_rates_at_step": { "lora": 3.769335755457375e-05, "row_tokens": 3.769335755457375e-05 }, "learning_rates_after_step": { "lora": 3.754195726519542e-05, "row_tokens": 3.754195726519542e-05 } }, { "update_id": 596, "row_count": 11, "row_ids_sha256": "5b0ad316fff30a05090315451be5fae9e5990863c4cfd80eeb36a6b64b9716e1", "input_ids_vector_sha256": "74ee14812abec3f3f7d424e1d1f739bdfa2e9ef3254643b001d9d69bfbf6e9be", "labels_vector_sha256": "245bf1c28d1653a9faaec0631783c08eb54acb4bf040675399d3b79f9328f46f", "planned_active_tokens": 60441, "realized_active_tokens": 60441, "cumulative_start": 39064777, "cumulative_end": 39125218, "loss_sum": 19303.39144897461, "token_normalized_loss": 0.31937577884175655, "grad_norm_before_clip": 0.08873400092124939, "learning_rates_at_step": { "lora": 3.754195726519542e-05, "row_tokens": 3.754195726519542e-05 }, "learning_rates_after_step": { "lora": 3.7363039745877137e-05, "row_tokens": 3.7363039745877137e-05 } }, { "update_id": 597, "row_count": 11, "row_ids_sha256": "126b31c9979c78bf87267c3d6ee5b2c882b84118c1fcc567b820fac7d6fdf1f0", "input_ids_vector_sha256": "fdf8d306a8e52890642ca9c8ab9fc8d958ac22b3a702efdfba3d334ead01a290", "labels_vector_sha256": "a9e49c7fd4df2b2ca06e4a4653325e0ea126b9e5e0df168f9ef4647fa8532f68", "planned_active_tokens": 71489, "realized_active_tokens": 71489, "cumulative_start": 39125218, "cumulative_end": 39196707, "loss_sum": 21312.48306274414, "token_normalized_loss": 0.29812255120010267, "grad_norm_before_clip": 0.08015847206115723, "learning_rates_at_step": { "lora": 3.7363039745877137e-05, "row_tokens": 3.7363039745877137e-05 }, "learning_rates_after_step": { "lora": 3.71961135076954e-05, "row_tokens": 3.71961135076954e-05 } }, { "update_id": 598, "row_count": 11, "row_ids_sha256": "296d2d02ea2298b3b08cf57a1551695a32a92e11cce277852b90a3359961d958", "input_ids_vector_sha256": "c3323ecdeb91ad4108431e37bede61a0d3203d549cacc80902d9e60f8e63f13e", "labels_vector_sha256": "30f0d78ba7cd3fe2f6224ab6f95f86ebf597cefe3a3282e79d01269446444bca", "planned_active_tokens": 66760, "realized_active_tokens": 66760, "cumulative_start": 39196707, "cumulative_end": 39263467, "loss_sum": 22351.262481689453, "token_normalized_loss": 0.33480021692165146, "grad_norm_before_clip": 0.08490227907896042, "learning_rates_at_step": { "lora": 3.71961135076954e-05, "row_tokens": 3.71961135076954e-05 }, "learning_rates_after_step": { "lora": 3.7045768069755456e-05, "row_tokens": 3.7045768069755456e-05 } }, { "update_id": 599, "row_count": 10, "row_ids_sha256": "3aab3138369eb6c035a1b5a731401141e3012b51be0f54b49b39e9b7232ad000", "input_ids_vector_sha256": "846f3e4d94dcc33a289023a9bacd6a73296a47706e91174f6d334a1e002905e5", "labels_vector_sha256": "99e35893e6f0c0e1850a4f67a34e571559836e628e16e01ca429c18beaa53569", "planned_active_tokens": 60181, "realized_active_tokens": 60181, "cumulative_start": 39263467, "cumulative_end": 39323648, "loss_sum": 18915.70474243164, "token_normalized_loss": 0.31431356644840797, "grad_norm_before_clip": 0.08947712182998657, "learning_rates_at_step": { "lora": 3.7045768069755456e-05, "row_tokens": 3.7045768069755456e-05 }, "learning_rates_after_step": { "lora": 3.6882294677739306e-05, "row_tokens": 3.6882294677739306e-05 } }, { "update_id": 600, "row_count": 11, "row_ids_sha256": "1451764dd9d6141c3dfe8e2da4d1f574b9e14033ed6f92459a7770189a7a2673", "input_ids_vector_sha256": "ebf2372240712024f1261dfff10270dfec8e6d0a2fd4ec212a43d9f65a2bedf9", "labels_vector_sha256": "e1527b5686b3f65f4ec44dd6e301398379633581597d0b44747040dcf261322c", "planned_active_tokens": 65493, "realized_active_tokens": 65493, "cumulative_start": 39323648, "cumulative_end": 39389141, "loss_sum": 22973.029724121094, "token_normalized_loss": 0.35077076518286066, "grad_norm_before_clip": 0.08785803616046906, "learning_rates_at_step": { "lora": 3.6882294677739306e-05, "row_tokens": 3.6882294677739306e-05 }, "learning_rates_after_step": { "lora": 3.6723632935524854e-05, "row_tokens": 3.6723632935524854e-05 } }, { "update_id": 601, "row_count": 12, "row_ids_sha256": "2bbbd038ba7b9daef1c3400d2c358d544c1157f99460d4a967777eb624aacac8", "input_ids_vector_sha256": "30cc768a73dcfa953219fe65a79c3c5a185be5a710891cffa8305e007f1763b6", "labels_vector_sha256": "09209f35429ce701ae8a3a60f26ce2c7a8e018961a85aad95d4c5702dd2d3196", "planned_active_tokens": 63623, "realized_active_tokens": 63623, "cumulative_start": 39389141, "cumulative_end": 39452764, "loss_sum": 19945.41812133789, "token_normalized_loss": 0.31349383275447384, "grad_norm_before_clip": 0.08632542192935944, "learning_rates_at_step": { "lora": 3.6723632935524854e-05, "row_tokens": 3.6723632935524854e-05 }, "learning_rates_after_step": { "lora": 3.65568544870107e-05, "row_tokens": 3.65568544870107e-05 } }, { "update_id": 602, "row_count": 11, "row_ids_sha256": "43e2b5bae19d42ad1b941aa8a0a0f89441cb9f1c8426c042c857eda5bede251a", "input_ids_vector_sha256": "494fc718a33e69af2c2e8a15e830433da666183a409aff1e83b5733053df37b2", "labels_vector_sha256": "cda165f02f38eec522c2a1e547cc87fcc92fda0308e521ae600f4f0935218bb4", "planned_active_tokens": 66940, "realized_active_tokens": 66940, "cumulative_start": 39452764, "cumulative_end": 39519704, "loss_sum": 23208.170166015625, "token_normalized_loss": 0.3467010780701468, "grad_norm_before_clip": 0.08628346771001816, "learning_rates_at_step": { "lora": 3.65568544870107e-05, "row_tokens": 3.65568544870107e-05 }, "learning_rates_after_step": { "lora": 3.6396944462174655e-05, "row_tokens": 3.6396944462174655e-05 } }, { "update_id": 603, "row_count": 12, "row_ids_sha256": "286f50f096b9ceee2ada3dbbfe0b16325b84911610479c35477b04d8c4e75f3e", "input_ids_vector_sha256": "f2108875b1c2f5e5ddc78529f7c2c1108893b728e8c4d90a9d5837c77caf62f1", "labels_vector_sha256": "1396bd57fe8c899b9a734bb7c35f531bda156edc72394f60e56a3194474b6842", "planned_active_tokens": 64244, "realized_active_tokens": 64244, "cumulative_start": 39519704, "cumulative_end": 39583948, "loss_sum": 17733.5595703125, "token_normalized_loss": 0.27603448680518805, "grad_norm_before_clip": 0.08185325562953949, "learning_rates_at_step": { "lora": 3.6396944462174655e-05, "row_tokens": 3.6396944462174655e-05 }, "learning_rates_after_step": { "lora": 3.6215427111382664e-05, "row_tokens": 3.6215427111382664e-05 } }, { "update_id": 604, "row_count": 12, "row_ids_sha256": "cdae23698aab7b42a5ea718f878705386c70e7112e8bacb753db8817f6a3f7fd", "input_ids_vector_sha256": "f943226f5add27f885c8f245bc23f8e67568ce5dda4d29eadb17a98758696af5", "labels_vector_sha256": "d563a305f5dba68ad0db6ad888faa8476ab4053526c211d64954e0ee42c96ba8", "planned_active_tokens": 72998, "realized_active_tokens": 72998, "cumulative_start": 39583948, "cumulative_end": 39656946, "loss_sum": 24548.17022705078, "token_normalized_loss": 0.3362855177820047, "grad_norm_before_clip": 0.08399821072816849, "learning_rates_at_step": { "lora": 3.6215427111382664e-05, "row_tokens": 3.6215427111382664e-05 }, "learning_rates_after_step": { "lora": 3.605849663128296e-05, "row_tokens": 3.605849663128296e-05 } }, { "update_id": 605, "row_count": 12, "row_ids_sha256": "f1d2d87aa1168b6914cd55fc76ebb8e17a2df33f788ab172df5a73614fdca87c", "input_ids_vector_sha256": "704cc077ab8f34aca23a084acbe5ffcf950f0962be923e0241f92ba76249907c", "labels_vector_sha256": "cb6d22ca60a79cb7414849b207f38392600a76d81d70331779fa35c2f1b4404a", "planned_active_tokens": 63174, "realized_active_tokens": 63174, "cumulative_start": 39656946, "cumulative_end": 39720120, "loss_sum": 18025.204711914062, "token_normalized_loss": 0.28532631639462536, "grad_norm_before_clip": 0.08168936520814896, "learning_rates_at_step": { "lora": 3.605849663128296e-05, "row_tokens": 3.605849663128296e-05 }, "learning_rates_after_step": { "lora": 3.5897190448980586e-05, "row_tokens": 3.5897190448980586e-05 } }, { "update_id": 606, "row_count": 10, "row_ids_sha256": "9ab15208214433da2f2cffcac23f48cc354776621d92fc300f816a6dda2cba11", "input_ids_vector_sha256": "9dffa7c4b1cd9aded9d27047b81b5c58c1fabfd0bdbc1eba987ccad82c0ffd87", "labels_vector_sha256": "76aa16187003a83d24761ae60795c0fb26e9acf353960b376803aa17eb21b78e", "planned_active_tokens": 64998, "realized_active_tokens": 64998, "cumulative_start": 39720120, "cumulative_end": 39785118, "loss_sum": 21700.25, "token_normalized_loss": 0.33386027262377305, "grad_norm_before_clip": 0.08602399379014969, "learning_rates_at_step": { "lora": 3.5897190448980586e-05, "row_tokens": 3.5897190448980586e-05 }, "learning_rates_after_step": { "lora": 3.5731808688931636e-05, "row_tokens": 3.5731808688931636e-05 } }, { "update_id": 607, "row_count": 12, "row_ids_sha256": "793cba1c18a02f68b9f5b718686e4b800601031a390b24979e744827959ebc77", "input_ids_vector_sha256": "e7270d4f4cdd93162ca3f4554c95cad5231572a1bd5749b69af7094dbf9bd20f", "labels_vector_sha256": "4b8f9eebe3cfc131215aac908fcaa02618ad72b517b025bb303f4fe2bef09b23", "planned_active_tokens": 66707, "realized_active_tokens": 66707, "cumulative_start": 39785118, "cumulative_end": 39851825, "loss_sum": 21076.5107421875, "token_normalized_loss": 0.3159565074458078, "grad_norm_before_clip": 0.08135484904050827, "learning_rates_at_step": { "lora": 3.5731808688931636e-05, "row_tokens": 3.5731808688931636e-05 }, "learning_rates_after_step": { "lora": 3.557790224468129e-05, "row_tokens": 3.557790224468129e-05 } }, { "update_id": 608, "row_count": 10, "row_ids_sha256": "71e94c32e49cb549f84382394453cc313a9f488eb973baf15b58a22baae13d78", "input_ids_vector_sha256": "ba9d50db6f538f0648629758eb7154808819e04815d596344723b11a180e2994", "labels_vector_sha256": "6486301ecd0f71c5a006a02fb71657f3b14a857fff245e958790a009c1885ca3", "planned_active_tokens": 62140, "realized_active_tokens": 62140, "cumulative_start": 39851825, "cumulative_end": 39913965, "loss_sum": 20173.095703125, "token_normalized_loss": 0.3246394545079659, "grad_norm_before_clip": 0.09021593630313873, "learning_rates_at_step": { "lora": 3.557790224468129e-05, "row_tokens": 3.557790224468129e-05 }, "learning_rates_after_step": { "lora": 3.54090368590223e-05, "row_tokens": 3.54090368590223e-05 } }, { "update_id": 609, "row_count": 10, "row_ids_sha256": "5728a26f0f3af85d710b93cd6d1e724de75e95411289a1ef4316e7021b6c296c", "input_ids_vector_sha256": "39b431e6f0f41e2603f8ac6df39ac5f172c92f41ea3a59894829f34230e81810", "labels_vector_sha256": "083de8a261b622b2da60b5ef1e3f6275a4a6a6b960bcf8627ad3f1e1834e93fc", "planned_active_tokens": 68249, "realized_active_tokens": 68249, "cumulative_start": 39913965, "cumulative_end": 39982214, "loss_sum": 26212.919860839844, "token_normalized_loss": 0.3840777133853953, "grad_norm_before_clip": 0.09110181778669357, "learning_rates_at_step": { "lora": 3.54090368590223e-05, "row_tokens": 3.54090368590223e-05 }, "learning_rates_after_step": { "lora": 3.525850566042014e-05, "row_tokens": 3.525850566042014e-05 } }, { "update_id": 610, "row_count": 15, "row_ids_sha256": "64426860e09bc90b21cd37c2f94a1b5f1f45b7a17c75ce59a187133511d536eb", "input_ids_vector_sha256": "ed8baf97b4f72e776a573621fb3b11f845034a5237279a6e87304bca8b68459b", "labels_vector_sha256": "4ed00ca3320d1181b253509371b1b58d803d06823a5fe70fae08badc46c1367d", "planned_active_tokens": 60901, "realized_active_tokens": 60901, "cumulative_start": 39982214, "cumulative_end": 40043115, "loss_sum": 21898.547760009766, "token_normalized_loss": 0.3595761606543368, "grad_norm_before_clip": 0.09094289690256119, "learning_rates_at_step": { "lora": 3.525850566042014e-05, "row_tokens": 3.525850566042014e-05 }, "learning_rates_after_step": { "lora": 3.508266897842335e-05, "row_tokens": 3.508266897842335e-05 } }, { "update_id": 611, "row_count": 11, "row_ids_sha256": "88df585e62103dcc2418b5c6a882979d06de7faa9bd62a95eb3d0afc532fbe2c", "input_ids_vector_sha256": "73d773865d69f52b74a7dd4e125d5dbed880b690d5a1e4d2b369ecc8cdd40e75", "labels_vector_sha256": "3f24f83dfaf792f78d4951866c78e957e1638cf2182992f486745ce4dc8183e6", "planned_active_tokens": 71214, "realized_active_tokens": 71214, "cumulative_start": 40043115, "cumulative_end": 40114329, "loss_sum": 26161.35009765625, "token_normalized_loss": 0.3673624581915951, "grad_norm_before_clip": 0.08556807041168213, "learning_rates_at_step": { "lora": 3.508266897842335e-05, "row_tokens": 3.508266897842335e-05 }, "learning_rates_after_step": { "lora": 3.492729954743235e-05, "row_tokens": 3.492729954743235e-05 } }, { "update_id": 612, "row_count": 10, "row_ids_sha256": "20de494f8e4ba076b192e3eed44b3e1fd97ca076b72eef2cbfffbc358f262995", "input_ids_vector_sha256": "db235eab2355b143484224f65ebc0faae4f139d515aa7e03ff84763d18ad9534", "labels_vector_sha256": "945cf57adb12a56c37cdadc4788940ff1e01566ed17af35a569b148b61e5c4c1", "planned_active_tokens": 62993, "realized_active_tokens": 62993, "cumulative_start": 40114329, "cumulative_end": 40177322, "loss_sum": 21119.147094726562, "token_normalized_loss": 0.335261808371193, "grad_norm_before_clip": 0.08508262038230896, "learning_rates_at_step": { "lora": 3.492729954743235e-05, "row_tokens": 3.492729954743235e-05 }, "learning_rates_after_step": { "lora": 3.476381334148981e-05, "row_tokens": 3.476381334148981e-05 } }, { "update_id": 613, "row_count": 9, "row_ids_sha256": "0fd4478d373d9e445614fab3d49dde0fb0be3712e620b03a5f72be2f0b67ceeb", "input_ids_vector_sha256": "cf631c8eec8c71e728c71cd4e39b895dd0ff645c9808a4d8632b409e5e359a7d", "labels_vector_sha256": "25de7107b0254d34c9c1829df61616ec004e4980e05f7ef10548ba941cb50e55", "planned_active_tokens": 66354, "realized_active_tokens": 66354, "cumulative_start": 40177322, "cumulative_end": 40243676, "loss_sum": 23697.401794433594, "token_normalized_loss": 0.357135994731796, "grad_norm_before_clip": 0.09074752777814865, "learning_rates_at_step": { "lora": 3.476381334148981e-05, "row_tokens": 3.476381334148981e-05 }, "learning_rates_after_step": { "lora": 3.461067806349955e-05, "row_tokens": 3.461067806349955e-05 } }, { "update_id": 614, "row_count": 8, "row_ids_sha256": "8e2ffbb80121a51c9e35e49a169a41d7b10543b81b70ea107a9bd48cda2acdde", "input_ids_vector_sha256": "dcdd492e52746f52049d18b9b8c9fcc4c731a837d17df7c81c55ffe81d3cd912", "labels_vector_sha256": "b1fc642d830ebbc8750c92a4b2a55832332842e1ead60fcd4e1836c450de5844", "planned_active_tokens": 62219, "realized_active_tokens": 62219, "cumulative_start": 40243676, "cumulative_end": 40305895, "loss_sum": 20776.437377929688, "token_normalized_loss": 0.33392432179767734, "grad_norm_before_clip": 0.08925805985927582, "learning_rates_at_step": { "lora": 3.461067806349955e-05, "row_tokens": 3.461067806349955e-05 }, "learning_rates_after_step": { "lora": 3.444774756996002e-05, "row_tokens": 3.444774756996002e-05 } }, { "update_id": 615, "row_count": 12, "row_ids_sha256": "c27509ae998024ff3acabf7f1e63969c86adb251fb015659794d2631bdd29723", "input_ids_vector_sha256": "7cfd0e96d525903c77c44d401528badb0fc3a2aed3871bb0b018a363ee3889d3", "labels_vector_sha256": "aa2ee30dfe990a397849897b10423b0c8f19cb5f9609472ff6bb0e98a131196f", "planned_active_tokens": 66270, "realized_active_tokens": 66270, "cumulative_start": 40305895, "cumulative_end": 40372165, "loss_sum": 24379.84307861328, "token_normalized_loss": 0.36788657127830515, "grad_norm_before_clip": 0.08940796554088593, "learning_rates_at_step": { "lora": 3.444774756996002e-05, "row_tokens": 3.444774756996002e-05 }, "learning_rates_after_step": { "lora": 3.428342150502274e-05, "row_tokens": 3.428342150502274e-05 } }, { "update_id": 616, "row_count": 11, "row_ids_sha256": "5b21e93b7a1a703d966924f6ba5e9a5d19940c5fe722624917d7dce5fb32e912", "input_ids_vector_sha256": "4eac7ea4bda9684e8c570896ba5a62462936d19c8bcf811c2307bbe5a82c22c8", "labels_vector_sha256": "4e2b56bc14cdab0be1c87845a0af6ef3fedb18754f13c0efbb630db452247289", "planned_active_tokens": 66913, "realized_active_tokens": 66913, "cumulative_start": 40372165, "cumulative_end": 40439078, "loss_sum": 21266.350646972656, "token_normalized_loss": 0.3178209114368308, "grad_norm_before_clip": 0.08406634628772736, "learning_rates_at_step": { "lora": 3.428342150502274e-05, "row_tokens": 3.428342150502274e-05 }, "learning_rates_after_step": { "lora": 3.4111316154978864e-05, "row_tokens": 3.4111316154978864e-05 } }, { "update_id": 617, "row_count": 14, "row_ids_sha256": "ca1f0d6939227a2efa1a3fa746748057a3e80d6b71153cb731d1a716ac73cb29", "input_ids_vector_sha256": "ee5e8b53d27f5345efc21a10d2766913ed349ef0a9ffb0ed01875b0ec7f933eb", "labels_vector_sha256": "dcca073316f32e44dfe1abdfbcd71ce030d28fd465fde6ef578a1c6030cd6c6c", "planned_active_tokens": 70163, "realized_active_tokens": 70163, "cumulative_start": 40439078, "cumulative_end": 40509241, "loss_sum": 22428.33837890625, "token_normalized_loss": 0.3196604817197989, "grad_norm_before_clip": 0.08067683130502701, "learning_rates_at_step": { "lora": 3.4111316154978864e-05, "row_tokens": 3.4111316154978864e-05 }, "learning_rates_after_step": { "lora": 3.396124472285067e-05, "row_tokens": 3.396124472285067e-05 } }, { "update_id": 618, "row_count": 11, "row_ids_sha256": "9d8f495f603c621631031b813fe283063a6e6b9ef115e7916e9a14a639bf9b7d", "input_ids_vector_sha256": "c79416d84172464f51ecf71a83b963548d77951fdc37a0b4d0ddd461653cf024", "labels_vector_sha256": "88b932790b3c1882fef1022d8cad1b42fe8055dbf5be820172650f6a8e28ab49", "planned_active_tokens": 61250, "realized_active_tokens": 61250, "cumulative_start": 40509241, "cumulative_end": 40570491, "loss_sum": 19554.910522460938, "token_normalized_loss": 0.3192638452646684, "grad_norm_before_clip": 0.09003402292728424, "learning_rates_at_step": { "lora": 3.396124472285067e-05, "row_tokens": 3.396124472285067e-05 }, "learning_rates_after_step": { "lora": 3.3805116082878755e-05, "row_tokens": 3.3805116082878755e-05 } }, { "update_id": 619, "row_count": 13, "row_ids_sha256": "73cc02051e799a12cdff49be26248c7f3477c5812041d26b630a0c3bafb08466", "input_ids_vector_sha256": "48e3c1d03e35d5a2d25ee5f0e40724c3bd8282b1daf561c03f131ff5fc64bf05", "labels_vector_sha256": "9c0cc090bf17d9520a2b6a326708cccc94663d97fc0f887d6db552fd7a9b2b71", "planned_active_tokens": 63792, "realized_active_tokens": 63792, "cumulative_start": 40570491, "cumulative_end": 40634283, "loss_sum": 19888.95947265625, "token_normalized_loss": 0.31177827114146367, "grad_norm_before_clip": 0.08422518521547318, "learning_rates_at_step": { "lora": 3.3805116082878755e-05, "row_tokens": 3.3805116082878755e-05 }, "learning_rates_after_step": { "lora": 3.364891688531041e-05, "row_tokens": 3.364891688531041e-05 } }, { "update_id": 620, "row_count": 11, "row_ids_sha256": "6ff8c62b1e7dc88c8895ef5d8585f15551f52ba3533ad74d7c88ea8ed5ecf3a5", "input_ids_vector_sha256": "ee07c0834d2a7c2434d6f3782bd4ca3f0bd903cc26de3a5249312a31bbc2b033", "labels_vector_sha256": "1263d447ea5dd70536e37f8c98b363c31b8e4bf86e3921c239e14ed24a656311", "planned_active_tokens": 63893, "realized_active_tokens": 63893, "cumulative_start": 40634283, "cumulative_end": 40698176, "loss_sum": 17981.722534179688, "token_normalized_loss": 0.2814349386345873, "grad_norm_before_clip": 0.0843622237443924, "learning_rates_at_step": { "lora": 3.364891688531041e-05, "row_tokens": 3.364891688531041e-05 }, "learning_rates_after_step": { "lora": 3.347196805786267e-05, "row_tokens": 3.347196805786267e-05 } }, { "update_id": 621, "row_count": 12, "row_ids_sha256": "90686c50785029686b37a1cb9a1318da0e8184c560d069b02c0e49936e10c14e", "input_ids_vector_sha256": "96bf5628d4bdda1d9650f2b6b4a0a8378b5b8c9fd3bccb460ac8997def5211b5", "labels_vector_sha256": "84767c629c0145cf22a9f3d0eda2769c3b2133c81629a5bfd98f85bb779ddee7", "planned_active_tokens": 72469, "realized_active_tokens": 72469, "cumulative_start": 40698176, "cumulative_end": 40770645, "loss_sum": 24493.423278808594, "token_normalized_loss": 0.3379848387422014, "grad_norm_before_clip": 0.08374995738267899, "learning_rates_at_step": { "lora": 3.347196805786267e-05, "row_tokens": 3.347196805786267e-05 }, "learning_rates_after_step": { "lora": 3.332692751065618e-05, "row_tokens": 3.332692751065618e-05 } }, { "update_id": 622, "row_count": 10, "row_ids_sha256": "7cabb41b6e6b2b5657ed8f7305929bddc23ce57e79edf84a0d3c8251f74bee3f", "input_ids_vector_sha256": "2f5901a1038f57a6bef7008ea1110c161569af8d8135624552300c1358dbee82", "labels_vector_sha256": "ba5bffed4b9f2c23cc16a24bdfacc4f1a7865d01aa41b3daa74d2af39a68da7a", "planned_active_tokens": 59472, "realized_active_tokens": 59472, "cumulative_start": 40770645, "cumulative_end": 40830117, "loss_sum": 14680.720458984375, "token_normalized_loss": 0.246850962788949, "grad_norm_before_clip": 0.07903587073087692, "learning_rates_at_step": { "lora": 3.332692751065618e-05, "row_tokens": 3.332692751065618e-05 }, "learning_rates_after_step": { "lora": 3.31604593045499e-05, "row_tokens": 3.31604593045499e-05 } }, { "update_id": 623, "row_count": 11, "row_ids_sha256": "23926a427b51ed44a8cc4a9b7e36a8424ca5d84d4829721d2a4916beab797bd2", "input_ids_vector_sha256": "ef072fdd15f0e06fc53a60848c43f8e79736cfb2ee99026025fdc438b7a2dc39", "labels_vector_sha256": "f0af44c8d4d23f28043e7fe4450d2428bda96f21e1bf22315944a6b030c1b69e", "planned_active_tokens": 68338, "realized_active_tokens": 68338, "cumulative_start": 40830117, "cumulative_end": 40898455, "loss_sum": 20505.762664794922, "token_normalized_loss": 0.3000638395152759, "grad_norm_before_clip": 0.08086689561605453, "learning_rates_at_step": { "lora": 3.31604593045499e-05, "row_tokens": 3.31604593045499e-05 }, "learning_rates_after_step": { "lora": 3.3003297291774486e-05, "row_tokens": 3.3003297291774486e-05 } }, { "update_id": 624, "row_count": 12, "row_ids_sha256": "0fe70f2f31cfd37e3549abade16e5c68a1d140bdc24fcf58c4f9e7c9d2ca26a8", "input_ids_vector_sha256": "b14f97023d00f1f4e414aa6a575ab0656cadafe8fbe59685d2a729b90d8f15e9", "labels_vector_sha256": "0da988f1784297a73effcd0beda5af4c4fe688d03c7c29ad171bc3aa358eeb9f", "planned_active_tokens": 64597, "realized_active_tokens": 64597, "cumulative_start": 40898455, "cumulative_end": 40963052, "loss_sum": 21197.733764648438, "token_normalized_loss": 0.3281535328985624, "grad_norm_before_clip": 0.08664273470640182, "learning_rates_at_step": { "lora": 3.3003297291774486e-05, "row_tokens": 3.3003297291774486e-05 }, "learning_rates_after_step": { "lora": 3.284472208505432e-05, "row_tokens": 3.284472208505432e-05 } }, { "update_id": 625, "row_count": 12, "row_ids_sha256": "11729e20c0fb6cecb809a8eb2cfb006916f338dd79a52d77e5031ba76bfac861", "input_ids_vector_sha256": "6035ffea4a714f36ca4c366feb4bac2d96eb4cef12b3e5507db9a201a4782ad6", "labels_vector_sha256": "5be9ae24ce4b405bdd9766b7c17a6ee5db727849783d6ff93ae9bf905d548ee6", "planned_active_tokens": 65257, "realized_active_tokens": 65257, "cumulative_start": 40963052, "cumulative_end": 41028309, "loss_sum": 18849.887084960938, "token_normalized_loss": 0.28885616998882785, "grad_norm_before_clip": 0.08657753467559814, "learning_rates_at_step": { "lora": 3.284472208505432e-05, "row_tokens": 3.284472208505432e-05 }, "learning_rates_after_step": { "lora": 3.26799366030822e-05, "row_tokens": 3.26799366030822e-05 } }, { "update_id": 626, "row_count": 10, "row_ids_sha256": "9dea07eb7637df041873947e7f970e2fc9f8b1f0e4bebaf25177a7e903d953d5", "input_ids_vector_sha256": "99ad266e03b27eee603b82e459412a7ee548cfb4c593645c0c5426b9f81fa8cf", "labels_vector_sha256": "60f78589219bc6b071f5570c177ca23ac93e6a969fe8b7336ad59ccebb8ee632", "planned_active_tokens": 67898, "realized_active_tokens": 67898, "cumulative_start": 41028309, "cumulative_end": 41096207, "loss_sum": 23995.387115478516, "token_normalized_loss": 0.35340344510115934, "grad_norm_before_clip": 0.09019146114587784, "learning_rates_at_step": { "lora": 3.26799366030822e-05, "row_tokens": 3.26799366030822e-05 }, "learning_rates_after_step": { "lora": 3.252532764843668e-05, "row_tokens": 3.252532764843668e-05 } }, { "update_id": 627, "row_count": 11, "row_ids_sha256": "c24a79761bb325cad38e8477378e6a020b3528bed73e79c352a62bd84168ae7a", "input_ids_vector_sha256": "8c6e209afb435cfcceb898ef10a45b224d4649e4752f3fc092666a6b278a414f", "labels_vector_sha256": "d68e58e68f67b70416afb7fae62f682804e77d6d2e29e1d094c581a5064beff9", "planned_active_tokens": 63785, "realized_active_tokens": 63785, "cumulative_start": 41096207, "cumulative_end": 41159992, "loss_sum": 20986.845092773438, "token_normalized_loss": 0.32902477216858883, "grad_norm_before_clip": 0.09165072441101074, "learning_rates_at_step": { "lora": 3.252532764843668e-05, "row_tokens": 3.252532764843668e-05 }, "learning_rates_after_step": { "lora": 3.2369169237255836e-05, "row_tokens": 3.2369169237255836e-05 } }, { "update_id": 628, "row_count": 12, "row_ids_sha256": "f0b888435439a6c9f7759dfd25c0c622a44713117a46be2009bfc96a142ef25b", "input_ids_vector_sha256": "885b63a4859f6b04f8f964687a6d6f9df76244a832a83ec1db2be6ac71284580", "labels_vector_sha256": "ccf55ef237e839cbd163d31dc12069abed037410ae2b1ed447f541c3ddd95775", "planned_active_tokens": 64504, "realized_active_tokens": 64504, "cumulative_start": 41159992, "cumulative_end": 41224496, "loss_sum": 21526.857696533203, "token_normalized_loss": 0.3337290353549114, "grad_norm_before_clip": 0.08630254119634628, "learning_rates_at_step": { "lora": 3.2369169237255836e-05, "row_tokens": 3.2369169237255836e-05 }, "learning_rates_after_step": { "lora": 3.2200142517242884e-05, "row_tokens": 3.2200142517242884e-05 } }, { "update_id": 629, "row_count": 11, "row_ids_sha256": "52d4ca07e2e5aaa6d00214a77e149401a958b2d0d43635d9225000e5209f4fd1", "input_ids_vector_sha256": "1306d05517cf7f6a34c236ff51fd43ceae03faaf9e04a78d00f3636cab7a3bd3", "labels_vector_sha256": "7f763c890597e85c463b26cb9c8dc415ad27a906384a77ead28279e4c6d83b5f", "planned_active_tokens": 69911, "realized_active_tokens": 69911, "cumulative_start": 41224496, "cumulative_end": 41294407, "loss_sum": 24161.554412841797, "token_normalized_loss": 0.34560447444381853, "grad_norm_before_clip": 0.08632335066795349, "learning_rates_at_step": { "lora": 3.2200142517242884e-05, "row_tokens": 3.2200142517242884e-05 }, "learning_rates_after_step": { "lora": 3.2057452245571316e-05, "row_tokens": 3.2057452245571316e-05 } }, { "update_id": 630, "row_count": 11, "row_ids_sha256": "fb8ec0997dfc974b799ada1d9c980fd90f4b4867266ae70611b013c4f59ac22b", "input_ids_vector_sha256": "4505ef3ad605fca368bd9bf6f5afceed61164b3d326a21a9f06ad53f3b4a57f3", "labels_vector_sha256": "4ddd308464a9e2e25ea3f83a6e82d50db2c405814ffb9a389edb70c182beb716", "planned_active_tokens": 59093, "realized_active_tokens": 59093, "cumulative_start": 41294407, "cumulative_end": 41353500, "loss_sum": 19344.211547851562, "token_normalized_loss": 0.3273519968160622, "grad_norm_before_clip": 0.09371176362037659, "learning_rates_at_step": { "lora": 3.2057452245571316e-05, "row_tokens": 3.2057452245571316e-05 }, "learning_rates_after_step": { "lora": 3.1892341238414416e-05, "row_tokens": 3.1892341238414416e-05 } }, { "update_id": 631, "row_count": 11, "row_ids_sha256": "9540f87d1187ea9df7578b54efe6f84ab7cbf5265b692cce70718ba643cb19f2", "input_ids_vector_sha256": "cd3772a15dab67b56b86acc3ff47ec62c9a9df9da63d4b7087d1f7e41a028f5b", "labels_vector_sha256": "eff990ce84ecddb48bdfc7d9f10d81cf43b7ed024dc91b8aced4e5ce95f5915b", "planned_active_tokens": 68465, "realized_active_tokens": 68465, "cumulative_start": 41353500, "cumulative_end": 41421965, "loss_sum": 23234.398193359375, "token_normalized_loss": 0.3393616912781622, "grad_norm_before_clip": 0.08696706593036652, "learning_rates_at_step": { "lora": 3.1892341238414416e-05, "row_tokens": 3.1892341238414416e-05 }, "learning_rates_after_step": { "lora": 3.172788556522253e-05, "row_tokens": 3.172788556522253e-05 } }, { "update_id": 632, "row_count": 11, "row_ids_sha256": "4bc386b1bd3cf12074e793e978cc1faa713a265d7061a4eaef7fc538f01c3155", "input_ids_vector_sha256": "ff26af7cf29dde027273db70bdf6e2956e82963f32658ad4b99434d89142430e", "labels_vector_sha256": "c9fc2e269e4bc5e0700b3976a3179e8fa7b1da4329e5f9d208f6f8f6e5ed4c90", "planned_active_tokens": 68287, "realized_active_tokens": 68287, "cumulative_start": 41421965, "cumulative_end": 41490252, "loss_sum": 24041.996643066406, "token_normalized_loss": 0.35207281976168825, "grad_norm_before_clip": 0.08930042386054993, "learning_rates_at_step": { "lora": 3.172788556522253e-05, "row_tokens": 3.172788556522253e-05 }, "learning_rates_after_step": { "lora": 3.1580364154927186e-05, "row_tokens": 3.1580364154927186e-05 } }, { "update_id": 633, "row_count": 10, "row_ids_sha256": "e5e9664f417f83d670cfb50cbf0f791ecf72632594c9ef11e9de2ff4c2120e72", "input_ids_vector_sha256": "7ca2521b0e1c2456c5201f4ab6edb4c97906b209d22758ecc85d67de30100513", "labels_vector_sha256": "ff420a7a4e09b2f6dcb22628ee5af987db3fcf80ec057399e8d93fa1ee34ef9c", "planned_active_tokens": 61336, "realized_active_tokens": 61336, "cumulative_start": 41490252, "cumulative_end": 41551588, "loss_sum": 20436.150482177734, "token_normalized_loss": 0.33318361944335684, "grad_norm_before_clip": 0.09251488000154495, "learning_rates_at_step": { "lora": 3.1580364154927186e-05, "row_tokens": 3.1580364154927186e-05 }, "learning_rates_after_step": { "lora": 3.1411820702015626e-05, "row_tokens": 3.1411820702015626e-05 } }, { "update_id": 634, "row_count": 14, "row_ids_sha256": "7dd02f373dbc683045514b14677f10ae5fdd1a791e783f6c71b23e313d768ce4", "input_ids_vector_sha256": "0e4e01600d8fdfe897041a2999628b187cf07b362c694ced876d73fef037d19d", "labels_vector_sha256": "90294a485abf354da8f31fe2fe0595f0aa56b4619f366e3ab8ed5a77d1e0790a", "planned_active_tokens": 70171, "realized_active_tokens": 70171, "cumulative_start": 41551588, "cumulative_end": 41621759, "loss_sum": 22152.186950683594, "token_normalized_loss": 0.3156886313531743, "grad_norm_before_clip": 0.08218666166067123, "learning_rates_at_step": { "lora": 3.1411820702015626e-05, "row_tokens": 3.1411820702015626e-05 }, "learning_rates_after_step": { "lora": 3.126477987729968e-05, "row_tokens": 3.126477987729968e-05 } }, { "update_id": 635, "row_count": 11, "row_ids_sha256": "5ea6b65d047caf43153f618b887a065e5b6490db89802413b2ed367803a277c7", "input_ids_vector_sha256": "cbea6c558183b6020b9a1f2d2b090823803f8e2ceeb76c92800b8dfdd26631f3", "labels_vector_sha256": "2018e56775be9586df50e07857e3235bb3435b2fcfdb7130185a8199e87e2495", "planned_active_tokens": 61302, "realized_active_tokens": 61302, "cumulative_start": 41621759, "cumulative_end": 41683061, "loss_sum": 22335.88851928711, "token_normalized_loss": 0.36435823495623487, "grad_norm_before_clip": 0.09216821938753128, "learning_rates_at_step": { "lora": 3.126477987729968e-05, "row_tokens": 3.126477987729968e-05 }, "learning_rates_after_step": { "lora": 3.11041601576104e-05, "row_tokens": 3.11041601576104e-05 } }, { "update_id": 636, "row_count": 10, "row_ids_sha256": "2e703c3ce6cd18a5b7096cb84f0f9b9a863867847d3b23bdfef199deb05a57f0", "input_ids_vector_sha256": "6ec66af281d94cf17536c9cf50755ad438d62d0846ce56ecf1ed909da7afe12d", "labels_vector_sha256": "1117e6b6e97e5a47658adc36b313d020ebf1846cb4ef6db26ce326054961df7d", "planned_active_tokens": 67053, "realized_active_tokens": 67053, "cumulative_start": 41683061, "cumulative_end": 41750114, "loss_sum": 24875.193359375, "token_normalized_loss": 0.37097808240309904, "grad_norm_before_clip": 0.09025490283966064, "learning_rates_at_step": { "lora": 3.11041601576104e-05, "row_tokens": 3.11041601576104e-05 }, "learning_rates_after_step": { "lora": 3.095564335535043e-05, "row_tokens": 3.095564335535043e-05 } }, { "update_id": 637, "row_count": 10, "row_ids_sha256": "28f5375a231418c73be08e185c67ffa929f453df509bcf55f91b1b5d9e6cd830", "input_ids_vector_sha256": "59469ed9a20489a5e77137be02b724a10537f33321fc2ae5f3cb6ade5e50e3b2", "labels_vector_sha256": "58c704343cf07b0626ba11614bf6a9de69b281b5a91b09f011c367fdf127f029", "planned_active_tokens": 62085, "realized_active_tokens": 62085, "cumulative_start": 41750114, "cumulative_end": 41812199, "loss_sum": 23371.671325683594, "token_normalized_loss": 0.37644634494134804, "grad_norm_before_clip": 0.09287688136100769, "learning_rates_at_step": { "lora": 3.095564335535043e-05, "row_tokens": 3.095564335535043e-05 }, "learning_rates_after_step": { "lora": 3.0796085899210794e-05, "row_tokens": 3.0796085899210794e-05 } }, { "update_id": 638, "row_count": 11, "row_ids_sha256": "20f5d8c8005fe85a6a41180fc77bdb58e8dbd4e4420324614e4e1b5667024282", "input_ids_vector_sha256": "0b3eb50626a713ed516ea1c3d71f4115df190c3527faef1973d38fe4218278ea", "labels_vector_sha256": "d2a532147203e5757ff9270ff9401d6efd0e850cefb7dc07d2bccdbfb257888e", "planned_active_tokens": 66792, "realized_active_tokens": 66792, "cumulative_start": 41812199, "cumulative_end": 41878991, "loss_sum": 24622.615173339844, "token_normalized_loss": 0.3686461727952426, "grad_norm_before_clip": 0.087869793176651, "learning_rates_at_step": { "lora": 3.0796085899210794e-05, "row_tokens": 3.0796085899210794e-05 }, "learning_rates_after_step": { "lora": 3.0627868996953616e-05, "row_tokens": 3.0627868996953616e-05 } }, { "update_id": 639, "row_count": 11, "row_ids_sha256": "0dd529e4f7de0e03c1e064abdd70680907683135b844f637c6645b0336580cbe", "input_ids_vector_sha256": "0031685fe9f5c75cd9d7cde6b7d686ad973d967f13b053902d17b6228ff1ab49", "labels_vector_sha256": "ccdd5174c512551968cbbef0db6e8b8e393c5dba1dfebabefe8d0b24127d7648", "planned_active_tokens": 70521, "realized_active_tokens": 70521, "cumulative_start": 41878991, "cumulative_end": 41949512, "loss_sum": 26638.013763427734, "token_normalized_loss": 0.37773165104618106, "grad_norm_before_clip": 0.09018349647521973, "learning_rates_at_step": { "lora": 3.0627868996953616e-05, "row_tokens": 3.0627868996953616e-05 }, "learning_rates_after_step": { "lora": 3.0479647631080505e-05, "row_tokens": 3.0479647631080505e-05 } }, { "update_id": 640, "row_count": 12, "row_ids_sha256": "f749242e78cb73ab4fb941f773c34b97f49762a4e8454b695fba46606983634f", "input_ids_vector_sha256": "e43a29404304ede512d130a7a849f94d9b83078fa7c50bdf963ab065c271738a", "labels_vector_sha256": "c1234ceb52a9693e42aa01e491ac4222752c5ff02063460f24ac1a8e048b0259", "planned_active_tokens": 62228, "realized_active_tokens": 62228, "cumulative_start": 41949512, "cumulative_end": 42011740, "loss_sum": 19239.480499267578, "token_normalized_loss": 0.30917722728140995, "grad_norm_before_clip": 0.08657842129468918, "learning_rates_at_step": { "lora": 3.0479647631080505e-05, "row_tokens": 3.0479647631080505e-05 }, "learning_rates_after_step": { "lora": 3.032948194443006e-05, "row_tokens": 3.032948194443006e-05 } }, { "update_id": 641, "row_count": 13, "row_ids_sha256": "4e10599bba5a15b4b5fc1313198f39c8c62f4e1e1cebe6342c504263226be3ef", "input_ids_vector_sha256": "d69b1aae7a898cfb0c2c9a361b59183d27783ce3adcbea306a5548c923418fba", "labels_vector_sha256": "ba507085ec157f5667f0122b39bcd6855ef97f40582761651217200847ca3fef", "planned_active_tokens": 63131, "realized_active_tokens": 63131, "cumulative_start": 42011740, "cumulative_end": 42074871, "loss_sum": 20130.54248046875, "token_normalized_loss": 0.31886937448272246, "grad_norm_before_clip": 0.08812632411718369, "learning_rates_at_step": { "lora": 3.032948194443006e-05, "row_tokens": 3.032948194443006e-05 }, "learning_rates_after_step": { "lora": 3.015179105972731e-05, "row_tokens": 3.015179105972731e-05 } }, { "update_id": 642, "row_count": 15, "row_ids_sha256": "7f25420869cad76e524a2cf6dd4ff3ff5e81ed36a5afe1204bac32e3f3884bcd", "input_ids_vector_sha256": "858f625e7178ce6f8339f843d17a7f26e984d59217f2ed925ccdf01040ecf7cd", "labels_vector_sha256": "49244b0038460a5ea80c346b7bd634105606a197a2bae82cb8f95c48a5c65780", "planned_active_tokens": 74817, "realized_active_tokens": 74817, "cumulative_start": 42074871, "cumulative_end": 42149688, "loss_sum": 23115.305694580078, "token_normalized_loss": 0.30895793328494964, "grad_norm_before_clip": 0.07721860706806183, "learning_rates_at_step": { "lora": 3.015179105972731e-05, "row_tokens": 3.015179105972731e-05 }, "learning_rates_after_step": { "lora": 3.0018394785591163e-05, "row_tokens": 3.0018394785591163e-05 } }, { "update_id": 643, "row_count": 10, "row_ids_sha256": "330df6a2b44477465f817059c2df8dcf1146bcde5f4bd8ba6a1529dececd8627", "input_ids_vector_sha256": "7ccd1eb0a77128b066f4faad0d0c3fb175d9885292c8d0651cf9de65ce0ebc07", "labels_vector_sha256": "c1caeb0ac5fa7eff5ba76b50865aca3810d43c7b9f74955f72bf8f2e8e74beef", "planned_active_tokens": 56249, "realized_active_tokens": 56249, "cumulative_start": 42149688, "cumulative_end": 42205937, "loss_sum": 16695.896545410156, "token_normalized_loss": 0.29682121540667666, "grad_norm_before_clip": 0.08962173759937286, "learning_rates_at_step": { "lora": 3.0018394785591163e-05, "row_tokens": 3.0018394785591163e-05 }, "learning_rates_after_step": { "lora": 2.986144801296477e-05, "row_tokens": 2.986144801296477e-05 } }, { "update_id": 644, "row_count": 14, "row_ids_sha256": "46b67478e68a4319ead56b060bcf2e6fac0c4796d79007861b6480784e4e33e4", "input_ids_vector_sha256": "9f51fa4cbf1d634661bba13d7e87aa0e43370e5283ceff1227e1a13a571ab694", "labels_vector_sha256": "13e3ec9cff2db67ee840e48b45f4dc47cac60bfb346f6abf0c91c5854e426945", "planned_active_tokens": 66271, "realized_active_tokens": 66271, "cumulative_start": 42205937, "cumulative_end": 42272208, "loss_sum": 18910.01382446289, "token_normalized_loss": 0.2853437223591449, "grad_norm_before_clip": 0.08070516586303711, "learning_rates_at_step": { "lora": 2.986144801296477e-05, "row_tokens": 2.986144801296477e-05 }, "learning_rates_after_step": { "lora": 2.9684385765054085e-05, "row_tokens": 2.9684385765054085e-05 } }, { "update_id": 645, "row_count": 13, "row_ids_sha256": "ba9236b859e986ba58f7d7756ec69e5a0163ab780b0f0f739b20c5bc80b45769", "input_ids_vector_sha256": "4256c6854f43e7e4fdd8bb48863ae84690b6ac8ebced7e008bd36f115ba7f1a1", "labels_vector_sha256": "a5bf6f4c1f854b9492fa21da69ff080b353d218d10b71513d05f8400d95014dd", "planned_active_tokens": 74885, "realized_active_tokens": 74885, "cumulative_start": 42272208, "cumulative_end": 42347093, "loss_sum": 26940.958251953125, "token_normalized_loss": 0.3597644154630851, "grad_norm_before_clip": 0.07746203243732452, "learning_rates_at_step": { "lora": 2.9684385765054085e-05, "row_tokens": 2.9684385765054085e-05 }, "learning_rates_after_step": { "lora": 2.9538180333134436e-05, "row_tokens": 2.9538180333134436e-05 } }, { "update_id": 646, "row_count": 8, "row_ids_sha256": "4c009dce547cf6b4e662d27c377c9f017c0acbeee521eb949ec72152ac5604b9", "input_ids_vector_sha256": "50c72863fcba6326ce1c149453fb44956b6b52cbe009f8d9baf7cc81eb9206c6", "labels_vector_sha256": "afd2c9e9b7ad394711a6e86cbb42dd061f1b9faef914b849f90de3e417710373", "planned_active_tokens": 61932, "realized_active_tokens": 61932, "cumulative_start": 42347093, "cumulative_end": 42409025, "loss_sum": 25181.703002929688, "token_normalized_loss": 0.4066024511226779, "grad_norm_before_clip": 0.09318512678146362, "learning_rates_at_step": { "lora": 2.9538180333134436e-05, "row_tokens": 2.9538180333134436e-05 }, "learning_rates_after_step": { "lora": 2.9381271614320505e-05, "row_tokens": 2.9381271614320505e-05 } }, { "update_id": 647, "row_count": 8, "row_ids_sha256": "ce0bda7b8e8db583167c1d715db1f5d27438f16b31fdc6168bfd5a2c02339908", "input_ids_vector_sha256": "0cbc4b6a55f6be5404c672789478a8358da793f1d2fb5bc5b4813419d792efbf", "labels_vector_sha256": "56f1a9d5e3391d5224961f58421ff95f636ad7f03a7cf445ea465c6a4934f658", "planned_active_tokens": 66565, "realized_active_tokens": 66565, "cumulative_start": 42409025, "cumulative_end": 42475590, "loss_sum": 24487.63232421875, "token_normalized_loss": 0.3678754949931458, "grad_norm_before_clip": 0.08547858893871307, "learning_rates_at_step": { "lora": 2.9381271614320505e-05, "row_tokens": 2.9381271614320505e-05 }, "learning_rates_after_step": { "lora": 2.9238831343978278e-05, "row_tokens": 2.9238831343978278e-05 } }, { "update_id": 648, "row_count": 8, "row_ids_sha256": "b3ef446b630a66462799b30f10cb18824e9d5d3a069dfa02bab4633724be272d", "input_ids_vector_sha256": "140a18b45546e668874fda1d944b1f05834b7d4329d0e3173e6981117fbf80ff", "labels_vector_sha256": "a89224676d8d580ae468849c6e2c2f2840e6517a5ed205d0543ae6909cf828cc", "planned_active_tokens": 60517, "realized_active_tokens": 60517, "cumulative_start": 42475590, "cumulative_end": 42536107, "loss_sum": 22166.870727539062, "token_normalized_loss": 0.36629163255843916, "grad_norm_before_clip": 0.08645419031381607, "learning_rates_at_step": { "lora": 2.9238831343978278e-05, "row_tokens": 2.9238831343978278e-05 }, "learning_rates_after_step": { "lora": 2.908223796195259e-05, "row_tokens": 2.908223796195259e-05 } }, { "update_id": 649, "row_count": 8, "row_ids_sha256": "36604f466b26ea6d1b2d8b24953a2c8ec82ac7b2821ad62e6f3687a0a4ac8817", "input_ids_vector_sha256": "f99d80f651b3a8381dd15c5616abf5c3c5cc1fd33621b3cffc4f9bf36067ceb2", "labels_vector_sha256": "f1cd73f3ca5af17499a052e66ac79c94751b1d8b176c73ebefd01e51e81c60b8", "planned_active_tokens": 66630, "realized_active_tokens": 66630, "cumulative_start": 42536107, "cumulative_end": 42602737, "loss_sum": 28388.95343017578, "token_normalized_loss": 0.426068639204199, "grad_norm_before_clip": 0.08306658267974854, "learning_rates_at_step": { "lora": 2.908223796195259e-05, "row_tokens": 2.908223796195259e-05 }, "learning_rates_after_step": { "lora": 2.891944546790053e-05, "row_tokens": 2.891944546790053e-05 } }, { "update_id": 650, "row_count": 8, "row_ids_sha256": "93e813cb132ab3691991674a593d3b4a5b6f535088a40ca8601120efc21cac51", "input_ids_vector_sha256": "86eab58903424b2c25fbd2fe16ac56969606cb02fe0f5d93de9cdc304e7f17c3", "labels_vector_sha256": "1c3a4a6135f415fe02ddb36e22de9548bfd3ed3cfad994e1043fece42c6141e1", "planned_active_tokens": 69380, "realized_active_tokens": 69380, "cumulative_start": 42602737, "cumulative_end": 42672117, "loss_sum": 28027.07049560547, "token_normalized_loss": 0.403964694373097, "grad_norm_before_clip": 0.08195129781961441, "learning_rates_at_step": { "lora": 2.891944546790053e-05, "row_tokens": 2.891944546790053e-05 }, "learning_rates_after_step": { "lora": 2.878120081401211e-05, "row_tokens": 2.878120081401211e-05 } }, { "update_id": 651, "row_count": 9, "row_ids_sha256": "15a2b452c5c2ff5ea46ce4daa75d961b4672b48cd780afe8dc26d7c79f350876", "input_ids_vector_sha256": "1efc663e30a528d3754efe9894abe262132fa5d9b5297a03f5509efd9907886c", "labels_vector_sha256": "c7468b137c1af9403a0e2bd379be91b101890a7c36c220043bb13fd3b9a07d61", "planned_active_tokens": 59009, "realized_active_tokens": 59009, "cumulative_start": 42672117, "cumulative_end": 42731126, "loss_sum": 24562.438598632812, "token_normalized_loss": 0.41624902300721606, "grad_norm_before_clip": 0.08925101906061172, "learning_rates_at_step": { "lora": 2.878120081401211e-05, "row_tokens": 2.878120081401211e-05 }, "learning_rates_after_step": { "lora": 2.8621602153575445e-05, "row_tokens": 2.8621602153575445e-05 } }, { "update_id": 652, "row_count": 7, "row_ids_sha256": "4e2d808834b83e278f09258c423803f4d950e87e3b90b7c6c0e79d46c76e21aa", "input_ids_vector_sha256": "d98a9919550a977912a0b7b219434b6da288d7493ec1ab435dc0df25943067ed", "labels_vector_sha256": "25c83d353f13be687376ebcbe543a4b53cab3e3f6d09f7c60f5a9ecc4d4717f9", "planned_active_tokens": 68229, "realized_active_tokens": 68229, "cumulative_start": 42731126, "cumulative_end": 42799355, "loss_sum": 25233.027587890625, "token_normalized_loss": 0.36982848331194396, "grad_norm_before_clip": 0.07959965616464615, "learning_rates_at_step": { "lora": 2.8621602153575445e-05, "row_tokens": 2.8621602153575445e-05 }, "learning_rates_after_step": { "lora": 2.8473750137632647e-05, "row_tokens": 2.8473750137632647e-05 } }, { "update_id": 653, "row_count": 8, "row_ids_sha256": "14457d4395352cf0f73e8fb26064d8417d3bec976da156a9d372c76bb1285b25", "input_ids_vector_sha256": "75aba76b5ed8f41dcacfb72baaf116c2da05cc7c5e20751ae2da592626e8a064", "labels_vector_sha256": "ef4196a9382e1c9ad5825a938112a19149c603b64e463ee65f8ee412ca75b928", "planned_active_tokens": 63309, "realized_active_tokens": 63309, "cumulative_start": 42799355, "cumulative_end": 42862664, "loss_sum": 22216.44287109375, "token_normalized_loss": 0.35092076752268636, "grad_norm_before_clip": 0.07826334983110428, "learning_rates_at_step": { "lora": 2.8473750137632647e-05, "row_tokens": 2.8473750137632647e-05 }, "learning_rates_after_step": { "lora": 2.8323111606644848e-05, "row_tokens": 2.8323111606644848e-05 } }, { "update_id": 654, "row_count": 7, "row_ids_sha256": "2db6102a1f8acbc7eb7ea1e81bf1745e272938914b96d357c4e75641454c95de", "input_ids_vector_sha256": "e6aa8463319a527a9de4dac0b89a2014be12e0a346a2d20ac46221c9723bd0e4", "labels_vector_sha256": "2943339c6d9cf381a4d7fa230ff8185011693caa190dd538b4172af18697a851", "planned_active_tokens": 64604, "realized_active_tokens": 64604, "cumulative_start": 42862664, "cumulative_end": 42927268, "loss_sum": 24805.728271484375, "token_normalized_loss": 0.3839658267519716, "grad_norm_before_clip": 0.08215506374835968, "learning_rates_at_step": { "lora": 2.8323111606644848e-05, "row_tokens": 2.8323111606644848e-05 }, "learning_rates_after_step": { "lora": 2.8156496536579634e-05, "row_tokens": 2.8156496536579634e-05 } }, { "update_id": 655, "row_count": 8, "row_ids_sha256": "748f685c1059102e6e51478322b21fa88ce2a2b2b7c01fb72c296d032e8abec0", "input_ids_vector_sha256": "be08ba8dd88943400337b90ede06ff75067e7231c1d1f1baff8d8c51e25abc8e", "labels_vector_sha256": "118692e8f5e0598a3b4203a6136010d7acde623041d34bca617062dc0b14ea9a", "planned_active_tokens": 71577, "realized_active_tokens": 71577, "cumulative_start": 42927268, "cumulative_end": 42998845, "loss_sum": 26208.802368164062, "token_normalized_loss": 0.36616234779557766, "grad_norm_before_clip": 0.0738176703453064, "learning_rates_at_step": { "lora": 2.8156496536579634e-05, "row_tokens": 2.8156496536579634e-05 }, "learning_rates_after_step": { "lora": 2.8000600147724654e-05, "row_tokens": 2.8000600147724654e-05 } }, { "update_id": 656, "row_count": 8, "row_ids_sha256": "a4eaf69c4597a7082b54afb722a19da34c2594655ec851397142deede9d5094e", "input_ids_vector_sha256": "67882a975b080173defb5a6a5fdedfcb4f3f78a1eedc42451990f18c8d636c79", "labels_vector_sha256": "f69c0274bd72625bf8e6a9e9fff6c6b0775220bb975bfa0f2cbb1b5be6fe5ed9", "planned_active_tokens": 67089, "realized_active_tokens": 67089, "cumulative_start": 42998845, "cumulative_end": 43065934, "loss_sum": 23184.478271484375, "token_normalized_loss": 0.3455779378360741, "grad_norm_before_clip": 0.07736439257860184, "learning_rates_at_step": { "lora": 2.8000600147724654e-05, "row_tokens": 2.8000600147724654e-05 }, "learning_rates_after_step": { "lora": 2.7866674957054556e-05, "row_tokens": 2.7866674957054556e-05 } }, { "update_id": 657, "row_count": 7, "row_ids_sha256": "fd2b8aac9f2b7001e39b8aef5130a464acb6a63258a5dd08dc56b61737139717", "input_ids_vector_sha256": "95c90e9cbd075802660673772f165f6af646aabe8688e2c90c5e1ddc04aa0303", "labels_vector_sha256": "ad0941b48d54bf2f94786f2cd998a02444b3d02900984744421f27c3fe8537d0", "planned_active_tokens": 57725, "realized_active_tokens": 57725, "cumulative_start": 43065934, "cumulative_end": 43123659, "loss_sum": 25085.937255859375, "token_normalized_loss": 0.43457665233190773, "grad_norm_before_clip": 0.09051207453012466, "learning_rates_at_step": { "lora": 2.7866674957054556e-05, "row_tokens": 2.7866674957054556e-05 }, "learning_rates_after_step": { "lora": 2.770148570896196e-05, "row_tokens": 2.770148570896196e-05 } }, { "update_id": 658, "row_count": 10, "row_ids_sha256": "7f226749563d4b452c5ef80bd73c5b4f19c4a7eb85e0e61a2c4f2c588c370206", "input_ids_vector_sha256": "676b13aa7a395188e14881b4e47e6dd6ad79d4829a8120a4851d16a5d7fe9593", "labels_vector_sha256": "e7f49565e7555a8536a3005563fff1a8a55521d7dfd8e5ec09f30d69516bc67a", "planned_active_tokens": 71318, "realized_active_tokens": 71318, "cumulative_start": 43123659, "cumulative_end": 43194977, "loss_sum": 24087.15087890625, "token_normalized_loss": 0.33774293837328934, "grad_norm_before_clip": 0.07588627934455872, "learning_rates_at_step": { "lora": 2.770148570896196e-05, "row_tokens": 2.770148570896196e-05 }, "learning_rates_after_step": { "lora": 2.7556635272761078e-05, "row_tokens": 2.7556635272761078e-05 } }, { "update_id": 659, "row_count": 7, "row_ids_sha256": "958781cf69648741c857f53a4c3d345634a0506a05ec5b929417f43d0a423489", "input_ids_vector_sha256": "75016876ba0e9055a4e8342d2e44a91968e2cc4d4cc1343285e9e5fce72d0254", "labels_vector_sha256": "3e63c9e5325a53798712de8a6019a1b4d8eb15f1900d06904c1c5b34a3758f16", "planned_active_tokens": 62645, "realized_active_tokens": 62645, "cumulative_start": 43194977, "cumulative_end": 43257622, "loss_sum": 21794.149047851562, "token_normalized_loss": 0.3478992584859376, "grad_norm_before_clip": 0.08674792945384979, "learning_rates_at_step": { "lora": 2.7556635272761078e-05, "row_tokens": 2.7556635272761078e-05 }, "learning_rates_after_step": { "lora": 2.7402591482509994e-05, "row_tokens": 2.7402591482509994e-05 } }, { "update_id": 660, "row_count": 8, "row_ids_sha256": "4f1505c3baed3a672cfb463f523353e37092649e2ac2965bf34942c95d01e568", "input_ids_vector_sha256": "44eb33d18351fadb92b3a79f581e6cd0a2e91e26bc6f51cde15244540c4d3a02", "labels_vector_sha256": "c7f5bb9575e12340271988740f9968fa42c703fc7d0d47552bd2076975586f67", "planned_active_tokens": 66733, "realized_active_tokens": 66733, "cumulative_start": 43257622, "cumulative_end": 43324355, "loss_sum": 24501.832641601562, "token_normalized_loss": 0.36716216327156825, "grad_norm_before_clip": 0.08278649300336838, "learning_rates_at_step": { "lora": 2.7402591482509994e-05, "row_tokens": 2.7402591482509994e-05 }, "learning_rates_after_step": { "lora": 2.7246526008248565e-05, "row_tokens": 2.7246526008248565e-05 } }, { "update_id": 661, "row_count": 9, "row_ids_sha256": "23f52298589885c641770e59675632d6045e73e3b9cee7ebfc229cf8bdbafda9", "input_ids_vector_sha256": "a971cb7ca0715562997fff92e730037d41b1f7d0850ebaa6b50ea1303529b065", "labels_vector_sha256": "c846f43a873ae192cd90c7960985f528a07f11906a239161f6de02766ba4e6be", "planned_active_tokens": 67728, "realized_active_tokens": 67728, "cumulative_start": 43324355, "cumulative_end": 43392083, "loss_sum": 23339.258728027344, "token_normalized_loss": 0.34460280427633094, "grad_norm_before_clip": 0.07836339622735977, "learning_rates_at_step": { "lora": 2.7246526008248565e-05, "row_tokens": 2.7246526008248565e-05 }, "learning_rates_after_step": { "lora": 2.7099923335526512e-05, "row_tokens": 2.7099923335526512e-05 } }, { "update_id": 662, "row_count": 8, "row_ids_sha256": "be5cf277fab8a48af524c97dd3d05d6680c9992ac21b15f916bf86ac90a95edc", "input_ids_vector_sha256": "5ee93db933590de44058a64582232ad0fd4cb966564a9cd332fb0574997acd74", "labels_vector_sha256": "3b665465b7aa63455a3fb3d793cae59e4285855cdab226b468ea5ac1ffaa8b6e", "planned_active_tokens": 63732, "realized_active_tokens": 63732, "cumulative_start": 43392083, "cumulative_end": 43455815, "loss_sum": 21284.0107421875, "token_normalized_loss": 0.333961130078885, "grad_norm_before_clip": 0.08487588167190552, "learning_rates_at_step": { "lora": 2.7099923335526512e-05, "row_tokens": 2.7099923335526512e-05 }, "learning_rates_after_step": { "lora": 2.6946973117539453e-05, "row_tokens": 2.6946973117539453e-05 } }, { "update_id": 663, "row_count": 13, "row_ids_sha256": "52756326bc6635d5baf96b33e22407cd5f459716b34c33bc83ee304c5ab06146", "input_ids_vector_sha256": "9c3990acec6a9ca3395f4be797afe6c8e03cd1f42878eba001ab1f2b03326f02", "labels_vector_sha256": "6538c0a037f08f45b3117a1a16a4721781cefbca2a559b2b54b44509583834a6", "planned_active_tokens": 66607, "realized_active_tokens": 66607, "cumulative_start": 43455815, "cumulative_end": 43522422, "loss_sum": 19973.106811523438, "token_normalized_loss": 0.2998649813311429, "grad_norm_before_clip": 0.08416280895471573, "learning_rates_at_step": { "lora": 2.6946973117539453e-05, "row_tokens": 2.6946973117539453e-05 }, "learning_rates_after_step": { "lora": 2.680384679311976e-05, "row_tokens": 2.680384679311976e-05 } }, { "update_id": 664, "row_count": 12, "row_ids_sha256": "0a15ac95babee2bc63511bcb782ee4a7f7cfdf31650d87fe4c01f4fa2f8898ea", "input_ids_vector_sha256": "705a603ca6a1ee5f87a8c3bff6b4175804c078e9ab7b2b5215d9ab6b77e05f04", "labels_vector_sha256": "c6aa2ca9921e96f750adc6de6ab655d0c97d9c1ce659253566135ac305f9aa7f", "planned_active_tokens": 62437, "realized_active_tokens": 62437, "cumulative_start": 43522422, "cumulative_end": 43584859, "loss_sum": 21588.217041015625, "token_normalized_loss": 0.34575999873497487, "grad_norm_before_clip": 0.09385879337787628, "learning_rates_at_step": { "lora": 2.680384679311976e-05, "row_tokens": 2.680384679311976e-05 }, "learning_rates_after_step": { "lora": 2.6660761044741135e-05, "row_tokens": 2.6660761044741135e-05 } }, { "update_id": 665, "row_count": 10, "row_ids_sha256": "23dc88ff41883a1de36bd2d7a53903835c900501797d68d1778b08ddc5483ecc", "input_ids_vector_sha256": "2a8d26d5d8c862feaaeec8a1f5a7f15073153d28528b8583b473f073a4290e63", "labels_vector_sha256": "c349bf05cd4fcbdc2edd7df63dd73a651a0d33550b1de0caed3d9a2502694717", "planned_active_tokens": 62525, "realized_active_tokens": 62525, "cumulative_start": 43584859, "cumulative_end": 43647384, "loss_sum": 20724.694061279297, "token_normalized_loss": 0.3314625199724798, "grad_norm_before_clip": 0.09356598556041718, "learning_rates_at_step": { "lora": 2.6660761044741135e-05, "row_tokens": 2.6660761044741135e-05 }, "learning_rates_after_step": { "lora": 2.6506744427015206e-05, "row_tokens": 2.6506744427015206e-05 } }, { "update_id": 666, "row_count": 14, "row_ids_sha256": "c314b3ad1db4ff4b012f2673ac144bfe850d29474fd1eb0993fa737473c5cc0a", "input_ids_vector_sha256": "a281ed34ca47d57eb146249699986c8b4dea0e01ff0bbd5c61c60989a3dd02b0", "labels_vector_sha256": "c94d94f7a68d2dcde88ed3a9b728f2c35184cfcfd3ce2d537f1a27da022a3d18", "planned_active_tokens": 67421, "realized_active_tokens": 67421, "cumulative_start": 43647384, "cumulative_end": 43714805, "loss_sum": 21438.62774658203, "token_normalized_loss": 0.31798145602382094, "grad_norm_before_clip": 0.08870238810777664, "learning_rates_at_step": { "lora": 2.6506744427015206e-05, "row_tokens": 2.6506744427015206e-05 }, "learning_rates_after_step": { "lora": 2.6350461987214116e-05, "row_tokens": 2.6350461987214116e-05 } }, { "update_id": 667, "row_count": 15, "row_ids_sha256": "10437a20c5ee378e2f3d9f20987ca5311c65400f9d0d59d998f095c6768a701e", "input_ids_vector_sha256": "8a4e8886b2f29f86196ca7e9ab28f9dad9604a37c49381d47bb187c694a4a552", "labels_vector_sha256": "76498340902b67cdc6d82ee16b412f954740a9a8fff8a10f05444362913ecb97", "planned_active_tokens": 68541, "realized_active_tokens": 68541, "cumulative_start": 43714805, "cumulative_end": 43783346, "loss_sum": 19202.698974609375, "token_normalized_loss": 0.28016368268057623, "grad_norm_before_clip": 0.07951018214225769, "learning_rates_at_step": { "lora": 2.6350461987214116e-05, "row_tokens": 2.6350461987214116e-05 }, "learning_rates_after_step": { "lora": 2.6202286878133286e-05, "row_tokens": 2.6202286878133286e-05 } }, { "update_id": 668, "row_count": 13, "row_ids_sha256": "f79fea371cbcd868f4f22f30f7e95cafe61d9d3a3e9f9649ec8ce911a2d4c1a0", "input_ids_vector_sha256": "ee0dc3f086c73c11950dfa90f418b336fdd3cea991628e9869a5ef7f46ad78bf", "labels_vector_sha256": "13534c7dc3afb0dbee291c260d70903df4a91a9c31f57bf528bcba53c3ad5fee", "planned_active_tokens": 65106, "realized_active_tokens": 65106, "cumulative_start": 43783346, "cumulative_end": 43848452, "loss_sum": 20906.53955078125, "token_normalized_loss": 0.3211154048901983, "grad_norm_before_clip": 0.08728858828544617, "learning_rates_at_step": { "lora": 2.6202286878133286e-05, "row_tokens": 2.6202286878133286e-05 }, "learning_rates_after_step": { "lora": 2.606109322153516e-05, "row_tokens": 2.606109322153516e-05 } }, { "update_id": 669, "row_count": 11, "row_ids_sha256": "55f03bfa8469d5ba4a054e201ec9cfbf51852ca5845e0d467439775dba0f0d33", "input_ids_vector_sha256": "86ed160ec1b4cb399a41e02ee39a3b01870913581e9fd17ffd3cbf5475a6436c", "labels_vector_sha256": "b85aacd7082edc0225eb288a75c2a23961e14aa155f17f83b11d8706ef5aeda4", "planned_active_tokens": 62149, "realized_active_tokens": 62149, "cumulative_start": 43848452, "cumulative_end": 43910601, "loss_sum": 17832.788330078125, "token_normalized_loss": 0.2869360461162388, "grad_norm_before_clip": 0.08895243704319, "learning_rates_at_step": { "lora": 2.606109322153516e-05, "row_tokens": 2.606109322153516e-05 }, "learning_rates_after_step": { "lora": 2.5915415777713015e-05, "row_tokens": 2.5915415777713015e-05 } }, { "update_id": 670, "row_count": 13, "row_ids_sha256": "03fbd45310ff7c6c681b6eec5a007f21dd40005296fd40a9c3c7823e4fd0dabf", "input_ids_vector_sha256": "e85881bd0ebb9c582483240e20f9ca895737522f8541adf7f6a5f427337c7ce2", "labels_vector_sha256": "4772812cc1bc70076bf3241fa845aa9e0e2bc224a04c0da1c7f76f7d508c602d", "planned_active_tokens": 64237, "realized_active_tokens": 64237, "cumulative_start": 43910601, "cumulative_end": 43974838, "loss_sum": 20491.086349487305, "token_normalized_loss": 0.3189919571195309, "grad_norm_before_clip": 0.09041915088891983, "learning_rates_at_step": { "lora": 2.5915415777713015e-05, "row_tokens": 2.5915415777713015e-05 }, "learning_rates_after_step": { "lora": 2.5767423625620547e-05, "row_tokens": 2.5767423625620547e-05 } }, { "update_id": 671, "row_count": 12, "row_ids_sha256": "b6c34cb2035e7715d24968b691c18cc53952e6b842ed4c89968a9fcc3e8b3904", "input_ids_vector_sha256": "06ba52c70d6b8eddbb2f38b8d1a598f9b6ba57effbb83e372ab8d513ba840d34", "labels_vector_sha256": "52a0759d8f8474819475b70b6ceddd294635fa11fe5b70640aa78151e68a8cd1", "planned_active_tokens": 65378, "realized_active_tokens": 65378, "cumulative_start": 43974838, "cumulative_end": 44040216, "loss_sum": 21173.159790039062, "token_normalized_loss": 0.3238575635540864, "grad_norm_before_clip": 0.10961495339870453, "learning_rates_at_step": { "lora": 2.5767423625620547e-05, "row_tokens": 2.5767423625620547e-05 }, "learning_rates_after_step": { "lora": 2.560870046453619e-05, "row_tokens": 2.560870046453619e-05 } }, { "update_id": 672, "row_count": 10, "row_ids_sha256": "6659bb69df820548a3e2288767f632371211efe8a72f932132b19032679fc97a", "input_ids_vector_sha256": "30f8a93e23062e324d76e622abaca3cc64b5fdc04068a6fafcb5da8fc357cc12", "labels_vector_sha256": "feef2de806106568fea8d9b0962a92e879dde2247597951f03a70b5d3dc7b7b1", "planned_active_tokens": 70255, "realized_active_tokens": 70255, "cumulative_start": 44040216, "cumulative_end": 44110471, "loss_sum": 24252.238037109375, "token_normalized_loss": 0.34520301810702975, "grad_norm_before_clip": 0.08995454013347626, "learning_rates_at_step": { "lora": 2.560870046453619e-05, "row_tokens": 2.560870046453619e-05 }, "learning_rates_after_step": { "lora": 2.5460699056589643e-05, "row_tokens": 2.5460699056589643e-05 } }, { "update_id": 673, "row_count": 12, "row_ids_sha256": "52e33b228a1986c18081929b911f82d4cc0b317dc3a98ff2b0c7810d97ba1b5d", "input_ids_vector_sha256": "a27171c52eb4de2ca05dd7b8af1ed58374df663ad8756df90c16b9fcd8c629e4", "labels_vector_sha256": "0337b62f7c4d432bffc97a4bb33a22498991408c23c7a9ed04e53c635e6c8075", "planned_active_tokens": 65638, "realized_active_tokens": 65638, "cumulative_start": 44110471, "cumulative_end": 44176109, "loss_sum": 21335.32452392578, "token_normalized_loss": 0.325045317101767, "grad_norm_before_clip": 0.08786410093307495, "learning_rates_at_step": { "lora": 2.5460699056589643e-05, "row_tokens": 2.5460699056589643e-05 }, "learning_rates_after_step": { "lora": 2.530973154985088e-05, "row_tokens": 2.530973154985088e-05 } }, { "update_id": 674, "row_count": 14, "row_ids_sha256": "294ef54eb450cbb92348a4822e2a60684f2df32f869f425766439fd8c86a5a3e", "input_ids_vector_sha256": "518b21808be1d52852bae333b4d7ff66a6eb4e50b62274ed8fadb1c3f7b803c3", "labels_vector_sha256": "aec63885f386346523f6a7fc0e33000b09bcdf40a90ab34120abe4f0c0fcd9ef", "planned_active_tokens": 67083, "realized_active_tokens": 67083, "cumulative_start": 44176109, "cumulative_end": 44243192, "loss_sum": 18210.609649658203, "token_normalized_loss": 0.27146385298299425, "grad_norm_before_clip": 0.08112307637929916, "learning_rates_at_step": { "lora": 2.530973154985088e-05, "row_tokens": 2.530973154985088e-05 }, "learning_rates_after_step": { "lora": 2.5160815809663418e-05, "row_tokens": 2.5160815809663418e-05 } }, { "update_id": 675, "row_count": 12, "row_ids_sha256": "dca7a6b12f48d7171eeb734e5081f7eb65f0d3010d10a2b7d2063306234b7c3c", "input_ids_vector_sha256": "4a97f480a9be01f31864ce370682c2f38630fb9839813547ca2a4a44e738b78e", "labels_vector_sha256": "cba2cfdc525b22d71460a4d6dbdc8f130fccf19c0bbfd0a989f213dc3a497d72", "planned_active_tokens": 66301, "realized_active_tokens": 66301, "cumulative_start": 44243192, "cumulative_end": 44309493, "loss_sum": 20755.912567138672, "token_normalized_loss": 0.31305579956770896, "grad_norm_before_clip": 0.08740730583667755, "learning_rates_at_step": { "lora": 2.5160815809663418e-05, "row_tokens": 2.5160815809663418e-05 }, "learning_rates_after_step": { "lora": 2.5022075330210902e-05, "row_tokens": 2.5022075330210902e-05 } }, { "update_id": 676, "row_count": 12, "row_ids_sha256": "7cb5c7cfbff00516b9343fb6ce6d2e805b92eac634e47d57ccd07d4a53ffe64c", "input_ids_vector_sha256": "ed15e022bc9b31ac6f282821bda747719989341bf06de46a5102cb28b9bcbb01", "labels_vector_sha256": "6cab0e51d2d07683ca2e2b400c7f5a54814215b1a49b0e4412fd8033efb3f43c", "planned_active_tokens": 61888, "realized_active_tokens": 61888, "cumulative_start": 44309493, "cumulative_end": 44371381, "loss_sum": 19232.244079589844, "token_normalized_loss": 0.3107588559913044, "grad_norm_before_clip": 0.08659552782773972, "learning_rates_at_step": { "lora": 2.5022075330210902e-05, "row_tokens": 2.5022075330210902e-05 }, "learning_rates_after_step": { "lora": 2.488287303248647e-05, "row_tokens": 2.488287303248647e-05 } }, { "update_id": 677, "row_count": 11, "row_ids_sha256": "40f109a05987058f1f8873435a5c6ed7df04a6af9b7363324ce6a82c1a0f0497", "input_ids_vector_sha256": "5c5efc070b2f371cbbad16ea22906bded2effe130d143e086fdc275db39a839b", "labels_vector_sha256": "5845ae9f5f4f1612dcf22e6bf594cfd9be7abaeb625b8290eca7cef899f3cd7d", "planned_active_tokens": 62209, "realized_active_tokens": 62209, "cumulative_start": 44371381, "cumulative_end": 44433590, "loss_sum": 19096.517700195312, "token_normalized_loss": 0.30697355206152344, "grad_norm_before_clip": 0.09097805619239807, "learning_rates_at_step": { "lora": 2.488287303248647e-05, "row_tokens": 2.488287303248647e-05 }, "learning_rates_after_step": { "lora": 2.4727422501961465e-05, "row_tokens": 2.4727422501961465e-05 } }, { "update_id": 678, "row_count": 12, "row_ids_sha256": "c24bff10d5f6f121557b8f8ad73d8441df302f59661527c881f44647c8de77b3", "input_ids_vector_sha256": "cf88ca15c744abe1448ad95e3799f9e09b146e11b12d34139d0093dafcf7f74b", "labels_vector_sha256": "1dff7fe995ddc4a504f6f069b01d15a7c02eeb5845af1cedadbf03f8a9f6ed67", "planned_active_tokens": 69608, "realized_active_tokens": 69608, "cumulative_start": 44433590, "cumulative_end": 44503198, "loss_sum": 22065.273010253906, "token_normalized_loss": 0.3169933486130029, "grad_norm_before_clip": 0.0836949348449707, "learning_rates_at_step": { "lora": 2.4727422501961465e-05, "row_tokens": 2.4727422501961465e-05 }, "learning_rates_after_step": { "lora": 2.4579381158313336e-05, "row_tokens": 2.4579381158313336e-05 } }, { "update_id": 679, "row_count": 13, "row_ids_sha256": "2ca36b8c23d569cbe453b676c930b8ad2635a4fbd44d5b1873270f8905cbf6e4", "input_ids_vector_sha256": "d28177e3b3e3acfc320369b0f1dfc41ff6faaba2ef5ba85d0eac405884af831e", "labels_vector_sha256": "a55d22f6265e929d2e74140d004aaea230f8e580edff217954d153990e11b71f", "planned_active_tokens": 66427, "realized_active_tokens": 66427, "cumulative_start": 44503198, "cumulative_end": 44569625, "loss_sum": 21557.274475097656, "token_normalized_loss": 0.3245257873319231, "grad_norm_before_clip": 0.0957554429769516, "learning_rates_at_step": { "lora": 2.4579381158313336e-05, "row_tokens": 2.4579381158313336e-05 }, "learning_rates_after_step": { "lora": 2.443724346409982e-05, "row_tokens": 2.443724346409982e-05 } }, { "update_id": 680, "row_count": 13, "row_ids_sha256": "fcb137d45165ca83d0a32f8b038a1e70f47374eda2a4c54c979338c1fbed583e", "input_ids_vector_sha256": "71f93eccd3fa7d82673fdf4ede6fd7746e1c54f609854b06041de09fe8fb6095", "labels_vector_sha256": "838022d57701bc05a31ef0dd8698e09107078685dc8bb251b33b4dc570078e0b", "planned_active_tokens": 63905, "realized_active_tokens": 63905, "cumulative_start": 44569625, "cumulative_end": 44633530, "loss_sum": 20083.619201660156, "token_normalized_loss": 0.3142730490831728, "grad_norm_before_clip": 0.08571131527423859, "learning_rates_at_step": { "lora": 2.443724346409982e-05, "row_tokens": 2.443724346409982e-05 }, "learning_rates_after_step": { "lora": 2.429681751646832e-05, "row_tokens": 2.429681751646832e-05 } }, { "update_id": 681, "row_count": 12, "row_ids_sha256": "dd5303c5c4f2a9ebfc1eae6af9e0a6a6a4d941a4ac4a309d416071650a9336a7", "input_ids_vector_sha256": "f6ccb69a9feed913bb95055294bed0045ab325450bf9e485e3a4d59a92cb85c2", "labels_vector_sha256": "e21afc5bc7d80d2c60137a938c7c5d8e9ae15a8e74203a801e084fd99dd6d4dc", "planned_active_tokens": 63259, "realized_active_tokens": 63259, "cumulative_start": 44633530, "cumulative_end": 44696789, "loss_sum": 20100.92803955078, "token_normalized_loss": 0.3177560195316205, "grad_norm_before_clip": 0.0910470262169838, "learning_rates_at_step": { "lora": 2.429681751646832e-05, "row_tokens": 2.429681751646832e-05 }, "learning_rates_after_step": { "lora": 2.414817234763873e-05, "row_tokens": 2.414817234763873e-05 } }, { "update_id": 682, "row_count": 13, "row_ids_sha256": "d3f3e436a969b741881532fbf92f9ad423167946a121527a3b7f1e27a25b1df5", "input_ids_vector_sha256": "ddad53b5977a479678018a40f3fd326d15f1d073a467f6569e82c8f4eaa6877d", "labels_vector_sha256": "ebb066e15bbfb86371334ffd33cb3561a62d6da4499a55e2e16e188feb88d1d4", "planned_active_tokens": 67097, "realized_active_tokens": 67097, "cumulative_start": 44696789, "cumulative_end": 44763886, "loss_sum": 19088.483840942383, "token_normalized_loss": 0.28449086905438964, "grad_norm_before_clip": 0.08387593179941177, "learning_rates_at_step": { "lora": 2.414817234763873e-05, "row_tokens": 2.414817234763873e-05 }, "learning_rates_after_step": { "lora": 2.400389755247059e-05, "row_tokens": 2.400389755247059e-05 } }, { "update_id": 683, "row_count": 15, "row_ids_sha256": "74860eb8d23ecda7238c02cefa1b4e8d7b7c006b7baabf232f28eb607dd50d53", "input_ids_vector_sha256": "a3e6a80bd1c5981c9ffd6e09ab0ab326057f029bf15ebe28625679ac9dc46bdd", "labels_vector_sha256": "fcc345a3dd12d2c8a802e9039986a4237a5394aa398d9cae35a99440756d3184", "planned_active_tokens": 65259, "realized_active_tokens": 65259, "cumulative_start": 44763886, "cumulative_end": 44829145, "loss_sum": 18474.72528076172, "token_normalized_loss": 0.28309850412604726, "grad_norm_before_clip": 0.08342134207487106, "learning_rates_at_step": { "lora": 2.400389755247059e-05, "row_tokens": 2.400389755247059e-05 }, "learning_rates_after_step": { "lora": 2.3857315916533966e-05, "row_tokens": 2.3857315916533966e-05 } }, { "update_id": 684, "row_count": 14, "row_ids_sha256": "18fdb29cf3dfd0972836269258ac7d225686554000f67cc70e5a276149897d6c", "input_ids_vector_sha256": "ca0926348e8d4b2c672278320a4b5b40832a0d4c8ce38bc9923bc9b88cfc67cc", "labels_vector_sha256": "fa2c09652c67de17aa3fbde342c6246d57dc8b490e94223eefa86ad118268c69", "planned_active_tokens": 66440, "realized_active_tokens": 66440, "cumulative_start": 44829145, "cumulative_end": 44895585, "loss_sum": 19807.71551513672, "token_normalized_loss": 0.29812937259386996, "grad_norm_before_clip": 0.08537689596414566, "learning_rates_at_step": { "lora": 2.3857315916533966e-05, "row_tokens": 2.3857315916533966e-05 }, "learning_rates_after_step": { "lora": 2.370926147524441e-05, "row_tokens": 2.370926147524441e-05 } }, { "update_id": 685, "row_count": 11, "row_ids_sha256": "4a11ca347437c0644c2fd875fd2ac2ea8dec949db2cd86e7e0f71014f877f819", "input_ids_vector_sha256": "48e6900a9f4a59804b2b75a385888b5af89e50324a1a07e180681ac28be35ba8", "labels_vector_sha256": "744ef4e1443c2e2adc4d6696e989350016a1786b1e6db850319fda59747cf93a", "planned_active_tokens": 67250, "realized_active_tokens": 67250, "cumulative_start": 44895585, "cumulative_end": 44962835, "loss_sum": 19876.404022216797, "token_normalized_loss": 0.2955599111110304, "grad_norm_before_clip": 0.08593707531690598, "learning_rates_at_step": { "lora": 2.370926147524441e-05, "row_tokens": 2.370926147524441e-05 }, "learning_rates_after_step": { "lora": 2.357629083740334e-05, "row_tokens": 2.357629083740334e-05 } }, { "update_id": 686, "row_count": 11, "row_ids_sha256": "5e4dcac0277c24c2bc65804d39a416ec437aeccfc87ba72c0e9d638096e0d2af", "input_ids_vector_sha256": "704b1266bc4081bcf55fe99c58b1c8e8af8855b50dcf7f7ae925f74fc06aaca1", "labels_vector_sha256": "20d81adb0ccdcb0658bcfb58a1030f93aad1f7710006de8bdda1ee94595f6ff3", "planned_active_tokens": 60522, "realized_active_tokens": 60522, "cumulative_start": 44962835, "cumulative_end": 45023357, "loss_sum": 17111.866271972656, "token_normalized_loss": 0.2827379510256214, "grad_norm_before_clip": 0.09002309292554855, "learning_rates_at_step": { "lora": 2.357629083740334e-05, "row_tokens": 2.357629083740334e-05 }, "learning_rates_after_step": { "lora": 2.34190460745299e-05, "row_tokens": 2.34190460745299e-05 } }, { "update_id": 687, "row_count": 11, "row_ids_sha256": "529a608f912f343fbe68a6835f9e217f6aa1e6e20afae3724220b8b16e2c7d3a", "input_ids_vector_sha256": "ff0d7e40844bdf7b81d6c8456da109303568758bcfe6bbc5d5f98508f4925ec1", "labels_vector_sha256": "61d6903c8373bda117190d96bf7a23f070c5dc107b0437d5f93a192f5e41e085", "planned_active_tokens": 71723, "realized_active_tokens": 71723, "cumulative_start": 45023357, "cumulative_end": 45095080, "loss_sum": 20269.35498046875, "token_normalized_loss": 0.2826060675162605, "grad_norm_before_clip": 0.08107616007328033, "learning_rates_at_step": { "lora": 2.34190460745299e-05, "row_tokens": 2.34190460745299e-05 }, "learning_rates_after_step": { "lora": 2.3289352723595425e-05, "row_tokens": 2.3289352723595425e-05 } }, { "update_id": 688, "row_count": 13, "row_ids_sha256": "381466ec70971ea82e65e8cbff407a50116dc0eb3181954e6f2e139b6d656a92", "input_ids_vector_sha256": "82858c610290087451a6bb835a608d7a061a990934315484f47a68e6eaf2ba53", "labels_vector_sha256": "dee886a25ee62335f9a66b6eb72f82212f504abda9aa604f7713aa60e3f6d60c", "planned_active_tokens": 59282, "realized_active_tokens": 59282, "cumulative_start": 45095080, "cumulative_end": 45154362, "loss_sum": 15231.223327636719, "token_normalized_loss": 0.25692829741973483, "grad_norm_before_clip": 0.08452603220939636, "learning_rates_at_step": { "lora": 2.3289352723595425e-05, "row_tokens": 2.3289352723595425e-05 }, "learning_rates_after_step": { "lora": 2.313910983120518e-05, "row_tokens": 2.313910983120518e-05 } }, { "update_id": 689, "row_count": 12, "row_ids_sha256": "dcaf90bb50b9580aacec532b5c8dd0b13683cfe7d12cf12d6e723b5ef59a7313", "input_ids_vector_sha256": "1b89cd9fec7a13b71910332685ed16bfaca937431817e87e3a4aec93468485e7", "labels_vector_sha256": "a16f5662c14625137085507504faee799410cfc647f582ffb6bc3aa28a9288d9", "planned_active_tokens": 68819, "realized_active_tokens": 68819, "cumulative_start": 45154362, "cumulative_end": 45223181, "loss_sum": 21786.465118408203, "token_normalized_loss": 0.3165763105887648, "grad_norm_before_clip": 0.08649556338787079, "learning_rates_at_step": { "lora": 2.313910983120518e-05, "row_tokens": 2.313910983120518e-05 }, "learning_rates_after_step": { "lora": 2.2984316217594158e-05, "row_tokens": 2.2984316217594158e-05 } }, { "update_id": 690, "row_count": 13, "row_ids_sha256": "12529c9bc1d213a50cee2219fd0482721eff3badde02c3b20813fe4994a89531", "input_ids_vector_sha256": "b782a651434473bb683ca58cd59b922c4c8f533def554c512f2fd0989a216451", "labels_vector_sha256": "4d13d0499937823ffe3cbcfb4c58dd05cbaddab205ef4fdc440e36267bfbd08e", "planned_active_tokens": 71067, "realized_active_tokens": 71067, "cumulative_start": 45223181, "cumulative_end": 45294248, "loss_sum": 23871.41082763672, "token_normalized_loss": 0.3359000777806397, "grad_norm_before_clip": 0.09658781439065933, "learning_rates_at_step": { "lora": 2.2984316217594158e-05, "row_tokens": 2.2984316217594158e-05 }, "learning_rates_after_step": { "lora": 2.2855805326208335e-05, "row_tokens": 2.2855805326208335e-05 } }, { "update_id": 691, "row_count": 8, "row_ids_sha256": "d5839afbfba1c026306942b7f5674c4f886fe67b03a51a8a58cd70e74debef8e", "input_ids_vector_sha256": "d432c09b361e2a336de40d20ddef043c68b43c55eed62e4845f0d9e11f9e2485", "labels_vector_sha256": "02821c04b46faea2f7c8bd9c51ebd8016904a89a8e9c44a7ddc4bd62889af083", "planned_active_tokens": 59128, "realized_active_tokens": 59128, "cumulative_start": 45294248, "cumulative_end": 45353376, "loss_sum": 18436.617553710938, "token_normalized_loss": 0.3118085772174086, "grad_norm_before_clip": 0.09906958043575287, "learning_rates_at_step": { "lora": 2.2855805326208335e-05, "row_tokens": 2.2855805326208335e-05 }, "learning_rates_after_step": { "lora": 2.2717554792339225e-05, "row_tokens": 2.2717554792339225e-05 } }, { "update_id": 692, "row_count": 14, "row_ids_sha256": "ad4a8db57284d9414b809f6f28e9686e547d546dac44125a0dfa0a6863ea9fb6", "input_ids_vector_sha256": "c3be4fa3471c5d1ae854f1981ca8d1fb3356dc396193db37383d71ddb2a2c528", "labels_vector_sha256": "aa9359d889d50cb46a6d1fd7a1d6f1b956e597a1bb63608d66fbe2a06e16e453", "planned_active_tokens": 63740, "realized_active_tokens": 63740, "cumulative_start": 45353376, "cumulative_end": 45417116, "loss_sum": 15017.967559814453, "token_normalized_loss": 0.23561292061208744, "grad_norm_before_clip": 0.07688930630683899, "learning_rates_at_step": { "lora": 2.2717554792339225e-05, "row_tokens": 2.2717554792339225e-05 }, "learning_rates_after_step": { "lora": 2.257510384725185e-05, "row_tokens": 2.257510384725185e-05 } }, { "update_id": 693, "row_count": 13, "row_ids_sha256": "95415e1c122d27a6806313faeec56325ee7818b221247c5252c54a7b49e952bf", "input_ids_vector_sha256": "c04698b2af7df2494a1c045c46ba60633cb8c956b756b204594adc00a6a2ea63", "labels_vector_sha256": "4b771cd0344b107ed9be7dd0e9907f580f717183eeed6a1bba5f13fcfc7860e1", "planned_active_tokens": 65820, "realized_active_tokens": 65820, "cumulative_start": 45417116, "cumulative_end": 45482936, "loss_sum": 18272.20538330078, "token_normalized_loss": 0.27760871138408966, "grad_norm_before_clip": 0.08187144249677658, "learning_rates_at_step": { "lora": 2.257510384725185e-05, "row_tokens": 2.257510384725185e-05 }, "learning_rates_after_step": { "lora": 2.2415630674985632e-05, "row_tokens": 2.2415630674985632e-05 } }, { "update_id": 694, "row_count": 14, "row_ids_sha256": "a17fa7b61243bc9e9a8ee21e8452e81085c339c9f3c7aa5f4fa53a4cea98d0ce", "input_ids_vector_sha256": "a5272965481cc6d5c568f401d8167885abfd7a74d2d36e9c89ac11bcdb93f4c2", "labels_vector_sha256": "ff5c6e9c9447ee181f4c02c3451b9e81b3963eb2040a4a8ccc6e95320a4e06f3", "planned_active_tokens": 73860, "realized_active_tokens": 73860, "cumulative_start": 45482936, "cumulative_end": 45556796, "loss_sum": 23729.293823242188, "token_normalized_loss": 0.3212739483244271, "grad_norm_before_clip": 0.08222995698451996, "learning_rates_at_step": { "lora": 2.2415630674985632e-05, "row_tokens": 2.2415630674985632e-05 }, "learning_rates_after_step": { "lora": 2.228252933494065e-05, "row_tokens": 2.228252933494065e-05 } }, { "update_id": 695, "row_count": 10, "row_ids_sha256": "76ee96d2310724767a57b5f801975afda7cdc747d26aa89767bc788a2472fe9e", "input_ids_vector_sha256": "6d6afbeb1a17724e77f97ce9d3de0b925ed674e367dad7611b32d7f2090ff3d1", "labels_vector_sha256": "6183441c8ed2b56fb5a4216ffcefc7507fe09e306d8cc000c5aaeb6454bf2145", "planned_active_tokens": 61789, "realized_active_tokens": 61789, "cumulative_start": 45556796, "cumulative_end": 45618585, "loss_sum": 22020.05535888672, "token_normalized_loss": 0.35637500783127607, "grad_norm_before_clip": 0.09396012872457504, "learning_rates_at_step": { "lora": 2.228252933494065e-05, "row_tokens": 2.228252933494065e-05 }, "learning_rates_after_step": { "lora": 2.2150733046506373e-05, "row_tokens": 2.2150733046506373e-05 } }, { "update_id": 696, "row_count": 11, "row_ids_sha256": "1d90dcd61fe842ea89be89a7bebf586015632a119911efefe00180e6c363ea21", "input_ids_vector_sha256": "f0a75fba50a9c51c9238accd08cf176964cec6a7829a09e0dcca5f1e2dc4a7df", "labels_vector_sha256": "8a99ecb472fba8bc3d6fcde68b256c2885a2e0ffdfbe6bb0f7c001e89d00318c", "planned_active_tokens": 61313, "realized_active_tokens": 61313, "cumulative_start": 45618585, "cumulative_end": 45679898, "loss_sum": 17719.375732421875, "token_normalized_loss": 0.28899867454572237, "grad_norm_before_clip": 0.08912699669599533, "learning_rates_at_step": { "lora": 2.2150733046506373e-05, "row_tokens": 2.2150733046506373e-05 }, "learning_rates_after_step": { "lora": 2.20096738062354e-05, "row_tokens": 2.20096738062354e-05 } }, { "update_id": 697, "row_count": 14, "row_ids_sha256": "923ca969635cbfce48876a7d5bcf2ad7377300cd3c0ae033d8ef6fb2fee08adf", "input_ids_vector_sha256": "a45f3b9fef5d51d2ce5182c57a7fc22be60a55f7754938c0731ef189f658cd27", "labels_vector_sha256": "cf453bbc4e0491cafd6381aad3d7fc3114d85a4cf4f0c145094907b44be1a211", "planned_active_tokens": 65767, "realized_active_tokens": 65767, "cumulative_start": 45679898, "cumulative_end": 45745665, "loss_sum": 19619.88688659668, "token_normalized_loss": 0.2983241882189651, "grad_norm_before_clip": 0.08556206524372101, "learning_rates_at_step": { "lora": 2.20096738062354e-05, "row_tokens": 2.20096738062354e-05 }, "learning_rates_after_step": { "lora": 2.1870558481808328e-05, "row_tokens": 2.1870558481808328e-05 } }, { "update_id": 698, "row_count": 14, "row_ids_sha256": "afd3dcb15452a09e4cc49de6ed49dcd5faa671d8b9c8e177977682916657c527", "input_ids_vector_sha256": "d757303c86dd36fc44feefc7ccb1f6ef5a4a51f49730584f05b90dc00ebabcb0", "labels_vector_sha256": "0d14f9890ba94e7bf853154584d67daf50636cdbb08d6d57e9c6b2b68b813faa", "planned_active_tokens": 65009, "realized_active_tokens": 65009, "cumulative_start": 45745665, "cumulative_end": 45810674, "loss_sum": 18319.93341064453, "token_normalized_loss": 0.28180611008698075, "grad_norm_before_clip": 0.08395083248615265, "learning_rates_at_step": { "lora": 2.1870558481808328e-05, "row_tokens": 2.1870558481808328e-05 }, "learning_rates_after_step": { "lora": 2.1732112903449964e-05, "row_tokens": 2.1732112903449964e-05 } }, { "update_id": 699, "row_count": 16, "row_ids_sha256": "3ccc6f4e3097c02e6d80d0b9711a8a08dc9176088a42428416cdb1ce06c576c0", "input_ids_vector_sha256": "a8811010b187ccb826581b9fbc128b389c5dcb66fe597dc566ce5257ba4d278a", "labels_vector_sha256": "283e6947523584dda4e3d8229b85dc1e8626b285c08854de11f984040c39dd0f", "planned_active_tokens": 64844, "realized_active_tokens": 64844, "cumulative_start": 45810674, "cumulative_end": 45875518, "loss_sum": 16982.76104736328, "token_normalized_loss": 0.2619018112294627, "grad_norm_before_clip": 0.08330994844436646, "learning_rates_at_step": { "lora": 2.1732112903449964e-05, "row_tokens": 2.1732112903449964e-05 }, "learning_rates_after_step": { "lora": 2.1591470252585705e-05, "row_tokens": 2.1591470252585705e-05 } }, { "update_id": 700, "row_count": 16, "row_ids_sha256": "2357a9da7e711d60e0d018748697f9d796dbd4fb592baf1cc68d2047522fb456", "input_ids_vector_sha256": "6678b2945255dad00cfbad423cacb4d97613be999d288629510dc44dfc962e82", "labels_vector_sha256": "9e33c29909a98c8f370f1d1523af2321edc1f169659c9311c933415c42e808bb", "planned_active_tokens": 66026, "realized_active_tokens": 66026, "cumulative_start": 45875518, "cumulative_end": 45941544, "loss_sum": 18678.713897705078, "token_normalized_loss": 0.2828993714249701, "grad_norm_before_clip": 0.08298646658658981, "learning_rates_at_step": { "lora": 2.1591470252585705e-05, "row_tokens": 2.1591470252585705e-05 }, "learning_rates_after_step": { "lora": 2.1450171753700803e-05, "row_tokens": 2.1450171753700803e-05 } }, { "update_id": 701, "row_count": 16, "row_ids_sha256": "110eb9094ad64fc83050142af10d8b1368c1ec29f5f0ac74471fa01ad757c0d2", "input_ids_vector_sha256": "699a84a946892aefe69317c32ba6cfb457b8788d02d0701f9137056e27f38256", "labels_vector_sha256": "93e4c88c73fc80add1007f3b19f5208a89b32f124e9c908fbf40690080b87274", "planned_active_tokens": 66491, "realized_active_tokens": 66491, "cumulative_start": 45941544, "cumulative_end": 46008035, "loss_sum": 16082.930770874023, "token_normalized_loss": 0.24188131883824915, "grad_norm_before_clip": 0.0784621387720108, "learning_rates_at_step": { "lora": 2.1450171753700803e-05, "row_tokens": 2.1450171753700803e-05 }, "learning_rates_after_step": { "lora": 2.13131938173306e-05, "row_tokens": 2.13131938173306e-05 } }, { "update_id": 702, "row_count": 14, "row_ids_sha256": "2abc4aca6ea3a5d116473c31614c6cd955507c507293c28273e4a0a5920639f5", "input_ids_vector_sha256": "2c057bf234dca2671b1b62f55ab51697f85c75e2510e91c9300ed71bf78c6db8", "labels_vector_sha256": "8e85a6758aefbe5db2b7f25d8ce05a14d600dd2f635de5d1bcd4e36354a3bd9e", "planned_active_tokens": 64610, "realized_active_tokens": 64610, "cumulative_start": 46008035, "cumulative_end": 46072645, "loss_sum": 19739.396728515625, "token_normalized_loss": 0.30551612333254335, "grad_norm_before_clip": 0.0843912810087204, "learning_rates_at_step": { "lora": 2.13131938173306e-05, "row_tokens": 2.13131938173306e-05 }, "learning_rates_after_step": { "lora": 2.1166001343252885e-05, "row_tokens": 2.1166001343252885e-05 } }, { "update_id": 703, "row_count": 16, "row_ids_sha256": "4fef3f7f12c312db55bc419df9c3eef672538747cd011a159c00638067b70d8f", "input_ids_vector_sha256": "f31ceea1596d9adb40c63d10dc98a4a7b7089e5b10a6965f1e9de07d82de7d43", "labels_vector_sha256": "787497983c22ed328ca22c8069dbb28a546ac0886588d4adbe48c9124340c172", "planned_active_tokens": 69597, "realized_active_tokens": 69597, "cumulative_start": 46072645, "cumulative_end": 46142242, "loss_sum": 20935.642822265625, "token_normalized_loss": 0.3008124318902485, "grad_norm_before_clip": 0.08334129303693771, "learning_rates_at_step": { "lora": 2.1166001343252885e-05, "row_tokens": 2.1166001343252885e-05 }, "learning_rates_after_step": { "lora": 2.1025551726044767e-05, "row_tokens": 2.1025551726044767e-05 } }, { "update_id": 704, "row_count": 15, "row_ids_sha256": "6543bd3a381a39e81209eaa512b25773b9462664b0d1c94e2128714e9efe0f0d", "input_ids_vector_sha256": "92ef041ed6a56fe267ed8cf3e6956c66b156c05ed0cff544edc61fd01e76b645", "labels_vector_sha256": "5c8c1e6ff0d8a5a9a437702d6eb1901ffc82446457aa79fe2a15e5373bec862a", "planned_active_tokens": 66574, "realized_active_tokens": 66574, "cumulative_start": 46142242, "cumulative_end": 46208816, "loss_sum": 19816.948333740234, "token_normalized_loss": 0.2976679835031729, "grad_norm_before_clip": 0.08189941197633743, "learning_rates_at_step": { "lora": 2.1025551726044767e-05, "row_tokens": 2.1025551726044767e-05 }, "learning_rates_after_step": { "lora": 2.0897886073521644e-05, "row_tokens": 2.0897886073521644e-05 } }, { "update_id": 705, "row_count": 15, "row_ids_sha256": "12f186334253c45b1a80db9181545eae9ceea6e2419de0438e5c41cc01b7b225", "input_ids_vector_sha256": "4107e92e0f5c38d0bc7af539cdd19fc0c221c368e54d0b02f4cdc31f1e163c5e", "labels_vector_sha256": "5ad9ec1d7a719dd775cf2f90ae60cf081b46ed669196c77fe4ea3112a3ee30b9", "planned_active_tokens": 60656, "realized_active_tokens": 60656, "cumulative_start": 46208816, "cumulative_end": 46269472, "loss_sum": 16573.15916442871, "token_normalized_loss": 0.27323198305903307, "grad_norm_before_clip": 0.0890120267868042, "learning_rates_at_step": { "lora": 2.0897886073521644e-05, "row_tokens": 2.0897886073521644e-05 }, "learning_rates_after_step": { "lora": 2.0753149137625344e-05, "row_tokens": 2.0753149137625344e-05 } }, { "update_id": 706, "row_count": 15, "row_ids_sha256": "7c750ea021064765885bc7c4b3202f787df82a1fa24b5657f09f2b59658aba17", "input_ids_vector_sha256": "a7274fc2e313c6b21c117d8f03040e720664752dd838fdcfd59ce7326fdbc723", "labels_vector_sha256": "f3c94e0a50d13c50a01f190b04f714fa620d9260820ae86ea1c433fab423943f", "planned_active_tokens": 68932, "realized_active_tokens": 68932, "cumulative_start": 46269472, "cumulative_end": 46338404, "loss_sum": 20367.521118164062, "token_normalized_loss": 0.29547265592415806, "grad_norm_before_clip": 0.08331739157438278, "learning_rates_at_step": { "lora": 2.0753149137625344e-05, "row_tokens": 2.0753149137625344e-05 }, "learning_rates_after_step": { "lora": 2.0622004338605382e-05, "row_tokens": 2.0622004338605382e-05 } }, { "update_id": 707, "row_count": 17, "row_ids_sha256": "be9720f07d4a340549b5355ac42625bc2ef4c98dd17c60c8d9b7fdf2cad2633a", "input_ids_vector_sha256": "2be8386dbff8e666bfd3d629c1781925f03335333072c418a124992c369ab98a", "labels_vector_sha256": "78b5a006d4e4a75222404e5297f82f257121d2f81bf4e41c078be2ebaffb4ee6", "planned_active_tokens": 62612, "realized_active_tokens": 62612, "cumulative_start": 46338404, "cumulative_end": 46401016, "loss_sum": 17901.705505371094, "token_normalized_loss": 0.2859149285340046, "grad_norm_before_clip": 0.08538477122783661, "learning_rates_at_step": { "lora": 2.0622004338605382e-05, "row_tokens": 2.0622004338605382e-05 }, "learning_rates_after_step": { "lora": 2.0472774158978564e-05, "row_tokens": 2.0472774158978564e-05 } }, { "update_id": 708, "row_count": 14, "row_ids_sha256": "3b15a52018719fd669d89d27936e8f2f44f8b61927b4391095a576b8f9c164ce", "input_ids_vector_sha256": "a5a904526bac451b069673fe0df30098a620d145e927f0bb3c181a50fa63c4fe", "labels_vector_sha256": "d0cce434dbd97bc6862267b9fd38e1cd2ee37b865177779146005432f7a22a0d", "planned_active_tokens": 71426, "realized_active_tokens": 71426, "cumulative_start": 46401016, "cumulative_end": 46472442, "loss_sum": 19943.68731689453, "token_normalized_loss": 0.27922167441680246, "grad_norm_before_clip": 0.08194775879383087, "learning_rates_at_step": { "lora": 2.0472774158978564e-05, "row_tokens": 2.0472774158978564e-05 }, "learning_rates_after_step": { "lora": 2.034868926946553e-05, "row_tokens": 2.034868926946553e-05 } }, { "update_id": 709, "row_count": 14, "row_ids_sha256": "5cd5f2943c267a34f669cf450efe93e9f26e9a68a7bd0dbc9550c1b64a3f9faf", "input_ids_vector_sha256": "9f4b65dc4050d698af47ae1134331752929aea2fbb8c06e213fe532ab75b1cc7", "labels_vector_sha256": "f061df56738a705ac401df8d34fec9c336ff9aeef272c6847f7c1b77bbd98476", "planned_active_tokens": 59538, "realized_active_tokens": 59538, "cumulative_start": 46472442, "cumulative_end": 46531980, "loss_sum": 17132.212371826172, "token_normalized_loss": 0.2877525676345556, "grad_norm_before_clip": 0.08597633987665176, "learning_rates_at_step": { "lora": 2.034868926946553e-05, "row_tokens": 2.034868926946553e-05 }, "learning_rates_after_step": { "lora": 2.0211566986506204e-05, "row_tokens": 2.0211566986506204e-05 } }, { "update_id": 710, "row_count": 16, "row_ids_sha256": "12fd2767de28c2daf0cd33d03937c58065dee005e8e31233d0cb746c27a5ffb2", "input_ids_vector_sha256": "c1349955aaa4d033ca742ae0458a3dbcc17ff9da6f212275bac3ac661a6598ad", "labels_vector_sha256": "6a01e37396b147a7521f5029f51dc39b1fab6eba607bb907fe213023d66e6caa", "planned_active_tokens": 65951, "realized_active_tokens": 65951, "cumulative_start": 46531980, "cumulative_end": 46597931, "loss_sum": 15787.865173339844, "token_normalized_loss": 0.23938780569422516, "grad_norm_before_clip": 0.07725188136100769, "learning_rates_at_step": { "lora": 2.0211566986506204e-05, "row_tokens": 2.0211566986506204e-05 }, "learning_rates_after_step": { "lora": 2.0079180336064883e-05, "row_tokens": 2.0079180336064883e-05 } }, { "update_id": 711, "row_count": 11, "row_ids_sha256": "0c6a0e54d1d0bf99ee93b9f346e6a1af96adcf3ebef8962f62cf1c6fb858cbf3", "input_ids_vector_sha256": "edac2356c4228a8183b9fdcb01c5885d80623579eee2a6a7fbfbfd1e1fa88466", "labels_vector_sha256": "9bce8867281ca535a7ea8d556ef96b31990965e5e8afbd53f676d1b7380f3322", "planned_active_tokens": 63832, "realized_active_tokens": 63832, "cumulative_start": 46597931, "cumulative_end": 46661763, "loss_sum": 19825.35595703125, "token_normalized_loss": 0.31058647632897685, "grad_norm_before_clip": 0.089459128677845, "learning_rates_at_step": { "lora": 2.0079180336064883e-05, "row_tokens": 2.0079180336064883e-05 }, "learning_rates_after_step": { "lora": 1.9937776594826968e-05, "row_tokens": 1.9937776594826968e-05 } }, { "update_id": 712, "row_count": 13, "row_ids_sha256": "f464aa116b786492641bf7fb0e20de06fb75922fa5c960887a6097d2554108be", "input_ids_vector_sha256": "2dd2e2908eaab6fa5a62e72abbe77c01e71fec49313eddf9b870f8476bffdb38", "labels_vector_sha256": "216785bc1f3f1e691ffc0b327da9dfcf7357bbe313a7c80596bd74336c2e5ded", "planned_active_tokens": 68354, "realized_active_tokens": 68354, "cumulative_start": 46661763, "cumulative_end": 46730117, "loss_sum": 21273.953491210938, "token_normalized_loss": 0.31123201994339666, "grad_norm_before_clip": 0.08741772919893265, "learning_rates_at_step": { "lora": 1.9937776594826968e-05, "row_tokens": 1.9937776594826968e-05 }, "learning_rates_after_step": { "lora": 1.9806905344021847e-05, "row_tokens": 1.9806905344021847e-05 } }, { "update_id": 713, "row_count": 12, "row_ids_sha256": "a8286825a1115788a35ea2224d32d4f85f38baca5b74f298e26a43b81d776efd", "input_ids_vector_sha256": "598d0defcba67ce171e4fa3aefbe0448487402f0cd762ab600e4f094347d0f68", "labels_vector_sha256": "2a3db01c1a2c3cf254ce435e036fdd0e50a68bd37b6afbb4f5dc6641e47a2d46", "planned_active_tokens": 63425, "realized_active_tokens": 63425, "cumulative_start": 46730117, "cumulative_end": 46793542, "loss_sum": 16449.44775390625, "token_normalized_loss": 0.2593527434593023, "grad_norm_before_clip": 0.08724207431077957, "learning_rates_at_step": { "lora": 1.9806905344021847e-05, "row_tokens": 1.9806905344021847e-05 }, "learning_rates_after_step": { "lora": 1.966643275947516e-05, "row_tokens": 1.966643275947516e-05 } }, { "update_id": 714, "row_count": 12, "row_ids_sha256": "c2b008acc4f118447307e82aa4b5e665101d790c647ab9a55499efe20647e2f8", "input_ids_vector_sha256": "b31bf652345e4c18cd5b34e6e1912fceb715745922549e926009321b151a879e", "labels_vector_sha256": "47ff01146ff366555753856f6f4f7ea92d567a45ce522612b31bf4a0429e47c4", "planned_active_tokens": 68254, "realized_active_tokens": 68254, "cumulative_start": 46793542, "cumulative_end": 46861796, "loss_sum": 22937.276733398438, "token_normalized_loss": 0.33605761909043336, "grad_norm_before_clip": 0.08801528811454773, "learning_rates_at_step": { "lora": 1.966643275947516e-05, "row_tokens": 1.966643275947516e-05 }, "learning_rates_after_step": { "lora": 1.9527121041646485e-05, "row_tokens": 1.9527121041646485e-05 } }, { "update_id": 715, "row_count": 17, "row_ids_sha256": "3cdeb16600502461959061e4d59b5b969f40e716e72df3dc7c57e476e8c79db7", "input_ids_vector_sha256": "7868a708c811ef57cb8b43e3abfb2a09a975b84a2ce0a4d3020f71df2baf3d32", "labels_vector_sha256": "bcffbc314ca5cd44ef00ca79d9423462a1f5917697dcaefbeeb58ed78c6f497c", "planned_active_tokens": 67872, "realized_active_tokens": 67872, "cumulative_start": 46861796, "cumulative_end": 46929668, "loss_sum": 14458.31332397461, "token_normalized_loss": 0.21302323968609455, "grad_norm_before_clip": 0.07368278503417969, "learning_rates_at_step": { "lora": 1.9527121041646485e-05, "row_tokens": 1.9527121041646485e-05 }, "learning_rates_after_step": { "lora": 1.9404451405473367e-05, "row_tokens": 1.9404451405473367e-05 } }, { "update_id": 716, "row_count": 13, "row_ids_sha256": "df3d70fef82e3bee847de4767ab22b0ef79a8026efcfcd8002b4b19d4f3e73bd", "input_ids_vector_sha256": "6ab3ef380732f6f1b0d5fa34e2c3f863d0b83b5a906c421592737f069cc9b2bc", "labels_vector_sha256": "cf0f3b94909060138bedf6592a0bc06709c328ed4182892d71ef2eafdb5fefac", "planned_active_tokens": 59916, "realized_active_tokens": 59916, "cumulative_start": 46929668, "cumulative_end": 46989584, "loss_sum": 14882.151977539062, "token_normalized_loss": 0.2483836033369895, "grad_norm_before_clip": 0.08442509174346924, "learning_rates_at_step": { "lora": 1.9404451405473367e-05, "row_tokens": 1.9404451405473367e-05 }, "learning_rates_after_step": { "lora": 1.9267911665049032e-05, "row_tokens": 1.9267911665049032e-05 } }, { "update_id": 717, "row_count": 10, "row_ids_sha256": "054fdb7e690f0d1c1723154207e7fa0763af84b4620de7ac70948bde92785893", "input_ids_vector_sha256": "0f31cdbcdff1c835a6d5511284f3a78bbd451777789c73a2c100e8694c637515", "labels_vector_sha256": "8b5ca61cb49c567f985d7d1740f79fd2ac5a7258c2f2c20f7ac7f4d462cb97ec", "planned_active_tokens": 66860, "realized_active_tokens": 66860, "cumulative_start": 46989584, "cumulative_end": 47056444, "loss_sum": 20189.040100097656, "token_normalized_loss": 0.3019599177400188, "grad_norm_before_clip": 0.08633964508771896, "learning_rates_at_step": { "lora": 1.9267911665049032e-05, "row_tokens": 1.9267911665049032e-05 }, "learning_rates_after_step": { "lora": 1.9137548484083923e-05, "row_tokens": 1.9137548484083923e-05 } }, { "update_id": 718, "row_count": 12, "row_ids_sha256": "8c50a13c2ca56422cc99bd6751bd3e034272b7e4aad90e3c8edc1a0480892515", "input_ids_vector_sha256": "3e53ca82e523820474b95f8cb0a2d5c7c41e4db9d30a1430672b75edf83a68bb", "labels_vector_sha256": "267e178513a67c9524d56c2e9c09430c7dfe507f861e195833705d14d1884019", "planned_active_tokens": 64004, "realized_active_tokens": 64004, "cumulative_start": 47056444, "cumulative_end": 47120448, "loss_sum": 18443.003997802734, "token_normalized_loss": 0.2881539278451774, "grad_norm_before_clip": 0.1020456850528717, "learning_rates_at_step": { "lora": 1.9137548484083923e-05, "row_tokens": 1.9137548484083923e-05 }, "learning_rates_after_step": { "lora": 1.8999771656045528e-05, "row_tokens": 1.8999771656045528e-05 } }, { "update_id": 719, "row_count": 15, "row_ids_sha256": "d92f2e7ab562aacbd9ef677d3cca497a9055b10000f6660969aeef5caff82bf0", "input_ids_vector_sha256": "d0ab181864c1616fe3ef9f6c8ed9a9087b3651b220fcef6c79e0ca2cb0c8a382", "labels_vector_sha256": "48e999147b0fcce1b2c3a5ead2da1f35c8ffbc133d5cfcc99d08b029e127e306", "planned_active_tokens": 67825, "realized_active_tokens": 67825, "cumulative_start": 47120448, "cumulative_end": 47188273, "loss_sum": 18462.53546142578, "token_normalized_loss": 0.2722084107840145, "grad_norm_before_clip": 0.0802999883890152, "learning_rates_at_step": { "lora": 1.8999771656045528e-05, "row_tokens": 1.8999771656045528e-05 }, "learning_rates_after_step": { "lora": 1.886510108435795e-05, "row_tokens": 1.886510108435795e-05 } }, { "update_id": 720, "row_count": 12, "row_ids_sha256": "efd3a664ec9e205888ca5a8e625d99e07603fb6977bcdf310b241b9c333fb5ad", "input_ids_vector_sha256": "b0232dca933f2f00594fb1b58c86f7e8bf2d8bb4dd79ea9b7e259eb7a2b9fad7", "labels_vector_sha256": "50ca4f981f1b724b7fdd23916b8af2f773f5589a912dbe0a7aa026d41666524e", "planned_active_tokens": 66478, "realized_active_tokens": 66478, "cumulative_start": 47188273, "cumulative_end": 47254751, "loss_sum": 19621.801818847656, "token_normalized_loss": 0.2951623366955633, "grad_norm_before_clip": 0.08912200480699539, "learning_rates_at_step": { "lora": 1.886510108435795e-05, "row_tokens": 1.886510108435795e-05 }, "learning_rates_after_step": { "lora": 1.8727959906717923e-05, "row_tokens": 1.8727959906717923e-05 } }, { "update_id": 721, "row_count": 16, "row_ids_sha256": "dc2f7a022a9403242be35f8cbcf8f94403016cb0102375d3d131bcb2876dbe31", "input_ids_vector_sha256": "fafd2df2d1981729bd9c1ae46b1c06b881ea246e15cba0da2b7db7a692efec66", "labels_vector_sha256": "65606ac0451857ce8877cdb8f378951bc6c9a0dc856bc3e424b93efe39e3b879", "planned_active_tokens": 67885, "realized_active_tokens": 67885, "cumulative_start": 47254751, "cumulative_end": 47322636, "loss_sum": 16860.89680480957, "token_normalized_loss": 0.24837440973425012, "grad_norm_before_clip": 0.07912987470626831, "learning_rates_at_step": { "lora": 1.8727959906717923e-05, "row_tokens": 1.8727959906717923e-05 }, "learning_rates_after_step": { "lora": 1.8600533109307257e-05, "row_tokens": 1.8600533109307257e-05 } }, { "update_id": 722, "row_count": 13, "row_ids_sha256": "8a55ff75583a76a7779b3e2bba7f42771734b50ce39473ee1c7c04c54b94aa62", "input_ids_vector_sha256": "e9cd2d9951ab848ddc76875661b26c9732be3533b084e09cf9a73284af2a27db", "labels_vector_sha256": "1487182d2b4386e3c3b1900d2b6f658b06ee71c223dbcc35e04649588a178b4e", "planned_active_tokens": 63248, "realized_active_tokens": 63248, "cumulative_start": 47322636, "cumulative_end": 47385884, "loss_sum": 16122.078643798828, "token_normalized_loss": 0.25490258417339406, "grad_norm_before_clip": 0.08349097520112991, "learning_rates_at_step": { "lora": 1.8600533109307257e-05, "row_tokens": 1.8600533109307257e-05 }, "learning_rates_after_step": { "lora": 1.8475153951021597e-05, "row_tokens": 1.8475153951021597e-05 } }, { "update_id": 723, "row_count": 15, "row_ids_sha256": "cd84668587865e41a33c499d6a3203d72adfc64ef872d379da06f84f2f246764", "input_ids_vector_sha256": "1a417082b09a4d735b8f74c414017001e8e2cc5a01f80dc6828d823465020a79", "labels_vector_sha256": "9ca0158cad1a5dcd3897c0a2ffdbee613c748c3f6ca68684b1e8718700f2be0e", "planned_active_tokens": 62395, "realized_active_tokens": 62395, "cumulative_start": 47385884, "cumulative_end": 47448279, "loss_sum": 16263.466598510742, "token_normalized_loss": 0.2606533632263922, "grad_norm_before_clip": 0.08575429767370224, "learning_rates_at_step": { "lora": 1.8475153951021597e-05, "row_tokens": 1.8475153951021597e-05 }, "learning_rates_after_step": { "lora": 1.833251863605705e-05, "row_tokens": 1.833251863605705e-05 } }, { "update_id": 724, "row_count": 13, "row_ids_sha256": "087a2cbf69fa3e9862420fb74b2411cf5eb38604fd3f4d34e17d60726c88cee0", "input_ids_vector_sha256": "c245a872ef2397983d89faaeaa630b13781fb10b82d6c519f641dfd1e4d0722f", "labels_vector_sha256": "28e62059e19dace89b306ba7b175c99294cc42128b1401949926d4fd0e0301c4", "planned_active_tokens": 71182, "realized_active_tokens": 71182, "cumulative_start": 47448279, "cumulative_end": 47519461, "loss_sum": 23231.332641601562, "token_normalized_loss": 0.3263652698940963, "grad_norm_before_clip": 0.08625154197216034, "learning_rates_at_step": { "lora": 1.833251863605705e-05, "row_tokens": 1.833251863605705e-05 }, "learning_rates_after_step": { "lora": 1.8206231264065344e-05, "row_tokens": 1.8206231264065344e-05 } }, { "update_id": 725, "row_count": 16, "row_ids_sha256": "41fe7affe449335f93dcbb25dca02e727858163850e45304c1a9a35aa266f86c", "input_ids_vector_sha256": "2238d164ffe3ac1a56173a297c8c19c48e097026984cd6a7a038bb14ac1ffc7b", "labels_vector_sha256": "b2df5aead952dd290d3401cd6fd46409df85c62ceeacf59866b3911d6d8361f1", "planned_active_tokens": 63203, "realized_active_tokens": 63203, "cumulative_start": 47519461, "cumulative_end": 47582664, "loss_sum": 17483.03936767578, "token_normalized_loss": 0.2766172391765546, "grad_norm_before_clip": 0.08295208215713501, "learning_rates_at_step": { "lora": 1.8206231264065344e-05, "row_tokens": 1.8206231264065344e-05 }, "learning_rates_after_step": { "lora": 1.8079266573767405e-05, "row_tokens": 1.8079266573767405e-05 } }, { "update_id": 726, "row_count": 13, "row_ids_sha256": "2dfeb1c314b66e6521f65f350257fdae4bf8c645df234e86ce29a8f6d5562e62", "input_ids_vector_sha256": "f7d698fc265d89ef02c67cb72c1e1a1a084f55b3e493c2a587b0bc9766393751", "labels_vector_sha256": "6cb8df840452df6ae9e10fa2c190b4d159e32814d99431d787616cf055d7e61f", "planned_active_tokens": 63714, "realized_active_tokens": 63714, "cumulative_start": 47582664, "cumulative_end": 47646378, "loss_sum": 16018.538864135742, "token_normalized_loss": 0.25141317236613214, "grad_norm_before_clip": 0.08360757678747177, "learning_rates_at_step": { "lora": 1.8079266573767405e-05, "row_tokens": 1.8079266573767405e-05 }, "learning_rates_after_step": { "lora": 1.7944177041588017e-05, "row_tokens": 1.7944177041588017e-05 } }, { "update_id": 727, "row_count": 13, "row_ids_sha256": "739697aa8e7a7634b4e2665db02d6716afeccb47d71d15a665c8e058b95f1ee5", "input_ids_vector_sha256": "e1712525f0a5dcd750664795871ddae176c804236f45cefda0774bdd0808ad27", "labels_vector_sha256": "55618b5700f946a7c269427bfa6aea3de3558311046ac5b18ccefd54ed430ea0", "planned_active_tokens": 67983, "realized_active_tokens": 67983, "cumulative_start": 47646378, "cumulative_end": 47714361, "loss_sum": 20255.653442382812, "token_normalized_loss": 0.29795174444174005, "grad_norm_before_clip": 0.08613231778144836, "learning_rates_at_step": { "lora": 1.7944177041588017e-05, "row_tokens": 1.7944177041588017e-05 }, "learning_rates_after_step": { "lora": 1.7812977561390585e-05, "row_tokens": 1.7812977561390585e-05 } }, { "update_id": 728, "row_count": 16, "row_ids_sha256": "4e2125091f97a8f3ab73458076c1845a1b7cdd8c54c303710e8cae7d30b0f0d2", "input_ids_vector_sha256": "9e804741ac8d11e5c79da2134ff4cb14f49dee9a47f16d047861c5974a2c3acd", "labels_vector_sha256": "0c6e23905ccf3ae0a5ec42012d914683a802a73e2b5045352b1d0ab6b22d9f7d", "planned_active_tokens": 66217, "realized_active_tokens": 66217, "cumulative_start": 47714361, "cumulative_end": 47780578, "loss_sum": 17237.662887573242, "token_normalized_loss": 0.26032080715787853, "grad_norm_before_clip": 0.08204369246959686, "learning_rates_at_step": { "lora": 1.7812977561390585e-05, "row_tokens": 1.7812977561390585e-05 }, "learning_rates_after_step": { "lora": 1.7690074958873115e-05, "row_tokens": 1.7690074958873115e-05 } }, { "update_id": 729, "row_count": 16, "row_ids_sha256": "1620b204e58ab179937ae5f6a03c7d039fd1fdbb82b60914163510c4a25e3f82", "input_ids_vector_sha256": "560041392d69a64efc7d3ab5a680bac024a0327ece48d822309093a797abb7a1", "labels_vector_sha256": "c178c0d2aee622d9111dde3ccbaf9581796809290234f33307474c533e9a9a5a", "planned_active_tokens": 62203, "realized_active_tokens": 62203, "cumulative_start": 47780578, "cumulative_end": 47842781, "loss_sum": 16383.851684570312, "token_normalized_loss": 0.26339327178062655, "grad_norm_before_clip": 0.08626201748847961, "learning_rates_at_step": { "lora": 1.7690074958873115e-05, "row_tokens": 1.7690074958873115e-05 }, "learning_rates_after_step": { "lora": 1.7554208494162654e-05, "row_tokens": 1.7554208494162654e-05 } }, { "update_id": 730, "row_count": 15, "row_ids_sha256": "52cfff48ec0bff933999fe0dd7dab7c46e318f17c09579a81bc57624ea563632", "input_ids_vector_sha256": "18969a800b14065924bf01d14bc8e13e282d8cc26714d8b49bbb4bad195a4123", "labels_vector_sha256": "cbaf22fad25fa7b23ddddd3179dcdc38a1f525e1d882942bb0e2c378fee827f8", "planned_active_tokens": 68962, "realized_active_tokens": 68962, "cumulative_start": 47842781, "cumulative_end": 47911743, "loss_sum": 19348.79376220703, "token_normalized_loss": 0.2805718187147564, "grad_norm_before_clip": 0.08124759048223495, "learning_rates_at_step": { "lora": 1.7554208494162654e-05, "row_tokens": 1.7554208494162654e-05 }, "learning_rates_after_step": { "lora": 1.7426641231426666e-05, "row_tokens": 1.7426641231426666e-05 } }, { "update_id": 731, "row_count": 15, "row_ids_sha256": "79e763a7bb59d241d1a4fcd3b054528009fed1d36c7ba30c767a55e32824f307", "input_ids_vector_sha256": "03a810ee41486607cfbdc1aedec0926718939962f63e777f817706161a532812", "labels_vector_sha256": "cc818b8d0bc524254ff843709d08ef093a70e2964e8a8b618504aeb6b033b75a", "planned_active_tokens": 64941, "realized_active_tokens": 64941, "cumulative_start": 47911743, "cumulative_end": 47976684, "loss_sum": 18787.11654663086, "token_normalized_loss": 0.289295153241109, "grad_norm_before_clip": 0.0892370268702507, "learning_rates_at_step": { "lora": 1.7426641231426666e-05, "row_tokens": 1.7426641231426666e-05 }, "learning_rates_after_step": { "lora": 1.7296720759160616e-05, "row_tokens": 1.7296720759160616e-05 } }, { "update_id": 732, "row_count": 14, "row_ids_sha256": "faf16ae0094cba999bda72d881856c8d0eeb20865003136a0732c6b48f283f10", "input_ids_vector_sha256": "de0850297f74ddd27bd1396a8ab31f01d5860dda774f32e1e20c2dc617baae9e", "labels_vector_sha256": "2f764aa7618593fe1a38b010537bc1ea79151281ff37792d4c4bef34dd700697", "planned_active_tokens": 66332, "realized_active_tokens": 66332, "cumulative_start": 47976684, "cumulative_end": 48043016, "loss_sum": 19266.39324951172, "token_normalized_loss": 0.2904539777107839, "grad_norm_before_clip": 0.08517403155565262, "learning_rates_at_step": { "lora": 1.7296720759160616e-05, "row_tokens": 1.7296720759160616e-05 }, "learning_rates_after_step": { "lora": 1.717305277372796e-05, "row_tokens": 1.717305277372796e-05 } }, { "update_id": 733, "row_count": 11, "row_ids_sha256": "deb34ce18b796a15f99a951b2330caf3795b4f5fd28a92816fbf2578a8ced8f0", "input_ids_vector_sha256": "2e53dc4c269291ae786b1c2b95aaa179d4f09fb7545195911c976732356de919", "labels_vector_sha256": "38980842b84cbb891708a59a5c32167271cf9b0fb827638efd03e00c09976267", "planned_active_tokens": 63323, "realized_active_tokens": 63323, "cumulative_start": 48043016, "cumulative_end": 48106339, "loss_sum": 21222.57745361328, "token_normalized_loss": 0.3351480102587256, "grad_norm_before_clip": 0.09266798943281174, "learning_rates_at_step": { "lora": 1.717305277372796e-05, "row_tokens": 1.717305277372796e-05 }, "learning_rates_after_step": { "lora": 1.7049021129045944e-05, "row_tokens": 1.7049021129045944e-05 } }, { "update_id": 734, "row_count": 11, "row_ids_sha256": "b82df40081a884b3fba35e32eeccd7bd770823b44cd7ae4295852bdda90a6e37", "input_ids_vector_sha256": "6535dd34b2c2ad403512826dcefaef1df2037cc8b3479e67adde27806fb894de", "labels_vector_sha256": "9fc0ae10b95c0cf5ead33019a9493be9ff2a067e73a9ee31a66ec3aa4bdb21b5", "planned_active_tokens": 63691, "realized_active_tokens": 63691, "cumulative_start": 48106339, "cumulative_end": 48170030, "loss_sum": 17680.00503540039, "token_normalized_loss": 0.27759031943917334, "grad_norm_before_clip": 0.0910266563296318, "learning_rates_at_step": { "lora": 1.7049021129045944e-05, "row_tokens": 1.7049021129045944e-05 }, "learning_rates_after_step": { "lora": 1.691552712928994e-05, "row_tokens": 1.691552712928994e-05 } }, { "update_id": 735, "row_count": 18, "row_ids_sha256": "4e5b18009ae61bd2605172cae6717c264b344653ac7c7dd97e2803afc0eedeae", "input_ids_vector_sha256": "65551e34d24d0c4c13a54fdbc2fa2260ad0c7e21effd03f10cbbc0fa0675e50e", "labels_vector_sha256": "c40dc25c222bcc0dbd57bb4af714dade282f3fdf10e058a0776c224e378dd500", "planned_active_tokens": 68756, "realized_active_tokens": 68756, "cumulative_start": 48170030, "cumulative_end": 48238786, "loss_sum": 17554.55940246582, "token_normalized_loss": 0.25531676366376493, "grad_norm_before_clip": 0.07999137043952942, "learning_rates_at_step": { "lora": 1.691552712928994e-05, "row_tokens": 1.691552712928994e-05 }, "learning_rates_after_step": { "lora": 1.6786498030332237e-05, "row_tokens": 1.6786498030332237e-05 } }, { "update_id": 736, "row_count": 13, "row_ids_sha256": "7bd2d0255c9cdcd15bb7e486c5727041fde2d7dfcfd270c34e92929f104a0e6f", "input_ids_vector_sha256": "a1141ff7355d2f59a7e4051dafa709bb620d8dd6249d35def3fde63542afd2ca", "labels_vector_sha256": "48d163dd8639e78b13cb35188015c4c2e029fec51d2c107c3c9a18ba6f6cd3b1", "planned_active_tokens": 66662, "realized_active_tokens": 66662, "cumulative_start": 48238786, "cumulative_end": 48305448, "loss_sum": 20059.945892333984, "token_normalized_loss": 0.30092025280270596, "grad_norm_before_clip": 0.0868699699640274, "learning_rates_at_step": { "lora": 1.6786498030332237e-05, "row_tokens": 1.6786498030332237e-05 }, "learning_rates_after_step": { "lora": 1.6669105370079957e-05, "row_tokens": 1.6669105370079957e-05 } }, { "update_id": 737, "row_count": 10, "row_ids_sha256": "a3ccd8d9e95bf8a2c5e10597b40a2db2f51f57d4df1b623b05ce4182dd922a65", "input_ids_vector_sha256": "9225cf261f8b5290d80e044bad140f0d1772f808fff0f08d70e62b949af252ce", "labels_vector_sha256": "9d1b566a9d03bb6097af408dc76341f8b8dd78e9311080395df712ddd694cfa4", "planned_active_tokens": 60828, "realized_active_tokens": 60828, "cumulative_start": 48305448, "cumulative_end": 48366276, "loss_sum": 18057.34112548828, "token_normalized_loss": 0.2968590307997679, "grad_norm_before_clip": 0.09271810948848724, "learning_rates_at_step": { "lora": 1.6669105370079957e-05, "row_tokens": 1.6669105370079957e-05 }, "learning_rates_after_step": { "lora": 1.6534454297008677e-05, "row_tokens": 1.6534454297008677e-05 } }, { "update_id": 738, "row_count": 15, "row_ids_sha256": "591583d8ce81537c20d317be7d2f664d3199edfc30fcbdf3ecab21ac93d67a16", "input_ids_vector_sha256": "3cb45a028adcdc64ab6e3781a18a15869f5aaeb8d2b4004f92bac853ef171d62", "labels_vector_sha256": "58b7a1a5ac0105b065263b13e4f317307da3bec28cff5d3f982d5f22faeb7d89", "planned_active_tokens": 69982, "realized_active_tokens": 69982, "cumulative_start": 48366276, "cumulative_end": 48436258, "loss_sum": 19623.693481445312, "token_normalized_loss": 0.2804105838850749, "grad_norm_before_clip": 0.0846891775727272, "learning_rates_at_step": { "lora": 1.6534454297008677e-05, "row_tokens": 1.6534454297008677e-05 }, "learning_rates_after_step": { "lora": 1.6409710649948307e-05, "row_tokens": 1.6409710649948307e-05 } }, { "update_id": 739, "row_count": 14, "row_ids_sha256": "f293ed51d77c3fad05509b7d9fa571313da30acdfb936f434c8c6c4ae000d684", "input_ids_vector_sha256": "886a2c2bf76ba35e0e96f5799b43c1fbb427d4aa130c0b79fe65e130f90388a9", "labels_vector_sha256": "c926f10dee6e972ae02e37d9654ac9185fbefc36257a1453d7c30a953fc5d037", "planned_active_tokens": 65037, "realized_active_tokens": 65037, "cumulative_start": 48436258, "cumulative_end": 48501295, "loss_sum": 17485.749893188477, "token_normalized_loss": 0.2688584942907649, "grad_norm_before_clip": 0.08552271872758865, "learning_rates_at_step": { "lora": 1.6409710649948307e-05, "row_tokens": 1.6409710649948307e-05 }, "learning_rates_after_step": { "lora": 1.6289490237328515e-05, "row_tokens": 1.6289490237328515e-05 } }, { "update_id": 740, "row_count": 13, "row_ids_sha256": "0fa8c71b0e9a1663f32dfc4471865acca315c5816b281a145f060c405c3f7091", "input_ids_vector_sha256": "d67936a5c5353eb009bd109ced76958dfa5f4635cfc645eebfa9d166756a02b3", "labels_vector_sha256": "1baacda1e0b5a18bd1255fc5a1ee1884f1ec191ecda8bac7b417737082be4aaa", "planned_active_tokens": 62867, "realized_active_tokens": 62867, "cumulative_start": 48501295, "cumulative_end": 48564162, "loss_sum": 18948.088165283203, "token_normalized_loss": 0.3013995922389044, "grad_norm_before_clip": 0.09452911466360092, "learning_rates_at_step": { "lora": 1.6289490237328515e-05, "row_tokens": 1.6289490237328515e-05 }, "learning_rates_after_step": { "lora": 1.6160664023607053e-05, "row_tokens": 1.6160664023607053e-05 } }, { "update_id": 741, "row_count": 14, "row_ids_sha256": "6a82c84f013b9106de6b0cea3b8aa9d32a46f702784eaf424a72822abcca8a5b", "input_ids_vector_sha256": "b143bd8c7919b0946d1330ec4d2c32729ba8bc80ce001a3d0953a1b15a13d45b", "labels_vector_sha256": "88aad8ba9285495a67124cee3695442377892f0f51c8544e0e3a0eb709b1bd09", "planned_active_tokens": 67575, "realized_active_tokens": 67575, "cumulative_start": 48564162, "cumulative_end": 48631737, "loss_sum": 18924.48570251465, "token_normalized_loss": 0.28005158272311725, "grad_norm_before_clip": 0.08346355706453323, "learning_rates_at_step": { "lora": 1.6160664023607053e-05, "row_tokens": 1.6160664023607053e-05 }, "learning_rates_after_step": { "lora": 1.603500017645904e-05, "row_tokens": 1.603500017645904e-05 } }, { "update_id": 742, "row_count": 14, "row_ids_sha256": "810ea59be411d5dd011af4f1d05da19a5194da3cf70378faac99c3bc6ea1bd7c", "input_ids_vector_sha256": "64b58174ace1a67cfbc2ac69678a986b1ac325b987d5117e5f740af22ef77b63", "labels_vector_sha256": "a12a250f77ad6fef930a3df5aea301c1709c692fb19deaa812f56a3d2e1ad4f7", "planned_active_tokens": 66126, "realized_active_tokens": 66126, "cumulative_start": 48631737, "cumulative_end": 48697863, "loss_sum": 18044.307861328125, "token_normalized_loss": 0.27287765570771144, "grad_norm_before_clip": 0.08729494363069534, "learning_rates_at_step": { "lora": 1.603500017645904e-05, "row_tokens": 1.603500017645904e-05 }, "learning_rates_after_step": { "lora": 1.5919013521932026e-05, "row_tokens": 1.5919013521932026e-05 } }, { "update_id": 743, "row_count": 12, "row_ids_sha256": "7367dadf924ddbcbdbedafdd25d11b7feef7c6b8444abe2272235f54ce7d655a", "input_ids_vector_sha256": "776a9a73341bccace0a184f0fcf90029796840fa69868e8e3c0882468e273448", "labels_vector_sha256": "28590a7ab4ae8d87bc59d3af3844cdd60ce6bb0ae31ae1a96dc33ea08ca2cd53", "planned_active_tokens": 61220, "realized_active_tokens": 61220, "cumulative_start": 48697863, "cumulative_end": 48759083, "loss_sum": 17925.81088256836, "token_normalized_loss": 0.29280971712787257, "grad_norm_before_clip": 0.09033911675214767, "learning_rates_at_step": { "lora": 1.5919013521932026e-05, "row_tokens": 1.5919013521932026e-05 }, "learning_rates_after_step": { "lora": 1.5792048998890364e-05, "row_tokens": 1.5792048998890364e-05 } }, { "update_id": 744, "row_count": 9, "row_ids_sha256": "dd1c0c34034f99bcb79f372c6b9a0b2efd0779c47784ca7fc934a4acdf20709e", "input_ids_vector_sha256": "68f757b5582bc2a6353200669769cede7461c524f974821ea8515e7c796c3bc0", "labels_vector_sha256": "4603a39e87435f7c0fb0e0fc0d8d7aad53737c93498b21f3adb24c5b3a4bc1f2", "planned_active_tokens": 67222, "realized_active_tokens": 67222, "cumulative_start": 48759083, "cumulative_end": 48826305, "loss_sum": 23027.816131591797, "token_normalized_loss": 0.34256368646561836, "grad_norm_before_clip": 0.0930546298623085, "learning_rates_at_step": { "lora": 1.5792048998890364e-05, "row_tokens": 1.5792048998890364e-05 }, "learning_rates_after_step": { "lora": 1.566299437784951e-05, "row_tokens": 1.566299437784951e-05 } }, { "update_id": 745, "row_count": 13, "row_ids_sha256": "fa69d1ad1e5bbad40ad55d6a145dc398df61fc5217e4e5c7115e5b59193f25a4", "input_ids_vector_sha256": "d4558f0bc329fefb70d4f88aa16f8606dd95c49c387f2a9ecf0ec883f7f4e7de", "labels_vector_sha256": "c0db7cb8eade5a19b38ded338acfec23eb5294eb8a2b67a31d4229abe731b800", "planned_active_tokens": 68554, "realized_active_tokens": 68554, "cumulative_start": 48826305, "cumulative_end": 48894859, "loss_sum": 22979.562744140625, "token_normalized_loss": 0.3352038209898857, "grad_norm_before_clip": 0.09024979174137115, "learning_rates_at_step": { "lora": 1.566299437784951e-05, "row_tokens": 1.566299437784951e-05 }, "learning_rates_after_step": { "lora": 1.5544779473604378e-05, "row_tokens": 1.5544779473604378e-05 } }, { "update_id": 746, "row_count": 10, "row_ids_sha256": "c3bd1e38e8582cf3d768db0ace500e58636851021f98f02bd6a9983281ad41fb", "input_ids_vector_sha256": "e724982e7e7ad2ecb2cabdc1175119ff2354611d906d6a0f3b17163afccdc5c8", "labels_vector_sha256": "f6128b2712dad6fdee6270661e31d552143ae0ae5b3dc9331e6271d150320c28", "planned_active_tokens": 62998, "realized_active_tokens": 62998, "cumulative_start": 48894859, "cumulative_end": 48957857, "loss_sum": 21371.528747558594, "token_normalized_loss": 0.33924138460837794, "grad_norm_before_clip": 0.09425011277198792, "learning_rates_at_step": { "lora": 1.5544779473604378e-05, "row_tokens": 1.5544779473604378e-05 }, "learning_rates_after_step": { "lora": 1.5426756499687083e-05, "row_tokens": 1.5426756499687083e-05 } }, { "update_id": 747, "row_count": 10, "row_ids_sha256": "ac3508c4a377c919c847119e3ad5cc26818d50ea040ccf032302bc642f6645ad", "input_ids_vector_sha256": "2e9361537cb328f0a405bfa6a5292a35678bf82a7bc55014e9e5579790db700c", "labels_vector_sha256": "61c571c6cd8329e0955bbc3230f50ff746d82d086cb40dea0bdff58fbd0504e4", "planned_active_tokens": 63091, "realized_active_tokens": 63091, "cumulative_start": 48957857, "cumulative_end": 49020948, "loss_sum": 18834.46534729004, "token_normalized_loss": 0.29852855949802726, "grad_norm_before_clip": 0.08747683465480804, "learning_rates_at_step": { "lora": 1.5426756499687083e-05, "row_tokens": 1.5426756499687083e-05 }, "learning_rates_after_step": { "lora": 1.5297321101991e-05, "row_tokens": 1.5297321101991e-05 } }, { "update_id": 748, "row_count": 15, "row_ids_sha256": "a19958f7074db416d93f3c72fa1566492f08b0ba93f51796c8dfaa6ac489d3e7", "input_ids_vector_sha256": "7d41fdf7f61bf4e629316547481c6886d22a38aebc05307e80507993bb5945da", "labels_vector_sha256": "4e7ed14e9676ee46da8ccda8975f24faaf5bbe7c8d7a5359ea6867c0204c377a", "planned_active_tokens": 69419, "realized_active_tokens": 69419, "cumulative_start": 49020948, "cumulative_end": 49090367, "loss_sum": 19595.072235107422, "token_normalized_loss": 0.2822724648166557, "grad_norm_before_clip": 0.08446426689624786, "learning_rates_at_step": { "lora": 1.5297321101991e-05, "row_tokens": 1.5297321101991e-05 }, "learning_rates_after_step": { "lora": 1.5178870094394953e-05, "row_tokens": 1.5178870094394953e-05 } }, { "update_id": 749, "row_count": 13, "row_ids_sha256": "8b62cf2a30aa2bd27acfecbfd5145a3e67927e6e748509b3d881d1038e381fe5", "input_ids_vector_sha256": "d96edce4ead4ef3019e3bf09a32ed77a911a637d245919f73bb7fe21b19af5e3", "labels_vector_sha256": "39f321781d3e3b216df9faa1deed8c6736403890c4defcb116c579b498e57884", "planned_active_tokens": 63739, "realized_active_tokens": 63739, "cumulative_start": 49090367, "cumulative_end": 49154106, "loss_sum": 20052.372497558594, "token_normalized_loss": 0.31460130371607015, "grad_norm_before_clip": 0.09092768281698227, "learning_rates_at_step": { "lora": 1.5178870094394953e-05, "row_tokens": 1.5178870094394953e-05 }, "learning_rates_after_step": { "lora": 1.5044547836720541e-05, "row_tokens": 1.5044547836720541e-05 } }, { "update_id": 750, "row_count": 12, "row_ids_sha256": "e7f27f41d431436d3ec181f1d70682b6c3424054ca88e63de6a933e13ea2bbbc", "input_ids_vector_sha256": "f2fa6777f44f5159a7d2d05852e3a733ae4487365d8cf87a88b303e57b568290", "labels_vector_sha256": "e94f29c7e4ea9ec6fc86e2ac1fd4e0c1f5e5e1515400f7987b298c48a9699b98", "planned_active_tokens": 72527, "realized_active_tokens": 72527, "cumulative_start": 49154106, "cumulative_end": 49226633, "loss_sum": 25102.931732177734, "token_normalized_loss": 0.34611843495770866, "grad_norm_before_clip": 0.08573397994041443, "learning_rates_at_step": { "lora": 1.5044547836720541e-05, "row_tokens": 1.5044547836720541e-05 }, "learning_rates_after_step": { "lora": 1.493752428824196e-05, "row_tokens": 1.493752428824196e-05 } }, { "update_id": 751, "row_count": 13, "row_ids_sha256": "4946141dd63a9f20e7fe5fdf9bc9d41870bc664c0232addea71a13c38797c418", "input_ids_vector_sha256": "e0c351d5ba5e47e26917f425d3cd79a51ddb6dc02b7aa169964a4ef0968f7426", "labels_vector_sha256": "902cfe34ef1fda859223f49f68828b61782ef254dfb776f2296049a36da3859f", "planned_active_tokens": 57978, "realized_active_tokens": 57978, "cumulative_start": 49226633, "cumulative_end": 49284611, "loss_sum": 16687.44512939453, "token_normalized_loss": 0.2878237457206963, "grad_norm_before_clip": 0.09124794602394104, "learning_rates_at_step": { "lora": 1.493752428824196e-05, "row_tokens": 1.493752428824196e-05 }, "learning_rates_after_step": { "lora": 1.4806782158076476e-05, "row_tokens": 1.4806782158076476e-05 } }, { "update_id": 752, "row_count": 13, "row_ids_sha256": "1bb1089290cdaa3e4fc139202f92796ec68b05fb195b170c22f8713c7adf8cfc", "input_ids_vector_sha256": "53c0a310346a2db0250d34d9ac828b9e8cb85c086e96f6a5a100831660c73e57", "labels_vector_sha256": "378038cae6cc8d7d02e2d2c9d83ef69b025c86104c1c94a091e1cc04eb0cb468", "planned_active_tokens": 71060, "realized_active_tokens": 71060, "cumulative_start": 49284611, "cumulative_end": 49355671, "loss_sum": 24440.08511352539, "token_normalized_loss": 0.3439359008376779, "grad_norm_before_clip": 0.0890514925122261, "learning_rates_at_step": { "lora": 1.4806782158076476e-05, "row_tokens": 1.4806782158076476e-05 }, "learning_rates_after_step": { "lora": 1.4698189010551572e-05, "row_tokens": 1.4698189010551572e-05 } }, { "update_id": 753, "row_count": 12, "row_ids_sha256": "542cca2444bf810f883d85d76fe7d61cec393efb0827ede2116172732c419886", "input_ids_vector_sha256": "39ea6f8ba52ba3622fd1623527127272177d640a58a8cefba04963130cafb427", "labels_vector_sha256": "547f5da8f94b58f3098812cbaf83e06e672b5642ec2e1807f81fc6d13ffdfc46", "planned_active_tokens": 59219, "realized_active_tokens": 59219, "cumulative_start": 49355671, "cumulative_end": 49414890, "loss_sum": 17342.314392089844, "token_normalized_loss": 0.29285051068221085, "grad_norm_before_clip": 0.0910802036523819, "learning_rates_at_step": { "lora": 1.4698189010551572e-05, "row_tokens": 1.4698189010551572e-05 }, "learning_rates_after_step": { "lora": 1.4574524178284104e-05, "row_tokens": 1.4574524178284104e-05 } }, { "update_id": 754, "row_count": 15, "row_ids_sha256": "bb240e07a122d8d9c7a88bac3623f0b9083960e01e16a52663c32d45bf5c5eac", "input_ids_vector_sha256": "3bddcc55017dc1efcc8f106f2634fbdbb610213195f9e9ae94a4304ddedbeb4e", "labels_vector_sha256": "1d5bcfe8240b6a11a46546c6e27f065f28991ff4981e4992bbc3d0957782637b", "planned_active_tokens": 67659, "realized_active_tokens": 67659, "cumulative_start": 49414890, "cumulative_end": 49482549, "loss_sum": 19766.377868652344, "token_normalized_loss": 0.29214705905574045, "grad_norm_before_clip": 0.08232980221509933, "learning_rates_at_step": { "lora": 1.4574524178284104e-05, "row_tokens": 1.4574524178284104e-05 }, "learning_rates_after_step": { "lora": 1.445534038765558e-05, "row_tokens": 1.445534038765558e-05 } }, { "update_id": 755, "row_count": 13, "row_ids_sha256": "d65ed591c1cd5d09fdcd36aa4f50989499a35fbe361cfbaa0cc3db8275330b5d", "input_ids_vector_sha256": "03d09a69e94c1c4bf921ab57468134e35cb1f45e870a9203488007f94465fcd0", "labels_vector_sha256": "31738b631930b67ee542f2c2213dd1a0379558f96ce4149fbe565744f3395dd8", "planned_active_tokens": 65433, "realized_active_tokens": 65433, "cumulative_start": 49482549, "cumulative_end": 49547982, "loss_sum": 18480.30157470703, "token_normalized_loss": 0.2824309075650976, "grad_norm_before_clip": 0.08517728745937347, "learning_rates_at_step": { "lora": 1.445534038765558e-05, "row_tokens": 1.445534038765558e-05 }, "learning_rates_after_step": { "lora": 1.4339337992524522e-05, "row_tokens": 1.4339337992524522e-05 } }, { "update_id": 756, "row_count": 13, "row_ids_sha256": "f167f41b454ef7922632e47f10f1b02c8706181b840a09d76736de0d2104a333", "input_ids_vector_sha256": "595564d65ee56064ba88a142480eac8a7a3c062826d2877aaa863157fbfdf13c", "labels_vector_sha256": "d37838be75f77bb15c7be537788228802a4095150bb20477c00c766f38b24e34", "planned_active_tokens": 63902, "realized_active_tokens": 63902, "cumulative_start": 49547982, "cumulative_end": 49611884, "loss_sum": 20179.096618652344, "token_normalized_loss": 0.3157819257402326, "grad_norm_before_clip": 0.08918509632349014, "learning_rates_at_step": { "lora": 1.4339337992524522e-05, "row_tokens": 1.4339337992524522e-05 }, "learning_rates_after_step": { "lora": 1.4217692883708584e-05, "row_tokens": 1.4217692883708584e-05 } }, { "update_id": 757, "row_count": 14, "row_ids_sha256": "bbf59f8f9a9497ba38b89ab0cb85d03b3447bc65b5817fee8226f89ab0060263", "input_ids_vector_sha256": "dac9ccd62b351599410b999c23b9f70b8fccd6eaf12d4c2bc51ddf1c5f195e3f", "labels_vector_sha256": "7d43e95b1914a6b3fdfe75780ccd5ca609af1b63ff7d8af461d16d392ba76f8a", "planned_active_tokens": 67242, "realized_active_tokens": 67242, "cumulative_start": 49611884, "cumulative_end": 49679126, "loss_sum": 19424.682586669922, "token_normalized_loss": 0.28887722831965024, "grad_norm_before_clip": 0.08246809244155884, "learning_rates_at_step": { "lora": 1.4217692883708584e-05, "row_tokens": 1.4217692883708584e-05 }, "learning_rates_after_step": { "lora": 1.4103288217929561e-05, "row_tokens": 1.4103288217929561e-05 } }, { "update_id": 758, "row_count": 12, "row_ids_sha256": "fa60c011f564dcff01cf7ab1a03d6395798fb79712bc1c621ba399564ca0b0fd", "input_ids_vector_sha256": "316af27c50e240980065c1299d657f50a731682d3da25cd6af84dca7f11bedd4", "labels_vector_sha256": "1d33c6abcc778d67a84fcd080d2b6c2411cb5c5664254cac33b45600d9922120", "planned_active_tokens": 63459, "realized_active_tokens": 63459, "cumulative_start": 49679126, "cumulative_end": 49742585, "loss_sum": 19554.64143371582, "token_normalized_loss": 0.30814606964679275, "grad_norm_before_clip": 0.09207351505756378, "learning_rates_at_step": { "lora": 1.4103288217929561e-05, "row_tokens": 1.4103288217929561e-05 }, "learning_rates_after_step": { "lora": 1.3982137415577712e-05, "row_tokens": 1.3982137415577712e-05 } }, { "update_id": 759, "row_count": 10, "row_ids_sha256": "e1aa84248eed16d4f1350b0d91914d0a24ca4befe2fc01d3a1dd45aa216df45d", "input_ids_vector_sha256": "dd19d833c0c9095f5a769a51af1a56bdc4b344ff771a915e5b15651b8aaf4906", "labels_vector_sha256": "bb531b448249c192b1eb96fb043c2a6625be296e22470c586befa41f2c27d20c", "planned_active_tokens": 67436, "realized_active_tokens": 67436, "cumulative_start": 49742585, "cumulative_end": 49810021, "loss_sum": 25154.296875, "token_normalized_loss": 0.3730099186636218, "grad_norm_before_clip": 0.09099912643432617, "learning_rates_at_step": { "lora": 1.3982137415577712e-05, "row_tokens": 1.3982137415577712e-05 }, "learning_rates_after_step": { "lora": 1.386474994389465e-05, "row_tokens": 1.386474994389465e-05 } }, { "update_id": 760, "row_count": 15, "row_ids_sha256": "7d1ba556355b57e010e50d19efdbc2d477525483341ac98aa934b2209881c7c6", "input_ids_vector_sha256": "47d059c0b034723b97b2d82719d43a1cd28c5e599ebef55663790cc0af99be8f", "labels_vector_sha256": "24809f5df7bfd604946060ba624161172e4280b22047b54e2501137c227538df", "planned_active_tokens": 65575, "realized_active_tokens": 65575, "cumulative_start": 49810021, "cumulative_end": 49875596, "loss_sum": 17978.393768310547, "token_normalized_loss": 0.27416536436615396, "grad_norm_before_clip": 0.08459767699241638, "learning_rates_at_step": { "lora": 1.386474994389465e-05, "row_tokens": 1.386474994389465e-05 }, "learning_rates_after_step": { "lora": 1.3740688307386274e-05, "row_tokens": 1.3740688307386274e-05 } }, { "update_id": 761, "row_count": 13, "row_ids_sha256": "dd222c32d649b6d498b14b66fac51d8884b76a8624887ba3f6917c74aa26f9b2", "input_ids_vector_sha256": "1d2fca1f1177095081356c6664807597174b086b84bdbd5f42ef4c0dfc4572c1", "labels_vector_sha256": "1b004a8f807478a1228c702bfeba7714c2a0553bbb399003369d6c94a57ae4c4", "planned_active_tokens": 69557, "realized_active_tokens": 69557, "cumulative_start": 49875596, "cumulative_end": 49945153, "loss_sum": 23868.92645263672, "token_normalized_loss": 0.3431563531008629, "grad_norm_before_clip": 0.091301329433918, "learning_rates_at_step": { "lora": 1.3740688307386274e-05, "row_tokens": 1.3740688307386274e-05 }, "learning_rates_after_step": { "lora": 1.3635463499687201e-05, "row_tokens": 1.3635463499687201e-05 } }, { "update_id": 762, "row_count": 11, "row_ids_sha256": "7169c71c81d97edc54335fd69980cf41032c8366ac0f2c87a7ac3f80bf0a12c1", "input_ids_vector_sha256": "27f40ad59bf512429972a894417c4b014c4afa4c0b1f5b91e1b3d1a6ad5cc05a", "labels_vector_sha256": "d8a1e8c72da136afe7caa50e0f3ea5b3ee8d1a3051bbbbd7b9841772e95f6f93", "planned_active_tokens": 59203, "realized_active_tokens": 59203, "cumulative_start": 49945153, "cumulative_end": 50004356, "loss_sum": 18268.31817626953, "token_normalized_loss": 0.3085708186454999, "grad_norm_before_clip": 0.09352398663759232, "learning_rates_at_step": { "lora": 1.3635463499687201e-05, "row_tokens": 1.3635463499687201e-05 }, "learning_rates_after_step": { "lora": 1.3519555215330116e-05, "row_tokens": 1.3519555215330116e-05 } }, { "update_id": 763, "row_count": 14, "row_ids_sha256": "749c07cc397b6c8c5d6440e8b590862d05c38a7e8c19d9f1c4dfd4c190c9320e", "input_ids_vector_sha256": "805cc45ee80fcc50aa2c7c44b982d5d7837364230c63593cfed72337dd78360b", "labels_vector_sha256": "54bf9d7dec35f624b705c9e857e82ed262d93b8f9a015ed6630ec3ebd262d172", "planned_active_tokens": 65437, "realized_active_tokens": 65437, "cumulative_start": 50004356, "cumulative_end": 50069793, "loss_sum": 17946.32568359375, "token_normalized_loss": 0.27425349089343565, "grad_norm_before_clip": 0.08390683680772781, "learning_rates_at_step": { "lora": 1.3519555215330116e-05, "row_tokens": 1.3519555215330116e-05 }, "learning_rates_after_step": { "lora": 1.3392374265991603e-05, "row_tokens": 1.3392374265991603e-05 } }, { "update_id": 764, "row_count": 14, "row_ids_sha256": "ac23dde57ba39f028353e5da9dfa6323674638e6ceb4d3568f6594c36fe537cd", "input_ids_vector_sha256": "348e2292b144da0fa9de8ef25d90f2e84146d2a9f923d4023f6afb215a847a2c", "labels_vector_sha256": "85e4a1934e91cd34eff0b1c15d94220a5e75069b279fdbd37a309bb2103ad779", "planned_active_tokens": 72074, "realized_active_tokens": 72074, "cumulative_start": 50069793, "cumulative_end": 50141867, "loss_sum": 22983.15802001953, "token_normalized_loss": 0.3188827874132077, "grad_norm_before_clip": 0.0841766893863678, "learning_rates_at_step": { "lora": 1.3392374265991603e-05, "row_tokens": 1.3392374265991603e-05 }, "learning_rates_after_step": { "lora": 1.3280315998023907e-05, "row_tokens": 1.3280315998023907e-05 } }, { "update_id": 765, "row_count": 12, "row_ids_sha256": "1ddce83fb20356a4eea42918ced8bd6c233263659bd0cd47aa280c374bdd118f", "input_ids_vector_sha256": "63ccc46544251d38fa8eb5050d9cc9b9f57950ac39d3a33e174fac7161f50e39", "labels_vector_sha256": "fc78c56c1d0512872050342f5cda6bc68dd01489996f886a5ff777944b579aa3", "planned_active_tokens": 63744, "realized_active_tokens": 63744, "cumulative_start": 50141867, "cumulative_end": 50205611, "loss_sum": 18971.834533691406, "token_normalized_loss": 0.297625416253944, "grad_norm_before_clip": 0.09051896631717682, "learning_rates_at_step": { "lora": 1.3280315998023907e-05, "row_tokens": 1.3280315998023907e-05 }, "learning_rates_after_step": { "lora": 1.3169072833432445e-05, "row_tokens": 1.3169072833432445e-05 } }, { "update_id": 766, "row_count": 13, "row_ids_sha256": "330336e21f36b878aa3eac1fc3a8aa30260c06f0a3b30be95331c6a3bad6bdbd", "input_ids_vector_sha256": "d165cee1ee12d8b8e65426155fb369778389f59dd95dbc761885205c8635dfbc", "labels_vector_sha256": "88fc1833cd8894852661b3bbe33c1b431e368244e018cc01c0c97dd619033388", "planned_active_tokens": 63506, "realized_active_tokens": 63506, "cumulative_start": 50205611, "cumulative_end": 50269117, "loss_sum": 19536.85369873047, "token_normalized_loss": 0.3076379192317335, "grad_norm_before_clip": 0.08909622579813004, "learning_rates_at_step": { "lora": 1.3169072833432445e-05, "row_tokens": 1.3169072833432445e-05 }, "learning_rates_after_step": { "lora": 1.305750901861365e-05, "row_tokens": 1.305750901861365e-05 } }, { "update_id": 767, "row_count": 15, "row_ids_sha256": "979b74044008b5c4e32cc758df2caa9fad764e6a83fea1712cfa5c5d390a3ff6", "input_ids_vector_sha256": "c1fc4926717767613b94345e722fad3a3c53453a63ddca790f8c8677d8de70c9", "labels_vector_sha256": "7d0603b413bbdfa90f2795377c8f951a2f327c60dc5ec4aa9af3e84c75b510d2", "planned_active_tokens": 63918, "realized_active_tokens": 63918, "cumulative_start": 50269117, "cumulative_end": 50333035, "loss_sum": 16839.500213623047, "token_normalized_loss": 0.2634547422263376, "grad_norm_before_clip": 0.08322732895612717, "learning_rates_at_step": { "lora": 1.305750901861365e-05, "row_tokens": 1.305750901861365e-05 }, "learning_rates_after_step": { "lora": 1.2943173889020233e-05, "row_tokens": 1.2943173889020233e-05 } }, { "update_id": 768, "row_count": 15, "row_ids_sha256": "04058a69f2f9e74d12616385c4834cf24a41067df54d0a6144d644aacfb687b1", "input_ids_vector_sha256": "72262802c00b1f410c228202661bb023c47fd8c20464f9c383f9166e7187a8de", "labels_vector_sha256": "63dc562e42cda7c750d28c9e4c28ea3daf2d16b64fb6ab066f28540d1d440520", "planned_active_tokens": 65747, "realized_active_tokens": 65747, "cumulative_start": 50333035, "cumulative_end": 50398782, "loss_sum": 19691.08578491211, "token_normalized_loss": 0.29949785974891796, "grad_norm_before_clip": 0.08650752902030945, "learning_rates_at_step": { "lora": 1.2943173889020233e-05, "row_tokens": 1.2943173889020233e-05 }, "learning_rates_after_step": { "lora": 1.2827349403936839e-05, "row_tokens": 1.2827349403936839e-05 } }, { "update_id": 769, "row_count": 14, "row_ids_sha256": "de78ad0f53b9523f03e6973e019dc4bf621a243346ab2e8ecd06312afba5804b", "input_ids_vector_sha256": "6a76b13a1fb8329642810402122d6373509dda0cae44965c8c7f8b4f0db7d8bc", "labels_vector_sha256": "dcf79ebdaa2fdd89ae5f265b751b3f1ac28021d639c3cd982a2477d9aa8f67fd", "planned_active_tokens": 66856, "realized_active_tokens": 66856, "cumulative_start": 50398782, "cumulative_end": 50465638, "loss_sum": 18348.35726928711, "token_normalized_loss": 0.2744459325907489, "grad_norm_before_clip": 0.08528561145067215, "learning_rates_at_step": { "lora": 1.2827349403936839e-05, "row_tokens": 1.2827349403936839e-05 }, "learning_rates_after_step": { "lora": 1.2711705645584893e-05, "row_tokens": 1.2711705645584893e-05 } }, { "update_id": 770, "row_count": 18, "row_ids_sha256": "35aeab4d51049b930531a8f6cd260f5d65660ef5b1b2c48b31864b528aa43860", "input_ids_vector_sha256": "b12047ec0c425a95e976ea20d0138f11bbe6e2806a882577750a309b44b2b852", "labels_vector_sha256": "d1f229c9a02a0cee368421043442bae25008deb64f87c9abdd394d61de1df468", "planned_active_tokens": 67009, "realized_active_tokens": 67009, "cumulative_start": 50465638, "cumulative_end": 50532647, "loss_sum": 17916.20428466797, "token_normalized_loss": 0.2673701187104414, "grad_norm_before_clip": 0.07956050336360931, "learning_rates_at_step": { "lora": 1.2711705645584893e-05, "row_tokens": 1.2711705645584893e-05 }, "learning_rates_after_step": { "lora": 1.2604964368226574e-05, "row_tokens": 1.2604964368226574e-05 } }, { "update_id": 771, "row_count": 14, "row_ids_sha256": "01f2b478dc9850fa15f731d04856234ee57f5631afa18e70027416a3fdd86fa2", "input_ids_vector_sha256": "6039fab66895b16508a5c647d95a87a1155bd8fd293b89e8d25ef76a3d6c07b1", "labels_vector_sha256": "293c17e7b13522bc0a1c8537319abc7f5221af0df8365cae73e183bc24a6fa92", "planned_active_tokens": 62082, "realized_active_tokens": 62082, "cumulative_start": 50532647, "cumulative_end": 50594729, "loss_sum": 15489.184631347656, "token_normalized_loss": 0.2494955805442424, "grad_norm_before_clip": 0.08424675464630127, "learning_rates_at_step": { "lora": 1.2604964368226574e-05, "row_tokens": 1.2604964368226574e-05 }, "learning_rates_after_step": { "lora": 1.2491021993653785e-05, "row_tokens": 1.2491021993653785e-05 } }, { "update_id": 772, "row_count": 15, "row_ids_sha256": "a16ca0c461e869a62b8b876175dd8a8588714b077ad68887c8d66deb561bc1d5", "input_ids_vector_sha256": "272b249c81c4e0f0a46cf8c35d4232f96547aef96610a7cb73d4a0cbb57eb6ed", "labels_vector_sha256": "5ab60e1cc1a157ffd59bbe235a5d7fb542796ed1b52df10c896977efe0e0b7c6", "planned_active_tokens": 66519, "realized_active_tokens": 66519, "cumulative_start": 50594729, "cumulative_end": 50661248, "loss_sum": 18120.954620361328, "token_normalized_loss": 0.27241772456533214, "grad_norm_before_clip": 0.08150996267795563, "learning_rates_at_step": { "lora": 1.2491021993653785e-05, "row_tokens": 1.2491021993653785e-05 }, "learning_rates_after_step": { "lora": 1.2374175656354287e-05, "row_tokens": 1.2374175656354287e-05 } }, { "update_id": 773, "row_count": 16, "row_ids_sha256": "08ad13469733045634be9ddc36dde4ea6c0f2f6e7cfa3c8331f3186ea96d6a80", "input_ids_vector_sha256": "b235aa032214c7ec1bdaef8aaa285d049ed27d6e5c00f0e799ac5c2a91087c1b", "labels_vector_sha256": "d10ca66bc079f159de47e1dd11805dd1be4a7cb5c3c8c4f61b5a8a5707ae4155", "planned_active_tokens": 68485, "realized_active_tokens": 68485, "cumulative_start": 50661248, "cumulative_end": 50729733, "loss_sum": 19533.39614868164, "token_normalized_loss": 0.2852215251322427, "grad_norm_before_clip": 0.08233202248811722, "learning_rates_at_step": { "lora": 1.2374175656354287e-05, "row_tokens": 1.2374175656354287e-05 }, "learning_rates_after_step": { "lora": 1.2257049942307336e-05, "row_tokens": 1.2257049942307336e-05 } }, { "update_id": 774, "row_count": 9, "row_ids_sha256": "c4fbc9a8265b4d09161759c5df4a8ebd1bb09224fad498bab368e77b3d10f62e", "input_ids_vector_sha256": "030a31b72530fdac66694a9ba8da178770db6793d51a97c8e24c9b41b68a0eda", "labels_vector_sha256": "b37a8cdfc6c22b2a3d2a7e44653180be8d7144535bdc2af281a4a99ab6dccedd", "planned_active_tokens": 68928, "realized_active_tokens": 68928, "cumulative_start": 50729733, "cumulative_end": 50798661, "loss_sum": 23235.858306884766, "token_normalized_loss": 0.3371033296611648, "grad_norm_before_clip": 0.08743957430124283, "learning_rates_at_step": { "lora": 1.2257049942307336e-05, "row_tokens": 1.2257049942307336e-05 }, "learning_rates_after_step": { "lora": 1.2153983281933501e-05, "row_tokens": 1.2153983281933501e-05 } }, { "update_id": 775, "row_count": 12, "row_ids_sha256": "567aa93d8ef25a17cc6c952310609be16168fc81ae8a52ba17bd5411f8966f14", "input_ids_vector_sha256": "28163ef12afd7f8aacb7a39c0a6fa685131d176ccd4dcb2f37babd4d989f2de3", "labels_vector_sha256": "5682af837377c2c3eb2c74deafb30ca0b2c6229ad6d51e700c5e93a383c28669", "planned_active_tokens": 60889, "realized_active_tokens": 60889, "cumulative_start": 50798661, "cumulative_end": 50859550, "loss_sum": 18092.528289794922, "token_normalized_loss": 0.2971395209281631, "grad_norm_before_clip": 0.09247933328151703, "learning_rates_at_step": { "lora": 1.2153983281933501e-05, "row_tokens": 1.2153983281933501e-05 }, "learning_rates_after_step": { "lora": 1.2043858673596209e-05, "row_tokens": 1.2043858673596209e-05 } }, { "update_id": 776, "row_count": 13, "row_ids_sha256": "7bfb5be1c59afe6fb4b0b1a1730978897b719dc03ceef1e159947381c26755ef", "input_ids_vector_sha256": "2a26e8c8541d821856b2a02b52842b3dee9b9d82ad332073017428fab730d37d", "labels_vector_sha256": "95a8c98472afa213888fc4d41e84b11b56d49c3f7ce0414fd557e246c0eee8f5", "planned_active_tokens": 65305, "realized_active_tokens": 65305, "cumulative_start": 50859550, "cumulative_end": 50924855, "loss_sum": 19031.515167236328, "token_normalized_loss": 0.2914250848669524, "grad_norm_before_clip": 0.08487412333488464, "learning_rates_at_step": { "lora": 1.2043858673596209e-05, "row_tokens": 1.2043858673596209e-05 }, "learning_rates_after_step": { "lora": 1.193277721873255e-05, "row_tokens": 1.193277721873255e-05 } }, { "update_id": 777, "row_count": 16, "row_ids_sha256": "6b5cdcb30694ee2a10a1ca73a839973b35cd2ef4f44c0c79150670dd52156fd1", "input_ids_vector_sha256": "a761cf87ce9643fb314ddab95dea446598babcb3c4957bd037a8d11908b12598", "labels_vector_sha256": "c756f3952e7394847e5f370a841c7aa83742fec58b21bf1248d871bf8f3f6336", "planned_active_tokens": 66134, "realized_active_tokens": 66134, "cumulative_start": 50924855, "cumulative_end": 50990989, "loss_sum": 18761.49234008789, "token_normalized_loss": 0.28368906069628164, "grad_norm_before_clip": 0.0878390446305275, "learning_rates_at_step": { "lora": 1.193277721873255e-05, "row_tokens": 1.193277721873255e-05 }, "learning_rates_after_step": { "lora": 1.181957665523939e-05, "row_tokens": 1.181957665523939e-05 } }, { "update_id": 778, "row_count": 17, "row_ids_sha256": "da692ecff4cd749c93ce5f6b7b30f0a1fb3df99a39d77f555fba730cfbff25a7", "input_ids_vector_sha256": "0a03811e93856e3601dd2a246507c94dc496a3a4c01b07ef2d7a686ac0f8ae6b", "labels_vector_sha256": "77b6dafc997597c0a9b1b508b895105d6f23e75dd285aa08356eaab25ccf2b06", "planned_active_tokens": 67670, "realized_active_tokens": 67670, "cumulative_start": 50990989, "cumulative_end": 51058659, "loss_sum": 17194.029266357422, "token_normalized_loss": 0.2540864381019273, "grad_norm_before_clip": 0.0810484066605568, "learning_rates_at_step": { "lora": 1.181957665523939e-05, "row_tokens": 1.181957665523939e-05 }, "learning_rates_after_step": { "lora": 1.1718844240780236e-05, "row_tokens": 1.1718844240780236e-05 } }, { "update_id": 779, "row_count": 11, "row_ids_sha256": "39525dfd59cfd3d772e701ceeff41249a937f3524d2fc66a805fa01ae5ab3e8d", "input_ids_vector_sha256": "5204cd03445c2ae69d3648f0815fb02732af7cae5f76859b71fbb32a103c777a", "labels_vector_sha256": "1c385bdb3deb316544f13903daca8969e5199212398286b8dab6f4888c04bba5", "planned_active_tokens": 60453, "realized_active_tokens": 60453, "cumulative_start": 51058659, "cumulative_end": 51119112, "loss_sum": 18603.788848876953, "token_normalized_loss": 0.30773971265076927, "grad_norm_before_clip": 0.09277775138616562, "learning_rates_at_step": { "lora": 1.1718844240780236e-05, "row_tokens": 1.1718844240780236e-05 }, "learning_rates_after_step": { "lora": 1.1606384210912463e-05, "row_tokens": 1.1606384210912463e-05 } }, { "update_id": 780, "row_count": 14, "row_ids_sha256": "d2f7d4622ef1ca21103accb3dfbbed9172be2ec47f858ee20d3cb82bbd31b614", "input_ids_vector_sha256": "d67be030fec7ad28bce9576361d75c9aa9f63d0fb8d6c9b22236ceed33f5e186", "labels_vector_sha256": "df7803288a3fe23b141274c9bd44f9b7faac0bf1d68a4ef2a2e162f139ff96bb", "planned_active_tokens": 67758, "realized_active_tokens": 67758, "cumulative_start": 51119112, "cumulative_end": 51186870, "loss_sum": 19818.84747314453, "token_normalized_loss": 0.2924945758898511, "grad_norm_before_clip": 0.08686652034521103, "learning_rates_at_step": { "lora": 1.1606384210912463e-05, "row_tokens": 1.1606384210912463e-05 }, "learning_rates_after_step": { "lora": 1.1491687506786397e-05, "row_tokens": 1.1491687506786397e-05 } }, { "update_id": 781, "row_count": 17, "row_ids_sha256": "a3bbea4772f8eaf093118721ca8c47629d022763a1ee10f80eb4862cb6b408cc", "input_ids_vector_sha256": "4ab52d1a86c9ced5a4c954bee30d9019cde7da6c06a59524360fc043abedb1ff", "labels_vector_sha256": "37bb97971c29af6e53bc6c59268a7a2c3d1ab149fe7c18443d5e1d859a1fc7b0", "planned_active_tokens": 69400, "realized_active_tokens": 69400, "cumulative_start": 51186870, "cumulative_end": 51256270, "loss_sum": 18292.280029296875, "token_normalized_loss": 0.263577522035978, "grad_norm_before_clip": 0.08094944059848785, "learning_rates_at_step": { "lora": 1.1491687506786397e-05, "row_tokens": 1.1491687506786397e-05 }, "learning_rates_after_step": { "lora": 1.1391989292854088e-05, "row_tokens": 1.1391989292854088e-05 } }, { "update_id": 782, "row_count": 10, "row_ids_sha256": "f2200d951447a805daa63abbeef0e41d891278fc796260812b967ebcffd6b31e", "input_ids_vector_sha256": "8d24f581b427206aa6215103913243458f55de93177e5d1abe4666474051b23b", "labels_vector_sha256": "7d477a410f037499b0dd788d3b00f1d2731f47fe9ed7c7f71680276cdff984ce", "planned_active_tokens": 60570, "realized_active_tokens": 60570, "cumulative_start": 51256270, "cumulative_end": 51316840, "loss_sum": 18838.387939453125, "token_normalized_loss": 0.3110184569828814, "grad_norm_before_clip": 0.09254215657711029, "learning_rates_at_step": { "lora": 1.1391989292854088e-05, "row_tokens": 1.1391989292854088e-05 }, "learning_rates_after_step": { "lora": 1.1285304451165551e-05, "row_tokens": 1.1285304451165551e-05 } }, { "update_id": 783, "row_count": 15, "row_ids_sha256": "cb4f6157e5e8a976099cc80a0859dc49c0c2f757ec3d67bdfffcacdd0aeb0428", "input_ids_vector_sha256": "7dfece695c3cb1ad7bec26e8b70da712721ddcd8757eff828573160fd401303a", "labels_vector_sha256": "53bcba2c0712a509148b3821435bd40072d97972d1abd194d50a0247a38b3a5c", "planned_active_tokens": 65071, "realized_active_tokens": 65071, "cumulative_start": 51316840, "cumulative_end": 51381911, "loss_sum": 20063.842315673828, "token_normalized_loss": 0.3083376975253773, "grad_norm_before_clip": 0.08922991156578064, "learning_rates_at_step": { "lora": 1.1285304451165551e-05, "row_tokens": 1.1285304451165551e-05 }, "learning_rates_after_step": { "lora": 1.1177842418969675e-05, "row_tokens": 1.1177842418969675e-05 } }, { "update_id": 784, "row_count": 13, "row_ids_sha256": "6b12235b6fa5ab97da25ec9697c3ed2185488860380d9b9dfc0ff407ca218511", "input_ids_vector_sha256": "00b9ec2c89a94e7d7cd1d4a3d61761b678dabb568527bf89cee20d36cbd89b9c", "labels_vector_sha256": "90996d5ee7982ca80df5fdd3deae3c7ef914ba4574547b70a853c85348ff7bdd", "planned_active_tokens": 65817, "realized_active_tokens": 65817, "cumulative_start": 51381911, "cumulative_end": 51447728, "loss_sum": 19526.579803466797, "token_normalized_loss": 0.29667988215000374, "grad_norm_before_clip": 0.09041640162467957, "learning_rates_at_step": { "lora": 1.1177842418969675e-05, "row_tokens": 1.1177842418969675e-05 }, "learning_rates_after_step": { "lora": 1.106706292507872e-05, "row_tokens": 1.106706292507872e-05 } }, { "update_id": 785, "row_count": 16, "row_ids_sha256": "ce0bf884b3a565b184d5447e64def3aaa648e9ab623e03118724016ed84459f1", "input_ids_vector_sha256": "5be71a65cb5adb4524960bf2290817086c0f29af3311e675582b92eebcd44662", "labels_vector_sha256": "178b5fbab4ca8fd5d9ca52611599e5a15bef3ca5dc446b9213f9e029d535b819", "planned_active_tokens": 68139, "realized_active_tokens": 68139, "cumulative_start": 51447728, "cumulative_end": 51515867, "loss_sum": 18656.802764892578, "token_normalized_loss": 0.2738050567940912, "grad_norm_before_clip": 0.08377441763877869, "learning_rates_at_step": { "lora": 1.106706292507872e-05, "row_tokens": 1.106706292507872e-05 }, "learning_rates_after_step": { "lora": 1.09628921252041e-05, "row_tokens": 1.09628921252041e-05 } }, { "update_id": 786, "row_count": 11, "row_ids_sha256": "985d556243b9904a2cfa23fc859b4dedacf50314aa148bb3874b93666ab79396", "input_ids_vector_sha256": "34b140474e04acf320b81b6e448e4a0e1a22e948e690fb464eec04fbaac8d6ff", "labels_vector_sha256": "2f66aefaadd8c68a86a77769d11502e7a4226014aa43176fa0ecef64bfebd31c", "planned_active_tokens": 64347, "realized_active_tokens": 64347, "cumulative_start": 51515867, "cumulative_end": 51580214, "loss_sum": 19502.04522705078, "token_normalized_loss": 0.3030762153177426, "grad_norm_before_clip": 0.08911969512701035, "learning_rates_at_step": { "lora": 1.09628921252041e-05, "row_tokens": 1.09628921252041e-05 }, "learning_rates_after_step": { "lora": 1.0852878337720985e-05, "row_tokens": 1.0852878337720985e-05 } }, { "update_id": 787, "row_count": 15, "row_ids_sha256": "c5af7aba1852454f47b472786bbcf41cac50565e79c82152e9e5cb22198dca17", "input_ids_vector_sha256": "31d1b6c2634304a8a24097ff25853942fdd98e6a283bbf5a173de210d6ecf75c", "labels_vector_sha256": "93cc6ac66afff0f7b41c0b50f119025e77975ea360a4fe7fbb76221392a870a1", "planned_active_tokens": 68248, "realized_active_tokens": 68248, "cumulative_start": 51580214, "cumulative_end": 51648462, "loss_sum": 18429.520919799805, "token_normalized_loss": 0.27003752373402595, "grad_norm_before_clip": 0.08273203670978546, "learning_rates_at_step": { "lora": 1.0852878337720985e-05, "row_tokens": 1.0852878337720985e-05 }, "learning_rates_after_step": { "lora": 1.0756910426511124e-05, "row_tokens": 1.0756910426511124e-05 } }, { "update_id": 788, "row_count": 12, "row_ids_sha256": "d7278cf3b233ac10e035bdb7f7dc3828fb7411a750d0fdf8c51ffcca4e8cb16d", "input_ids_vector_sha256": "587e906608a2e171d923ef1c781474208fb3f8465ce30290974c212d87e5d48d", "labels_vector_sha256": "4afdeb99651e8502dfa0271484210e1c8f841a7cd5de569c1696586406b515b5", "planned_active_tokens": 59783, "realized_active_tokens": 59783, "cumulative_start": 51648462, "cumulative_end": 51708245, "loss_sum": 17648.928833007812, "token_normalized_loss": 0.295216513607678, "grad_norm_before_clip": 0.0935305655002594, "learning_rates_at_step": { "lora": 1.0756910426511124e-05, "row_tokens": 1.0756910426511124e-05 }, "learning_rates_after_step": { "lora": 1.0650417101173927e-05, "row_tokens": 1.0650417101173927e-05 } }, { "update_id": 789, "row_count": 11, "row_ids_sha256": "8e5759dbfc2613b9a2425c6ca34f6d2c02b0388ce07ec875330e0177723ee97c", "input_ids_vector_sha256": "b0f6b04eae633dacd11b215bfdcd83a8bac31e9d652fd72d04ad40791b3f7811", "labels_vector_sha256": "d129c289a531e8280858e824663805fa2eea8696dad954b42454cb66addbc6b5", "planned_active_tokens": 66615, "realized_active_tokens": 66615, "cumulative_start": 51708245, "cumulative_end": 51774860, "loss_sum": 19406.938110351562, "token_normalized_loss": 0.29132985229079883, "grad_norm_before_clip": 0.08583911508321762, "learning_rates_at_step": { "lora": 1.0650417101173927e-05, "row_tokens": 1.0650417101173927e-05 }, "learning_rates_after_step": { "lora": 1.0543377474055411e-05, "row_tokens": 1.0543377474055411e-05 } }, { "update_id": 790, "row_count": 12, "row_ids_sha256": "56dbaf2a06a73264c64204ae0f76e62e6c7a6c3076efc44da4cc0b066f84c0c1", "input_ids_vector_sha256": "a2e68992d857871d66175dbcd0896785baead5a208829deedb15946f5a1e7937", "labels_vector_sha256": "8df25828e0aacb734164987ebf6813f85e80ebd2f43e18de7cdda45e6d33d41a", "planned_active_tokens": 67253, "realized_active_tokens": 67253, "cumulative_start": 51774860, "cumulative_end": 51842113, "loss_sum": 19304.132354736328, "token_normalized_loss": 0.28703749059129446, "grad_norm_before_clip": 0.08317982405424118, "learning_rates_at_step": { "lora": 1.0543377474055411e-05, "row_tokens": 1.0543377474055411e-05 }, "learning_rates_after_step": { "lora": 1.0443383191028833e-05, "row_tokens": 1.0443383191028833e-05 } }, { "update_id": 791, "row_count": 12, "row_ids_sha256": "bf1104292de714ab894185bcba974d7ddd6dcdbdd9926f8aa793eb90c615435b", "input_ids_vector_sha256": "cdaad7ad6aac07dca300f799281ee14636aeb996bd25582f7a14201d1d750a78", "labels_vector_sha256": "a6ac13f3733a043c182c42b9de9d34f9d0ac24456249f42e9179bf9cfd9921fa", "planned_active_tokens": 63099, "realized_active_tokens": 63099, "cumulative_start": 51842113, "cumulative_end": 51905212, "loss_sum": 17969.140899658203, "token_normalized_loss": 0.2847769520857415, "grad_norm_before_clip": 0.08956562727689743, "learning_rates_at_step": { "lora": 1.0443383191028833e-05, "row_tokens": 1.0443383191028833e-05 }, "learning_rates_after_step": { "lora": 1.033855425145412e-05, "row_tokens": 1.033855425145412e-05 } }, { "update_id": 792, "row_count": 15, "row_ids_sha256": "7f1fb8eab568e4cd85e2cd691469cf4782b853719d9a6d551349139c992f58e0", "input_ids_vector_sha256": "3faaeed7586fafb9aa4724a293d66ed6d548fce3fb3e12cba85960c5ab86274e", "labels_vector_sha256": "45c5471b35cb6d457475281096e0990de325c5d38b3fe1c0ddb3c79baf327317", "planned_active_tokens": 66437, "realized_active_tokens": 66437, "cumulative_start": 51905212, "cumulative_end": 51971649, "loss_sum": 17536.470642089844, "token_normalized_loss": 0.26395638939280586, "grad_norm_before_clip": 0.08922582119703293, "learning_rates_at_step": { "lora": 1.033855425145412e-05, "row_tokens": 1.033855425145412e-05 }, "learning_rates_after_step": { "lora": 1.0230065510411701e-05, "row_tokens": 1.0230065510411701e-05 } }, { "update_id": 793, "row_count": 11, "row_ids_sha256": "89d7a7ce6ce8eb4894707820e1099cbb93aecd61d9a812d7527a1adfca718848", "input_ids_vector_sha256": "2401f39f9b59a361402f379045afcec88b2a38d87d76517170b62febd6238ccf", "labels_vector_sha256": "e99ba6518e7860f69b44ebde427a89b8e52de5b62471b71d3ce15af9f18ed16d", "planned_active_tokens": 69071, "realized_active_tokens": 69071, "cumulative_start": 51971649, "cumulative_end": 52040720, "loss_sum": 22326.33558654785, "token_normalized_loss": 0.3232374742880203, "grad_norm_before_clip": 0.08624236285686493, "learning_rates_at_step": { "lora": 1.0230065510411701e-05, "row_tokens": 1.0230065510411701e-05 }, "learning_rates_after_step": { "lora": 1.0130359589011922e-05, "row_tokens": 1.0130359589011922e-05 } }, { "update_id": 794, "row_count": 11, "row_ids_sha256": "ed3919caf1c8bd482e0cb1aed5fd8d8515a67a7d6babb2c56bc64b19f9fa3760", "input_ids_vector_sha256": "a855116cb9fb30005eb9a5755f028796d035e8a427c03379d920da894b18cccc", "labels_vector_sha256": "db699f9b431c25d54f9b8f2e42e0fca309486708fb4603e7c997f7f929f0ddd3", "planned_active_tokens": 63766, "realized_active_tokens": 63766, "cumulative_start": 52040720, "cumulative_end": 52104486, "loss_sum": 20859.386108398438, "token_normalized_loss": 0.3271239549038428, "grad_norm_before_clip": 0.09603175520896912, "learning_rates_at_step": { "lora": 1.0130359589011922e-05, "row_tokens": 1.0130359589011922e-05 }, "learning_rates_after_step": { "lora": 1.0030611794553407e-05, "row_tokens": 1.0030611794553407e-05 } }, { "update_id": 795, "row_count": 14, "row_ids_sha256": "015ad223f75b66d3487a3f0b409b5b9926de51161e0478cb107f000bb39e9fde", "input_ids_vector_sha256": "a60309f6882fcc9226ba6fe5c0633cbd18e9bac28b3aeda683caf84a54c4c662", "labels_vector_sha256": "a2c22930eeb3654c161106b508a4e62379c40536dd47af608fa369a38fd9792b", "planned_active_tokens": 64072, "realized_active_tokens": 64072, "cumulative_start": 52104486, "cumulative_end": 52168558, "loss_sum": 19473.219467163086, "token_normalized_loss": 0.30392713614625866, "grad_norm_before_clip": 0.08858693391084671, "learning_rates_at_step": { "lora": 1.0030611794553407e-05, "row_tokens": 1.0030611794553407e-05 }, "learning_rates_after_step": { "lora": 9.92309525675068e-06, "row_tokens": 9.92309525675068e-06 } }, { "update_id": 796, "row_count": 16, "row_ids_sha256": "7105cf6ae1a5953536a5416b67e9344e340e6adbe127f09fe53b7f32e97ac35b", "input_ids_vector_sha256": "e115ecdcf74ae3a869b0a2e84b1bd138bd7c329ef0d1274b9329acdfed0709ff", "labels_vector_sha256": "46005957efdf46abf1dec085debd6d1259611b9af9a59fd7d4d778eba3dcf9f0", "planned_active_tokens": 69380, "realized_active_tokens": 69380, "cumulative_start": 52168558, "cumulative_end": 52237938, "loss_sum": 20910.44105529785, "token_normalized_loss": 0.3013900411544804, "grad_norm_before_clip": 0.08441753685474396, "learning_rates_at_step": { "lora": 9.92309525675068e-06, "row_tokens": 9.92309525675068e-06 }, "learning_rates_after_step": { "lora": 9.829462156418395e-06, "row_tokens": 9.829462156418395e-06 } }, { "update_id": 797, "row_count": 14, "row_ids_sha256": "486cf2ed170715a3544b761ecf4eb20d6f8701ac64b6babc52a1b523600ee6e6", "input_ids_vector_sha256": "a8890dd5468b0bb61935229c2a9b151924714ff97ad65bf01b7f01417e778e6d", "labels_vector_sha256": "f6cfc95a55d79449b1e427e09fcf6c77341734f463dbc6835df5b8cb97cbcb63", "planned_active_tokens": 60694, "realized_active_tokens": 60694, "cumulative_start": 52237938, "cumulative_end": 52298632, "loss_sum": 14224.099853515625, "token_normalized_loss": 0.23435759471307913, "grad_norm_before_clip": 0.08393263071775436, "learning_rates_at_step": { "lora": 9.829462156418395e-06, "row_tokens": 9.829462156418395e-06 }, "learning_rates_after_step": { "lora": 9.729954437803652e-06, "row_tokens": 9.729954437803652e-06 } }, { "update_id": 798, "row_count": 15, "row_ids_sha256": "c0c6945df23ac3bf55412acba1be35bc24225f7edd0eba1c23175587f7cb3381", "input_ids_vector_sha256": "f4db4851e2f228d880da437b73ddb202a222d86add016a21f875210038aafd12", "labels_vector_sha256": "45742bf8430c39c0152ffd96ac247d8d32bbdb600aea9b5c353b0749f10348c6", "planned_active_tokens": 64785, "realized_active_tokens": 64785, "cumulative_start": 52298632, "cumulative_end": 52363417, "loss_sum": 16308.939590454102, "token_normalized_loss": 0.25173943953776495, "grad_norm_before_clip": 0.08398407697677612, "learning_rates_at_step": { "lora": 9.729954437803652e-06, "row_tokens": 9.729954437803652e-06 }, "learning_rates_after_step": { "lora": 9.624811238501818e-06, "row_tokens": 9.624811238501818e-06 } }, { "update_id": 799, "row_count": 14, "row_ids_sha256": "185009aef91de0e22d63940564f419d29f07a172312b11bb264e1857cf7fb956", "input_ids_vector_sha256": "51d518be57c3bb133a2f7e467dc2bdb646c7684dbdf0453e3ec29fc78cbb0625", "labels_vector_sha256": "a3ce16ce5d3b4a38bc981a1bad72624fb464fb8940dc3277a9b640f1d9a8da60", "planned_active_tokens": 68776, "realized_active_tokens": 68776, "cumulative_start": 52363417, "cumulative_end": 52432193, "loss_sum": 19402.24951171875, "token_normalized_loss": 0.2821078502925257, "grad_norm_before_clip": 0.08497106283903122, "learning_rates_at_step": { "lora": 9.624811238501818e-06, "row_tokens": 9.624811238501818e-06 }, "learning_rates_after_step": { "lora": 9.526864918006612e-06, "row_tokens": 9.526864918006612e-06 } }, { "update_id": 800, "row_count": 16, "row_ids_sha256": "dc05716299c3e10c22284baea0d5668b866d9f1d476183373adfd81742e7c709", "input_ids_vector_sha256": "a273d4c1fd32e5da421ddc29e842cfed0eda17dc5fc58683b2339155d4d5bd51", "labels_vector_sha256": "8fd9b969a4b8d4ef46cacdd6b89350625bf31e0959fd29761983f2e54ede5076", "planned_active_tokens": 64371, "realized_active_tokens": 64371, "cumulative_start": 52432193, "cumulative_end": 52496564, "loss_sum": 15900.505737304688, "token_normalized_loss": 0.2470134957869955, "grad_norm_before_clip": 0.08056654781103134, "learning_rates_at_step": { "lora": 9.526864918006612e-06, "row_tokens": 9.526864918006612e-06 }, "learning_rates_after_step": { "lora": 9.43032207616667e-06, "row_tokens": 9.43032207616667e-06 } }, { "update_id": 801, "row_count": 15, "row_ids_sha256": "6edba27864388473f27566bcc1e2b221101555c4d129e89aa8329f45ab41851f", "input_ids_vector_sha256": "7062a7554361d44c9fc297e781d75ded239d3e1c882bfa72e7973ee011035e29", "labels_vector_sha256": "b1a4274299ad38564fba92a0e73f7ebe8d7257fbee971c64cfb86c05d1a94761", "planned_active_tokens": 63739, "realized_active_tokens": 63739, "cumulative_start": 52496564, "cumulative_end": 52560303, "loss_sum": 15091.401504516602, "token_normalized_loss": 0.23676872094818874, "grad_norm_before_clip": 0.0810430645942688, "learning_rates_at_step": { "lora": 9.43032207616667e-06, "row_tokens": 9.43032207616667e-06 }, "learning_rates_after_step": { "lora": 9.326817180986753e-06, "row_tokens": 9.326817180986753e-06 } }, { "update_id": 802, "row_count": 14, "row_ids_sha256": "032399f87c7103e73dcd3946a30ecc8b477189660ea742233db936140aaee2a6", "input_ids_vector_sha256": "f5a4555b0a058a4e52a10ea9ce9860cd17550d128b4a013de528a73b857df600", "labels_vector_sha256": "86e7c34ecaa212672a5bef2d419b73386addc2c32d702d8e7d39c3a85877c997", "planned_active_tokens": 68661, "realized_active_tokens": 68661, "cumulative_start": 52560303, "cumulative_end": 52628964, "loss_sum": 19016.33822631836, "token_normalized_loss": 0.2769598203684531, "grad_norm_before_clip": 0.08582974225282669, "learning_rates_at_step": { "lora": 9.326817180986753e-06, "row_tokens": 9.326817180986753e-06 }, "learning_rates_after_step": { "lora": 9.23229412666483e-06, "row_tokens": 9.23229412666483e-06 } }, { "update_id": 803, "row_count": 13, "row_ids_sha256": "95161a4f6cd41a706e4428357191b5a8b48c84217a97d1a6e892d0dd2074616a", "input_ids_vector_sha256": "ce07d1187c1251213c6aad755f8b31ecbec96b224fa31f65c9e04e777c30d6ac", "labels_vector_sha256": "98c8bf85acfac337df77764ca79f131f5c25b2cd696d63594a1a99cadc8dfa3d", "planned_active_tokens": 63002, "realized_active_tokens": 63002, "cumulative_start": 52628964, "cumulative_end": 52691966, "loss_sum": 19331.818786621094, "token_normalized_loss": 0.30684452535825996, "grad_norm_before_clip": 0.09570204466581345, "learning_rates_at_step": { "lora": 9.23229412666483e-06, "row_tokens": 9.23229412666483e-06 }, "learning_rates_after_step": { "lora": 9.132816579733578e-06, "row_tokens": 9.132816579733578e-06 } }, { "update_id": 804, "row_count": 17, "row_ids_sha256": "40bfef51c463330ec25cbd3c2606a8bd2ef17523d338a729ea53bf5d8f7c3350", "input_ids_vector_sha256": "e9b7ef61031ccd8ec432123e36265353d06fbc939ddc822c715e2c902b4e47e3", "labels_vector_sha256": "d928dd15316f84efd845392580731fe06e68e4a6ee9e566659c4015b863c746f", "planned_active_tokens": 66618, "realized_active_tokens": 66618, "cumulative_start": 52691966, "cumulative_end": 52758584, "loss_sum": 16883.48406982422, "token_normalized_loss": 0.2534372702546492, "grad_norm_before_clip": 0.07957448065280914, "learning_rates_at_step": { "lora": 9.132816579733578e-06, "row_tokens": 9.132816579733578e-06 }, "learning_rates_after_step": { "lora": 9.037623546846347e-06, "row_tokens": 9.037623546846347e-06 } }, { "update_id": 805, "row_count": 13, "row_ids_sha256": "77c4d0201ff85f49696b9a9be7f13b94dbc8b49ed93faf83ad6b461936cd017c", "input_ids_vector_sha256": "8a57f70a2a7bb92217b8b6263683eb0e27a2bddc97274c6818d9f147c8609d0b", "labels_vector_sha256": "0e8faf785a252afe1b161841a362cfbbe0cb573300b29d40eb0e5b79bf1ed636", "planned_active_tokens": 64055, "realized_active_tokens": 64055, "cumulative_start": 52758584, "cumulative_end": 52822639, "loss_sum": 17742.66082763672, "token_normalized_loss": 0.27699103626003774, "grad_norm_before_clip": 0.08618709444999695, "learning_rates_at_step": { "lora": 9.037623546846347e-06, "row_tokens": 9.037623546846347e-06 }, "learning_rates_after_step": { "lora": 8.938820989882778e-06, "row_tokens": 8.938820989882778e-06 } }, { "update_id": 806, "row_count": 16, "row_ids_sha256": "8f716989dc087361eac3dfe5b3da01316af710c3e09e720661f56b0dc5a54d2e", "input_ids_vector_sha256": "76006692d111b092164f7a00f90feef5703e84f9ce744ff7027c5e69cdf6a4a6", "labels_vector_sha256": "2c896a3baef4cccf9d0c92298c2a576f31a0cb1165a358aa49b80307dd9282a6", "planned_active_tokens": 66806, "realized_active_tokens": 66806, "cumulative_start": 52822639, "cumulative_end": 52889445, "loss_sum": 20974.952560424805, "token_normalized_loss": 0.3139680950876389, "grad_norm_before_clip": 0.0899517685174942, "learning_rates_at_step": { "lora": 8.938820989882778e-06, "row_tokens": 8.938820989882778e-06 }, "learning_rates_after_step": { "lora": 8.84462643925863e-06, "row_tokens": 8.84462643925863e-06 } }, { "update_id": 807, "row_count": 13, "row_ids_sha256": "9ce9f40fed374c2be717dd900858db1e407117b1297b2d67db9fd36d59946bfa", "input_ids_vector_sha256": "1e724384ce7e69e2231fe69c11608ded46b545458ef52cdda15aafe70db6d5cc", "labels_vector_sha256": "03b82f6a07fbe05aa9693314bedf740c9f3103c27c7b5403c0c15afd7696bdff", "planned_active_tokens": 64001, "realized_active_tokens": 64001, "cumulative_start": 52889445, "cumulative_end": 52953446, "loss_sum": 17388.6259765625, "token_normalized_loss": 0.27169303568010655, "grad_norm_before_clip": 0.08690188080072403, "learning_rates_at_step": { "lora": 8.84462643925863e-06, "row_tokens": 8.84462643925863e-06 }, "learning_rates_after_step": { "lora": 8.74868220184546e-06, "row_tokens": 8.74868220184546e-06 } }, { "update_id": 808, "row_count": 15, "row_ids_sha256": "16e2424331962de64787a5a3b4d05c789268dff31941fcec06572392b3813480", "input_ids_vector_sha256": "aad635007fbe7be29b5a3f83b6ed3f4893363b28bc45984d7000653743662202", "labels_vector_sha256": "98b21133db86813e8a0e05307696e5ccf89d32f1b330f15b9396382459c627d7", "planned_active_tokens": 65507, "realized_active_tokens": 65507, "cumulative_start": 52953446, "cumulative_end": 53018953, "loss_sum": 17394.31869506836, "token_normalized_loss": 0.26553373983037476, "grad_norm_before_clip": 0.08751590549945831, "learning_rates_at_step": { "lora": 8.74868220184546e-06, "row_tokens": 8.74868220184546e-06 }, "learning_rates_after_step": { "lora": 8.650189073433036e-06, "row_tokens": 8.650189073433036e-06 } }, { "update_id": 809, "row_count": 15, "row_ids_sha256": "7752a4e558e2e31aa9718f78e9c697f71886277a17d30a8d67b123e9476a0860", "input_ids_vector_sha256": "0e4abdb49c888314f496e23cedea36e776efa0b23ab4c7d5eb4c73c6445707fe", "labels_vector_sha256": "ca9c777e1af27c6a8b1dc5e3dfebdad91f5b07e4e6b794ee279ce6ae1217f12d", "planned_active_tokens": 67586, "realized_active_tokens": 67586, "cumulative_start": 53018953, "cumulative_end": 53086539, "loss_sum": 17030.645629882812, "token_normalized_loss": 0.25198481386504323, "grad_norm_before_clip": 0.07940542697906494, "learning_rates_at_step": { "lora": 8.650189073433036e-06, "row_tokens": 8.650189073433036e-06 }, "learning_rates_after_step": { "lora": 8.554248751571858e-06, "row_tokens": 8.554248751571858e-06 } }, { "update_id": 810, "row_count": 16, "row_ids_sha256": "b88ca447e12166bfb02fef9f71719a583d48b64acbdb9e2326426a04ffdf1637", "input_ids_vector_sha256": "2f763832a1e63810f7690fb888ba7588a97111055c5a251baac01edfcd29ddb0", "labels_vector_sha256": "881b909ca23a1edb763e02dc80e4c91aef3608adf7987746d8ea170496b6bdf4", "planned_active_tokens": 66170, "realized_active_tokens": 66170, "cumulative_start": 53086539, "cumulative_end": 53152709, "loss_sum": 15764.163391113281, "token_normalized_loss": 0.23823731889244795, "grad_norm_before_clip": 0.07908731698989868, "learning_rates_at_step": { "lora": 8.554248751571858e-06, "row_tokens": 8.554248751571858e-06 }, "learning_rates_after_step": { "lora": 8.45693899816296e-06, "row_tokens": 8.45693899816296e-06 } }, { "update_id": 811, "row_count": 18, "row_ids_sha256": "76d4a463c320feb268591c912c788acc019ecc7d1bd9c5ac6835246679689c53", "input_ids_vector_sha256": "53afa95727e20c637653c7e888810ea628115deaf95b49a1f308ab3e7c69c186", "labels_vector_sha256": "2f04286377ea535d5d3eca49e6d558fb710b64ac08b4153e816bf0515b5f7f42", "planned_active_tokens": 67459, "realized_active_tokens": 67459, "cumulative_start": 53152709, "cumulative_end": 53220168, "loss_sum": 16200.85433959961, "token_normalized_loss": 0.24015853095361048, "grad_norm_before_clip": 0.07802405208349228, "learning_rates_at_step": { "lora": 8.45693899816296e-06, "row_tokens": 8.45693899816296e-06 }, "learning_rates_after_step": { "lora": 8.364282985931204e-06, "row_tokens": 8.364282985931204e-06 } }, { "update_id": 812, "row_count": 13, "row_ids_sha256": "c2e22d6fcfaf543fe81eb8a2461ba5580a42fc5e225572d79605eef8a4aebf85", "input_ids_vector_sha256": "a24ded0bc1e0c5336bf795d7fa00f88882a07b46495e0cb73f42b1f1c68adafc", "labels_vector_sha256": "0d930be4f54385ff84b6fba8e2edad13096313bf9024dce95e8513f8a71503f3", "planned_active_tokens": 64561, "realized_active_tokens": 64561, "cumulative_start": 53220168, "cumulative_end": 53284729, "loss_sum": 18463.67919921875, "token_normalized_loss": 0.28598812284844954, "grad_norm_before_clip": 0.08924999833106995, "learning_rates_at_step": { "lora": 8.364282985931204e-06, "row_tokens": 8.364282985931204e-06 }, "learning_rates_after_step": { "lora": 8.274184965137677e-06, "row_tokens": 8.274184965137677e-06 } }, { "update_id": 813, "row_count": 16, "row_ids_sha256": "694a768dd0885d84b26085c2980960717d55698b8bfd1d5bfbf92785b89e56fa", "input_ids_vector_sha256": "d138d24c76f3b5cb2193f25807a428c7709122b6033fe808a2f3bebc7e09e4b2", "labels_vector_sha256": "0cb40225615b0bee1a28231a8db272b26241856a4620701a9c265994cd55ded9", "planned_active_tokens": 63091, "realized_active_tokens": 63091, "cumulative_start": 53284729, "cumulative_end": 53347820, "loss_sum": 16627.037231445312, "token_normalized_loss": 0.2635405562036632, "grad_norm_before_clip": 0.08513566851615906, "learning_rates_at_step": { "lora": 8.274184965137677e-06, "row_tokens": 8.274184965137677e-06 }, "learning_rates_after_step": { "lora": 8.182019403534623e-06, "row_tokens": 8.182019403534623e-06 } }, { "update_id": 814, "row_count": 15, "row_ids_sha256": "ab9a02070123daf5784c9844a4b1a1b93ea70c23303cc5502371d657bbadc97c", "input_ids_vector_sha256": "137a4dddd9a5c5b62fb91241c232ce4bd88098745cde0a91a4f03e559d8e5a75", "labels_vector_sha256": "1efc90a190e682ed359c77c9ba059064a68914c7827d738dab055437a80fefd7", "planned_active_tokens": 64863, "realized_active_tokens": 64863, "cumulative_start": 53347820, "cumulative_end": 53412683, "loss_sum": 15897.02914428711, "token_normalized_loss": 0.2450862455373188, "grad_norm_before_clip": 0.08300509303808212, "learning_rates_at_step": { "lora": 8.182019403534623e-06, "row_tokens": 8.182019403534623e-06 }, "learning_rates_after_step": { "lora": 8.090496296657307e-06, "row_tokens": 8.090496296657307e-06 } }, { "update_id": 815, "row_count": 11, "row_ids_sha256": "66821c2f4affa34b73e9131e907c454ebea9ff4e5d73d7dda3bf0bd7144f69e9", "input_ids_vector_sha256": "69b93c852d1b1638a48dba3bd36849b7e2d4998ae3bf35977f7a213e592705fa", "labels_vector_sha256": "ba286765afeaae8518cf783d539d56d9e7141242bea1cb8eb785a49e0b2517f0", "planned_active_tokens": 64741, "realized_active_tokens": 64741, "cumulative_start": 53412683, "cumulative_end": 53477424, "loss_sum": 20831.750854492188, "token_normalized_loss": 0.32177060679464614, "grad_norm_before_clip": 0.09737160056829453, "learning_rates_at_step": { "lora": 8.090496296657307e-06, "row_tokens": 8.090496296657307e-06 }, "learning_rates_after_step": { "lora": 7.99441318181996e-06, "row_tokens": 7.99441318181996e-06 } }, { "update_id": 816, "row_count": 13, "row_ids_sha256": "10fc6f3e499d6e8ce02cd4b289550c3df1c7f5aa492d75ba283a1a311444b1f1", "input_ids_vector_sha256": "47475c32463fe6be976fc75fe149b4704af4377e87af7221d5e46420f4956e3e", "labels_vector_sha256": "8d5ca44c8350b56796f62fddbb2a03361e185dd6fc865acbec52dc38d47b104e", "planned_active_tokens": 68327, "realized_active_tokens": 68327, "cumulative_start": 53477424, "cumulative_end": 53545751, "loss_sum": 21259.39520263672, "token_normalized_loss": 0.31114193807187085, "grad_norm_before_clip": 0.08696777373552322, "learning_rates_at_step": { "lora": 7.99441318181996e-06, "row_tokens": 7.99441318181996e-06 }, "learning_rates_after_step": { "lora": 7.903775654209761e-06, "row_tokens": 7.903775654209761e-06 } }, { "update_id": 817, "row_count": 9, "row_ids_sha256": "26ac120b0187dc8f0ec5338dd80e2779dcdca986dfad0788b6065e67ce4df923", "input_ids_vector_sha256": "568d10f4ed4feacf3cee1659c106eec8c4b6a037f323cd8a8d343451053ef392", "labels_vector_sha256": "de438c816749cc733faf30e8119374599bd8289e8371750cbff4c7128f6c4784", "planned_active_tokens": 64799, "realized_active_tokens": 64799, "cumulative_start": 53545751, "cumulative_end": 53610550, "loss_sum": 21924.819946289062, "token_normalized_loss": 0.3383512082947123, "grad_norm_before_clip": 0.09271548688411713, "learning_rates_at_step": { "lora": 7.903775654209761e-06, "row_tokens": 7.903775654209761e-06 }, "learning_rates_after_step": { "lora": 7.81351915660249e-06, "row_tokens": 7.81351915660249e-06 } }, { "update_id": 818, "row_count": 12, "row_ids_sha256": "986e21d2565c722022829a63e39604a84d0650fe8b5e56e9679f40020797922d", "input_ids_vector_sha256": "0cba3e75d583912ecfec9a5a5cecd2aa87707555c9bb76b682b3eddb77587fb5", "labels_vector_sha256": "a892475aeafff8ee7db4126c54b4c5756e82e439ab05ecae284726bf400a8787", "planned_active_tokens": 64865, "realized_active_tokens": 64865, "cumulative_start": 53610550, "cumulative_end": 53675415, "loss_sum": 19436.675842285156, "token_normalized_loss": 0.29964812830162885, "grad_norm_before_clip": 0.0885806456208229, "learning_rates_at_step": { "lora": 7.81351915660249e-06, "row_tokens": 7.81351915660249e-06 }, "learning_rates_after_step": { "lora": 7.722817893755974e-06, "row_tokens": 7.722817893755974e-06 } }, { "update_id": 819, "row_count": 14, "row_ids_sha256": "4c3ccecc918d8866b3e451d0c373f7216824c79f75ebb03faaf8312b7ea2cd7f", "input_ids_vector_sha256": "b1210844f3fbd251c339b7094782b3455ed29d2a728f1c553bbd431c7c2c1733", "labels_vector_sha256": "8bd91052b03e930dc5a5d3a3684bf71b6692f1b4ddee5daad95e85e78014cd2f", "planned_active_tokens": 65531, "realized_active_tokens": 65531, "cumulative_start": 53675415, "cumulative_end": 53740946, "loss_sum": 19161.525115966797, "token_normalized_loss": 0.29240397851347905, "grad_norm_before_clip": 0.08666354417800903, "learning_rates_at_step": { "lora": 7.722817893755974e-06, "row_tokens": 7.722817893755974e-06 }, "learning_rates_after_step": { "lora": 7.630427413491897e-06, "row_tokens": 7.630427413491897e-06 } }, { "update_id": 820, "row_count": 14, "row_ids_sha256": "cdbc33a34df3b38ee9270efc6282e85370f5cf65e46971e05ec2e6d9d9e5df23", "input_ids_vector_sha256": "d4b4acf59fee81a2803eb3b5fdde244cda48472e2ca4dd222c0e38c0a31e3900", "labels_vector_sha256": "10f942ec516bdb282a17c191e9f8b1695606f2e757c1e72d36c4172672325ce9", "planned_active_tokens": 67115, "realized_active_tokens": 67115, "cumulative_start": 53740946, "cumulative_end": 53808061, "loss_sum": 21112.189193725586, "token_normalized_loss": 0.31456737232698484, "grad_norm_before_clip": 0.09000755846500397, "learning_rates_at_step": { "lora": 7.630427413491897e-06, "row_tokens": 7.630427413491897e-06 }, "learning_rates_after_step": { "lora": 7.54181719142163e-06, "row_tokens": 7.54181719142163e-06 } }, { "update_id": 821, "row_count": 14, "row_ids_sha256": "b46185195154f1c194061e38bb23512ff0a7b51a6ebcf0d2c2160bd3fc613a1a", "input_ids_vector_sha256": "4183a9a4cf19a605c5c35378ba0caadd012b60aee598c6c5e66f45383c205491", "labels_vector_sha256": "d3ee10112f841db27be2d117e02a5dc970d430e691910052217dcdd8486e891e", "planned_active_tokens": 64720, "realized_active_tokens": 64720, "cumulative_start": 53808061, "cumulative_end": 53872781, "loss_sum": 17236.679748535156, "token_normalized_loss": 0.26632694296253334, "grad_norm_before_clip": 0.08477871865034103, "learning_rates_at_step": { "lora": 7.54181719142163e-06, "row_tokens": 7.54181719142163e-06 }, "learning_rates_after_step": { "lora": 7.4510561326048385e-06, "row_tokens": 7.4510561326048385e-06 } }, { "update_id": 822, "row_count": 15, "row_ids_sha256": "1c2a3c6bdfe1d3d55a0f226e7460120ee2f2df9316193b99b7ac2bffe692dc1e", "input_ids_vector_sha256": "c5c7d61a890aa0bf75a7f00bd58678eee040df4dd0c158a21daed5a86d7df98d", "labels_vector_sha256": "b44df2b777d65fa106e22a24e11069c3c77902d20b582f5258a2d1758fb67365", "planned_active_tokens": 66654, "realized_active_tokens": 66654, "cumulative_start": 53872781, "cumulative_end": 53939435, "loss_sum": 16411.732666015625, "token_normalized_loss": 0.2462227723169746, "grad_norm_before_clip": 0.07887107878923416, "learning_rates_at_step": { "lora": 7.4510561326048385e-06, "row_tokens": 7.4510561326048385e-06 }, "learning_rates_after_step": { "lora": 7.35826892176929e-06, "row_tokens": 7.35826892176929e-06 } }, { "update_id": 823, "row_count": 14, "row_ids_sha256": "945e814624d357d6bdd65672a34bfca36bf14228da39f126b9eedd90740c2f55", "input_ids_vector_sha256": "9ce6c0370a38c1e185a0dcf53a8463498f352876370c28c53a64f6876c1639e5", "labels_vector_sha256": "d232b4bbca54b0d97bc908d19bde1df4dc8566e44641e49f94e4d680bc29a33c", "planned_active_tokens": 68529, "realized_active_tokens": 68529, "cumulative_start": 53939435, "cumulative_end": 54007964, "loss_sum": 19279.632293701172, "token_normalized_loss": 0.2813353805498573, "grad_norm_before_clip": 0.08546696603298187, "learning_rates_at_step": { "lora": 7.35826892176929e-06, "row_tokens": 7.35826892176929e-06 }, "learning_rates_after_step": { "lora": 7.271149452605452e-06, "row_tokens": 7.271149452605452e-06 } }, { "update_id": 824, "row_count": 12, "row_ids_sha256": "375bd15e9e7bc9786092c76e33027ed3b29632638c3ddaeddd936493bf860936", "input_ids_vector_sha256": "78933d80572eccdc1365c462cec1f4617906ead0eaf5344f2d606c17f3abcea4", "labels_vector_sha256": "dee910f1bacb4d42c860eef4d9646f47329f77b7f0a386ee0a259438e0f49c33", "planned_active_tokens": 64706, "realized_active_tokens": 64706, "cumulative_start": 54007964, "cumulative_end": 54072670, "loss_sum": 20758.537796020508, "token_normalized_loss": 0.32081318264180303, "grad_norm_before_clip": 0.08880960941314697, "learning_rates_at_step": { "lora": 7.271149452605452e-06, "row_tokens": 7.271149452605452e-06 }, "learning_rates_after_step": { "lora": 7.181870014801728e-06, "row_tokens": 7.181870014801728e-06 } }, { "update_id": 825, "row_count": 14, "row_ids_sha256": "471da435d0b6f760b4327bcc3473cb719e7d6b50559649418470fba52b79302a", "input_ids_vector_sha256": "a31de71b9696531470fd616a8f1f6426bc34878eed838ddb3eff25e66c9b9a99", "labels_vector_sha256": "7f817058a53bbe2cf1a4e5500a04b05b9716ef14b3415f6d436a2f9e67302216", "planned_active_tokens": 66682, "realized_active_tokens": 66682, "cumulative_start": 54072670, "cumulative_end": 54139352, "loss_sum": 20643.878204345703, "token_normalized_loss": 0.30958696806253116, "grad_norm_before_clip": 0.08954647183418274, "learning_rates_at_step": { "lora": 7.181870014801728e-06, "row_tokens": 7.181870014801728e-06 }, "learning_rates_after_step": { "lora": 7.101601517217693e-06, "row_tokens": 7.101601517217693e-06 } }, { "update_id": 826, "row_count": 11, "row_ids_sha256": "9b9f9a5a1b0c325721d5acf14ce86257a6aa5f89be644430e02dc9836a22b25b", "input_ids_vector_sha256": "2fb6a16cfe4dd0df126430e28875d8d73de7369b4bda676fd06a30789ecf2ca8", "labels_vector_sha256": "4bf30dcd91e252b7477dfc2ff8bff8957097d350679b7fc5a27ad9941a1b4554", "planned_active_tokens": 60279, "realized_active_tokens": 60279, "cumulative_start": 54139352, "cumulative_end": 54199631, "loss_sum": 17805.28530883789, "token_normalized_loss": 0.29538123241656117, "grad_norm_before_clip": 0.09457115828990936, "learning_rates_at_step": { "lora": 7.101601517217693e-06, "row_tokens": 7.101601517217693e-06 }, "learning_rates_after_step": { "lora": 7.011062086086012e-06, "row_tokens": 7.011062086086012e-06 } }, { "update_id": 827, "row_count": 13, "row_ids_sha256": "d98c1ef94ce218984576638e00e9bfad783c643adbf427e95c09ca421b2ec89c", "input_ids_vector_sha256": "6590218eeabec8f39d5fb547eb3fee8a9c892899355e6b8ddd1d7215006ae736", "labels_vector_sha256": "956f4268099ef0e0cbd36935d222279f037bee96bd5b8be7738f4d4802191c89", "planned_active_tokens": 68371, "realized_active_tokens": 68371, "cumulative_start": 54199631, "cumulative_end": 54268002, "loss_sum": 22098.09848022461, "token_normalized_loss": 0.32320864811432637, "grad_norm_before_clip": 0.0921902060508728, "learning_rates_at_step": { "lora": 7.011062086086012e-06, "row_tokens": 7.011062086086012e-06 }, "learning_rates_after_step": { "lora": 6.9218999675733805e-06, "row_tokens": 6.9218999675733805e-06 } }, { "update_id": 828, "row_count": 11, "row_ids_sha256": "276c55eb5bc64164846eb4c9e88cdbfc6d6f39368f822889f040ccd3d032dd4a", "input_ids_vector_sha256": "f4b6863dea262e60f91c2759a8d7ac99d5f4ff11d7ece0ba54789c8fd434ba82", "labels_vector_sha256": "95f66b0ce5b09c662e14cd90cfd8a5dd7eeae6333f9ef88245915eff4b6f9f84", "planned_active_tokens": 67731, "realized_active_tokens": 67731, "cumulative_start": 54268002, "cumulative_end": 54335733, "loss_sum": 21286.49365234375, "token_normalized_loss": 0.31427992577023445, "grad_norm_before_clip": 0.12863868474960327, "learning_rates_at_step": { "lora": 6.9218999675733805e-06, "row_tokens": 6.9218999675733805e-06 }, "learning_rates_after_step": { "lora": 6.835945063410143e-06, "row_tokens": 6.835945063410143e-06 } }, { "update_id": 829, "row_count": 11, "row_ids_sha256": "009ba4356664faed7a800019827b65fc97b7ae013c20860689b529de10ea916f", "input_ids_vector_sha256": "e948f26754632f458b5aea7f711c273c9b758df41bb7d01a515b069960f60c8a", "labels_vector_sha256": "d9006161e2c2c65eaff8169aef8f937b61dec8d52aac5a3cb78f4927abd00d1f", "planned_active_tokens": 65678, "realized_active_tokens": 65678, "cumulative_start": 54335733, "cumulative_end": 54401411, "loss_sum": 19616.661407470703, "token_normalized_loss": 0.2986793356598968, "grad_norm_before_clip": 0.09258779883384705, "learning_rates_at_step": { "lora": 6.835945063410143e-06, "row_tokens": 6.835945063410143e-06 }, "learning_rates_after_step": { "lora": 6.753071276143075e-06, "row_tokens": 6.753071276143075e-06 } }, { "update_id": 830, "row_count": 14, "row_ids_sha256": "707fc97de8cf32c658612ec0b2ff0c46fe54831e32ff13751eda18907ae3b6dd", "input_ids_vector_sha256": "8d11fefcfcb3e9a856eaa0e3a919aa7e7791fdd6f40c58fb0bd09749a00b1214", "labels_vector_sha256": "c83aa4ca9f22c5093a279d03dc1c564017d9971638f58fc4d1923185af44fcd8", "planned_active_tokens": 63687, "realized_active_tokens": 63687, "cumulative_start": 54401411, "cumulative_end": 54465098, "loss_sum": 17909.652282714844, "token_normalized_loss": 0.2812136273134995, "grad_norm_before_clip": 0.08684965968132019, "learning_rates_at_step": { "lora": 6.753071276143075e-06, "row_tokens": 6.753071276143075e-06 }, "learning_rates_after_step": { "lora": 6.669006099864661e-06, "row_tokens": 6.669006099864661e-06 } }, { "update_id": 831, "row_count": 12, "row_ids_sha256": "6ba84fbcce19a8c19a1fb16fd9622b707cd0937dac6c5079adce9f765a80066b", "input_ids_vector_sha256": "7d374569fdb4605a2eb075676c5d67e9c12a596ba9f53562f52d5f122bc7ce5f", "labels_vector_sha256": "cb209d0eda9a8bdaa73378ba6c37accf3557f875e98c7d2223b9b572b833d110", "planned_active_tokens": 64974, "realized_active_tokens": 64974, "cumulative_start": 54465098, "cumulative_end": 54530072, "loss_sum": 21598.802795410156, "token_normalized_loss": 0.3324222426726099, "grad_norm_before_clip": 0.09320659935474396, "learning_rates_at_step": { "lora": 6.669006099864661e-06, "row_tokens": 6.669006099864661e-06 }, "learning_rates_after_step": { "lora": 6.587166696298142e-06, "row_tokens": 6.587166696298142e-06 } }, { "update_id": 832, "row_count": 14, "row_ids_sha256": "b724bccbf747c47ce4bbdc1504d78fcd1929f109da67925cc91c90797e40bea1", "input_ids_vector_sha256": "092ba886608ef52ab55935c13593a8fe108bd54c9c16fada687a6dbff699a59f", "labels_vector_sha256": "69799cedc6abe2587fc28ec824e9214f224605832ba3ff7502cb604753331a50", "planned_active_tokens": 63620, "realized_active_tokens": 63620, "cumulative_start": 54530072, "cumulative_end": 54593692, "loss_sum": 20055.062133789062, "token_normalized_loss": 0.3152320360545279, "grad_norm_before_clip": 0.0883210152387619, "learning_rates_at_step": { "lora": 6.587166696298142e-06, "row_tokens": 6.587166696298142e-06 }, "learning_rates_after_step": { "lora": 6.501695097315935e-06, "row_tokens": 6.501695097315935e-06 } }, { "update_id": 833, "row_count": 15, "row_ids_sha256": "4e018da8f0810914a9eba3cf0c12ed3f5a7292635f29b5de80e47af16710b122", "input_ids_vector_sha256": "77d8d96686c979294c03ca8a98c4548fc20f14a773535b4a1a9dbc60fcfba94c", "labels_vector_sha256": "d5f1334f88f5d981502f290bb5f631278409b47cce7e5e2796391f3629658e3f", "planned_active_tokens": 66837, "realized_active_tokens": 66837, "cumulative_start": 54593692, "cumulative_end": 54660529, "loss_sum": 18300.816040039062, "token_normalized_loss": 0.27381264928167126, "grad_norm_before_clip": 0.08104448020458221, "learning_rates_at_step": { "lora": 6.501695097315935e-06, "row_tokens": 6.501695097315935e-06 }, "learning_rates_after_step": { "lora": 6.42049558250114e-06, "row_tokens": 6.42049558250114e-06 } }, { "update_id": 834, "row_count": 12, "row_ids_sha256": "9220edf33e36cadd2d70c7b8bbcaf092fb06b4dda02d7f9a9b1ccc5d9429d778", "input_ids_vector_sha256": "0d4941328bf130c1e7bfe28db14370a5d6c8f6e77e0468a7b844756ab603deac", "labels_vector_sha256": "881b9c7428419c96f05dd2d4df02e33749c4dfbeb5322628e18758c04339fb38", "planned_active_tokens": 63876, "realized_active_tokens": 63876, "cumulative_start": 54660529, "cumulative_end": 54724405, "loss_sum": 17563.899017333984, "token_normalized_loss": 0.2749686739516248, "grad_norm_before_clip": 0.08537248522043228, "learning_rates_at_step": { "lora": 6.42049558250114e-06, "row_tokens": 6.42049558250114e-06 }, "learning_rates_after_step": { "lora": 6.330704791233749e-06, "row_tokens": 6.330704791233749e-06 } }, { "update_id": 835, "row_count": 17, "row_ids_sha256": "b34ec10fe86fc0495e35bb72ef0d4baed3ef4cf1fc3d2f788548d7e5b1688bf3", "input_ids_vector_sha256": "3496e58b4472ed6dafe83207e953f570e02c61040a37b420bad49b6b9115334c", "labels_vector_sha256": "b5a97ae258eebfc1e7d2f8b57a2747016c75309ba033c9bdbee50ad5490c2db5", "planned_active_tokens": 71074, "realized_active_tokens": 71074, "cumulative_start": 54724405, "cumulative_end": 54795479, "loss_sum": 20883.531829833984, "token_normalized_loss": 0.2938280078486364, "grad_norm_before_clip": 0.08634805679321289, "learning_rates_at_step": { "lora": 6.330704791233749e-06, "row_tokens": 6.330704791233749e-06 }, "learning_rates_after_step": { "lora": 6.257651284543075e-06, "row_tokens": 6.257651284543075e-06 } }, { "update_id": 836, "row_count": 12, "row_ids_sha256": "491933982c9d166fe3761618ce436ef86a7bd3d32cc5ec3d92489797b4057722", "input_ids_vector_sha256": "40a0c1721dc9c0d7bbfe101cd04a2fc0bcccdc460b6a35cc6930e1d74a545276", "labels_vector_sha256": "f9d684e32eba9f39ff12370a8c8eee446dc7aff5134f223ed589057566766c49", "planned_active_tokens": 58173, "realized_active_tokens": 58173, "cumulative_start": 54795479, "cumulative_end": 54853652, "loss_sum": 14748.243347167969, "token_normalized_loss": 0.25352385723906223, "grad_norm_before_clip": 0.08803700655698776, "learning_rates_at_step": { "lora": 6.257651284543075e-06, "row_tokens": 6.257651284543075e-06 }, "learning_rates_after_step": { "lora": 6.17321929886498e-06, "row_tokens": 6.17321929886498e-06 } }, { "update_id": 837, "row_count": 14, "row_ids_sha256": "bd7c11d3c2a17f1d3aaafdf82e621749cfbdf2f45afcdc34c05a1b7a816df0ec", "input_ids_vector_sha256": "50c8d908a62acd56457f8797ccf08e53f87183ce565fb56868d95a51d587ab48", "labels_vector_sha256": "f37fd76ab6b3760a906fe6af011ef533c4704675603b7377f9f2b0ec8e7acdfb", "planned_active_tokens": 67630, "realized_active_tokens": 67630, "cumulative_start": 54853652, "cumulative_end": 54921282, "loss_sum": 18438.741729736328, "token_normalized_loss": 0.27264145689392766, "grad_norm_before_clip": 0.0861835926771164, "learning_rates_at_step": { "lora": 6.17321929886498e-06, "row_tokens": 6.17321929886498e-06 }, "learning_rates_after_step": { "lora": 6.091968543369308e-06, "row_tokens": 6.091968543369308e-06 } }, { "update_id": 838, "row_count": 14, "row_ids_sha256": "f0c1605d77ec1063ea50b7cb5a0b6617369e24c5878af4aa665e1111deee23b7", "input_ids_vector_sha256": "d7333a5c0bcc39f47ab5db10a7816f9aae5ecc9aea8d7cf92d908820aca61b7a", "labels_vector_sha256": "517a3486e048dbc610af7ebf88b663e205b685f2d24db69596fec31be097ac17", "planned_active_tokens": 65491, "realized_active_tokens": 65491, "cumulative_start": 54921282, "cumulative_end": 54986773, "loss_sum": 17352.2264251709, "token_normalized_loss": 0.2649558935605029, "grad_norm_before_clip": 0.08412939310073853, "learning_rates_at_step": { "lora": 6.091968543369308e-06, "row_tokens": 6.091968543369308e-06 }, "learning_rates_after_step": { "lora": 6.010487586470504e-06, "row_tokens": 6.010487586470504e-06 } }, { "update_id": 839, "row_count": 14, "row_ids_sha256": "a6bf09b7c62fbd808cc5c98ff4c9e65b70d13760c93cbfb2e6cfde917c47d926", "input_ids_vector_sha256": "35466c8ae776e89841c8c283a4ce9ebd04dd7c8574acb21e4574193116c31c9a", "labels_vector_sha256": "bc51d3ae2375e59e417e63b4b9ba3c0918bc56d3acaf768260479dde50258a13", "planned_active_tokens": 66088, "realized_active_tokens": 66088, "cumulative_start": 54986773, "cumulative_end": 55052861, "loss_sum": 18592.834503173828, "token_normalized_loss": 0.28133450101643004, "grad_norm_before_clip": 0.08555405586957932, "learning_rates_at_step": { "lora": 6.010487586470504e-06, "row_tokens": 6.010487586470504e-06 }, "learning_rates_after_step": { "lora": 5.925909630232751e-06, "row_tokens": 5.925909630232751e-06 } }, { "update_id": 840, "row_count": 13, "row_ids_sha256": "9097e5dbe1ceb3f06788a17275c1847a9b21a62f0a41d03e46a4d8590160be9b", "input_ids_vector_sha256": "0d3c677f39a1269109d7bc2cad3d045cbd15ef07074e9f3b5cdb4020261df2cf", "labels_vector_sha256": "ca804c56ce152d39877262012ee71fa4b49f0399bb4ce7e6697ca8603cbb3f59", "planned_active_tokens": 69045, "realized_active_tokens": 69045, "cumulative_start": 55052861, "cumulative_end": 55121906, "loss_sum": 17877.050842285156, "token_normalized_loss": 0.2589188332578051, "grad_norm_before_clip": 0.08023790270090103, "learning_rates_at_step": { "lora": 5.925909630232751e-06, "row_tokens": 5.925909630232751e-06 }, "learning_rates_after_step": { "lora": 5.852594597503936e-06, "row_tokens": 5.852594597503936e-06 } }, { "update_id": 841, "row_count": 13, "row_ids_sha256": "874f77b5c4b33dedfb50f9c0ad5385c1403e0c45af68d42ea7c1b86a1a31531a", "input_ids_vector_sha256": "8d4d0e430b6430af4a305bfc62d1baa5da79fd32dae70b6f59c78d9f7d65eeec", "labels_vector_sha256": "79a3965637e743e434350a011f335b942c94978d04ff1a8be8a57ed4cf0b33b5", "planned_active_tokens": 60225, "realized_active_tokens": 60225, "cumulative_start": 55121906, "cumulative_end": 55182131, "loss_sum": 19088.054809570312, "token_normalized_loss": 0.3169457004494863, "grad_norm_before_clip": 0.09303033351898193, "learning_rates_at_step": { "lora": 5.852594597503936e-06, "row_tokens": 5.852594597503936e-06 }, "learning_rates_after_step": { "lora": 5.773429729536712e-06, "row_tokens": 5.773429729536712e-06 } }, { "update_id": 842, "row_count": 14, "row_ids_sha256": "19cc17dddfa6bed157c17b2ed94a8965b658a545038531d3ba06ae762293da77", "input_ids_vector_sha256": "70064413e71b3d1f6285f25520142ce39550126772781c2fc27638805d70e36f", "labels_vector_sha256": "4e8f70ed0a8bd32197307cb86f0f024c2959e8382d82c16285fce6d3a1b4f646", "planned_active_tokens": 65429, "realized_active_tokens": 65429, "cumulative_start": 55182131, "cumulative_end": 55247560, "loss_sum": 19737.130859375, "token_normalized_loss": 0.3016572293535741, "grad_norm_before_clip": 0.08702680468559265, "learning_rates_at_step": { "lora": 5.773429729536712e-06, "row_tokens": 5.773429729536712e-06 }, "learning_rates_after_step": { "lora": 5.687773711521505e-06, "row_tokens": 5.687773711521505e-06 } }, { "update_id": 843, "row_count": 16, "row_ids_sha256": "0f6aec0b3130fcf1ec25af982cb437cb28b71313a738659a801b4faea203994c", "input_ids_vector_sha256": "a9be1cfa591155e83a9cace2850f77efc00238e9a841ee3c4564f8b392f72f28", "labels_vector_sha256": "732f4c0cc2a1243dc19b6b80e213f0aee7c8fb365d3b51efb5fd2063e42ca0ed", "planned_active_tokens": 71270, "realized_active_tokens": 71270, "cumulative_start": 55247560, "cumulative_end": 55318830, "loss_sum": 19823.46127319336, "token_normalized_loss": 0.27814594181553753, "grad_norm_before_clip": 0.08534696698188782, "learning_rates_at_step": { "lora": 5.687773711521505e-06, "row_tokens": 5.687773711521505e-06 }, "learning_rates_after_step": { "lora": 5.612258187458091e-06, "row_tokens": 5.612258187458091e-06 } }, { "update_id": 844, "row_count": 15, "row_ids_sha256": "6a8fe196a1dfbfb022d226f7d9aea05e9eb637ea14c24c9a0a04ffaf31425ee7", "input_ids_vector_sha256": "97796713bd3859a942e49d3b2c52457ccd063216848ccd19ed371da20c3d0149", "labels_vector_sha256": "c1641b59533725486552a6ed4a025031579d48a06d70d2b6928acf5108290e5a", "planned_active_tokens": 63252, "realized_active_tokens": 63252, "cumulative_start": 55318830, "cumulative_end": 55382082, "loss_sum": 17168.962203979492, "token_normalized_loss": 0.2714374597479841, "grad_norm_before_clip": 0.08152418583631516, "learning_rates_at_step": { "lora": 5.612258187458091e-06, "row_tokens": 5.612258187458091e-06 }, "learning_rates_after_step": { "lora": 5.5368071429950815e-06, "row_tokens": 5.5368071429950815e-06 } }, { "update_id": 845, "row_count": 12, "row_ids_sha256": "2c12a346a5d41b9f91d6be3c26d3210e03f173b7e5bb54089e0e5f3d7f9c28dd", "input_ids_vector_sha256": "94b59d40a71010233709a5da14248d190d038e9e7a0a63359c43e040133dda37", "labels_vector_sha256": "2d1204e876f426f53aabb3cbedaee998c26259f3476663744b33d8331f2829fc", "planned_active_tokens": 63599, "realized_active_tokens": 63599, "cumulative_start": 55382082, "cumulative_end": 55445681, "loss_sum": 21244.478088378906, "token_normalized_loss": 0.3340379265142362, "grad_norm_before_clip": 0.09185352176427841, "learning_rates_at_step": { "lora": 5.5368071429950815e-06, "row_tokens": 5.5368071429950815e-06 }, "learning_rates_after_step": { "lora": 5.461208366674292e-06, "row_tokens": 5.461208366674292e-06 } }, { "update_id": 846, "row_count": 13, "row_ids_sha256": "892efbbbbb47fa51096eeaaf6d75f98201eb2c6be5929819a3599039db1c7a6c", "input_ids_vector_sha256": "315b62ddd8273081692ec63656f0c4598119a0cd21153d4bce7a6f0d2a261d80", "labels_vector_sha256": "88f79714e49bb6194cd8a80d685ad6899973563383fc09051ef4292f85ae5799", "planned_active_tokens": 64134, "realized_active_tokens": 64134, "cumulative_start": 55445681, "cumulative_end": 55509815, "loss_sum": 17680.697463989258, "token_normalized_loss": 0.2756836851590304, "grad_norm_before_clip": 0.08722545206546783, "learning_rates_at_step": { "lora": 5.461208366674292e-06, "row_tokens": 5.461208366674292e-06 }, "learning_rates_after_step": { "lora": 5.382319162286931e-06, "row_tokens": 5.382319162286931e-06 } }, { "update_id": 847, "row_count": 14, "row_ids_sha256": "98e7e01399d4755215680762e6215715364d6c579b25f1935de9dd6963f6f9cf", "input_ids_vector_sha256": "17cf909585dca35e34b141733c8b78a7ec3ed4d10db11868de9c6cc561e462ea", "labels_vector_sha256": "6bf47a53d50990c260f23de04534f7c9e07ffa34b6a069d9a2dd5aa2ac03ef6d", "planned_active_tokens": 67373, "realized_active_tokens": 67373, "cumulative_start": 55509815, "cumulative_end": 55577188, "loss_sum": 18671.92547607422, "token_normalized_loss": 0.2771425567523224, "grad_norm_before_clip": 0.08521754294633865, "learning_rates_at_step": { "lora": 5.382319162286931e-06, "row_tokens": 5.382319162286931e-06 }, "learning_rates_after_step": { "lora": 5.2990288235912735e-06, "row_tokens": 5.2990288235912735e-06 } }, { "update_id": 848, "row_count": 16, "row_ids_sha256": "f6edf7bc7e2756c4a6972d1aa316eeb918253c37c5dfc5c808fcd0633bfbc00b", "input_ids_vector_sha256": "c8f1641ede195f0729ec8be8545bab86d7fa30a54a4276d9d4baebd33c1b7651", "labels_vector_sha256": "efd0b6b1ad02393700029e128393830391e331f0b4f560c6aa309cb7b022c31a", "planned_active_tokens": 71639, "realized_active_tokens": 71639, "cumulative_start": 55577188, "cumulative_end": 55648827, "loss_sum": 21757.576782226562, "token_normalized_loss": 0.30371134133958544, "grad_norm_before_clip": 0.08422095328569412, "learning_rates_at_step": { "lora": 5.2990288235912735e-06, "row_tokens": 5.2990288235912735e-06 }, "learning_rates_after_step": { "lora": 5.231365707238062e-06, "row_tokens": 5.231365707238062e-06 } }, { "update_id": 849, "row_count": 12, "row_ids_sha256": "c9ee7e45f04521a5074e944ccfee9e96b543d7d684182031118841fa93e69397", "input_ids_vector_sha256": "de341f5dbd8a30db781d6b58083cb726cc78ae7816cb4457b5310722ab4f4e63", "labels_vector_sha256": "6a4da6a0f9809ca7d6ece5cba8b4c36e91f239f14ee23ea9ed92df72819f7b82", "planned_active_tokens": 58590, "realized_active_tokens": 58590, "cumulative_start": 55648827, "cumulative_end": 55707417, "loss_sum": 13952.62565612793, "token_normalized_loss": 0.238140052161255, "grad_norm_before_clip": 0.08386773616075516, "learning_rates_at_step": { "lora": 5.231365707238062e-06, "row_tokens": 5.231365707238062e-06 }, "learning_rates_after_step": { "lora": 5.1515970998091855e-06, "row_tokens": 5.1515970998091855e-06 } }, { "update_id": 850, "row_count": 12, "row_ids_sha256": "1bbdbb20acc41d3fd43a6cca506377b1df438bff1a4e73f3c64c35219d503554", "input_ids_vector_sha256": "8477cb34fac4dbe3ab8e19b26034bfb8620b0937f0ff4422e37d61da7060eee7", "labels_vector_sha256": "42cdc6b03a09703b69aa8451c575dc08deba4b561e1c93e3d74c4061e39c3128", "planned_active_tokens": 69534, "realized_active_tokens": 69534, "cumulative_start": 55707417, "cumulative_end": 55776951, "loss_sum": 23737.65740966797, "token_normalized_loss": 0.341382020445652, "grad_norm_before_clip": 0.09217826277017593, "learning_rates_at_step": { "lora": 5.1515970998091855e-06, "row_tokens": 5.1515970998091855e-06 }, "learning_rates_after_step": { "lora": 5.076310018450376e-06, "row_tokens": 5.076310018450376e-06 } }, { "update_id": 851, "row_count": 15, "row_ids_sha256": "21eab414ec508b77c589cafb30b01e55a9b425da58ab5d30fd81361dd3f27e34", "input_ids_vector_sha256": "b75640654ce16ad0c66674fd4e3382178049f21c1a508b79e8ce60a4ce0c4ee6", "labels_vector_sha256": "ba96756438f869728eba30f3ac56f8ff4584cc079988358ed678e752a2f7b72e", "planned_active_tokens": 66096, "realized_active_tokens": 66096, "cumulative_start": 55776951, "cumulative_end": 55843047, "loss_sum": 19922.6474609375, "token_normalized_loss": 0.30141986596673775, "grad_norm_before_clip": 0.08916819840669632, "learning_rates_at_step": { "lora": 5.076310018450376e-06, "row_tokens": 5.076310018450376e-06 }, "learning_rates_after_step": { "lora": 5.001800182272664e-06, "row_tokens": 5.001800182272664e-06 } }, { "update_id": 852, "row_count": 14, "row_ids_sha256": "788123b0dee8f91624c21977e3668e0bd93900eaa6c5ec5d4080cb573992b198", "input_ids_vector_sha256": "664d0ddbeaba9b649939d24700df6f478b82d659e38a81b72c87c338579511b4", "labels_vector_sha256": "3a0f1ca1c554f71ce47d3375e177a215082c4598b58542007df4503d9da11d2c", "planned_active_tokens": 65872, "realized_active_tokens": 65872, "cumulative_start": 55843047, "cumulative_end": 55908919, "loss_sum": 17510.83026123047, "token_normalized_loss": 0.2658311613618908, "grad_norm_before_clip": 0.08369896560907364, "learning_rates_at_step": { "lora": 5.001800182272664e-06, "row_tokens": 5.001800182272664e-06 }, "learning_rates_after_step": { "lora": 4.934614015583461e-06, "row_tokens": 4.934614015583461e-06 } }, { "update_id": 853, "row_count": 12, "row_ids_sha256": "8fd33965269db9c52834417c5aff014a449d3a9423869cb5f9f6ca70ea4f9721", "input_ids_vector_sha256": "7671cc05a0679a9605b645d7b196294c909e94be721a17eb9e7780de8200846a", "labels_vector_sha256": "93c1ec71b787065d674255c0da78299636ec1aa4b368ad9e5608d8d3d2aef32a", "planned_active_tokens": 59797, "realized_active_tokens": 59797, "cumulative_start": 55908919, "cumulative_end": 55968716, "loss_sum": 14660.545913696289, "token_normalized_loss": 0.24517193025898104, "grad_norm_before_clip": 0.08442055433988571, "learning_rates_at_step": { "lora": 4.934614015583461e-06, "row_tokens": 4.934614015583461e-06 }, "learning_rates_after_step": { "lora": 4.860721732509765e-06, "row_tokens": 4.860721732509765e-06 } }, { "update_id": 854, "row_count": 15, "row_ids_sha256": "e630b45e733867ac810b735981933c9e7ec428370b053ffc5c0a983e1e34dc0c", "input_ids_vector_sha256": "3cac8017edf344abbfef5b8a63da04134b1d2b558273b8b704baa5016d902bda", "labels_vector_sha256": "cebc02ffee5a7f1ceaef8ba6166e446456f54c61bdae728a6207cdb007918a9e", "planned_active_tokens": 66213, "realized_active_tokens": 66213, "cumulative_start": 55968716, "cumulative_end": 56034929, "loss_sum": 19628.850128173828, "token_normalized_loss": 0.29645009481784285, "grad_norm_before_clip": 0.0875331461429596, "learning_rates_at_step": { "lora": 4.860721732509765e-06, "row_tokens": 4.860721732509765e-06 }, "learning_rates_after_step": { "lora": 4.787697527888257e-06, "row_tokens": 4.787697527888257e-06 } }, { "update_id": 855, "row_count": 15, "row_ids_sha256": "47e0d7d3c076f5320668249ee41787d4e47d11a95743d8fbaf9cb328424e2c27", "input_ids_vector_sha256": "936d5b31c803031f552c940faf67fe184c8d0df34ac72aa279ba3a298f639de6", "labels_vector_sha256": "c749483d9e8e7437a4409969b68499a5bbd1983b7a0bb3b22412eeaa9a95e4a9", "planned_active_tokens": 65906, "realized_active_tokens": 65906, "cumulative_start": 56034929, "cumulative_end": 56100835, "loss_sum": 19048.802490234375, "token_normalized_loss": 0.2890298681490968, "grad_norm_before_clip": 0.08590540289878845, "learning_rates_at_step": { "lora": 4.787697527888257e-06, "row_tokens": 4.787697527888257e-06 }, "learning_rates_after_step": { "lora": 4.7148772872878115e-06, "row_tokens": 4.7148772872878115e-06 } }, { "update_id": 856, "row_count": 14, "row_ids_sha256": "59661591a372386f5ea7f3b6528833530ecd6cfcb7d682372e56d9415666db8b", "input_ids_vector_sha256": "8ae4de44d5d91ac29b049e8265fa2ba4106e47cfdf94ac58c8889242257eec37", "labels_vector_sha256": "350b5e897cc406f0eb4ecd4adefcbf86d73d8143cdfe2106e8d0b825dc4994ae", "planned_active_tokens": 66199, "realized_active_tokens": 66199, "cumulative_start": 56100835, "cumulative_end": 56167034, "loss_sum": 19756.989990234375, "token_normalized_loss": 0.298448465841393, "grad_norm_before_clip": 0.08833116292953491, "learning_rates_at_step": { "lora": 4.7148772872878115e-06, "row_tokens": 4.7148772872878115e-06 }, "learning_rates_after_step": { "lora": 4.643387387876913e-06, "row_tokens": 4.643387387876913e-06 } }, { "update_id": 857, "row_count": 16, "row_ids_sha256": "7066cd5c89eb7348629868d2fd43eae46ba7a0f4b22024e73611cde070b25de1", "input_ids_vector_sha256": "4d1036308a8c27ed47f029dbf61c2d5af20a0ed1b737c0a65c36a00f07c36f25", "labels_vector_sha256": "101fe085fbf96b5bc13fbc0c31a7b25ffaa0d1cd52cbd2bfbed741d90d22e5ec", "planned_active_tokens": 65464, "realized_active_tokens": 65464, "cumulative_start": 56167034, "cumulative_end": 56232498, "loss_sum": 15961.475051879883, "token_normalized_loss": 0.2438206503097868, "grad_norm_before_clip": 0.08206761628389359, "learning_rates_at_step": { "lora": 4.643387387876913e-06, "row_tokens": 4.643387387876913e-06 }, "learning_rates_after_step": { "lora": 4.572123431481501e-06, "row_tokens": 4.572123431481501e-06 } }, { "update_id": 858, "row_count": 15, "row_ids_sha256": "5cc26b90d3e7c30c213c6a8c7bcb5b52d1403b9569b3f7234d113c6a93fd7cd3", "input_ids_vector_sha256": "f6f291debbf19886e4753c1e6e7600fb9d37370a3c09180b7076bf1b1b452622", "labels_vector_sha256": "2eca1d5d622a9703ba9d6dd7241b4b08544a89af7428e5a34a80ff27033da8f2", "planned_active_tokens": 65736, "realized_active_tokens": 65736, "cumulative_start": 56232498, "cumulative_end": 56298234, "loss_sum": 20552.846969604492, "token_normalized_loss": 0.31265740187423163, "grad_norm_before_clip": 0.08938320726156235, "learning_rates_at_step": { "lora": 4.572123431481501e-06, "row_tokens": 4.572123431481501e-06 }, "learning_rates_after_step": { "lora": 4.50364571665472e-06, "row_tokens": 4.50364571665472e-06 } }, { "update_id": 859, "row_count": 17, "row_ids_sha256": "410e9a5ab25fe3b266c80f572ca51ac8b6ad892d149ab8230f9773f6fe827378", "input_ids_vector_sha256": "ca804028d5afc3f75a74e9a088227085453dd39530411aaaf5e5fd467495d3ba", "labels_vector_sha256": "7db3aaf30accaac10d2fc11a101fa1f5cf0da15b380f192866173e4b0e3a3e1d", "planned_active_tokens": 63627, "realized_active_tokens": 63627, "cumulative_start": 56298234, "cumulative_end": 56361861, "loss_sum": 13990.875366210938, "token_normalized_loss": 0.2198889679886045, "grad_norm_before_clip": 0.07771565020084381, "learning_rates_at_step": { "lora": 4.50364571665472e-06, "row_tokens": 4.50364571665472e-06 }, "learning_rates_after_step": { "lora": 4.433398442731701e-06, "row_tokens": 4.433398442731701e-06 } }, { "update_id": 860, "row_count": 19, "row_ids_sha256": "a3ca79140613dcb0e8bf1ca30cb6e61b9b7f910dfdae42701ab52dc9727d1416", "input_ids_vector_sha256": "36de687d8ad3e3395eb414ef07d9018382d80fad2b5259e90445540d12ec0282", "labels_vector_sha256": "1f965b85b708cbfb99fa5be19b1e38f9db50a49cbc61a923142f8fcf03d65e53", "planned_active_tokens": 65752, "realized_active_tokens": 65752, "cumulative_start": 56361861, "cumulative_end": 56427613, "loss_sum": 16475.81999206543, "token_normalized_loss": 0.25057519150847773, "grad_norm_before_clip": 0.08121417462825775, "learning_rates_at_step": { "lora": 4.433398442731701e-06, "row_tokens": 4.433398442731701e-06 }, "learning_rates_after_step": { "lora": 4.358421990394989e-06, "row_tokens": 4.358421990394989e-06 } }, { "update_id": 861, "row_count": 15, "row_ids_sha256": "06d399b409fafc0d5c33585edac9d5c62673d7f0850352ef689ca2ad998c4e5b", "input_ids_vector_sha256": "978d8a151571d8e750d043372eeb00b9ff4de364cf30296feec5e44a2b47ecf7", "labels_vector_sha256": "cb7162deb6e49ee7c456f3ce909f1d971729e5f6c531b3c84fefcd33fb118f06", "planned_active_tokens": 70729, "realized_active_tokens": 70729, "cumulative_start": 56427613, "cumulative_end": 56498342, "loss_sum": 22112.825073242188, "token_normalized_loss": 0.312641562488402, "grad_norm_before_clip": 0.08757200092077255, "learning_rates_at_step": { "lora": 4.358421990394989e-06, "row_tokens": 4.358421990394989e-06 }, "learning_rates_after_step": { "lora": 4.295123386627131e-06, "row_tokens": 4.295123386627131e-06 } }, { "update_id": 862, "row_count": 12, "row_ids_sha256": "3e2a954024827604f7eb19584d2642bb579daf0d171db4ac59b9c08346f13058", "input_ids_vector_sha256": "fda9f5d76dac74eef792e7c43ce6e6e40230e2769e24ed12377d7c09aafdf593", "labels_vector_sha256": "4e6638cf2818abdd444fe9d2fb1f8637bc5cca8c0b5a040f2c8d683b66780546", "planned_active_tokens": 60166, "realized_active_tokens": 60166, "cumulative_start": 56498342, "cumulative_end": 56558508, "loss_sum": 16983.62158203125, "token_normalized_loss": 0.28227938673056624, "grad_norm_before_clip": 0.10633702576160431, "learning_rates_at_step": { "lora": 4.295123386627131e-06, "row_tokens": 4.295123386627131e-06 }, "learning_rates_after_step": { "lora": 4.226786783554898e-06, "row_tokens": 4.226786783554898e-06 } }, { "update_id": 863, "row_count": 15, "row_ids_sha256": "b3cd57f04e068194003b93f5ced1b5d9b95db897d54185f8776dc5352f96abf2", "input_ids_vector_sha256": "4eb05b2f5a3d96f1f2a4425b92463779d0e8fdfea30991e6752bcfd6b6373a87", "labels_vector_sha256": "a20c8b64a6b6e50ab8ca17f2ea8d4d857ca424cdef316398dc147397c676a15a", "planned_active_tokens": 65432, "realized_active_tokens": 65432, "cumulative_start": 56558508, "cumulative_end": 56623940, "loss_sum": 17734.673416137695, "token_normalized_loss": 0.2710397575519271, "grad_norm_before_clip": 0.09017208218574524, "learning_rates_at_step": { "lora": 4.226786783554898e-06, "row_tokens": 4.226786783554898e-06 }, "learning_rates_after_step": { "lora": 4.1595089637195665e-06, "row_tokens": 4.1595089637195665e-06 } }, { "update_id": 864, "row_count": 16, "row_ids_sha256": "cecc775a9b7aa6e28f0d4dd9b113c2ee21bdec704a5582aa11d2aeda1cacb286", "input_ids_vector_sha256": "158ccb38ec0d629824d452720e685e3aed3b2838bc4bf278d7b075176e366f6b", "labels_vector_sha256": "53a56c111f11c46d9e24516b0068048b20d72e46f38cd9ed774713561239b490", "planned_active_tokens": 64914, "realized_active_tokens": 64914, "cumulative_start": 56623940, "cumulative_end": 56688854, "loss_sum": 15739.163024902344, "token_normalized_loss": 0.24246176518012053, "grad_norm_before_clip": 0.08184193819761276, "learning_rates_at_step": { "lora": 4.1595089637195665e-06, "row_tokens": 4.1595089637195665e-06 }, "learning_rates_after_step": { "lora": 4.0918533141055644e-06, "row_tokens": 4.0918533141055644e-06 } }, { "update_id": 865, "row_count": 12, "row_ids_sha256": "c6a66f24677fffa550b46ea5a00f36acaa976bc8ecb45421a8614dba48e89afb", "input_ids_vector_sha256": "5b3beebd07c5665dcb0188fab6542395971656f27700cce49959d88f6f884c8a", "labels_vector_sha256": "0b295631d7addd77e7358b53a80711402a6d5c595d429a1f6bc4129ff7e64814", "planned_active_tokens": 65787, "realized_active_tokens": 65787, "cumulative_start": 56688854, "cumulative_end": 56754641, "loss_sum": 20439.005889892578, "token_normalized_loss": 0.3106845712662468, "grad_norm_before_clip": 0.08712980896234512, "learning_rates_at_step": { "lora": 4.0918533141055644e-06, "row_tokens": 4.0918533141055644e-06 }, "learning_rates_after_step": { "lora": 4.022805312055056e-06, "row_tokens": 4.022805312055056e-06 } }, { "update_id": 866, "row_count": 17, "row_ids_sha256": "5aa7f6a37f296171a4d7044a0b8df6bad3876c3b99d3ac186ac25cb92c26af4e", "input_ids_vector_sha256": "10a35ad23d5675a60aa0a18e2a4f47e03115359b5fed0ee64de6afdc7691d99a", "labels_vector_sha256": "61ec5e645ea9ed6e7d2e3b744ca66cbc0c442b65837559cea00eec75241099e1", "planned_active_tokens": 67680, "realized_active_tokens": 67680, "cumulative_start": 56754641, "cumulative_end": 56822321, "loss_sum": 18286.194381713867, "token_normalized_loss": 0.270186087200264, "grad_norm_before_clip": 0.08216702938079834, "learning_rates_at_step": { "lora": 4.022805312055056e-06, "row_tokens": 4.022805312055056e-06 }, "learning_rates_after_step": { "lora": 3.957674829790825e-06, "row_tokens": 3.957674829790825e-06 } }, { "update_id": 867, "row_count": 16, "row_ids_sha256": "d80a2d3aef3fc1c53d73db3ca1819c1786cd2347b0e59ede3b6e16b4a2fac001", "input_ids_vector_sha256": "e5db6611c155e7a9985cfa855a16afd5cae4bb821955179a89b9813faec7507f", "labels_vector_sha256": "b761d2f710f2cb8b66c43ca09c3c8289915182269f8c64c5645bc7d21e04aed6", "planned_active_tokens": 64352, "realized_active_tokens": 64352, "cumulative_start": 56822321, "cumulative_end": 56886673, "loss_sum": 16434.479370117188, "token_normalized_loss": 0.2553841274570672, "grad_norm_before_clip": 0.08387001603841782, "learning_rates_at_step": { "lora": 3.957674829790825e-06, "row_tokens": 3.957674829790825e-06 }, "learning_rates_after_step": { "lora": 3.8925350765723175e-06, "row_tokens": 3.8925350765723175e-06 } }, { "update_id": 868, "row_count": 12, "row_ids_sha256": "acd4fe2fd31a86805673afdb8f411faf136c82f5c2be1266f342e90cbf193491", "input_ids_vector_sha256": "6920e0aa2c0f84a9e3b0399903c868054ce81eebf73b37237d3e50d9f24aaff8", "labels_vector_sha256": "0dddf00f13dfbc062b68746bc026fdbbb7ac513a44a5c24b50d05c3696db9bfb", "planned_active_tokens": 64871, "realized_active_tokens": 64871, "cumulative_start": 56886673, "cumulative_end": 56951544, "loss_sum": 18864.315338134766, "token_normalized_loss": 0.29079735687957275, "grad_norm_before_clip": 0.09359277784824371, "learning_rates_at_step": { "lora": 3.8925350765723175e-06, "row_tokens": 3.8925350765723175e-06 }, "learning_rates_after_step": { "lora": 3.823821604125305e-06, "row_tokens": 3.823821604125305e-06 } }, { "update_id": 869, "row_count": 15, "row_ids_sha256": "fc2d99701dd222001f786ed55ef9b100286e8710eba21ee3b7c8e014a0d92723", "input_ids_vector_sha256": "2b063a643aa007fd8163cc5222e44ebd89f79cba7590794124c94d7de8ae8590", "labels_vector_sha256": "4ce73e70c25e9d1603a84b7932edee2e12f6735a52c328b058524ef230b4f91d", "planned_active_tokens": 68997, "realized_active_tokens": 68997, "cumulative_start": 56951544, "cumulative_end": 57020541, "loss_sum": 17299.001708984375, "token_normalized_loss": 0.25072107061153925, "grad_norm_before_clip": 0.07948631793260574, "learning_rates_at_step": { "lora": 3.823821604125305e-06, "row_tokens": 3.823821604125305e-06 }, "learning_rates_after_step": { "lora": 3.757640741818247e-06, "row_tokens": 3.757640741818247e-06 } }, { "update_id": 870, "row_count": 15, "row_ids_sha256": "6f70f0fb3805d8e3a09c01e14f6a318be3b18ceddc5445420dc0d714598cb253", "input_ids_vector_sha256": "72e4a7cded346e3241ff5c73fc2f699494e4a24b84d923fb34e1f69c742915a6", "labels_vector_sha256": "ac78cb4706b5665894b246e519006bb9df5bee3c8c95e14f7d143631274f4921", "planned_active_tokens": 67019, "realized_active_tokens": 67019, "cumulative_start": 57020541, "cumulative_end": 57087560, "loss_sum": 16039.232528686523, "token_normalized_loss": 0.23932366237464783, "grad_norm_before_clip": 0.08044533431529999, "learning_rates_at_step": { "lora": 3.757640741818247e-06, "row_tokens": 3.757640741818247e-06 }, "learning_rates_after_step": { "lora": 3.6959993911133083e-06, "row_tokens": 3.6959993911133083e-06 } }, { "update_id": 871, "row_count": 15, "row_ids_sha256": "da832eadb659681b4b7dae4c868ad7b2bbe6584da5bc47221679a2f455d63148", "input_ids_vector_sha256": "e2035986b338459202bb074e6047da99be7cb7aed53909dc30493db122a9a347", "labels_vector_sha256": "605fe07f016335c5c72cc92a4935f636df9dcdaaa393c98fbb1fab44f6d7abb5", "planned_active_tokens": 62934, "realized_active_tokens": 62934, "cumulative_start": 57087560, "cumulative_end": 57150494, "loss_sum": 15411.86018371582, "token_normalized_loss": 0.24488925197374742, "grad_norm_before_clip": 0.08469104766845703, "learning_rates_at_step": { "lora": 3.6959993911133083e-06, "row_tokens": 3.6959993911133083e-06 }, "learning_rates_after_step": { "lora": 3.634171972443268e-06, "row_tokens": 3.634171972443268e-06 } }, { "update_id": 872, "row_count": 17, "row_ids_sha256": "c836b9e0d0f3f6b07f4401885788f7054ed22e6cb2b750194886d701d84e44c6", "input_ids_vector_sha256": "58baddfb7f1d3335afd452fd4d272f415fa6e58b37a4112da986bf4c69b8b1c4", "labels_vector_sha256": "47ac0d4acfe7d647cc49c4b6418a17f66d86ad86e393f6361af0bc7c4fe4e452", "planned_active_tokens": 63633, "realized_active_tokens": 63633, "cumulative_start": 57150494, "cumulative_end": 57214127, "loss_sum": 15247.210968017578, "token_normalized_loss": 0.2396116946869954, "grad_norm_before_clip": 0.0826679989695549, "learning_rates_at_step": { "lora": 3.634171972443268e-06, "row_tokens": 3.634171972443268e-06 }, "learning_rates_after_step": { "lora": 3.5716852960813953e-06, "row_tokens": 3.5716852960813953e-06 } }, { "update_id": 873, "row_count": 14, "row_ids_sha256": "5c26831e706003a12465f3592cf4d476f5a9122b0b6c5ca68be8692847351a58", "input_ids_vector_sha256": "38979693e426c5ce3565e9d4ae200cd23167acf436ce38ece254cbf51e78b7dc", "labels_vector_sha256": "c8a93c9541f85609715cb93079327df675308e1000429e3f444d959f3a0604f9", "planned_active_tokens": 64843, "realized_active_tokens": 64843, "cumulative_start": 57214127, "cumulative_end": 57278970, "loss_sum": 17945.184539794922, "token_normalized_loss": 0.27674821553282425, "grad_norm_before_clip": 0.08616053313016891, "learning_rates_at_step": { "lora": 3.5716852960813953e-06, "row_tokens": 3.5716852960813953e-06 }, "learning_rates_after_step": { "lora": 3.507319190868691e-06, "row_tokens": 3.507319190868691e-06 } }, { "update_id": 874, "row_count": 19, "row_ids_sha256": "8a7a46f1da5ad9d45847455922439a184d5d9616487fd4783fc0bdeb81cc7476", "input_ids_vector_sha256": "b3b7c71d053cc63bf15e228cf0e58ab4d77b5d84f0b2a369d059c00c7b846c58", "labels_vector_sha256": "b93fb0f988a867ecde98503484ee1556c6b2d1e599b596098f2e55d065f03033", "planned_active_tokens": 67367, "realized_active_tokens": 67367, "cumulative_start": 57278970, "cumulative_end": 57346337, "loss_sum": 17321.34864807129, "token_normalized_loss": 0.25711919260277716, "grad_norm_before_clip": 0.0830472931265831, "learning_rates_at_step": { "lora": 3.507319190868691e-06, "row_tokens": 3.507319190868691e-06 }, "learning_rates_after_step": { "lora": 3.446920015585259e-06, "row_tokens": 3.446920015585259e-06 } }, { "update_id": 875, "row_count": 12, "row_ids_sha256": "5e18aa6fb257ae4c7a1e7bf43d1e574a263e7ea6146e96b80fdc7e8ff70cf23c", "input_ids_vector_sha256": "06e392735c51e116589388d96a4f0c13ab2d66a957737c76bb7d8efdd094cd7d", "labels_vector_sha256": "85b8b6dd230ec361a6dc8e0842a5df699996369c0b1aa0e08e62a1e3b4e789bf", "planned_active_tokens": 63759, "realized_active_tokens": 63759, "cumulative_start": 57346337, "cumulative_end": 57410096, "loss_sum": 16503.927520751953, "token_normalized_loss": 0.25884859424946993, "grad_norm_before_clip": 0.08411889523267746, "learning_rates_at_step": { "lora": 3.446920015585259e-06, "row_tokens": 3.446920015585259e-06 }, "learning_rates_after_step": { "lora": 3.3832320492588776e-06, "row_tokens": 3.3832320492588776e-06 } }, { "update_id": 876, "row_count": 15, "row_ids_sha256": "5e0111fb88344c40068f4fb7a0dbc46770cf1f8daf931c2db4fff76765e85038", "input_ids_vector_sha256": "6dd9221957ba6829483c8043d8cff557cd6e56ca95274c33d9ade2f491656328", "labels_vector_sha256": "380fb5eb5d55d9c2b40bf65139bf000187e0b53725d13272d6636f0d40720d48", "planned_active_tokens": 67817, "realized_active_tokens": 67817, "cumulative_start": 57410096, "cumulative_end": 57477913, "loss_sum": 16276.537353515625, "token_normalized_loss": 0.24000674393611668, "grad_norm_before_clip": 0.07866497337818146, "learning_rates_at_step": { "lora": 3.3832320492588776e-06, "row_tokens": 3.3832320492588776e-06 }, "learning_rates_after_step": { "lora": 3.3242439858183483e-06, "row_tokens": 3.3242439858183483e-06 } }, { "update_id": 877, "row_count": 14, "row_ids_sha256": "20e191d2189ab0cc7311e69057c3f8d04576f57f2f7384706db889f473fa4511", "input_ids_vector_sha256": "07bb811aed45034b639de3d6143fd560c76168c4c2b440b12727e2b5e0182cd4", "labels_vector_sha256": "0b705173c17a06bff879bfffb150e3bba6bca5f74651b2d0db6700d1f961fcce", "planned_active_tokens": 63364, "realized_active_tokens": 63364, "cumulative_start": 57477913, "cumulative_end": 57541277, "loss_sum": 17909.280731201172, "token_normalized_loss": 0.28264125893569175, "grad_norm_before_clip": 0.0909658819437027, "learning_rates_at_step": { "lora": 3.3242439858183483e-06, "row_tokens": 3.3242439858183483e-06 }, "learning_rates_after_step": { "lora": 3.2624013835675815e-06, "row_tokens": 3.2624013835675815e-06 } }, { "update_id": 878, "row_count": 16, "row_ids_sha256": "f8f3f6e2dfa91d7f8432032ed7a9c2fc6255d9333e8a2fbb76b548906afa2f8e", "input_ids_vector_sha256": "d3620f1b7b19a3ce6822d05b35f507546f50ed18c4309450c2c83f354992687e", "labels_vector_sha256": "2702b187bb68dbb57b97f9b2ca7b8a2410320119d28deba80afa1f8ce58d3e48", "planned_active_tokens": 67016, "realized_active_tokens": 67016, "cumulative_start": 57541277, "cumulative_end": 57608293, "loss_sum": 16788.753936767578, "token_normalized_loss": 0.2505185916313653, "grad_norm_before_clip": 0.08119799941778183, "learning_rates_at_step": { "lora": 3.2624013835675815e-06, "row_tokens": 3.2624013835675815e-06 }, "learning_rates_after_step": { "lora": 3.2033568673018597e-06, "row_tokens": 3.2033568673018597e-06 } }, { "update_id": 879, "row_count": 17, "row_ids_sha256": "ea994b56cc01d67699d9738514de0e84a25b29aafd2b477872a25752184b65a0", "input_ids_vector_sha256": "083d4cb83128566a152bdf1981ffb5870af21b011b1b42fc85ef6a75830bb9f2", "labels_vector_sha256": "58af17ba287744ac9469bd7cb2076b42469583eabbc2a4fc450a7a516e55f131", "planned_active_tokens": 64559, "realized_active_tokens": 64559, "cumulative_start": 57608293, "cumulative_end": 57672852, "loss_sum": 17289.355194091797, "token_normalized_loss": 0.26780704772520947, "grad_norm_before_clip": 0.08767526596784592, "learning_rates_at_step": { "lora": 3.2033568673018597e-06, "row_tokens": 3.2033568673018597e-06 }, "learning_rates_after_step": { "lora": 3.1426511754312495e-06, "row_tokens": 3.1426511754312495e-06 } }, { "update_id": 880, "row_count": 17, "row_ids_sha256": "75cfd23388ac0febefc14e2e2eae58b1f5b345486e5597985fea71179ac3eca9", "input_ids_vector_sha256": "5d8823b680312a8aa2567f0fdfd98c437409de6bf8de2858d56eafd4cf171396", "labels_vector_sha256": "76c560c7f72debf533bfa39a1c8e164904ba99c3399493f860d5c4cac3d02eeb", "planned_active_tokens": 66978, "realized_active_tokens": 66978, "cumulative_start": 57672852, "cumulative_end": 57739830, "loss_sum": 16532.191345214844, "token_normalized_loss": 0.24683017326905615, "grad_norm_before_clip": 0.08208198100328445, "learning_rates_at_step": { "lora": 3.1426511754312495e-06, "row_tokens": 3.1426511754312495e-06 }, "learning_rates_after_step": { "lora": 3.082762265648126e-06, "row_tokens": 3.082762265648126e-06 } }, { "update_id": 881, "row_count": 17, "row_ids_sha256": "857207f186558b0aa61f033c7d7849bcd4b7cc0889ab87b4b251d44f94e181c0", "input_ids_vector_sha256": "98b87cd5e0c2826a5cf37c0a086aeb0e87c5d1588d8216ca731046bb264d54de", "labels_vector_sha256": "6ea07cf888622a9c0f010391efaf840df853b82120aa5337297e05c87b04b72c", "planned_active_tokens": 66693, "realized_active_tokens": 66693, "cumulative_start": 57739830, "cumulative_end": 57806523, "loss_sum": 16984.066528320312, "token_normalized_loss": 0.2546604070640144, "grad_norm_before_clip": 0.08424676954746246, "learning_rates_at_step": { "lora": 3.082762265648126e-06, "row_tokens": 3.082762265648126e-06 }, "learning_rates_after_step": { "lora": 3.026294587074935e-06, "row_tokens": 3.026294587074935e-06 } }, { "update_id": 882, "row_count": 14, "row_ids_sha256": "6002d1739ebb584cd5fa0db782eaf5909377bba8b846ca60c4606017875231c8", "input_ids_vector_sha256": "be4106f8e15a33483d8b1f9d7f8bcd9b0020d010be3a743715d9d99ceed714b2", "labels_vector_sha256": "caa4bd71b9ff37bab8287b360b004945909b187408bce73dd9c7fc8dc4a9269c", "planned_active_tokens": 63460, "realized_active_tokens": 63460, "cumulative_start": 57806523, "cumulative_end": 57869983, "loss_sum": 17470.63900756836, "token_normalized_loss": 0.2753015916729965, "grad_norm_before_clip": 0.08996128290891647, "learning_rates_at_step": { "lora": 3.026294587074935e-06, "row_tokens": 3.026294587074935e-06 }, "learning_rates_after_step": { "lora": 2.9669354842997598e-06, "row_tokens": 2.9669354842997598e-06 } }, { "update_id": 883, "row_count": 13, "row_ids_sha256": "bac76896b962da274e16c011e362fbbb1768d5c7da58018a1d00a92f236ab141", "input_ids_vector_sha256": "60a03323901f9a059030dcd2747eaaac439280ebee39a40ea9e3b47923cce8d3", "labels_vector_sha256": "8adfdcc3f6233447174286595dd6306e7d209093137bf9c987d24fe76fc32085", "planned_active_tokens": 67331, "realized_active_tokens": 67331, "cumulative_start": 57869983, "cumulative_end": 57937314, "loss_sum": 19035.814331054688, "token_normalized_loss": 0.2827199110521853, "grad_norm_before_clip": 0.09253660589456558, "learning_rates_at_step": { "lora": 2.9669354842997598e-06, "row_tokens": 2.9669354842997598e-06 }, "learning_rates_after_step": { "lora": 2.909380466657097e-06, "row_tokens": 2.909380466657097e-06 } }, { "update_id": 884, "row_count": 12, "row_ids_sha256": "c73a907ee2ce7638f0a74988cea5212382aad4df0f86999b7eb9085bb3479a1d", "input_ids_vector_sha256": "a3a51185e1881efa8658dd54817a1309d92482d9f7efc76a1e71faaeb3e2be67", "labels_vector_sha256": "55d85db66d6bbe1b4689a5c3bf4db8be82b624f65450d8e54a9fd70b9cf80791", "planned_active_tokens": 65911, "realized_active_tokens": 65911, "cumulative_start": 57937314, "cumulative_end": 58003225, "loss_sum": 23625.454498291016, "token_normalized_loss": 0.358444789159488, "grad_norm_before_clip": 0.09869097918272018, "learning_rates_at_step": { "lora": 2.909380466657097e-06, "row_tokens": 2.909380466657097e-06 }, "learning_rates_after_step": { "lora": 2.8545333815607144e-06, "row_tokens": 2.8545333815607144e-06 } }, { "update_id": 885, "row_count": 13, "row_ids_sha256": "49bc024b21be415c555fcf65657cecebb7a3f2dcf2d4274a72bbb348dccfa816", "input_ids_vector_sha256": "fbdf2cbf1c2306b21031d374a565bb15737b80f9887359db08a34dfa1639ea01", "labels_vector_sha256": "83ed583a69306db78a2866960fbcef556ecb8a0d3e9c2833e3d9fb7c9755f04e", "planned_active_tokens": 63401, "realized_active_tokens": 63401, "cumulative_start": 58003225, "cumulative_end": 58066626, "loss_sum": 19598.014282226562, "token_normalized_loss": 0.3091120689299311, "grad_norm_before_clip": 0.09021028876304626, "learning_rates_at_step": { "lora": 2.8545333815607144e-06, "row_tokens": 2.8545333815607144e-06 }, "learning_rates_after_step": { "lora": 2.798273882657476e-06, "row_tokens": 2.798273882657476e-06 } }, { "update_id": 886, "row_count": 16, "row_ids_sha256": "eb8d5cd820990b2013cdaade5ca0681bd52d15e5ef2f27c6bdfe4617ed58a9e7", "input_ids_vector_sha256": "87a2c93d09cae06a7cbc203e4f9b0ca53539866d4369310b925c45455c3a030c", "labels_vector_sha256": "4b414524f201e725fb8798e1f0e6bf024659461b16a0807eb3fb3791c6ff5226", "planned_active_tokens": 65651, "realized_active_tokens": 65651, "cumulative_start": 58066626, "cumulative_end": 58132277, "loss_sum": 20606.285400390625, "token_normalized_loss": 0.31387618467945083, "grad_norm_before_clip": 0.09571405500173569, "learning_rates_at_step": { "lora": 2.798273882657476e-06, "row_tokens": 2.798273882657476e-06 }, "learning_rates_after_step": { "lora": 2.741428507270244e-06, "row_tokens": 2.741428507270244e-06 } }, { "update_id": 887, "row_count": 13, "row_ids_sha256": "df7e159e102fd568799d0407a4f1784ab06e58800670bd604c5c49f85589abad", "input_ids_vector_sha256": "0a8547aba69ceb4e6aebf36c6f47b8c12cbab8b5878291c580bcd8223dadba5d", "labels_vector_sha256": "22d42cbd479688121611121f0136ed9443ddb43273a7314cd8d7ece93eac252b", "planned_active_tokens": 66989, "realized_active_tokens": 66989, "cumulative_start": 58132277, "cumulative_end": 58199266, "loss_sum": 21921.678283691406, "token_normalized_loss": 0.327242954570025, "grad_norm_before_clip": 0.0938853919506073, "learning_rates_at_step": { "lora": 2.741428507270244e-06, "row_tokens": 2.741428507270244e-06 }, "learning_rates_after_step": { "lora": 2.6881509632756762e-06, "row_tokens": 2.6881509632756762e-06 } }, { "update_id": 888, "row_count": 15, "row_ids_sha256": "180786a296e6dc7427665b4fc67e99dd0a21c3478decb5990e36d9155094d26f", "input_ids_vector_sha256": "39888f19ffd25f98cf2312ca526ddab5b99e283bbf61811dea2d8e0d1c3b083c", "labels_vector_sha256": "eb7bc8dc91417aead3a920a8f7a647e610120f09d5003f22899a59c7e26393f2", "planned_active_tokens": 63400, "realized_active_tokens": 63400, "cumulative_start": 58199266, "cumulative_end": 58262666, "loss_sum": 18201.837936401367, "token_normalized_loss": 0.28709523558992694, "grad_norm_before_clip": 0.08722665905952454, "learning_rates_at_step": { "lora": 2.6881509632756762e-06, "row_tokens": 2.6881509632756762e-06 }, "learning_rates_after_step": { "lora": 2.6309315960473923e-06, "row_tokens": 2.6309315960473923e-06 } }, { "update_id": 889, "row_count": 14, "row_ids_sha256": "fe4188fe17b1800d745b54f34d79a1bf97979e96c7975f97f4a6970c8fdcae5e", "input_ids_vector_sha256": "f28064508cf9abd07f827add6e019d266f18cfb83cc6c380dea1bbdacf14e000", "labels_vector_sha256": "59ad10666383887824f5c8346f90f2f7803c0ac49f1a530d3558b316638e6e3b", "planned_active_tokens": 68775, "realized_active_tokens": 68775, "cumulative_start": 58262666, "cumulative_end": 58331441, "loss_sum": 20515.405883789062, "token_normalized_loss": 0.29829743197076064, "grad_norm_before_clip": 0.08539136499166489, "learning_rates_at_step": { "lora": 2.6309315960473923e-06, "row_tokens": 2.6309315960473923e-06 }, "learning_rates_after_step": { "lora": 2.57847875234824e-06, "row_tokens": 2.57847875234824e-06 } }, { "update_id": 890, "row_count": 15, "row_ids_sha256": "afa3c394cb64b926ac688e1f02a7cababf6bd27958401769f51a48401f80f93d", "input_ids_vector_sha256": "e1cc173aa2c19c888451f045af50ad1c38b4e2dfb0dd39b083e18fb8ae860d3e", "labels_vector_sha256": "d389c0ea9f008535a7df8d192c256e9e549bccb75f48aabae0555bafd6ff8dc9", "planned_active_tokens": 63688, "realized_active_tokens": 63688, "cumulative_start": 58331441, "cumulative_end": 58395129, "loss_sum": 16280.36312866211, "token_normalized_loss": 0.2556268548025077, "grad_norm_before_clip": 0.08306210488080978, "learning_rates_at_step": { "lora": 2.57847875234824e-06, "row_tokens": 2.57847875234824e-06 }, "learning_rates_after_step": { "lora": 2.5232223527174916e-06, "row_tokens": 2.5232223527174916e-06 } }, { "update_id": 891, "row_count": 14, "row_ids_sha256": "ff6fe1ea91082c2b78d6a4437859804aa9c6b099c36ac6497596af7b41e20feb", "input_ids_vector_sha256": "6d4fec3f256d96638917a8df73db1b54cf7f1717c0303fc6397026a3c8197edc", "labels_vector_sha256": "b9223a8045c04979e271205889480fa8367d9cf763762823fa4c1a7fe32e2bf1", "planned_active_tokens": 67778, "realized_active_tokens": 67778, "cumulative_start": 58395129, "cumulative_end": 58462907, "loss_sum": 18756.416885375977, "token_normalized_loss": 0.27673311229862163, "grad_norm_before_clip": 0.08277330547571182, "learning_rates_at_step": { "lora": 2.5232223527174916e-06, "row_tokens": 2.5232223527174916e-06 }, "learning_rates_after_step": { "lora": 2.4658066446423044e-06, "row_tokens": 2.4658066446423044e-06 } }, { "update_id": 892, "row_count": 14, "row_ids_sha256": "c5ea2d52cde6267da631e7eb387ebf55f986ca676bba25025a9487cd042067ca", "input_ids_vector_sha256": "1f2d9ef32569666c7d35b0b25578381c372b078027c60a8b719c163b345bd199", "labels_vector_sha256": "c4b2f8a0fc8948bb26ecc263a9b4523b2857e40114f7199d8be1bd262d9fe08e", "planned_active_tokens": 71197, "realized_active_tokens": 71197, "cumulative_start": 58462907, "cumulative_end": 58534104, "loss_sum": 20150.116455078125, "token_normalized_loss": 0.28301917854794617, "grad_norm_before_clip": 0.08130951225757599, "learning_rates_at_step": { "lora": 2.4658066446423044e-06, "row_tokens": 2.4658066446423044e-06 }, "learning_rates_after_step": { "lora": 2.4183529099160053e-06, "row_tokens": 2.4183529099160053e-06 } }, { "update_id": 893, "row_count": 9, "row_ids_sha256": "f92c5c74da9bc02b01704464b8cd92b907d9755b72430524a0b2d8054422b2e2", "input_ids_vector_sha256": "9715e334410630e06d3cd5d98846e90171e24972bf1e2d3b31a27ebcaffcd169", "labels_vector_sha256": "96d2ccfd7fae5b262043caa77239f1d20d401859fb94e1f6e96eb4931009708b", "planned_active_tokens": 59456, "realized_active_tokens": 59456, "cumulative_start": 58534104, "cumulative_end": 58593560, "loss_sum": 18203.481414794922, "token_normalized_loss": 0.30616727352655615, "grad_norm_before_clip": 0.08779065310955048, "learning_rates_at_step": { "lora": 2.4183529099160053e-06, "row_tokens": 2.4183529099160053e-06 }, "learning_rates_after_step": { "lora": 2.366364849183811e-06, "row_tokens": 2.366364849183811e-06 } }, { "update_id": 894, "row_count": 8, "row_ids_sha256": "6372d830bf0d3b21e6c7346d899b25b1dff5198b4f423da4dc71af3b928b9fd0", "input_ids_vector_sha256": "2673c9bd60e7450d03d7497256dbc93c49004c8a0baf7c6b6e908eba3f189065", "labels_vector_sha256": "293aaea5a8415be69c20904f41b11bbc3b1f5c0bb25b38ab96ed3b27ebfe0217", "planned_active_tokens": 65794, "realized_active_tokens": 65794, "cumulative_start": 58593560, "cumulative_end": 58659354, "loss_sum": 18031.896240234375, "token_normalized_loss": 0.2740659671130251, "grad_norm_before_clip": 0.08696182817220688, "learning_rates_at_step": { "lora": 2.366364849183811e-06, "row_tokens": 2.366364849183811e-06 }, "learning_rates_after_step": { "lora": 2.3185686566833175e-06, "row_tokens": 2.3185686566833175e-06 } }, { "update_id": 895, "row_count": 14, "row_ids_sha256": "0339948f5b7994afae8f9b9cd7ecd872f019463d994a14329926bcab6dcd6d8b", "input_ids_vector_sha256": "9fe72a7ce35039d56a0a9428e1876e96500bff7e536521eea4b4f243ecf0a150", "labels_vector_sha256": "809e50703e970ea529d6c958d48ff392e264f919df7b9e1dc1bea2bf5019916a", "planned_active_tokens": 61114, "realized_active_tokens": 61114, "cumulative_start": 58659354, "cumulative_end": 58720468, "loss_sum": 16877.405334472656, "token_normalized_loss": 0.27616266869248707, "grad_norm_before_clip": 0.08494618535041809, "learning_rates_at_step": { "lora": 2.3185686566833175e-06, "row_tokens": 2.3185686566833175e-06 }, "learning_rates_after_step": { "lora": 2.2628627879802744e-06, "row_tokens": 2.2628627879802744e-06 } }, { "update_id": 896, "row_count": 8, "row_ids_sha256": "853c7c4ce888c9618fda4f6a1121b9415fd2b03232f5b67e206843590fda7d9d", "input_ids_vector_sha256": "457fd197de0d9b5f4035ba6473f02620f69e09fc23b631b4cb5fee75060d028a", "labels_vector_sha256": "0a279f09977b572cf7e082565cbce2843fcc2b2223efb6360c22e3b4ab92ceb0", "planned_active_tokens": 72009, "realized_active_tokens": 72009, "cumulative_start": 58720468, "cumulative_end": 58792477, "loss_sum": 22104.189208984375, "token_normalized_loss": 0.30696425737038946, "grad_norm_before_clip": 0.08918941766023636, "learning_rates_at_step": { "lora": 2.2628627879802744e-06, "row_tokens": 2.2628627879802744e-06 }, "learning_rates_after_step": { "lora": 2.2147040559094776e-06, "row_tokens": 2.2147040559094776e-06 } }, { "update_id": 897, "row_count": 12, "row_ids_sha256": "4131b183012073ddbafd319d4132d4aca9815130ca42c3ebe409dee0db872d91", "input_ids_vector_sha256": "9537389eae5f30488c4c52dc2046ecb64b53d0b3fdfeadf34be24036ced96e72", "labels_vector_sha256": "f1dcc0274bb845d16ccede345a7a1151af428fd54788b45c94043788873f5e90", "planned_active_tokens": 62954, "realized_active_tokens": 62954, "cumulative_start": 58792477, "cumulative_end": 58855431, "loss_sum": 19680.81756591797, "token_normalized_loss": 0.31262219344152825, "grad_norm_before_clip": 0.08932511508464813, "learning_rates_at_step": { "lora": 2.2147040559094776e-06, "row_tokens": 2.2147040559094776e-06 }, "learning_rates_after_step": { "lora": 2.163125489787854e-06, "row_tokens": 2.163125489787854e-06 } }, { "update_id": 898, "row_count": 10, "row_ids_sha256": "f78b0006eacd10e9c13f2e7b420c29e6a00de847e990d29a413b397bfefd1d56", "input_ids_vector_sha256": "64b7d81ab27e3af2a01640ff77a38d3998b17aaa33145a16b300a13cdc530697", "labels_vector_sha256": "93a247edc3c0dc94f9aad1dc88bd4bf94ba846ab992482fddc8f97828e3a33f0", "planned_active_tokens": 68171, "realized_active_tokens": 68171, "cumulative_start": 58855431, "cumulative_end": 58923602, "loss_sum": 20960.32745361328, "token_normalized_loss": 0.30746692073775184, "grad_norm_before_clip": 0.08378805965185165, "learning_rates_at_step": { "lora": 2.163125489787854e-06, "row_tokens": 2.163125489787854e-06 }, "learning_rates_after_step": { "lora": 2.116441797647806e-06, "row_tokens": 2.116441797647806e-06 } }, { "update_id": 899, "row_count": 7, "row_ids_sha256": "48e71de6a9f91315c8834a91741171bd12b6b6ea050f86fbdcbbae2892ff5907", "input_ids_vector_sha256": "c812c121da0235355316d42170d6bf04ecea765c87144560c3cbe5b7cab8c4ea", "labels_vector_sha256": "e42b3b2d06de0b8e6b6c12b6dff79a01373c2e952fa55a2c4c032b96bb600626", "planned_active_tokens": 62390, "realized_active_tokens": 62390, "cumulative_start": 58923602, "cumulative_end": 58985992, "loss_sum": 20483.280670166016, "token_normalized_loss": 0.3283103168803657, "grad_norm_before_clip": 0.09807037562131882, "learning_rates_at_step": { "lora": 2.116441797647806e-06, "row_tokens": 2.116441797647806e-06 }, "learning_rates_after_step": { "lora": 2.067638370219488e-06, "row_tokens": 2.067638370219488e-06 } }, { "update_id": 900, "row_count": 9, "row_ids_sha256": "f7cb7d87e73b0d772845773aa465a73c51bb9e56898fa7da3a28c1d267a97ea8", "input_ids_vector_sha256": "4bf82b0aeac979b853fe65b8eec02a6f27c90147faf610800fff7b0555bd1a10", "labels_vector_sha256": "d94bf5e11d9c12a8f93e6d264784557a531b865dbb2986565cafa6c5a3614afe", "planned_active_tokens": 65947, "realized_active_tokens": 65947, "cumulative_start": 58985992, "cumulative_end": 59051939, "loss_sum": 21265.08819580078, "token_normalized_loss": 0.3224572489393116, "grad_norm_before_clip": 0.09115331619977951, "learning_rates_at_step": { "lora": 2.067638370219488e-06, "row_tokens": 2.067638370219488e-06 }, "learning_rates_after_step": { "lora": 2.017855704496241e-06, "row_tokens": 2.017855704496241e-06 } }, { "update_id": 901, "row_count": 12, "row_ids_sha256": "14549f70faaa7aa96d98973ddab9a22e0ef6c183383b9afb7d2b585b889377a4", "input_ids_vector_sha256": "4788bb8645908a9b052d475fabcadcff4704b4cbdbcb446970538ad84efb3a8a", "labels_vector_sha256": "d20df6e326d6cdc5d134e7465bcab98fcdf00055ecfb489997435dab4a482ad5", "planned_active_tokens": 68060, "realized_active_tokens": 68060, "cumulative_start": 59051939, "cumulative_end": 59119999, "loss_sum": 24516.468048095703, "token_normalized_loss": 0.3602184550116912, "grad_norm_before_clip": 0.09346560388803482, "learning_rates_at_step": { "lora": 2.017855704496241e-06, "row_tokens": 2.017855704496241e-06 }, "learning_rates_after_step": { "lora": 1.9685344383455874e-06, "row_tokens": 1.9685344383455874e-06 } }, { "update_id": 902, "row_count": 9, "row_ids_sha256": "695f6b7a6d4bc10c09bfab8b9ac56a9c1d0ced3e8a5d95823659a099f92a0a61", "input_ids_vector_sha256": "1dab2125d002dca067b6da73cee6b728cf3a68ed61f173e9f1efe58cf3bb00f4", "labels_vector_sha256": "a633cc148fbfc7ff01dd65c04702a9fec0f56e9012153c3697db6d358e342a4d", "planned_active_tokens": 68245, "realized_active_tokens": 68245, "cumulative_start": 59119999, "cumulative_end": 59188244, "loss_sum": 20092.775115966797, "token_normalized_loss": 0.29442120471780786, "grad_norm_before_clip": 0.08762701600790024, "learning_rates_at_step": { "lora": 1.9685344383455874e-06, "row_tokens": 1.9685344383455874e-06 }, "learning_rates_after_step": { "lora": 1.9234459408736584e-06, "row_tokens": 1.9234459408736584e-06 } }, { "update_id": 903, "row_count": 10, "row_ids_sha256": "dc5fbaee1cf18088d5c1cf5a850339a7d3e7a79154db8e47c24ee9acc2551251", "input_ids_vector_sha256": "b8b0ab45492291da7a80e4bcbd2b804f9b2cb255f04fc53cf9cabd4405384d94", "labels_vector_sha256": "bdf2f37e6a0db1ecd506e7f148622c3051f9f39eccc36c0ff224c4bb86b80a66", "planned_active_tokens": 63125, "realized_active_tokens": 63125, "cumulative_start": 59188244, "cumulative_end": 59251369, "loss_sum": 20021.39093017578, "token_normalized_loss": 0.31717054938892325, "grad_norm_before_clip": 0.09549673646688461, "learning_rates_at_step": { "lora": 1.9234459408736584e-06, "row_tokens": 1.9234459408736584e-06 }, "learning_rates_after_step": { "lora": 1.876224386597275e-06, "row_tokens": 1.876224386597275e-06 } }, { "update_id": 904, "row_count": 8, "row_ids_sha256": "fa89acc53740f67f9fdb10c649c0c889f2f2d1c7a2cceea9644a130c47f5462f", "input_ids_vector_sha256": "bf0c5d58a44dc829b686c877c95f7bb6c63a71c979adba304faa96d062e06ee7", "labels_vector_sha256": "43c3d1b56e6882ec7df6fb898bf3c7aac3bfcf5abfa0f7d08f8d9b1164bd1448", "planned_active_tokens": 66894, "realized_active_tokens": 66894, "cumulative_start": 59251369, "cumulative_end": 59318263, "loss_sum": 24167.315673828125, "token_normalized_loss": 0.3612777778848346, "grad_norm_before_clip": 0.0941697210073471, "learning_rates_at_step": { "lora": 1.876224386597275e-06, "row_tokens": 1.876224386597275e-06 }, "learning_rates_after_step": { "lora": 1.8341108425780573e-06, "row_tokens": 1.8341108425780573e-06 } }, { "update_id": 905, "row_count": 13, "row_ids_sha256": "66336c7dd4f3d6ea5b626e21e8770c991a1dda5a86656d92d787cf006750a989", "input_ids_vector_sha256": "12b5c51ce0be48933a179d0d9ba22db523cc33eb63342f4455d2af6c6c8eb71c", "labels_vector_sha256": "f6a628cda9d28d5ca5318de5927d69087433b5250be466c03c29b6c050692002", "planned_active_tokens": 60358, "realized_active_tokens": 60358, "cumulative_start": 59318263, "cumulative_end": 59378621, "loss_sum": 17465.155059814453, "token_normalized_loss": 0.2893594065378981, "grad_norm_before_clip": 0.09163742512464523, "learning_rates_at_step": { "lora": 1.8341108425780573e-06, "row_tokens": 1.8341108425780573e-06 }, "learning_rates_after_step": { "lora": 1.7812583140442873e-06, "row_tokens": 1.7812583140442873e-06 } }, { "update_id": 906, "row_count": 11, "row_ids_sha256": "0f1f6660c4d77ee0d046a9f32dbb5d166aab29f8b6a081b178d1035babf0abd5", "input_ids_vector_sha256": "4c19bdad35903fcfb345a2826114fa3ebd92d92a5db0e9194a8561553c055c90", "labels_vector_sha256": "f1fe9f4a41b3184d3aa178155082ecbecb54eb2f654016e374c8568fc15bdc2d", "planned_active_tokens": 76720, "realized_active_tokens": 76720, "cumulative_start": 59378621, "cumulative_end": 59455341, "loss_sum": 21416.529052734375, "token_normalized_loss": 0.2791518385392906, "grad_norm_before_clip": 0.07830382138490677, "learning_rates_at_step": { "lora": 1.7812583140442873e-06, "row_tokens": 1.7812583140442873e-06 }, "learning_rates_after_step": { "lora": 1.7449777539961464e-06, "row_tokens": 1.7449777539961464e-06 } }, { "update_id": 907, "row_count": 6, "row_ids_sha256": "b54dc653113e2e7699f26ee22a8698fbc284e1552b5ffa50e82f36cac9d22b7b", "input_ids_vector_sha256": "f7594f36bb41aa203fb3403bf2c725466507c2fe02db7e601db9c7d505337b58", "labels_vector_sha256": "1a7dfacd7b6b695a8d3d0b961814fa3662bc0140a93c0cf301d6a8ef7e75c03c", "planned_active_tokens": 53313, "realized_active_tokens": 53313, "cumulative_start": 59455341, "cumulative_end": 59508654, "loss_sum": 17892.392944335938, "token_normalized_loss": 0.3356103191404711, "grad_norm_before_clip": 0.10337486118078232, "learning_rates_at_step": { "lora": 1.7449777539961464e-06, "row_tokens": 1.7449777539961464e-06 }, "learning_rates_after_step": { "lora": 1.7015637755087798e-06, "row_tokens": 1.7015637755087798e-06 } }, { "update_id": 908, "row_count": 9, "row_ids_sha256": "4f5ee2036dc0530a8610ca93b72ed9327c8d77538967ebdadaf1f9f187b1861a", "input_ids_vector_sha256": "3ac8040bb1f0126378dbe6772d651f0479875dce403e32440f90c12f4c8d5058", "labels_vector_sha256": "210f8d83fe3c9bb5da06f56d55a74c972479390636ea67a7135e26f9a81ff0bd", "planned_active_tokens": 64516, "realized_active_tokens": 64516, "cumulative_start": 59508654, "cumulative_end": 59573170, "loss_sum": 24653.24395751953, "token_normalized_loss": 0.38212604559364394, "grad_norm_before_clip": 0.09160492569208145, "learning_rates_at_step": { "lora": 1.7015637755087798e-06, "row_tokens": 1.7015637755087798e-06 }, "learning_rates_after_step": { "lora": 1.6579979236044375e-06, "row_tokens": 1.6579979236044375e-06 } }, { "update_id": 909, "row_count": 10, "row_ids_sha256": "d69cbd112de078170af8fdf6ad45ba441b6c9c90c63cb043a5d61d52e0baf54a", "input_ids_vector_sha256": "aea7c73c5d1632d6acd7a915f0e5ad401ee7174490ccac59e8791278d85e8ce9", "labels_vector_sha256": "98ae8cc81543df523434abd81b5f6cb6f0e27621c00be76de24aaac9514677eb", "planned_active_tokens": 65560, "realized_active_tokens": 65560, "cumulative_start": 59573170, "cumulative_end": 59638730, "loss_sum": 20035.483276367188, "token_normalized_loss": 0.30560529707698575, "grad_norm_before_clip": 0.08828941732645035, "learning_rates_at_step": { "lora": 1.6579979236044375e-06, "row_tokens": 1.6579979236044375e-06 }, "learning_rates_after_step": { "lora": 1.6078002508589263e-06, "row_tokens": 1.6078002508589263e-06 } }, { "update_id": 910, "row_count": 11, "row_ids_sha256": "9c60191bb755c3cd14dfe32322b8f689828a5736cd26979543dffdd1c8570036", "input_ids_vector_sha256": "7eb573bfa5dfb04e559689e22499a7d9a480861ac348fbd3951b5ed6d8de70eb", "labels_vector_sha256": "eafb13a4c2193c0a53bd6f355bb57062f4f0aaa16f1abff96ba1d92873a7f707", "planned_active_tokens": 76599, "realized_active_tokens": 76599, "cumulative_start": 59638730, "cumulative_end": 59715329, "loss_sum": 23042.66552734375, "token_normalized_loss": 0.3008220150046835, "grad_norm_before_clip": 0.07973472028970718, "learning_rates_at_step": { "lora": 1.6078002508589263e-06, "row_tokens": 1.6078002508589263e-06 }, "learning_rates_after_step": { "lora": 1.57276374244702e-06, "row_tokens": 1.57276374244702e-06 } }, { "update_id": 911, "row_count": 13, "row_ids_sha256": "5debaf74be43dd1adcae5829e5f7199222a82d4463036ed52f896f6602739f5f", "input_ids_vector_sha256": "96e2ce32dc9d8e22fb179cd723ff9be373c0b9932729d0fa2ac403ad9fc610a7", "labels_vector_sha256": "3cb30dedf9049a8a97254e4b2c4b2365b62e602d2dbadbd772064f782235515d", "planned_active_tokens": 54163, "realized_active_tokens": 54163, "cumulative_start": 59715329, "cumulative_end": 59769492, "loss_sum": 17316.80972290039, "token_normalized_loss": 0.31971659108432676, "grad_norm_before_clip": 0.09663283824920654, "learning_rates_at_step": { "lora": 1.57276374244702e-06, "row_tokens": 1.57276374244702e-06 }, "learning_rates_after_step": { "lora": 1.5273947590380088e-06, "row_tokens": 1.5273947590380088e-06 } }, { "update_id": 912, "row_count": 13, "row_ids_sha256": "3bcab9bf313efa75b8a60899581a2cd76403e7fc6f11fe43709843ca36232caa", "input_ids_vector_sha256": "d893669a98af654c821731367a911ba49db97617df3b7fa056cc28c50f796e58", "labels_vector_sha256": "2b9ec6914183b6eb06d3c20051e0d94e87dd76b26cd67303a0ea1ae0829fab65", "planned_active_tokens": 71026, "realized_active_tokens": 71026, "cumulative_start": 59769492, "cumulative_end": 59840518, "loss_sum": 23208.505828857422, "token_normalized_loss": 0.326760704937029, "grad_norm_before_clip": 0.0871066302061081, "learning_rates_at_step": { "lora": 1.5273947590380088e-06, "row_tokens": 1.5273947590380088e-06 }, "learning_rates_after_step": { "lora": 1.488740258469995e-06, "row_tokens": 1.488740258469995e-06 } }, { "update_id": 913, "row_count": 10, "row_ids_sha256": "00f693e6274657e36a3ed181e1ef85f0a7d3ccfa186d2938f08195c003856137", "input_ids_vector_sha256": "e26a45e58a8fd41f847a9e470c8f1a4f94ebe8ec7736dd145bb0f796739d9f88", "labels_vector_sha256": "82de7b9e21206a64860fde34d0b52f9a7a45208783e533740912c01f1b6708b4", "planned_active_tokens": 61338, "realized_active_tokens": 61338, "cumulative_start": 59840518, "cumulative_end": 59901856, "loss_sum": 20576.556274414062, "token_normalized_loss": 0.3354618062932287, "grad_norm_before_clip": 0.09357845783233643, "learning_rates_at_step": { "lora": 1.488740258469995e-06, "row_tokens": 1.488740258469995e-06 }, "learning_rates_after_step": { "lora": 1.4445384188234601e-06, "row_tokens": 1.4445384188234601e-06 } }, { "update_id": 914, "row_count": 9, "row_ids_sha256": "c35c28a513f05d9f8d6bb77f798b4201353272310c0b99ed7278533cfd81728d", "input_ids_vector_sha256": "2943e2744edb3cb13a2f1c780a9d82c55cc7d2d53debce1b829d0f73bfd90ed9", "labels_vector_sha256": "a81c5d599ba032c448c3e556da4df003a19638227f422353f9ab8049e3a28ede", "planned_active_tokens": 71110, "realized_active_tokens": 71110, "cumulative_start": 59901856, "cumulative_end": 59972966, "loss_sum": 25358.72186279297, "token_normalized_loss": 0.35661259826737407, "grad_norm_before_clip": 0.09069767594337463, "learning_rates_at_step": { "lora": 1.4445384188234601e-06, "row_tokens": 1.4445384188234601e-06 }, "learning_rates_after_step": { "lora": 1.407122727173571e-06, "row_tokens": 1.407122727173571e-06 } }, { "update_id": 915, "row_count": 8, "row_ids_sha256": "27c462f70bdb56689bda9b4c8a80fbc88d66c7c8b29ea15091fd388d389e167f", "input_ids_vector_sha256": "ecac60623775479d2f46459e1e43acd840663771338688410d343eb3e4129b09", "labels_vector_sha256": "85ab926430663f409687a1f7fbe551373334e071b5d0f8e30578eee63de0e07d", "planned_active_tokens": 61035, "realized_active_tokens": 61035, "cumulative_start": 59972966, "cumulative_end": 60034001, "loss_sum": 19013.928985595703, "token_normalized_loss": 0.3115250100040256, "grad_norm_before_clip": 0.09508784860372543, "learning_rates_at_step": { "lora": 1.407122727173571e-06, "row_tokens": 1.407122727173571e-06 }, "learning_rates_after_step": { "lora": 1.3665926669719998e-06, "row_tokens": 1.3665926669719998e-06 } }, { "update_id": 916, "row_count": 9, "row_ids_sha256": "07b278c2330fa9c1e21dd309a331214f8696c4fa9c64ab84fb42d682fb660e48", "input_ids_vector_sha256": "e1eecfb6244adb22ee7900697c264c6b0f71496308618ce0feef23e410460354", "labels_vector_sha256": "3ea528897dcc5c0cb0bd0ab860265e975b117f970c775595501666036e544838", "planned_active_tokens": 67025, "realized_active_tokens": 67025, "cumulative_start": 60034001, "cumulative_end": 60101026, "loss_sum": 19782.883758544922, "token_normalized_loss": 0.29515678863923794, "grad_norm_before_clip": 0.09004718065261841, "learning_rates_at_step": { "lora": 1.3665926669719998e-06, "row_tokens": 1.3665926669719998e-06 }, "learning_rates_after_step": { "lora": 1.3266621668307611e-06, "row_tokens": 1.3266621668307611e-06 } }, { "update_id": 917, "row_count": 9, "row_ids_sha256": "87a32be45658631881a7b6cc1d21b82997a6bf87925b3531b5d6e7a331641036", "input_ids_vector_sha256": "ea612549e5430292e3dcc7caf45efc12ab43ac7eb068d2ed519a6b6b2b6d2a1d", "labels_vector_sha256": "c306995a863b337924605f398a7cf037acf2f17603698cfd067135ea5562d959", "planned_active_tokens": 66999, "realized_active_tokens": 66999, "cumulative_start": 60101026, "cumulative_end": 60168025, "loss_sum": 23175.695556640625, "token_normalized_loss": 0.3459110666821986, "grad_norm_before_clip": 0.1136465072631836, "learning_rates_at_step": { "lora": 1.3266621668307611e-06, "row_tokens": 1.3266621668307611e-06 }, "learning_rates_after_step": { "lora": 1.2867569248280752e-06, "row_tokens": 1.2867569248280752e-06 } }, { "update_id": 918, "row_count": 7, "row_ids_sha256": "fc29ba5788ca1c711dde7495d40ff7ae9c9849eb12764bc5441b88ef331aad34", "input_ids_vector_sha256": "aa5fbf8f11d0bff2fefc32b7d9fff2e048869526583ebff8794b1fc48db16b21", "labels_vector_sha256": "794ea0d5800918e01401b4433c085d8ee52554f0fac131d49a315e64b53bc4ee", "planned_active_tokens": 67958, "realized_active_tokens": 67958, "cumulative_start": 60168025, "cumulative_end": 60235983, "loss_sum": 21646.711059570312, "token_normalized_loss": 0.31853072573604746, "grad_norm_before_clip": 0.08620444685220718, "learning_rates_at_step": { "lora": 1.2867569248280752e-06, "row_tokens": 1.2867569248280752e-06 }, "learning_rates_after_step": { "lora": 1.2531811550714035e-06, "row_tokens": 1.2531811550714035e-06 } }, { "update_id": 919, "row_count": 8, "row_ids_sha256": "c8c4a40dd113e85be0a6acb48eb18a020f675c2752f2701ccbabd10b6ec6c107", "input_ids_vector_sha256": "39a5816e5b9eae61dcbc6b853e99c6f49f496c8dd388d3ef43b70d95e9f8dcf4", "labels_vector_sha256": "a9bc1362ef72fb2a3fc4b13e54cbc556ea54e8b51117d74d4b73baa2ecbc7760", "planned_active_tokens": 57989, "realized_active_tokens": 57989, "cumulative_start": 60235983, "cumulative_end": 60293972, "loss_sum": 22053.606964111328, "token_normalized_loss": 0.38030672996794784, "grad_norm_before_clip": 0.10270209610462189, "learning_rates_at_step": { "lora": 1.2531811550714035e-06, "row_tokens": 1.2531811550714035e-06 }, "learning_rates_after_step": { "lora": 1.2121504940248219e-06, "row_tokens": 1.2121504940248219e-06 } }, { "update_id": 920, "row_count": 11, "row_ids_sha256": "dce927da83124ed64e365809a6255bf5d6b5c7a488212c43681b5cce3e090b5d", "input_ids_vector_sha256": "479a496df3e48ee5950cda0eb443db0a07c734eb466296c0893e4ef9ee565c88", "labels_vector_sha256": "8be01edaadeecf710bd79107252aef776ca9e027c3bfaae210e25c72b6fb8224", "planned_active_tokens": 71916, "realized_active_tokens": 71916, "cumulative_start": 60293972, "cumulative_end": 60365888, "loss_sum": 23415.542205810547, "token_normalized_loss": 0.3255957256495154, "grad_norm_before_clip": 0.08713755011558533, "learning_rates_at_step": { "lora": 1.2121504940248219e-06, "row_tokens": 1.2121504940248219e-06 }, "learning_rates_after_step": { "lora": 1.1743266502858618e-06, "row_tokens": 1.1743266502858618e-06 } }, { "update_id": 921, "row_count": 8, "row_ids_sha256": "ad127f08929b055e08635d0859ff65a7f5317672f5b17d666d377d768a7f5674", "input_ids_vector_sha256": "6dacd576b507c96d9677735812c1aecd98e7c845c7044221801dacf5a7c93c36", "labels_vector_sha256": "71af13344f68c91a0ce3a657482af3086b1adac0f68afffd48a284f357196737", "planned_active_tokens": 67368, "realized_active_tokens": 67368, "cumulative_start": 60365888, "cumulative_end": 60433256, "loss_sum": 23050.1845703125, "token_normalized_loss": 0.34215331567379914, "grad_norm_before_clip": 0.09397446364164352, "learning_rates_at_step": { "lora": 1.1743266502858618e-06, "row_tokens": 1.1743266502858618e-06 }, "learning_rates_after_step": { "lora": 1.1419288723554023e-06, "row_tokens": 1.1419288723554023e-06 } }, { "update_id": 922, "row_count": 8, "row_ids_sha256": "3c1001a7d0f329c9e8ec765db650a21f439397abea25a62ba6c56ef60cf432e6", "input_ids_vector_sha256": "1bc0394b70227893200e2d7f9946ef3cd81b826c6e6d1cf661deb3d0f626c734", "labels_vector_sha256": "270dc4ad10e60eaeb4742b892d935e3937c3ba57aa59ffba255f2bc67f6c9641", "planned_active_tokens": 58561, "realized_active_tokens": 58561, "cumulative_start": 60433256, "cumulative_end": 60491817, "loss_sum": 18805.38949584961, "token_normalized_loss": 0.3211248014181727, "grad_norm_before_clip": 0.0963272675871849, "learning_rates_at_step": { "lora": 1.1419288723554023e-06, "row_tokens": 1.1419288723554023e-06 }, "learning_rates_after_step": { "lora": 1.1052837685585293e-06, "row_tokens": 1.1052837685585293e-06 } }, { "update_id": 923, "row_count": 7, "row_ids_sha256": "67002edfbb40344f391ec13ae39daa40bcc498fae5b9c4aa8f010ddb8047031e", "input_ids_vector_sha256": "78a1ec62a7928027db72a4b667e9c880f1744a005bc88888cff5399276527ea0", "labels_vector_sha256": "1ef018b216190b1980f974b3bc13e36f9dbcd2d5d9edefefc28a27a09b82a394", "planned_active_tokens": 67237, "realized_active_tokens": 67237, "cumulative_start": 60491817, "cumulative_end": 60559054, "loss_sum": 22719.76953125, "token_normalized_loss": 0.3379057591988042, "grad_norm_before_clip": 0.09088977426290512, "learning_rates_at_step": { "lora": 1.1052837685585293e-06, "row_tokens": 1.1052837685585293e-06 }, "learning_rates_after_step": { "lora": 1.069535524301518e-06, "row_tokens": 1.069535524301518e-06 } }, { "update_id": 924, "row_count": 10, "row_ids_sha256": "0fe54155ac8cf30e1e4ff0e7fefb398fe17672f194a977cfeeaf51fa91a1ddcb", "input_ids_vector_sha256": "9d490bd1e13509ceb80589336a8e1dff4f060c7a2d0c3f5c620ea96d2a9d7bc6", "labels_vector_sha256": "d276569d26bab556d3c24a22d53ca0106a940176d27d9b6db5588fbd2720570e", "planned_active_tokens": 66662, "realized_active_tokens": 66662, "cumulative_start": 60559054, "cumulative_end": 60625716, "loss_sum": 22831.35922241211, "token_normalized_loss": 0.3424943629415875, "grad_norm_before_clip": 0.09178228676319122, "learning_rates_at_step": { "lora": 1.069535524301518e-06, "row_tokens": 1.069535524301518e-06 }, "learning_rates_after_step": { "lora": 1.03352757798445e-06, "row_tokens": 1.03352757798445e-06 } }, { "update_id": 925, "row_count": 9, "row_ids_sha256": "6131fdc41465c97c701419428642585cac2c3958a77fbcb69f0adef4b3b16f3d", "input_ids_vector_sha256": "0c74899a6c14a88d499ac976bd99ec6d565a21c2e288fb361ae6e190d6b727a8", "labels_vector_sha256": "41ff3e92eda0c060dc48f0e029395819a594e123d9ab1c4c3e00b1980f826749", "planned_active_tokens": 68270, "realized_active_tokens": 68270, "cumulative_start": 60625716, "cumulative_end": 60693986, "loss_sum": 22087.44989013672, "token_normalized_loss": 0.32353083184615083, "grad_norm_before_clip": 0.08935601264238358, "learning_rates_at_step": { "lora": 1.03352757798445e-06, "row_tokens": 1.03352757798445e-06 }, "learning_rates_after_step": { "lora": 1.0017827401606283e-06, "row_tokens": 1.0017827401606283e-06 } }, { "update_id": 926, "row_count": 8, "row_ids_sha256": "2f5def53a9dc7f7768aa0a516e1b95c5647626add991bf035e9338d7bdbbe935", "input_ids_vector_sha256": "03046b82bbd9963fb9276fd208f76c8d98aa74a960f5da6492ea3f8d604591b2", "labels_vector_sha256": "56ea57011502be83f7a1f1d9fded3b3d3c289e309fb13f996d26b534cba5e6cf", "planned_active_tokens": 61170, "realized_active_tokens": 61170, "cumulative_start": 60693986, "cumulative_end": 60755156, "loss_sum": 22534.658660888672, "token_normalized_loss": 0.36839396208743946, "grad_norm_before_clip": 0.10036806017160416, "learning_rates_at_step": { "lora": 1.0017827401606283e-06, "row_tokens": 1.0017827401606283e-06 }, "learning_rates_after_step": { "lora": 9.67807252600833e-07, "row_tokens": 9.67807252600833e-07 } }, { "update_id": 927, "row_count": 9, "row_ids_sha256": "bdb4eb1efacbfd45558e1cdd5806a6490601ea7a641a70f5a6c771b2c13398eb", "input_ids_vector_sha256": "2f993c41aaca0d6ce79695145476afaefe9d2a2021e2cfafa42d7a3877686e71", "labels_vector_sha256": "1b3412d70e1a6ca947be2cb36ca2a497a53fe25d59e1e9ccbdd54b533a1d4301", "planned_active_tokens": 66541, "realized_active_tokens": 66541, "cumulative_start": 60755156, "cumulative_end": 60821697, "loss_sum": 20905.856689453125, "token_normalized_loss": 0.3141800797922052, "grad_norm_before_clip": 0.09195848554372787, "learning_rates_at_step": { "lora": 9.67807252600833e-07, "row_tokens": 9.67807252600833e-07 }, "learning_rates_after_step": { "lora": 9.330451064531675e-07, "row_tokens": 9.330451064531675e-07 } }, { "update_id": 928, "row_count": 9, "row_ids_sha256": "f504928cb141755c43688a6015ce2c349c9ce127c132bd6fc28281df6d09d306", "input_ids_vector_sha256": "fd587ab99b093a92b1a190ea123b555602bdb4c09adc98828e316a8a30a5d5ee", "labels_vector_sha256": "350fc24f3a52d9ec8714cb9d4181d7e4fe19c485a08de92ffeb9d51a83f573af", "planned_active_tokens": 69290, "realized_active_tokens": 69290, "cumulative_start": 60821697, "cumulative_end": 60890987, "loss_sum": 22577.66815185547, "token_normalized_loss": 0.32584309643318615, "grad_norm_before_clip": 0.08522005379199982, "learning_rates_at_step": { "lora": 9.330451064531675e-07, "row_tokens": 9.330451064531675e-07 }, "learning_rates_after_step": { "lora": 8.999849333755472e-07, "row_tokens": 8.999849333755472e-07 } }, { "update_id": 929, "row_count": 11, "row_ids_sha256": "356cf212c3e974a2a812929c608c9b33e14efeef1dc9aab6786922b66570096e", "input_ids_vector_sha256": "b097a3aba92087a9d16bdf56d12e52404ce007f6558ad45e30003c5368e24127", "labels_vector_sha256": "8b282c6b7dc095fe9ec5e895eb75f01e376ad98d8a424381e070bd0acdb773d5", "planned_active_tokens": 67094, "realized_active_tokens": 67094, "cumulative_start": 60890987, "cumulative_end": 60958081, "loss_sum": 19429.479614257812, "token_normalized_loss": 0.28958594828535805, "grad_norm_before_clip": 0.115513876080513, "learning_rates_at_step": { "lora": 8.999849333755472e-07, "row_tokens": 8.999849333755472e-07 }, "learning_rates_after_step": { "lora": 8.723873439569708e-07, "row_tokens": 8.723873439569708e-07 } }, { "update_id": 930, "row_count": 8, "row_ids_sha256": "4ac04e4470c7034dd505a4e47314bf8661a40569c315ce32bc619b7517811a8b", "input_ids_vector_sha256": "37ef2e817ff522a7fdd5946d739f20a60fe8d41e703ddb49b44cf0c1826ffa16", "labels_vector_sha256": "eaef705c4ed3f3ad6128145ff053838b34f03887ec361d84bdf08b7988c9f1df", "planned_active_tokens": 56949, "realized_active_tokens": 56949, "cumulative_start": 60958081, "cumulative_end": 61015030, "loss_sum": 19173.477661132812, "token_normalized_loss": 0.3366780393182113, "grad_norm_before_clip": 0.10600507259368896, "learning_rates_at_step": { "lora": 8.723873439569708e-07, "row_tokens": 8.723873439569708e-07 }, "learning_rates_after_step": { "lora": 8.350821512659702e-07, "row_tokens": 8.350821512659702e-07 } }, { "update_id": 931, "row_count": 11, "row_ids_sha256": "6898f8d15494fbf0a978eb5be012e93d82d183df6f79baf2699ae268a76fc450", "input_ids_vector_sha256": "b3b775673ae428bea6f88d6a35b4a17f7e3d92bda492bc6a5d40f838e80fc0fc", "labels_vector_sha256": "3723fd2bfdd5890fc21d43ada1ececf782c53b53e6bcf623307230a2edc65648", "planned_active_tokens": 78420, "realized_active_tokens": 78420, "cumulative_start": 61015030, "cumulative_end": 61093450, "loss_sum": 26427.46646118164, "token_normalized_loss": 0.3369990622440913, "grad_norm_before_clip": 0.0858827531337738, "learning_rates_at_step": { "lora": 8.350821512659702e-07, "row_tokens": 8.350821512659702e-07 }, "learning_rates_after_step": { "lora": 8.100612213968739e-07, "row_tokens": 8.100612213968739e-07 } }, { "update_id": 932, "row_count": 6, "row_ids_sha256": "a762446beaa41be3af79bfb22cb903cec7a4e4ca86a9d97ebf80cccad5fb7cca", "input_ids_vector_sha256": "88e1d7d67e9a1a815ec7287414aba5cb1507b0add165b6af238606bf68eb313e", "labels_vector_sha256": "64c34b335e5e9bea8cbba3ca2491f4b7befa2fc180dab976d7159c39692b0fa8", "planned_active_tokens": 53574, "realized_active_tokens": 53574, "cumulative_start": 61093450, "cumulative_end": 61147024, "loss_sum": 18992.008361816406, "token_normalized_loss": 0.35450047339784985, "grad_norm_before_clip": 0.10327225923538208, "learning_rates_at_step": { "lora": 8.100612213968739e-07, "row_tokens": 8.100612213968739e-07 }, "learning_rates_after_step": { "lora": 7.805912189812691e-07, "row_tokens": 7.805912189812691e-07 } }, { "update_id": 933, "row_count": 12, "row_ids_sha256": "ccff58390922a8e003b9ce2556d3a5e70a4af65e58a1a6e22727eb9233935d87", "input_ids_vector_sha256": "f5a1829d47b0ccbcb75e2721f7a479a0ac1682a1f80242307adff262a286b491", "labels_vector_sha256": "dd2e49df0d5a59c07e181c63e4048cabfb6f5c416e87fbeeb47ad30f33351312", "planned_active_tokens": 64164, "realized_active_tokens": 64164, "cumulative_start": 61147024, "cumulative_end": 61211188, "loss_sum": 18608.333053588867, "token_normalized_loss": 0.29001204808909775, "grad_norm_before_clip": 0.08577881753444672, "learning_rates_at_step": { "lora": 7.805912189812691e-07, "row_tokens": 7.805912189812691e-07 }, "learning_rates_after_step": { "lora": 7.480390122879876e-07, "row_tokens": 7.480390122879876e-07 } }, { "update_id": 934, "row_count": 9, "row_ids_sha256": "83a5dd359007e02d5693328136f32314f4722837d5b50a641e6bf453449d30e8", "input_ids_vector_sha256": "413e20baf86fdedc283e56b4aac9ce76735a83e0ce4169847bc864de84c06f57", "labels_vector_sha256": "148d51a0eee217431b77210cb809023b93373bfa31e4bf80003bf85eb10343e4", "planned_active_tokens": 72288, "realized_active_tokens": 72288, "cumulative_start": 61211188, "cumulative_end": 61283476, "loss_sum": 24758.234252929688, "token_normalized_loss": 0.34249438707572055, "grad_norm_before_clip": 0.0865153893828392, "learning_rates_at_step": { "lora": 7.480390122879876e-07, "row_tokens": 7.480390122879876e-07 }, "learning_rates_after_step": { "lora": 7.199712415097703e-07, "row_tokens": 7.199712415097703e-07 } }, { "update_id": 935, "row_count": 9, "row_ids_sha256": "a1b70530b3e1e036e6a429832d0a658b228ace3484196e5737ec90fcedf18881", "input_ids_vector_sha256": "cbd2552c32a49afb95d1895984c52b26603b501390ea0207f0f9361c4b00a639", "labels_vector_sha256": "a6495f1a29ea38bfa1c3a5717511145ce8ee9ed0b07bee1c68c92fdb8869cc2a", "planned_active_tokens": 63593, "realized_active_tokens": 63593, "cumulative_start": 61283476, "cumulative_end": 61347069, "loss_sum": 22122.27569580078, "token_normalized_loss": 0.34787281140692816, "grad_norm_before_clip": 0.08765775710344315, "learning_rates_at_step": { "lora": 7.199712415097703e-07, "row_tokens": 7.199712415097703e-07 }, "learning_rates_after_step": { "lora": 6.926018715875338e-07, "row_tokens": 6.926018715875338e-07 } }, { "update_id": 936, "row_count": 10, "row_ids_sha256": "3ae785b0f3e81059e42b6182d4b81199b756accabe4427f1804b890d571edc21", "input_ids_vector_sha256": "04f6c676b2b05996c9abecb87422cc3219e79f470f0d6cc30b7c5ad40905a5de", "labels_vector_sha256": "5db382baf8bdef4091161db36358c1ddd2787f7b23834ec4b032285111836715", "planned_active_tokens": 63207, "realized_active_tokens": 63207, "cumulative_start": 61347069, "cumulative_end": 61410276, "loss_sum": 20675.55860900879, "token_normalized_loss": 0.3271086843072569, "grad_norm_before_clip": 0.08879665285348892, "learning_rates_at_step": { "lora": 6.926018715875338e-07, "row_tokens": 6.926018715875338e-07 }, "learning_rates_after_step": { "lora": 6.65247557544929e-07, "row_tokens": 6.65247557544929e-07 } }, { "update_id": 937, "row_count": 9, "row_ids_sha256": "727310fac33e52bc6b9d31ebd1f7cdfbac829300e632d2d8b19ac9052c335741", "input_ids_vector_sha256": "a0475dc5af43c14a440ea612631185dd0c637c5cb3efc948d7701218ca0f5d1e", "labels_vector_sha256": "60d62b2e818e4cb26b02b8ecd6e1ad1237db2920c92f9294e02a2125d6a955ee", "planned_active_tokens": 64424, "realized_active_tokens": 64424, "cumulative_start": 61410276, "cumulative_end": 61474700, "loss_sum": 20732.66421508789, "token_normalized_loss": 0.321815848365328, "grad_norm_before_clip": 0.08658552914857864, "learning_rates_at_step": { "lora": 6.65247557544929e-07, "row_tokens": 6.65247557544929e-07 }, "learning_rates_after_step": { "lora": 6.384069734907516e-07, "row_tokens": 6.384069734907516e-07 } }, { "update_id": 938, "row_count": 10, "row_ids_sha256": "c533631d59bfad8dc0179044aa9034c95ed934c7322f4b483901be49dbc18251", "input_ids_vector_sha256": "e26c268fc403caf2fa9aa337d2614edf30ee9db837243a4df896c5b002cc31ad", "labels_vector_sha256": "f784ded76b0329a66d07c63c6181d683d76a27a74bb6cc92a8141bd9ac27a1d9", "planned_active_tokens": 64506, "realized_active_tokens": 64506, "cumulative_start": 61474700, "cumulative_end": 61539206, "loss_sum": 22612.630004882812, "token_normalized_loss": 0.3505508015515272, "grad_norm_before_clip": 0.0878262147307396, "learning_rates_at_step": { "lora": 6.384069734907516e-07, "row_tokens": 6.384069734907516e-07 }, "learning_rates_after_step": { "lora": 6.120325023058926e-07, "row_tokens": 6.120325023058926e-07 } }, { "update_id": 939, "row_count": 15, "row_ids_sha256": "674f047f3f9b5dedadfb8eb0e8390491471b41285b13eb478dbec4c8335cb801", "input_ids_vector_sha256": "ee86272881a706b7adc6cd0c73619b7fc691beda3837b4e18adfb81ea9e3b9c4", "labels_vector_sha256": "5772db5d74c6f09930c8b56420af9853f9112cf118f51ca71e373aa7249f55f2", "planned_active_tokens": 64712, "realized_active_tokens": 64712, "cumulative_start": 61539206, "cumulative_end": 61603918, "loss_sum": 20601.458938598633, "token_normalized_loss": 0.31835608447581026, "grad_norm_before_clip": 0.08906436711549759, "learning_rates_at_step": { "lora": 6.120325023058926e-07, "row_tokens": 6.120325023058926e-07 }, "learning_rates_after_step": { "lora": 5.858779147263737e-07, "row_tokens": 5.858779147263737e-07 } }, { "update_id": 940, "row_count": 12, "row_ids_sha256": "23362e91483381aecfbb8278183277644bb8832e645764a65e92998601876972", "input_ids_vector_sha256": "b21a149e5b642dca94ef896b1fca51b913f2ce56986e764946d446d945a47cee", "labels_vector_sha256": "2dccfb143772dbb69c40a677e4379001048ce95132a3262bcae87c238611000d", "planned_active_tokens": 65556, "realized_active_tokens": 65556, "cumulative_start": 61603918, "cumulative_end": 61669474, "loss_sum": 22021.43814086914, "token_normalized_loss": 0.33591796541688235, "grad_norm_before_clip": 0.08953327685594559, "learning_rates_at_step": { "lora": 5.858779147263737e-07, "row_tokens": 5.858779147263737e-07 }, "learning_rates_after_step": { "lora": 5.575309815839314e-07, "row_tokens": 5.575309815839314e-07 } }, { "update_id": 941, "row_count": 18, "row_ids_sha256": "709f09a40308ef4344f6ea23f73935ebacd179cad9613c5e197f58b008404c33", "input_ids_vector_sha256": "5ba0192f7b3d6065deb6ae363c13e0d9385676da3dae7483f80b6382e216003d", "labels_vector_sha256": "49a97bea878d91bc8959e0bee4320d37bb44014361d5b847e8b377665a267b9f", "planned_active_tokens": 72716, "realized_active_tokens": 72716, "cumulative_start": 61669474, "cumulative_end": 61742190, "loss_sum": 21102.635986328125, "token_normalized_loss": 0.2902062267771622, "grad_norm_before_clip": 0.07526785880327225, "learning_rates_at_step": { "lora": 5.575309815839314e-07, "row_tokens": 5.575309815839314e-07 }, "learning_rates_after_step": { "lora": 5.343130698928111e-07, "row_tokens": 5.343130698928111e-07 } }, { "update_id": 942, "row_count": 11, "row_ids_sha256": "e3d0dd0bd872b85fcc8a08116d1fab688bcab624217f70356ca5d23dedefac8d", "input_ids_vector_sha256": "bdd24031e469df107940d496c273d2132c4ad16b48d8a6fba787072dc121f611", "labels_vector_sha256": "baf7d6b92598d52904bbacd631ee1b42d5f4ecac89cef3c3c818801eb48a54b3", "planned_active_tokens": 60940, "realized_active_tokens": 60940, "cumulative_start": 61742190, "cumulative_end": 61803130, "loss_sum": 20064.852249145508, "token_normalized_loss": 0.3292558623095751, "grad_norm_before_clip": 0.08940713107585907, "learning_rates_at_step": { "lora": 5.343130698928111e-07, "row_tokens": 5.343130698928111e-07 }, "learning_rates_after_step": { "lora": 5.107065137460565e-07, "row_tokens": 5.107065137460565e-07 } }, { "update_id": 943, "row_count": 10, "row_ids_sha256": "6f56e07d3667426a4035971123d5cdca4a1d936263f268de31ae52f3a75e5992", "input_ids_vector_sha256": "819b31dfb5accce063ad40d4b937e09942ca40f34cbb745b3cb2f9260553baa0", "labels_vector_sha256": "9c3a21776127b0a72e227efc49f0c2d1097e4218954fefaae3677631927ae2d3", "planned_active_tokens": 63326, "realized_active_tokens": 63326, "cumulative_start": 61803130, "cumulative_end": 61866456, "loss_sum": 18827.01919555664, "token_normalized_loss": 0.2973031487154824, "grad_norm_before_clip": 0.08402731269598007, "learning_rates_at_step": { "lora": 5.107065137460565e-07, "row_tokens": 5.107065137460565e-07 }, "learning_rates_after_step": { "lora": 4.866585351079423e-07, "row_tokens": 4.866585351079423e-07 } }, { "update_id": 944, "row_count": 13, "row_ids_sha256": "fdb8603e028411d505f17bd5aa45e3129e55bf11f0c469507e73cb1fc98b32ab", "input_ids_vector_sha256": "479725a6ef0f0eeeda1b3044f6087547cd2bdd6f7cf700407c1ff7358efc0bfc", "labels_vector_sha256": "302fc60dd7f72699d2b2b1fac2d3d4580b44afe717c7a705f577576448a489e0", "planned_active_tokens": 66026, "realized_active_tokens": 66026, "cumulative_start": 61866456, "cumulative_end": 61932482, "loss_sum": 18199.94073486328, "token_normalized_loss": 0.2756480891597747, "grad_norm_before_clip": 0.07989832758903503, "learning_rates_at_step": { "lora": 4.866585351079423e-07, "row_tokens": 4.866585351079423e-07 }, "learning_rates_after_step": { "lora": 4.6185130274523646e-07, "row_tokens": 4.6185130274523646e-07 } }, { "update_id": 945, "row_count": 12, "row_ids_sha256": "d74b99720cc8719b990569356cffe52afb89ae795ba47ece62d9faed9c0e37c3", "input_ids_vector_sha256": "cb3d40d1e7d4b75640d90d73922442c5444a2faf41a23f12ac561de88151fba0", "labels_vector_sha256": "840ef5f61df181d12c547192537581ec3fd2233f7ad726ec7ad50c4405e4d316", "planned_active_tokens": 69835, "realized_active_tokens": 69835, "cumulative_start": 61932482, "cumulative_end": 62002317, "loss_sum": 23652.614624023438, "token_normalized_loss": 0.33869284204229166, "grad_norm_before_clip": 0.08454611897468567, "learning_rates_at_step": { "lora": 4.6185130274523646e-07, "row_tokens": 4.6185130274523646e-07 }, "learning_rates_after_step": { "lora": 4.3999376204467146e-07, "row_tokens": 4.3999376204467146e-07 } }, { "update_id": 946, "row_count": 14, "row_ids_sha256": "0336bd6f0fbcf837951e2e2ca73defc7e62db10ceecab9d25aa6c65af411c2b6", "input_ids_vector_sha256": "55635aeb0fa90734012601471776af6fdc60d96fddf525e378d6ffd6432d081c", "labels_vector_sha256": "cfdb8a3e5f6d4ce0a761c29c942bd1e4a542ef34172fc2dfae5772d945b0e212", "planned_active_tokens": 63095, "realized_active_tokens": 63095, "cumulative_start": 62002317, "cumulative_end": 62065412, "loss_sum": 20884.484970092773, "token_normalized_loss": 0.33100063349065334, "grad_norm_before_clip": 0.08863556385040283, "learning_rates_at_step": { "lora": 4.3999376204467146e-07, "row_tokens": 4.3999376204467146e-07 }, "learning_rates_after_step": { "lora": 4.179192084490413e-07, "row_tokens": 4.179192084490413e-07 } }, { "update_id": 947, "row_count": 11, "row_ids_sha256": "0723019307fa8d491b9af860941f84856f03732ee904bf3800123e04782dadaf", "input_ids_vector_sha256": "6f8570fa14955f95fc6265cce6386184fe1a79c7bc0009421f24fbf49f58fe2d", "labels_vector_sha256": "38dc7115f94bb6921627911f444c4ff035e85b8c5f74ca19e7d822d0ca94dfa4", "planned_active_tokens": 65326, "realized_active_tokens": 65326, "cumulative_start": 62065412, "cumulative_end": 62130738, "loss_sum": 19614.673248291016, "token_normalized_loss": 0.30025829299652534, "grad_norm_before_clip": 0.08302415162324905, "learning_rates_at_step": { "lora": 4.179192084490413e-07, "row_tokens": 4.179192084490413e-07 }, "learning_rates_after_step": { "lora": 3.965286968678428e-07, "row_tokens": 3.965286968678428e-07 } }, { "update_id": 948, "row_count": 13, "row_ids_sha256": "538e6b48158b2b617d9a0dfcc540cb7722b48fef400f0ec652b66384a5573dd8", "input_ids_vector_sha256": "55e1907b7780fa1235cf9305abfd3aa3104d5791dde0efb8564538e7487ec7f0", "labels_vector_sha256": "2c2948cdecceaf56dc99fe26d3f6380e5ddbad7d1b0a31632691745adca64903", "planned_active_tokens": 64962, "realized_active_tokens": 64962, "cumulative_start": 62130738, "cumulative_end": 62195700, "loss_sum": 21438.310333251953, "token_normalized_loss": 0.3300130897024715, "grad_norm_before_clip": 0.08498126268386841, "learning_rates_at_step": { "lora": 3.965286968678428e-07, "row_tokens": 3.965286968678428e-07 }, "learning_rates_after_step": { "lora": 3.744130264666357e-07, "row_tokens": 3.744130264666357e-07 } }, { "update_id": 949, "row_count": 15, "row_ids_sha256": "73d57c4755eebd18026db9c623601157b06255b3a9ba95068b3c632b75235d14", "input_ids_vector_sha256": "c89711121e7e3822c89af8e9074ab14e2c1d6567bc70002a4a568fe6d955db09", "labels_vector_sha256": "501837de35dd41085edb459f88d8dd2a5c42053dec7273805d0da196f76578cf", "planned_active_tokens": 69027, "realized_active_tokens": 69027, "cumulative_start": 62195700, "cumulative_end": 62264727, "loss_sum": 21189.04997253418, "token_normalized_loss": 0.3069675630193139, "grad_norm_before_clip": 0.08120466023683548, "learning_rates_at_step": { "lora": 3.744130264666357e-07, "row_tokens": 3.744130264666357e-07 }, "learning_rates_after_step": { "lora": 3.5309581818691595e-07, "row_tokens": 3.5309581818691595e-07 } }, { "update_id": 950, "row_count": 10, "row_ids_sha256": "d83fbd5790ea6eb0e528bf257c577695c72f6147f938f05f90f529c6b1c00eef", "input_ids_vector_sha256": "e4be42c0179fdf42126bb451b365ed1c906cb6536c6f4db89e1c3749fa8890f2", "labels_vector_sha256": "702c966b2cb094ce4281a85435b3ac432a055a75e112a262bfc35c1987e2b90d", "planned_active_tokens": 68485, "realized_active_tokens": 68485, "cumulative_start": 62264727, "cumulative_end": 62333212, "loss_sum": 24308.994903564453, "token_normalized_loss": 0.3549535650662839, "grad_norm_before_clip": 0.08673273772001266, "learning_rates_at_step": { "lora": 3.5309581818691595e-07, "row_tokens": 3.5309581818691595e-07 }, "learning_rates_after_step": { "lora": 3.35752284394808e-07, "row_tokens": 3.35752284394808e-07 } }, { "update_id": 951, "row_count": 7, "row_ids_sha256": "fe51ac86bcf194d015e3131a4a65cdaebd0da19122e52f8f3db348b9ae096200", "input_ids_vector_sha256": "c5d32c4c82be40457e60a480189a18d3e964a62794dbf0d3089c70068f23bffa", "labels_vector_sha256": "e845cd22e2c480a6fc2c05de75ae079f1cb31f20511abd2b16530ba6a5db8a07", "planned_active_tokens": 57254, "realized_active_tokens": 57254, "cumulative_start": 62333212, "cumulative_end": 62390466, "loss_sum": 22350.590850830078, "token_normalized_loss": 0.3903760584558298, "grad_norm_before_clip": 0.09667229652404785, "learning_rates_at_step": { "lora": 3.35752284394808e-07, "row_tokens": 3.35752284394808e-07 }, "learning_rates_after_step": { "lora": 3.1524496093501834e-07, "row_tokens": 3.1524496093501834e-07 } }, { "update_id": 952, "row_count": 15, "row_ids_sha256": "a18ef9db0babd3e96b375032d50a1556c382b070e962b21c8b11705a5daf80d5", "input_ids_vector_sha256": "1e41b6bf0dd2258a61d689defec010350bc71bf4ea86cb87f207f9165c6290b5", "labels_vector_sha256": "33a3edec88d6e05be6e19b7d1a68eb7d935b73677a47833e30951632d284d8f9", "planned_active_tokens": 69635, "realized_active_tokens": 69635, "cumulative_start": 62390466, "cumulative_end": 62460101, "loss_sum": 24452.549530029297, "token_normalized_loss": 0.35115314899158895, "grad_norm_before_clip": 0.08229377865791321, "learning_rates_at_step": { "lora": 3.1524496093501834e-07, "row_tokens": 3.1524496093501834e-07 }, "learning_rates_after_step": { "lora": 2.972824174799271e-07, "row_tokens": 2.972824174799271e-07 } }, { "update_id": 953, "row_count": 13, "row_ids_sha256": "7eb9497bf84d1b39c9b03ffec6bef97ea228da5650ce239fdc6f9a3ba47e0f85", "input_ids_vector_sha256": "3cfeaf0b08e2192a58da52d388d87a5ded68dc17c729173a3e5e91f2f588bf81", "labels_vector_sha256": "0fdc2cd03649630e89ff32bbe55c06888ecedbfd4091ad57eeb46816b2890589", "planned_active_tokens": 62873, "realized_active_tokens": 62873, "cumulative_start": 62460101, "cumulative_end": 62522974, "loss_sum": 20803.295623779297, "token_normalized_loss": 0.3308780497793854, "grad_norm_before_clip": 0.08818762749433517, "learning_rates_at_step": { "lora": 2.972824174799271e-07, "row_tokens": 2.972824174799271e-07 }, "learning_rates_after_step": { "lora": 2.7897423932846666e-07, "row_tokens": 2.7897423932846666e-07 } }, { "update_id": 954, "row_count": 8, "row_ids_sha256": "4dfabc0ad4adc636d7c104a39e53972345082c0a458703719ba754065ca8a2ec", "input_ids_vector_sha256": "91b122c4a1761fd8e07ef0dbac91ae9f56083194a2a2090c2db976030bb32787", "labels_vector_sha256": "d475c4bcfececf92684b1039f6d2f04ebe93105c024bc0c0b7a74affd5a9a4dc", "planned_active_tokens": 66064, "realized_active_tokens": 66064, "cumulative_start": 62522974, "cumulative_end": 62589038, "loss_sum": 23574.521545410156, "token_normalized_loss": 0.3568436901400181, "grad_norm_before_clip": 0.09071685373783112, "learning_rates_at_step": { "lora": 2.7897423932846666e-07, "row_tokens": 2.7897423932846666e-07 }, "learning_rates_after_step": { "lora": 2.60328814108618e-07, "row_tokens": 2.60328814108618e-07 } }, { "update_id": 955, "row_count": 9, "row_ids_sha256": "4a496a71714ff6189ffc0cdd2bb521260cc7257b2938156fc3960082bc96bf7a", "input_ids_vector_sha256": "28e85a072ca6220180eb5494e17f6c891046d6643443c5d697f5fa3c16baa4c1", "labels_vector_sha256": "d6b70c6bceae97adbb29f61b8aac264db40d5d9e4aff2b4e65803f05a80fb674", "planned_active_tokens": 69543, "realized_active_tokens": 69543, "cumulative_start": 62589038, "cumulative_end": 62658581, "loss_sum": 24503.323760986328, "token_normalized_loss": 0.3523478101460439, "grad_norm_before_clip": 0.0861019566655159, "learning_rates_at_step": { "lora": 2.60328814108618e-07, "row_tokens": 2.60328814108618e-07 }, "learning_rates_after_step": { "lora": 2.4444799516568084e-07, "row_tokens": 2.4444799516568084e-07 } }, { "update_id": 956, "row_count": 13, "row_ids_sha256": "a94d0ccad86fce2c2eccc23881d3d15437b067713e96c8846afbee397e066aa9", "input_ids_vector_sha256": "9fe5f66da1f92820c610e344b3f97834a26cd5b29c0f298b07fbb14590088eb3", "labels_vector_sha256": "23adab0dde6d3e3f66ff4473cdc5d76b99bb5153e70e42402060bed999ee1261", "planned_active_tokens": 61217, "realized_active_tokens": 61217, "cumulative_start": 62658581, "cumulative_end": 62719798, "loss_sum": 18834.399673461914, "token_normalized_loss": 0.3076661658274975, "grad_norm_before_clip": 0.08486272394657135, "learning_rates_at_step": { "lora": 2.4444799516568084e-07, "row_tokens": 2.4444799516568084e-07 }, "learning_rates_after_step": { "lora": 2.2642929001498448e-07, "row_tokens": 2.2642929001498448e-07 } }, { "update_id": 957, "row_count": 14, "row_ids_sha256": "da63f2346f830de24b325d11ba83b0b5f1e0b0fed01d06f5b249048b82b010e6", "input_ids_vector_sha256": "498d6a09689d2f8edeb4650a76a66dbab9cf5c41672af4122c4f2e006bdd9512", "labels_vector_sha256": "cac891363dffd507b2f0c0c9d3fc5e56aed2150df62149463916c3254f15f33b", "planned_active_tokens": 71913, "realized_active_tokens": 71913, "cumulative_start": 62719798, "cumulative_end": 62791711, "loss_sum": 24334.03890991211, "token_normalized_loss": 0.33838164045321584, "grad_norm_before_clip": 0.08475325256586075, "learning_rates_at_step": { "lora": 2.2642929001498448e-07, "row_tokens": 2.2642929001498448e-07 }, "learning_rates_after_step": { "lora": 2.1090330325140296e-07, "row_tokens": 2.1090330325140296e-07 } }, { "update_id": 958, "row_count": 12, "row_ids_sha256": "1ff860879f327ccf83772e9d1a165b0ed99aa286163ba88bc0fbe76c68ef0422", "input_ids_vector_sha256": "9afca723a93d945044526366308bfbb72fcbed84295a7235ec77d01e6a3104bd", "labels_vector_sha256": "d32747da87fa157a8269f4ba29338610e5e781a637f164b03ce313249ced3b18", "planned_active_tokens": 64290, "realized_active_tokens": 64290, "cumulative_start": 62791711, "cumulative_end": 62856001, "loss_sum": 25494.551147460938, "token_normalized_loss": 0.3965554697069675, "grad_norm_before_clip": 0.09138238430023193, "learning_rates_at_step": { "lora": 2.1090330325140296e-07, "row_tokens": 2.1090330325140296e-07 }, "learning_rates_after_step": { "lora": 1.9715532430818474e-07, "row_tokens": 1.9715532430818474e-07 } }, { "update_id": 959, "row_count": 7, "row_ids_sha256": "0eb09e3203cbc2bf2514499bfea821a4bf3df713e36dfc35a5c12c6a2624dd4e", "input_ids_vector_sha256": "53533f0d900d9b20f56d33b5147810e14ff5825c814a15262b6769988ede7ca7", "labels_vector_sha256": "b03a0b89c9838e78f60d7bfaaba5a80d0fd2c7a43604fb7f5be3b021ef1ab6d0", "planned_active_tokens": 58929, "realized_active_tokens": 58929, "cumulative_start": 62856001, "cumulative_end": 62914930, "loss_sum": 20901.858459472656, "token_normalized_loss": 0.3546956245562059, "grad_norm_before_clip": 0.09157528728246689, "learning_rates_at_step": { "lora": 1.9715532430818474e-07, "row_tokens": 1.9715532430818474e-07 }, "learning_rates_after_step": { "lora": 1.8031740758165383e-07, "row_tokens": 1.8031740758165383e-07 } }, { "update_id": 960, "row_count": 15, "row_ids_sha256": "d9220d0b35221a09ae9bd647c25715a193d707931caf3570258cd22933efdd19", "input_ids_vector_sha256": "694332b090db964405c5e899c6d139382ded088a9c21abbd2189441f86a771cc", "labels_vector_sha256": "1d2fd4c7bb3568e34fa6e56f69cad7725a8e5b445885cb42f6e235681ea0ec17", "planned_active_tokens": 75043, "realized_active_tokens": 75043, "cumulative_start": 62914930, "cumulative_end": 62989973, "loss_sum": 23477.810821533203, "token_normalized_loss": 0.31285810563987587, "grad_norm_before_clip": 0.0816531702876091, "learning_rates_at_step": { "lora": 1.8031740758165383e-07, "row_tokens": 1.8031740758165383e-07 }, "learning_rates_after_step": { "lora": 1.681486785229669e-07, "row_tokens": 1.681486785229669e-07 } }, { "update_id": 961, "row_count": 11, "row_ids_sha256": "9fa5ce4fe38eb88ecaaca8b543b2f71cce819ff3a89934a5b1d1108e1808057a", "input_ids_vector_sha256": "d7bff51de604e1e6c8264c7e4cfafc1c5525d1fd12dd6dd4ce364b3741b978c4", "labels_vector_sha256": "7b7754018991ef7c32e673d924b047d140a28b06280940a0ec01228bb64dec26", "planned_active_tokens": 56436, "realized_active_tokens": 56436, "cumulative_start": 62989973, "cumulative_end": 63046409, "loss_sum": 18468.01626586914, "token_normalized_loss": 0.3272382214520721, "grad_norm_before_clip": 0.09582436084747314, "learning_rates_at_step": { "lora": 1.681486785229669e-07, "row_tokens": 1.681486785229669e-07 }, "learning_rates_after_step": { "lora": 1.5431157131094997e-07, "row_tokens": 1.5431157131094997e-07 } }, { "update_id": 962, "row_count": 13, "row_ids_sha256": "b6c1e71faf66783c89a48f7f481efaf55ce700f8bdeb390ba74f33dde88bd393", "input_ids_vector_sha256": "944c77a644ecc66b5b78d64cedda2cfac6132742b89bbc0e0cd8414f112c0482", "labels_vector_sha256": "b32480db6b4cecf91212725e712ab14dca971dd74091030a30d73ec04e6612d8", "planned_active_tokens": 66712, "realized_active_tokens": 66712, "cumulative_start": 63046409, "cumulative_end": 63113121, "loss_sum": 21137.449737548828, "token_normalized_loss": 0.3168462905856342, "grad_norm_before_clip": 0.08276130259037018, "learning_rates_at_step": { "lora": 1.5431157131094997e-07, "row_tokens": 1.5431157131094997e-07 }, "learning_rates_after_step": { "lora": 1.4163178844441294e-07, "row_tokens": 1.4163178844441294e-07 } }, { "update_id": 963, "row_count": 12, "row_ids_sha256": "a76f8c03062885be88c20b48c76928810628d83141ce8f763de05f949dd5e04b", "input_ids_vector_sha256": "a6e042067135dbe5839ef2faa970c4810637c07a6ecc724f9e061331ce095c23", "labels_vector_sha256": "8531ad5bf048fea6719dccc9a3bf6576fa81eb5da25fb2787ea3c5a0a5a78949", "planned_active_tokens": 63808, "realized_active_tokens": 63808, "cumulative_start": 63113121, "cumulative_end": 63176929, "loss_sum": 19466.116333007812, "token_normalized_loss": 0.30507328756594493, "grad_norm_before_clip": 0.086124949157238, "learning_rates_at_step": { "lora": 1.4163178844441294e-07, "row_tokens": 1.4163178844441294e-07 }, "learning_rates_after_step": { "lora": 1.2880951234377492e-07, "row_tokens": 1.2880951234377492e-07 } }, { "update_id": 964, "row_count": 9, "row_ids_sha256": "fe073953c0180fe2596847e261712fa1f3d45f8300e72ecadc318d837d2c07cb", "input_ids_vector_sha256": "c47fc0442b7d37529a7028bfd9be91bc817e7c14d1e311d886dc85d287e00b35", "labels_vector_sha256": "280678785c6d8417d5fad31d8f55f7702da67c21ce1e3892d5e97df3f3700099", "planned_active_tokens": 67498, "realized_active_tokens": 67498, "cumulative_start": 63176929, "cumulative_end": 63244427, "loss_sum": 24380.133102416992, "token_normalized_loss": 0.3611978592316364, "grad_norm_before_clip": 0.08777698129415512, "learning_rates_at_step": { "lora": 1.2880951234377492e-07, "row_tokens": 1.2880951234377492e-07 }, "learning_rates_after_step": { "lora": 1.1665388968235546e-07, "row_tokens": 1.1665388968235546e-07 } }, { "update_id": 965, "row_count": 12, "row_ids_sha256": "e8d8537a8946c2d9dc63c44d1b9086973c69e6caccfccbfbe77bdeefc332cf13", "input_ids_vector_sha256": "b06086240d79f4d836a7f44ccf31cd9f6357f7cc5ecbe88926d235c0a7e6c18d", "labels_vector_sha256": "69ef51e3b6e9cacdae3ce2bacd3e5606c95e240e7e0624526380ddeb7fba6613", "planned_active_tokens": 67163, "realized_active_tokens": 67163, "cumulative_start": 63244427, "cumulative_end": 63311590, "loss_sum": 22373.806121826172, "token_normalized_loss": 0.3331269615982933, "grad_norm_before_clip": 0.08428167551755905, "learning_rates_at_step": { "lora": 1.1665388968235546e-07, "row_tokens": 1.1665388968235546e-07 }, "learning_rates_after_step": { "lora": 1.0554272267681021e-07, "row_tokens": 1.0554272267681021e-07 } }, { "update_id": 966, "row_count": 11, "row_ids_sha256": "71285ef4fb3d8fc82377a8bcbf7cc934598beb3ade90b9ca7f02332dfd708592", "input_ids_vector_sha256": "ba66d92c6dd71815d40f9c3133f449d9270bd05646e097cdcdc9301118a94e18", "labels_vector_sha256": "c311b49a004abb22069726da6b5e975f108f651fd67e856130f5ffd911c7dd3a", "planned_active_tokens": 64523, "realized_active_tokens": 64523, "cumulative_start": 63311590, "cumulative_end": 63376113, "loss_sum": 17879.44953918457, "token_normalized_loss": 0.2771019564989937, "grad_norm_before_clip": 0.0801820307970047, "learning_rates_at_step": { "lora": 1.0554272267681021e-07, "row_tokens": 1.0554272267681021e-07 }, "learning_rates_after_step": { "lora": 9.50943645217306e-08, "row_tokens": 9.50943645217306e-08 } }, { "update_id": 967, "row_count": 8, "row_ids_sha256": "bf1eab73b1e387c5f0610585d17059e339e447e42825edcd28188669a00a36b7", "input_ids_vector_sha256": "1148780c9746c2e5ba9192b7d26b403640b25ce7929d78e16b97567ac78a8f53", "labels_vector_sha256": "01875857442a92b38a6f1c1ee339923a861a10598ed3abba60e2eee9c485d823", "planned_active_tokens": 63849, "realized_active_tokens": 63849, "cumulative_start": 63376113, "cumulative_end": 63439962, "loss_sum": 17505.502807617188, "token_normalized_loss": 0.27417035204337087, "grad_norm_before_clip": 0.08650116622447968, "learning_rates_at_step": { "lora": 9.50943645217306e-08, "row_tokens": 9.50943645217306e-08 }, "learning_rates_after_step": { "lora": 8.43435096932188e-08, "row_tokens": 8.43435096932188e-08 } }, { "update_id": 968, "row_count": 11, "row_ids_sha256": "6ab1de333837091e07b79cab24ff823ab51d738593f581c84763b4c440100882", "input_ids_vector_sha256": "f611f5784a883d18add31017356e218066d143971dee44ea9ff106b2827ffc02", "labels_vector_sha256": "a161bff6f0c8c71eb88605cb5f75cc4fa566b867c03df005e0fe32c3d8d018be", "planned_active_tokens": 69474, "realized_active_tokens": 69474, "cumulative_start": 63439962, "cumulative_end": 63509436, "loss_sum": 25991.257888793945, "token_normalized_loss": 0.37411489030132056, "grad_norm_before_clip": 0.090381920337677, "learning_rates_at_step": { "lora": 8.43435096932188e-08, "row_tokens": 8.43435096932188e-08 }, "learning_rates_after_step": { "lora": 7.546945769989488e-08, "row_tokens": 7.546945769989488e-08 } }, { "update_id": 969, "row_count": 9, "row_ids_sha256": "a6d8bfa244bfcec0a82577083f7ad22b5221d07a63513b3b606e29c18c0e414f", "input_ids_vector_sha256": "f160bee7463526368ebdd901756764238a6b924f9dfef4714748ef209fa9fed0", "labels_vector_sha256": "d063154a656343ab391869124808f64e8bb396d649e5ac869d1995e4349d5a1d", "planned_active_tokens": 60758, "realized_active_tokens": 60758, "cumulative_start": 63509436, "cumulative_end": 63570194, "loss_sum": 20611.380767822266, "token_normalized_loss": 0.33923731472106167, "grad_norm_before_clip": 0.09491543471813202, "learning_rates_at_step": { "lora": 7.546945769989488e-08, "row_tokens": 7.546945769989488e-08 }, "learning_rates_after_step": { "lora": 6.631614168264855e-08, "row_tokens": 6.631614168264855e-08 } }, { "update_id": 970, "row_count": 14, "row_ids_sha256": "1dfb7de7176d4eb7e06507ff8a45574e40988a40f28a824e9322b512d448c7f9", "input_ids_vector_sha256": "71c58834deff6c2753a344254d8e6df64d0fd3f1d8a3b0ca8b30621d4f4735fd", "labels_vector_sha256": "bf8c3ffe9aa586487fac692cc83728099a51e6b165cf61344a1bf4de9e45925d", "planned_active_tokens": 66541, "realized_active_tokens": 66541, "cumulative_start": 63570194, "cumulative_end": 63636735, "loss_sum": 21402.720733642578, "token_normalized_loss": 0.3216471158179555, "grad_norm_before_clip": 0.08632876724004745, "learning_rates_at_step": { "lora": 6.631614168264855e-08, "row_tokens": 6.631614168264855e-08 }, "learning_rates_after_step": { "lora": 5.719815272771656e-08, "row_tokens": 5.719815272771656e-08 } }, { "update_id": 971, "row_count": 14, "row_ids_sha256": "06de453ba683df286ae24e4834d650ad2d11e47929c4f6dfa42567fc88d24e76", "input_ids_vector_sha256": "806b07a33c9b965f4d63f2ed290e8e98c37b1b8cf42e19186a4d9d34451cd67a", "labels_vector_sha256": "6f0e491a51f49c900a4afc97608c5e07868101de565d17dc7bbc6fd157be9bc3", "planned_active_tokens": 71026, "realized_active_tokens": 71026, "cumulative_start": 63636735, "cumulative_end": 63707761, "loss_sum": 20940.37875366211, "token_normalized_loss": 0.29482694722583436, "grad_norm_before_clip": 0.08138556778430939, "learning_rates_at_step": { "lora": 5.719815272771656e-08, "row_tokens": 5.719815272771656e-08 }, "learning_rates_after_step": { "lora": 4.9846105644507646e-08, "row_tokens": 4.9846105644507646e-08 } }, { "update_id": 972, "row_count": 11, "row_ids_sha256": "c6cfb6eb6eb9f3b6d8ab3337b1ca31f332e7f0e9cc9fd918932b4490e5826df5", "input_ids_vector_sha256": "dc390aca6df42b708b174c8411f557c9f18d0538a65a45b3f07e3761df073d25", "labels_vector_sha256": "768c1acfa5385b996d44cddf1eb1c4d5d40ddbdaae813c19b126834c2f0aa55a", "planned_active_tokens": 61510, "realized_active_tokens": 61510, "cumulative_start": 63707761, "cumulative_end": 63769271, "loss_sum": 21724.143600463867, "token_normalized_loss": 0.3531806795718398, "grad_norm_before_clip": 0.09166397899389267, "learning_rates_at_step": { "lora": 4.9846105644507646e-08, "row_tokens": 4.9846105644507646e-08 }, "learning_rates_after_step": { "lora": 4.2089053939103894e-08, "row_tokens": 4.2089053939103894e-08 } }, { "update_id": 973, "row_count": 11, "row_ids_sha256": "eba142e9351884c543e178b7cf20587b7b0fc50cd72f00755fa1109d6d9b6152", "input_ids_vector_sha256": "ddd821c6502001ab5e90bae26591e0447ebe432cd3bd3bae3a0be4acf685603e", "labels_vector_sha256": "f7ff9d823d4065d5b90e5fcbe77e8d3910604d6324277fb5cd85348845c7a419", "planned_active_tokens": 70047, "realized_active_tokens": 70047, "cumulative_start": 63769271, "cumulative_end": 63839318, "loss_sum": 22148.722534179688, "token_normalized_loss": 0.3161980175336515, "grad_norm_before_clip": 0.08230322599411011, "learning_rates_at_step": { "lora": 4.2089053939103894e-08, "row_tokens": 4.2089053939103894e-08 }, "learning_rates_after_step": { "lora": 3.518740319936042e-08, "row_tokens": 3.518740319936042e-08 } }, { "update_id": 974, "row_count": 10, "row_ids_sha256": "175bb84157e4997d2215536a6c066c8cb6912ad6aa7c14f23a8866d96a7fcabf", "input_ids_vector_sha256": "d432ba03450f0c5c76576cf80b190aa02eb76e3de6cc32b6c8749d49c84c920e", "labels_vector_sha256": "41e6734bd9b57ba9fd128107141b33933d3fad03ff39fa215496a315935c2233", "planned_active_tokens": 67982, "realized_active_tokens": 67982, "cumulative_start": 63839318, "cumulative_end": 63907300, "loss_sum": 24041.255401611328, "token_normalized_loss": 0.35364148453430805, "grad_norm_before_clip": 0.08579307049512863, "learning_rates_at_step": { "lora": 3.518740319936042e-08, "row_tokens": 3.518740319936042e-08 }, "learning_rates_after_step": { "lora": 2.9775638823364982e-08, "row_tokens": 2.9775638823364982e-08 } }, { "update_id": 975, "row_count": 10, "row_ids_sha256": "c670158745c9418adf356395cdb138a0a4bcb8a20fae4fc2913e594c42f90d3d", "input_ids_vector_sha256": "fc12e0465c2761eb277d9535aa3930b8d176cc05dbfbb17b18a05c8d1a18c9af", "labels_vector_sha256": "c905eeec756e841c5e2a8e069af10aa696881a0ff6230e8ea2986c96e138e41d", "planned_active_tokens": 58130, "realized_active_tokens": 58130, "cumulative_start": 63907300, "cumulative_end": 63965430, "loss_sum": 19109.260803222656, "token_normalized_loss": 0.3287331980599115, "grad_norm_before_clip": 0.09234584867954254, "learning_rates_at_step": { "lora": 2.9775638823364982e-08, "row_tokens": 2.9775638823364982e-08 }, "learning_rates_after_step": { "lora": 2.435046413274411e-08, "row_tokens": 2.435046413274411e-08 } }, { "update_id": 976, "row_count": 12, "row_ids_sha256": "19340ab05ad85614b859e4a7179875b175b46bf05624fce70efdd465343abf50", "input_ids_vector_sha256": "0790fe4e5a70bed8fa3b2ea1b30fb0671d542718c9b03d8271e35ca00efcf78c", "labels_vector_sha256": "6ef133401cfa2eedf856a42e648b55d94e8ce84e8f36c241a62f3f6f3a8b03f3", "planned_active_tokens": 63865, "realized_active_tokens": 63865, "cumulative_start": 63965430, "cumulative_end": 64029295, "loss_sum": 22419.512451171875, "token_normalized_loss": 0.35104536837347333, "grad_norm_before_clip": 0.09087023884057999, "learning_rates_at_step": { "lora": 2.435046413274411e-08, "row_tokens": 2.435046413274411e-08 }, "learning_rates_after_step": { "lora": 1.9259003509142225e-08, "row_tokens": 1.9259003509142225e-08 } }, { "update_id": 977, "row_count": 14, "row_ids_sha256": "7849bad4179053378f007c14859fcea1a57dc957a4ec52bc9448ee057cef7fcf", "input_ids_vector_sha256": "376fc1374bfb4d698cb343596a2e1b11d9bdf66fe88358d2d278d9f5a59567e7", "labels_vector_sha256": "22b749c677187d2251345f6418dd0dc46e1d7dc47bb2a2134066d7388c9df50c", "planned_active_tokens": 66802, "realized_active_tokens": 66802, "cumulative_start": 64029295, "cumulative_end": 64096097, "loss_sum": 23112.018280029297, "token_normalized_loss": 0.34597793898430135, "grad_norm_before_clip": 0.08327709883451462, "learning_rates_at_step": { "lora": 1.9259003509142225e-08, "row_tokens": 1.9259003509142225e-08 }, "learning_rates_after_step": { "lora": 1.454914806700014e-08, "row_tokens": 1.454914806700014e-08 } }, { "update_id": 978, "row_count": 14, "row_ids_sha256": "c6d01df9db5301acc101d78064010ebf23ab3b8d5f436486ed95e170bdd93f38", "input_ids_vector_sha256": "acf493af95befe1b22f4512a0297634973afc5f847ee159361c0bdd143ad3ee2", "labels_vector_sha256": "ced29bc90311aef8f357592f7a61cacf003ae5ddcae75d7d87b14db04578bcc9", "planned_active_tokens": 70233, "realized_active_tokens": 70233, "cumulative_start": 64096097, "cumulative_end": 64166330, "loss_sum": 22564.420028686523, "token_normalized_loss": 0.32127945593505225, "grad_norm_before_clip": 0.0874740481376648, "learning_rates_at_step": { "lora": 1.454914806700014e-08, "row_tokens": 1.454914806700014e-08 }, "learning_rates_after_step": { "lora": 1.1010885722290144e-08, "row_tokens": 1.1010885722290144e-08 } }, { "update_id": 979, "row_count": 8, "row_ids_sha256": "86fe6c10a6f73781c249fe0f6bd8809357587f2d6b6719723fa7ff1c5c831b8a", "input_ids_vector_sha256": "7ab91b87fd12926e5d2636d44652a08e0276a11405d70c4c4931ec5043e2c49f", "labels_vector_sha256": "defdfe2c30f278c7167f508eca686199aeb2fedad84330f00ee191d578909919", "planned_active_tokens": 60678, "realized_active_tokens": 60678, "cumulative_start": 64166330, "cumulative_end": 64227008, "loss_sum": 22808.64111328125, "token_normalized_loss": 0.37589638935497627, "grad_norm_before_clip": 0.09652061760425568, "learning_rates_at_step": { "lora": 1.1010885722290144e-08, "row_tokens": 1.1010885722290144e-08 }, "learning_rates_after_step": { "lora": 7.59949252525094e-09, "row_tokens": 7.59949252525094e-09 } }, { "update_id": 980, "row_count": 9, "row_ids_sha256": "5417f264821ccb0b29bcc03a44b449054a8faeef39e8695ee30c4090645e498e", "input_ids_vector_sha256": "733f02fede46d8276891a1dc0d509d7cfcbe64703724fc1fb1144a813224b126", "labels_vector_sha256": "2dd37a1ddb1d0107b1434240fb7f7495361cc8262fe14a1904b91728fe5cec43", "planned_active_tokens": 68686, "realized_active_tokens": 68686, "cumulative_start": 64227008, "cumulative_end": 64295694, "loss_sum": 21075.964904785156, "token_normalized_loss": 0.30684513444930783, "grad_norm_before_clip": 0.08202153444290161, "learning_rates_at_step": { "lora": 7.59949252525094e-09, "row_tokens": 7.59949252525094e-09 }, "learning_rates_after_step": { "lora": 5.0435893623412834e-09, "row_tokens": 5.0435893623412834e-09 } }, { "update_id": 981, "row_count": 11, "row_ids_sha256": "255eee0f05f65a263c94a36e02c9fa980d8c69d1c397ec12ebf47923d34becaf", "input_ids_vector_sha256": "34f9bf7faa6fdc90733f9535d6ee6a118ac4e43da9184a09c8205d76d57d53b1", "labels_vector_sha256": "42fbd7b5dc1952363be359c84ad53e957768a1996d78f44593db0bf2828d0068", "planned_active_tokens": 62493, "realized_active_tokens": 62493, "cumulative_start": 64295694, "cumulative_end": 64358187, "loss_sum": 22498.79670715332, "token_normalized_loss": 0.3600210696742566, "grad_norm_before_clip": 0.09227330982685089, "learning_rates_at_step": { "lora": 5.0435893623412834e-09, "row_tokens": 5.0435893623412834e-09 }, "learning_rates_after_step": { "lora": 2.8001236840102807e-09, "row_tokens": 2.8001236840102807e-09 } }, { "update_id": 982, "row_count": 12, "row_ids_sha256": "4a6e5765f7f4a7eabf0f091ee8a374acf09c03181455b7d8d6d48b51dc6a25b2", "input_ids_vector_sha256": "1951fcf101e3f24ae62f10b908df48c66132ece0807fbc1946712d38040cbb87", "labels_vector_sha256": "dcd7b3675aeed33ed4ee06944d6bd8527393301ce608b5f31b75cfab92f6055e", "planned_active_tokens": 70016, "realized_active_tokens": 70016, "cumulative_start": 64358187, "cumulative_end": 64428203, "loss_sum": 23504.767578125, "token_normalized_loss": 0.3357056612506427, "grad_norm_before_clip": 0.08318427205085754, "learning_rates_at_step": { "lora": 2.8001236840102807e-09, "row_tokens": 2.8001236840102807e-09 }, "learning_rates_after_step": { "lora": 1.3498570676451218e-09, "row_tokens": 1.3498570676451218e-09 } }, { "update_id": 983, "row_count": 9, "row_ids_sha256": "ec54684f7eeb86399b019287cf1b51d5f47083b7ae68bf845da68ab86ed6e2a0", "input_ids_vector_sha256": "d77f64b9e536e6fb73747fcdfd6bf284f6c73e3a3fb392cf4dc552263f7bb3d2", "labels_vector_sha256": "e1c8c03f9af8b6ecd2162d56186881bafd1f5d1c90a50f144204909c4d7bb0e8", "planned_active_tokens": 62565, "realized_active_tokens": 62565, "cumulative_start": 64428203, "cumulative_end": 64490768, "loss_sum": 22108.550231933594, "token_normalized_loss": 0.35336929963931263, "grad_norm_before_clip": 0.09390882402658463, "learning_rates_at_step": { "lora": 1.3498570676451218e-09, "row_tokens": 1.3498570676451218e-09 }, "learning_rates_after_step": { "lora": 3.709731731860178e-10, "row_tokens": 3.709731731860178e-10 } }, { "update_id": 984, "row_count": 12, "row_ids_sha256": "154bad81f07aae865fdc483f1c76fd09cfb74e65eedba2e62a35b610a887bc78", "input_ids_vector_sha256": "4bc1c80bc323eea86a4d9f58b23a3ddb4ab1799fb8b76373429eded3cdecf0c3", "labels_vector_sha256": "e6492bcd832d756f51d46b6eb94bfcbb489085a75e17b33580f494e3864198d3", "planned_active_tokens": 67608, "realized_active_tokens": 67608, "cumulative_start": 64490768, "cumulative_end": 64558376, "loss_sum": 22742.268005371094, "token_normalized_loss": 0.3363842741298529, "grad_norm_before_clip": 0.08466363698244095, "learning_rates_at_step": { "lora": 3.709731731860178e-10, "row_tokens": 3.709731731860178e-10 }, "learning_rates_after_step": { "lora": 1.054355915353078e-11, "row_tokens": 1.054355915353078e-11 } }, { "update_id": 985, "row_count": 10, "row_ids_sha256": "2df92cc4a77a46aa09a023216ddecfd232911972db028f7d314160de2e05d232", "input_ids_vector_sha256": "da149d41e880fce773f967832b9c0ca316e717634f7a962cf5d87ad9a1c2418c", "labels_vector_sha256": "4bb26b31620d01363c418e435f78be5815c9bd55207e366fbd18d5550b677c34", "planned_active_tokens": 61937, "realized_active_tokens": 61937, "cumulative_start": 64558376, "cumulative_end": 64620313, "loss_sum": 23021.250427246094, "token_normalized_loss": 0.3716881739064871, "grad_norm_before_clip": 0.09745325893163681, "learning_rates_at_step": { "lora": 1.054355915353078e-11, "row_tokens": 1.054355915353078e-11 }, "learning_rates_after_step": { "lora": 0.0, "row_tokens": 0.0 } }, { "update_id": 986, "row_count": 1, "row_ids_sha256": "cfd00db4a7f6c07dcb3872920e1e667db91d5bc97c9f1b1752c7e981b3f0379a", "input_ids_vector_sha256": "b23378ad40b0303a61ea90b607e731fb707f3952839d374ec397928f0dd565e6", "labels_vector_sha256": "d1b2399963a3ded79f4d77a933aa5981501412943ff6508fea425ca0f0128c6e", "planned_active_tokens": 12559, "realized_active_tokens": 12559, "cumulative_start": 64620313, "cumulative_end": 64632872, "loss_sum": 5150.732421875, "token_normalized_loss": 0.4101228140676009, "grad_norm_before_clip": 0.2151578962802887, "learning_rates_at_step": { "lora": 0.0, "row_tokens": 0.0 }, "learning_rates_after_step": { "lora": 0.0, "row_tokens": 0.0 } } ], "frozen_base_digest_start": { "scope": "frozen_base", "sha256": "5d57dc425b2edd8291c27f6806bbaf90b43e8923f1103860cd0a20346464b375", "parameter_count": 355, "bytes": 14596022272, "names_sha256": "55a15eecdc0d2c8fdc49edbfe55db4accc70117860d030d39e44f294cd5304d2" }, "optimizer_membership": { "schema": "think-b-2ep-optimizer-membership/1", "token_bake_enabled": false, "groups": [ { "group": "lora", "param_count": 448, "params": [ { "name": "base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.24.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.24.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.24.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.24.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.25.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.25.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.25.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.25.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.26.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.26.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.26.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.26.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.27.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.27.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.27.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.27.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.28.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.28.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.28.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.28.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.29.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.29.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.29.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.29.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.30.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.30.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.30.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.30.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.self_attn.o_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.31.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.mlp.gate_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.31.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.mlp.up_proj.lora_B.default.weight", "shape": [ 11008, 64 ] }, { "name": "base_model.model.model.layers.31.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 11008 ] }, { "name": "base_model.model.model.layers.31.mlp.down_proj.lora_B.default.weight", "shape": [ 4096, 64 ] } ] }, { "group": "row_tokens", "param_count": 2, "params": [ { "name": "base_model.model.model.embed_tokens.token_adapter.trainable_tokens_delta.default", "shape": [ 1, 4096 ] }, { "name": "base_model.model.lm_head.token_adapter.trainable_tokens_delta.default", "shape": [ 1, 4096 ] } ] } ] }, "tied_token_canary": null, "continuation": null, "lora_digest_start": { "scope": "lora", "sha256": "dfdc674eb25a281ac54726af632cb4deba0c0f9e742bd35ff3f3308c75e0a19a", "parameter_count": 450, "bytes": 639664128, "names_sha256": "8682f1cd731b6e577fe15b72c310880afd96758ffb839b1c1159f8e04f2c050f" } }