Image-Text-to-Text
PEFT
Safetensors
laboratory
protocol-conditioned-action-prediction
lora
qwen
long-horizon-planning
conversational
Instructions to use Stanford-CongLab/LabHorizon-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Stanford-CongLab/LabHorizon-Model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B") model = PeftModel.from_pretrained(base_model, "Stanford-CongLab/LabHorizon-Model") - Notebooks
- Google Colab
- Kaggle
| {"current_steps": 10, "total_steps": 2500, "loss": 1.1145790100097657, "lr": 3.6e-06, "epoch": 0.04, "percentage": 0.4, "elapsed_time": "0:01:53", "remaining_time": "7:49:28"} | |
| {"current_steps": 20, "total_steps": 2500, "loss": 1.2167404174804688, "lr": 7.6e-06, "epoch": 0.08, "percentage": 0.8, "elapsed_time": "0:02:32", "remaining_time": "5:15:11"} | |
| {"current_steps": 30, "total_steps": 2500, "loss": 1.0437713623046876, "lr": 1.16e-05, "epoch": 0.12, "percentage": 1.2, "elapsed_time": "0:03:15", "remaining_time": "4:27:50"} | |
| {"current_steps": 40, "total_steps": 2500, "loss": 0.9282869338989258, "lr": 1.56e-05, "epoch": 0.16, "percentage": 1.6, "elapsed_time": "0:03:58", "remaining_time": "4:04:27"} | |
| {"current_steps": 50, "total_steps": 2500, "loss": 0.8799624443054199, "lr": 1.9600000000000002e-05, "epoch": 0.2, "percentage": 2.0, "elapsed_time": "0:04:40", "remaining_time": "3:48:42"} | |
| {"current_steps": 60, "total_steps": 2500, "loss": 0.7062759399414062, "lr": 2.36e-05, "epoch": 0.24, "percentage": 2.4, "elapsed_time": "0:05:21", "remaining_time": "3:37:36"} | |
| {"current_steps": 70, "total_steps": 2500, "loss": 0.7228042602539062, "lr": 2.7600000000000003e-05, "epoch": 0.28, "percentage": 2.8, "elapsed_time": "0:06:01", "remaining_time": "3:29:20"} | |
| {"current_steps": 80, "total_steps": 2500, "loss": 0.6257906913757324, "lr": 3.16e-05, "epoch": 0.32, "percentage": 3.2, "elapsed_time": "0:06:42", "remaining_time": "3:23:02"} | |
| {"current_steps": 90, "total_steps": 2500, "loss": 0.5399329185485839, "lr": 3.56e-05, "epoch": 0.36, "percentage": 3.6, "elapsed_time": "0:07:23", "remaining_time": "3:17:44"} | |
| {"current_steps": 100, "total_steps": 2500, "loss": 0.5184461116790772, "lr": 3.960000000000001e-05, "epoch": 0.4, "percentage": 4.0, "elapsed_time": "0:08:03", "remaining_time": "3:13:14"} | |
| {"current_steps": 100, "total_steps": 2500, "eval_loss": 0.5476460456848145, "epoch": 0.4, "percentage": 4.0, "elapsed_time": "0:08:24", "remaining_time": "3:21:50"} | |
| {"current_steps": 110, "total_steps": 2500, "loss": 0.5210700988769531, "lr": 4.36e-05, "epoch": 0.44, "percentage": 4.4, "elapsed_time": "0:09:05", "remaining_time": "3:17:37"} | |
| {"current_steps": 120, "total_steps": 2500, "loss": 0.5155693531036377, "lr": 4.76e-05, "epoch": 0.48, "percentage": 4.8, "elapsed_time": "0:09:46", "remaining_time": "3:13:46"} | |
| {"current_steps": 130, "total_steps": 2500, "loss": 0.45534143447875974, "lr": 5.16e-05, "epoch": 0.52, "percentage": 5.2, "elapsed_time": "0:10:26", "remaining_time": "3:10:12"} | |
| {"current_steps": 140, "total_steps": 2500, "loss": 0.45524797439575193, "lr": 5.560000000000001e-05, "epoch": 0.56, "percentage": 5.6, "elapsed_time": "0:11:06", "remaining_time": "3:07:08"} | |
| {"current_steps": 150, "total_steps": 2500, "loss": 0.47152209281921387, "lr": 5.96e-05, "epoch": 0.6, "percentage": 6.0, "elapsed_time": "0:11:45", "remaining_time": "3:04:10"} | |
| {"current_steps": 160, "total_steps": 2500, "loss": 0.4532940864562988, "lr": 6.36e-05, "epoch": 0.64, "percentage": 6.4, "elapsed_time": "0:12:23", "remaining_time": "3:01:14"} | |
| {"current_steps": 170, "total_steps": 2500, "loss": 0.48988704681396483, "lr": 6.76e-05, "epoch": 0.68, "percentage": 6.8, "elapsed_time": "0:12:59", "remaining_time": "2:58:08"} | |
| {"current_steps": 180, "total_steps": 2500, "loss": 0.46865572929382326, "lr": 7.16e-05, "epoch": 0.72, "percentage": 7.2, "elapsed_time": "0:13:37", "remaining_time": "2:55:41"} | |
| {"current_steps": 190, "total_steps": 2500, "loss": 0.45577139854431153, "lr": 7.560000000000001e-05, "epoch": 0.76, "percentage": 7.6, "elapsed_time": "0:14:15", "remaining_time": "2:53:22"} | |
| {"current_steps": 200, "total_steps": 2500, "loss": 0.4559042453765869, "lr": 7.960000000000001e-05, "epoch": 0.8, "percentage": 8.0, "elapsed_time": "0:14:52", "remaining_time": "2:50:58"} | |
| {"current_steps": 200, "total_steps": 2500, "eval_loss": 0.485470175743103, "epoch": 0.8, "percentage": 8.0, "elapsed_time": "0:15:09", "remaining_time": "2:54:18"} | |
| {"current_steps": 210, "total_steps": 2500, "loss": 0.45926451683044434, "lr": 8.36e-05, "epoch": 0.84, "percentage": 8.4, "elapsed_time": "0:15:49", "remaining_time": "2:52:34"} | |
| {"current_steps": 220, "total_steps": 2500, "loss": 0.4545453548431396, "lr": 8.76e-05, "epoch": 0.88, "percentage": 8.8, "elapsed_time": "0:16:33", "remaining_time": "2:51:32"} | |
| {"current_steps": 230, "total_steps": 2500, "loss": 0.47637343406677246, "lr": 9.16e-05, "epoch": 0.92, "percentage": 9.2, "elapsed_time": "0:17:13", "remaining_time": "2:49:56"} | |
| {"current_steps": 240, "total_steps": 2500, "loss": 0.43120541572570803, "lr": 9.56e-05, "epoch": 0.96, "percentage": 9.6, "elapsed_time": "0:17:50", "remaining_time": "2:48:02"} | |
| {"current_steps": 250, "total_steps": 2500, "loss": 0.4153712272644043, "lr": 9.960000000000001e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:18:29", "remaining_time": "2:46:26"} | |
| {"current_steps": 260, "total_steps": 2500, "loss": 0.44300012588500975, "lr": 9.999605221019081e-05, "epoch": 1.04, "percentage": 10.4, "elapsed_time": "0:19:08", "remaining_time": "2:44:53"} | |
| {"current_steps": 270, "total_steps": 2500, "loss": 0.462084436416626, "lr": 9.998240632972073e-05, "epoch": 1.08, "percentage": 10.8, "elapsed_time": "0:19:48", "remaining_time": "2:43:34"} | |
| {"current_steps": 280, "total_steps": 2500, "loss": 0.39808471202850343, "lr": 9.995901628010196e-05, "epoch": 1.12, "percentage": 11.2, "elapsed_time": "0:20:26", "remaining_time": "2:42:01"} | |
| {"current_steps": 290, "total_steps": 2500, "loss": 0.423044490814209, "lr": 9.9925886621271e-05, "epoch": 1.16, "percentage": 11.6, "elapsed_time": "0:21:04", "remaining_time": "2:40:38"} | |
| {"current_steps": 300, "total_steps": 2500, "loss": 0.41622562408447267, "lr": 9.98830238119205e-05, "epoch": 1.2, "percentage": 12.0, "elapsed_time": "0:21:43", "remaining_time": "2:39:22"} | |
| {"current_steps": 300, "total_steps": 2500, "eval_loss": 0.4695434272289276, "epoch": 1.2, "percentage": 12.0, "elapsed_time": "0:22:03", "remaining_time": "2:41:43"} | |
| {"current_steps": 310, "total_steps": 2500, "loss": 0.4166346549987793, "lr": 9.983043620824005e-05, "epoch": 1.24, "percentage": 12.4, "elapsed_time": "0:22:45", "remaining_time": "2:40:48"} | |
| {"current_steps": 320, "total_steps": 2500, "loss": 0.43734130859375, "lr": 9.97681340622872e-05, "epoch": 1.28, "percentage": 12.8, "elapsed_time": "0:23:23", "remaining_time": "2:39:19"} | |
| {"current_steps": 330, "total_steps": 2500, "loss": 0.3747305631637573, "lr": 9.969612951998874e-05, "epoch": 1.32, "percentage": 13.2, "elapsed_time": "0:23:57", "remaining_time": "2:37:32"} | |
| {"current_steps": 340, "total_steps": 2500, "loss": 0.42578792572021484, "lr": 9.961443661877289e-05, "epoch": 1.3599999999999999, "percentage": 13.6, "elapsed_time": "0:24:31", "remaining_time": "2:35:46"} | |
| {"current_steps": 350, "total_steps": 2500, "loss": 0.39537777900695803, "lr": 9.952307128483256e-05, "epoch": 1.4, "percentage": 14.0, "elapsed_time": "0:25:06", "remaining_time": "2:34:17"} | |
| {"current_steps": 360, "total_steps": 2500, "loss": 0.4084367275238037, "lr": 9.942205133002068e-05, "epoch": 1.44, "percentage": 14.4, "elapsed_time": "0:25:44", "remaining_time": "2:33:03"} | |
| {"current_steps": 370, "total_steps": 2500, "loss": 0.3781426906585693, "lr": 9.931139644837754e-05, "epoch": 1.48, "percentage": 14.8, "elapsed_time": "0:26:21", "remaining_time": "2:31:45"} | |
| {"current_steps": 380, "total_steps": 2500, "loss": 0.3952002048492432, "lr": 9.919112821229163e-05, "epoch": 1.52, "percentage": 15.2, "elapsed_time": "0:27:00", "remaining_time": "2:30:37"} | |
| {"current_steps": 390, "total_steps": 2500, "loss": 0.4087832927703857, "lr": 9.906127006829384e-05, "epoch": 1.56, "percentage": 15.6, "elapsed_time": "0:27:37", "remaining_time": "2:29:29"} | |
| {"current_steps": 400, "total_steps": 2500, "loss": 0.3861570119857788, "lr": 9.892184733248666e-05, "epoch": 1.6, "percentage": 16.0, "elapsed_time": "0:28:16", "remaining_time": "2:28:27"} | |
| {"current_steps": 400, "total_steps": 2500, "eval_loss": 0.45406103134155273, "epoch": 1.6, "percentage": 16.0, "elapsed_time": "0:28:36", "remaining_time": "2:30:10"} | |
| {"current_steps": 410, "total_steps": 2500, "loss": 0.39033331871032717, "lr": 9.877288718560866e-05, "epoch": 1.6400000000000001, "percentage": 16.4, "elapsed_time": "0:29:17", "remaining_time": "2:29:19"} | |
| {"current_steps": 420, "total_steps": 2500, "loss": 0.43663845062255857, "lr": 9.861441866773564e-05, "epoch": 1.6800000000000002, "percentage": 16.8, "elapsed_time": "0:29:55", "remaining_time": "2:28:12"} | |
| {"current_steps": 430, "total_steps": 2500, "loss": 0.43364706039428713, "lr": 9.844647267261916e-05, "epoch": 1.72, "percentage": 17.2, "elapsed_time": "0:30:30", "remaining_time": "2:26:53"} | |
| {"current_steps": 440, "total_steps": 2500, "loss": 0.409498929977417, "lr": 9.82690819416637e-05, "epoch": 1.76, "percentage": 17.6, "elapsed_time": "0:31:04", "remaining_time": "2:25:28"} | |
| {"current_steps": 450, "total_steps": 2500, "loss": 0.4264820098876953, "lr": 9.808228105754376e-05, "epoch": 1.8, "percentage": 18.0, "elapsed_time": "0:31:38", "remaining_time": "2:24:06"} | |
| {"current_steps": 460, "total_steps": 2500, "loss": 0.417040491104126, "lr": 9.788610643746184e-05, "epoch": 1.8399999999999999, "percentage": 18.4, "elapsed_time": "0:32:11", "remaining_time": "2:22:47"} | |
| {"current_steps": 470, "total_steps": 2500, "loss": 0.3749807357788086, "lr": 9.76805963260488e-05, "epoch": 1.88, "percentage": 18.8, "elapsed_time": "0:32:48", "remaining_time": "2:21:43"} | |
| {"current_steps": 480, "total_steps": 2500, "loss": 0.4022481918334961, "lr": 9.746579078790807e-05, "epoch": 1.92, "percentage": 19.2, "elapsed_time": "0:33:25", "remaining_time": "2:20:40"} | |
| {"current_steps": 490, "total_steps": 2500, "loss": 0.38319835662841795, "lr": 9.724173169980491e-05, "epoch": 1.96, "percentage": 19.6, "elapsed_time": "0:34:02", "remaining_time": "2:19:40"} | |
| {"current_steps": 500, "total_steps": 2500, "loss": 0.4122174263000488, "lr": 9.700846274250251e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:34:41", "remaining_time": "2:18:46"} | |
| {"current_steps": 500, "total_steps": 2500, "eval_loss": 0.44415727257728577, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:35:00", "remaining_time": "2:20:01"} | |
| {"current_steps": 510, "total_steps": 2500, "loss": 0.3524669408798218, "lr": 9.676602939224629e-05, "epoch": 2.04, "percentage": 20.4, "elapsed_time": "0:35:41", "remaining_time": "2:19:16"} | |
| {"current_steps": 520, "total_steps": 2500, "loss": 0.3717231273651123, "lr": 9.651447891189825e-05, "epoch": 2.08, "percentage": 20.8, "elapsed_time": "0:36:17", "remaining_time": "2:18:10"} | |
| {"current_steps": 530, "total_steps": 2500, "loss": 0.40065832138061525, "lr": 9.62538603417229e-05, "epoch": 2.12, "percentage": 21.2, "elapsed_time": "0:36:49", "remaining_time": "2:16:53"} | |
| {"current_steps": 540, "total_steps": 2500, "loss": 0.33635973930358887, "lr": 9.598422448982696e-05, "epoch": 2.16, "percentage": 21.6, "elapsed_time": "0:37:25", "remaining_time": "2:15:49"} | |
| {"current_steps": 550, "total_steps": 2500, "loss": 0.3708656787872314, "lr": 9.570562392225396e-05, "epoch": 2.2, "percentage": 22.0, "elapsed_time": "0:38:03", "remaining_time": "2:14:55"} | |
| {"current_steps": 560, "total_steps": 2500, "loss": 0.35284056663513186, "lr": 9.541811295273656e-05, "epoch": 2.24, "percentage": 22.4, "elapsed_time": "0:38:38", "remaining_time": "2:13:51"} | |
| {"current_steps": 570, "total_steps": 2500, "loss": 0.3429510831832886, "lr": 9.512174763210797e-05, "epoch": 2.2800000000000002, "percentage": 22.8, "elapsed_time": "0:39:15", "remaining_time": "2:12:55"} | |
| {"current_steps": 580, "total_steps": 2500, "loss": 0.36770102977752683, "lr": 9.481658573737465e-05, "epoch": 2.32, "percentage": 23.2, "elapsed_time": "0:39:52", "remaining_time": "2:12:01"} | |
| {"current_steps": 590, "total_steps": 2500, "loss": 0.3684037208557129, "lr": 9.450268676045262e-05, "epoch": 2.36, "percentage": 23.6, "elapsed_time": "0:40:31", "remaining_time": "2:11:12"} | |
| {"current_steps": 600, "total_steps": 2500, "loss": 0.3221792697906494, "lr": 9.418011189656941e-05, "epoch": 2.4, "percentage": 24.0, "elapsed_time": "0:41:11", "remaining_time": "2:10:25"} | |
| {"current_steps": 600, "total_steps": 2500, "eval_loss": 0.44748273491859436, "epoch": 2.4, "percentage": 24.0, "elapsed_time": "0:41:30", "remaining_time": "2:11:25"} | |
| {"current_steps": 610, "total_steps": 2500, "loss": 0.40174164772033694, "lr": 9.384892403233384e-05, "epoch": 2.44, "percentage": 24.4, "elapsed_time": "0:42:07", "remaining_time": "2:10:30"} | |
| {"current_steps": 620, "total_steps": 2500, "loss": 0.3701002836227417, "lr": 9.35091877334763e-05, "epoch": 2.48, "percentage": 24.8, "elapsed_time": "0:42:41", "remaining_time": "2:09:28"} | |
| {"current_steps": 630, "total_steps": 2500, "loss": 0.3759175777435303, "lr": 9.316096923226135e-05, "epoch": 2.52, "percentage": 25.2, "elapsed_time": "0:43:18", "remaining_time": "2:08:33"} | |
| {"current_steps": 640, "total_steps": 2500, "loss": 0.3581662178039551, "lr": 9.28043364145758e-05, "epoch": 2.56, "percentage": 25.6, "elapsed_time": "0:43:53", "remaining_time": "2:07:33"} | |
| {"current_steps": 650, "total_steps": 2500, "loss": 0.35065665245056155, "lr": 9.24393588066941e-05, "epoch": 2.6, "percentage": 26.0, "elapsed_time": "0:44:26", "remaining_time": "2:06:28"} | |
| {"current_steps": 660, "total_steps": 2500, "loss": 0.36879355907440187, "lr": 9.206610756172402e-05, "epoch": 2.64, "percentage": 26.4, "elapsed_time": "0:45:03", "remaining_time": "2:05:37"} | |
| {"current_steps": 670, "total_steps": 2500, "loss": 0.3592060565948486, "lr": 9.168465544573536e-05, "epoch": 2.68, "percentage": 26.8, "elapsed_time": "0:45:43", "remaining_time": "2:04:53"} | |
| {"current_steps": 680, "total_steps": 2500, "loss": 0.36156315803527833, "lr": 9.129507682357394e-05, "epoch": 2.7199999999999998, "percentage": 27.2, "elapsed_time": "0:46:22", "remaining_time": "2:04:08"} | |
| {"current_steps": 690, "total_steps": 2500, "loss": 0.34445748329162595, "lr": 9.089744764436403e-05, "epoch": 2.76, "percentage": 27.6, "elapsed_time": "0:47:02", "remaining_time": "2:03:23"} | |
| {"current_steps": 700, "total_steps": 2500, "loss": 0.3526463985443115, "lr": 9.049184542670199e-05, "epoch": 2.8, "percentage": 28.0, "elapsed_time": "0:47:37", "remaining_time": "2:02:27"} | |
| {"current_steps": 700, "total_steps": 2500, "eval_loss": 0.44259119033813477, "epoch": 2.8, "percentage": 28.0, "elapsed_time": "0:47:54", "remaining_time": "2:03:10"} | |
| {"current_steps": 710, "total_steps": 2500, "loss": 0.3458081245422363, "lr": 9.007834924354383e-05, "epoch": 2.84, "percentage": 28.4, "elapsed_time": "0:48:32", "remaining_time": "2:02:23"} | |
| {"current_steps": 720, "total_steps": 2500, "loss": 0.3651163101196289, "lr": 8.965703970678974e-05, "epoch": 2.88, "percentage": 28.8, "elapsed_time": "0:49:08", "remaining_time": "2:01:28"} | |
| {"current_steps": 730, "total_steps": 2500, "loss": 0.3218229293823242, "lr": 8.922799895156867e-05, "epoch": 2.92, "percentage": 29.2, "elapsed_time": "0:49:42", "remaining_time": "2:00:31"} | |
| {"current_steps": 740, "total_steps": 2500, "loss": 0.3561582088470459, "lr": 8.879131062022598e-05, "epoch": 2.96, "percentage": 29.6, "elapsed_time": "0:50:18", "remaining_time": "1:59:39"} | |
| {"current_steps": 750, "total_steps": 2500, "loss": 0.36128854751586914, "lr": 8.834705984601708e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:50:55", "remaining_time": "1:58:48"} | |
| {"current_steps": 760, "total_steps": 2500, "loss": 0.31422438621521, "lr": 8.789533323651066e-05, "epoch": 3.04, "percentage": 30.4, "elapsed_time": "0:51:32", "remaining_time": "1:57:59"} | |
| {"current_steps": 770, "total_steps": 2500, "loss": 0.29355826377868655, "lr": 8.74362188567043e-05, "epoch": 3.08, "percentage": 30.8, "elapsed_time": "0:52:11", "remaining_time": "1:57:15"} | |
| {"current_steps": 780, "total_steps": 2500, "loss": 0.3185117721557617, "lr": 8.696980621185602e-05, "epoch": 3.12, "percentage": 31.2, "elapsed_time": "0:52:51", "remaining_time": "1:56:32"} | |
| {"current_steps": 790, "total_steps": 2500, "loss": 0.28971233367919924, "lr": 8.649618623003508e-05, "epoch": 3.16, "percentage": 31.6, "elapsed_time": "0:53:28", "remaining_time": "1:55:45"} | |
| {"current_steps": 800, "total_steps": 2500, "loss": 0.3055370092391968, "lr": 8.601545124439535e-05, "epoch": 3.2, "percentage": 32.0, "elapsed_time": "0:54:06", "remaining_time": "1:54:58"} | |
| {"current_steps": 800, "total_steps": 2500, "eval_loss": 0.4529191255569458, "epoch": 3.2, "percentage": 32.0, "elapsed_time": "0:54:24", "remaining_time": "1:55:37"} | |
| {"current_steps": 810, "total_steps": 2500, "loss": 0.28035550117492675, "lr": 8.552769497517482e-05, "epoch": 3.24, "percentage": 32.4, "elapsed_time": "0:55:03", "remaining_time": "1:54:52"} | |
| {"current_steps": 820, "total_steps": 2500, "loss": 0.3199602603912354, "lr": 8.503301251142459e-05, "epoch": 3.2800000000000002, "percentage": 32.8, "elapsed_time": "0:55:37", "remaining_time": "1:53:57"} | |
| {"current_steps": 830, "total_steps": 2500, "loss": 0.29444499015808107, "lr": 8.453150029247114e-05, "epoch": 3.32, "percentage": 33.2, "elapsed_time": "0:56:12", "remaining_time": "1:53:04"} | |
| {"current_steps": 840, "total_steps": 2500, "loss": 0.30467259883880615, "lr": 8.402325608911526e-05, "epoch": 3.36, "percentage": 33.6, "elapsed_time": "0:56:45", "remaining_time": "1:52:10"} | |
| {"current_steps": 850, "total_steps": 2500, "loss": 0.3117033004760742, "lr": 8.350837898457143e-05, "epoch": 3.4, "percentage": 34.0, "elapsed_time": "0:57:19", "remaining_time": "1:51:15"} | |
| {"current_steps": 860, "total_steps": 2500, "loss": 0.34261503219604494, "lr": 8.298696935515132e-05, "epoch": 3.44, "percentage": 34.4, "elapsed_time": "0:57:55", "remaining_time": "1:50:27"} | |
| {"current_steps": 870, "total_steps": 2500, "loss": 0.3159458637237549, "lr": 8.245912885069531e-05, "epoch": 3.48, "percentage": 34.8, "elapsed_time": "0:58:33", "remaining_time": "1:49:42"} | |
| {"current_steps": 880, "total_steps": 2500, "loss": 0.2982481002807617, "lr": 8.192496037475562e-05, "epoch": 3.52, "percentage": 35.2, "elapsed_time": "0:59:13", "remaining_time": "1:49:01"} | |
| {"current_steps": 890, "total_steps": 2500, "loss": 0.3232215404510498, "lr": 8.138456806453503e-05, "epoch": 3.56, "percentage": 35.6, "elapsed_time": "0:59:53", "remaining_time": "1:48:20"} | |
| {"current_steps": 900, "total_steps": 2500, "loss": 0.3305091381072998, "lr": 8.083805727058513e-05, "epoch": 3.6, "percentage": 36.0, "elapsed_time": "1:00:32", "remaining_time": "1:47:38"} | |
| {"current_steps": 900, "total_steps": 2500, "eval_loss": 0.44760578870773315, "epoch": 3.6, "percentage": 36.0, "elapsed_time": "1:00:52", "remaining_time": "1:48:13"} | |
| {"current_steps": 910, "total_steps": 2500, "loss": 0.35752732753753663, "lr": 8.028553453626808e-05, "epoch": 3.64, "percentage": 36.4, "elapsed_time": "1:01:35", "remaining_time": "1:47:37"} | |
| {"current_steps": 920, "total_steps": 2500, "loss": 0.3292932271957397, "lr": 7.972710757698567e-05, "epoch": 3.68, "percentage": 36.8, "elapsed_time": "1:02:16", "remaining_time": "1:46:56"} | |
| {"current_steps": 930, "total_steps": 2500, "loss": 0.28986682891845705, "lr": 7.916288525918007e-05, "epoch": 3.7199999999999998, "percentage": 37.2, "elapsed_time": "1:02:55", "remaining_time": "1:46:13"} | |
| {"current_steps": 940, "total_steps": 2500, "loss": 0.3027395725250244, "lr": 7.859297757911013e-05, "epoch": 3.76, "percentage": 37.6, "elapsed_time": "1:03:33", "remaining_time": "1:45:28"} | |
| {"current_steps": 950, "total_steps": 2500, "loss": 0.3238774061203003, "lr": 7.801749564140724e-05, "epoch": 3.8, "percentage": 38.0, "elapsed_time": "1:04:12", "remaining_time": "1:44:46"} | |
| {"current_steps": 960, "total_steps": 2500, "loss": 0.34537086486816404, "lr": 7.743655163741543e-05, "epoch": 3.84, "percentage": 38.4, "elapsed_time": "1:04:51", "remaining_time": "1:44:02"} | |
| {"current_steps": 970, "total_steps": 2500, "loss": 0.3292637825012207, "lr": 7.685025882331936e-05, "epoch": 3.88, "percentage": 38.8, "elapsed_time": "1:05:30", "remaining_time": "1:43:20"} | |
| {"current_steps": 980, "total_steps": 2500, "loss": 0.32722015380859376, "lr": 7.62587314980648e-05, "epoch": 3.92, "percentage": 39.2, "elapsed_time": "1:06:11", "remaining_time": "1:42:39"} | |
| {"current_steps": 990, "total_steps": 2500, "loss": 0.29880056381225584, "lr": 7.566208498107585e-05, "epoch": 3.96, "percentage": 39.6, "elapsed_time": "1:06:50", "remaining_time": "1:41:56"} | |
| {"current_steps": 1000, "total_steps": 2500, "loss": 0.2978524684906006, "lr": 7.506043558977321e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "1:07:29", "remaining_time": "1:41:14"} | |
| {"current_steps": 1000, "total_steps": 2500, "eval_loss": 0.44613513350486755, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "1:07:49", "remaining_time": "1:41:43"} | |
| {"current_steps": 1010, "total_steps": 2500, "loss": 0.27530927658081056, "lr": 7.445390061689782e-05, "epoch": 4.04, "percentage": 40.4, "elapsed_time": "1:08:31", "remaining_time": "1:41:05"} | |
| {"current_steps": 1020, "total_steps": 2500, "loss": 0.2517704486846924, "lr": 7.38425983076444e-05, "epoch": 4.08, "percentage": 40.8, "elapsed_time": "1:09:11", "remaining_time": "1:40:23"} | |
| {"current_steps": 1030, "total_steps": 2500, "loss": 0.28200175762176516, "lr": 7.32266478366094e-05, "epoch": 4.12, "percentage": 41.2, "elapsed_time": "1:09:50", "remaining_time": "1:39:40"} | |
| {"current_steps": 1040, "total_steps": 2500, "loss": 0.2569046258926392, "lr": 7.260616928455754e-05, "epoch": 4.16, "percentage": 41.6, "elapsed_time": "1:10:30", "remaining_time": "1:38:58"} | |
| {"current_steps": 1050, "total_steps": 2500, "loss": 0.2665576696395874, "lr": 7.1981283615012e-05, "epoch": 4.2, "percentage": 42.0, "elapsed_time": "1:11:09", "remaining_time": "1:38:15"} | |
| {"current_steps": 1060, "total_steps": 2500, "loss": 0.2635650634765625, "lr": 7.135211265067216e-05, "epoch": 4.24, "percentage": 42.4, "elapsed_time": "1:11:47", "remaining_time": "1:37:31"} | |
| {"current_steps": 1070, "total_steps": 2500, "loss": 0.26842334270477297, "lr": 7.071877904966423e-05, "epoch": 4.28, "percentage": 42.8, "elapsed_time": "1:12:27", "remaining_time": "1:36:49"} | |
| {"current_steps": 1080, "total_steps": 2500, "loss": 0.2633937358856201, "lr": 7.00814062816285e-05, "epoch": 4.32, "percentage": 43.2, "elapsed_time": "1:13:07", "remaining_time": "1:36:08"} | |
| {"current_steps": 1090, "total_steps": 2500, "loss": 0.2895397186279297, "lr": 6.944011860364905e-05, "epoch": 4.36, "percentage": 43.6, "elapsed_time": "1:13:45", "remaining_time": "1:35:24"} | |
| {"current_steps": 1100, "total_steps": 2500, "loss": 0.27405414581298826, "lr": 6.879504103602935e-05, "epoch": 4.4, "percentage": 44.0, "elapsed_time": "1:14:25", "remaining_time": "1:34:43"} | |
| {"current_steps": 1100, "total_steps": 2500, "eval_loss": 0.46795058250427246, "epoch": 4.4, "percentage": 44.0, "elapsed_time": "1:14:42", "remaining_time": "1:35:05"} | |
| {"current_steps": 1110, "total_steps": 2500, "loss": 0.2581511974334717, "lr": 6.814629933791931e-05, "epoch": 4.44, "percentage": 44.4, "elapsed_time": "1:15:21", "remaining_time": "1:34:22"} | |
| {"current_steps": 1120, "total_steps": 2500, "loss": 0.2689012050628662, "lr": 6.749401998279846e-05, "epoch": 4.48, "percentage": 44.8, "elapsed_time": "1:16:00", "remaining_time": "1:33:39"} | |
| {"current_steps": 1130, "total_steps": 2500, "loss": 0.27230424880981446, "lr": 6.683833013381941e-05, "epoch": 4.52, "percentage": 45.2, "elapsed_time": "1:16:39", "remaining_time": "1:32:56"} | |
| {"current_steps": 1140, "total_steps": 2500, "loss": 0.2903036594390869, "lr": 6.617935761901748e-05, "epoch": 4.5600000000000005, "percentage": 45.6, "elapsed_time": "1:17:18", "remaining_time": "1:32:13"} | |
| {"current_steps": 1150, "total_steps": 2500, "loss": 0.2551115989685059, "lr": 6.551723090639007e-05, "epoch": 4.6, "percentage": 46.0, "elapsed_time": "1:17:57", "remaining_time": "1:31:31"} | |
| {"current_steps": 1160, "total_steps": 2500, "loss": 0.2783109188079834, "lr": 6.485207907885175e-05, "epoch": 4.64, "percentage": 46.4, "elapsed_time": "1:18:37", "remaining_time": "1:30:49"} | |
| {"current_steps": 1170, "total_steps": 2500, "loss": 0.29131503105163575, "lr": 6.418403180906922e-05, "epoch": 4.68, "percentage": 46.8, "elapsed_time": "1:19:17", "remaining_time": "1:30:08"} | |
| {"current_steps": 1180, "total_steps": 2500, "loss": 0.2730400085449219, "lr": 6.351321933418139e-05, "epoch": 4.72, "percentage": 47.2, "elapsed_time": "1:19:57", "remaining_time": "1:29:26"} | |
| {"current_steps": 1190, "total_steps": 2500, "loss": 0.2572148323059082, "lr": 6.283977243040939e-05, "epoch": 4.76, "percentage": 47.6, "elapsed_time": "1:20:37", "remaining_time": "1:28:44"} | |
| {"current_steps": 1200, "total_steps": 2500, "loss": 0.27444655895233155, "lr": 6.216382238756146e-05, "epoch": 4.8, "percentage": 48.0, "elapsed_time": "1:21:16", "remaining_time": "1:28:03"} | |
| {"current_steps": 1200, "total_steps": 2500, "eval_loss": 0.466619610786438, "epoch": 4.8, "percentage": 48.0, "elapsed_time": "1:21:36", "remaining_time": "1:28:24"} | |
| {"current_steps": 1210, "total_steps": 2500, "loss": 0.27054529190063475, "lr": 6.148550098343778e-05, "epoch": 4.84, "percentage": 48.4, "elapsed_time": "1:22:17", "remaining_time": "1:27:43"} | |
| {"current_steps": 1220, "total_steps": 2500, "loss": 0.26785056591033934, "lr": 6.080494045814011e-05, "epoch": 4.88, "percentage": 48.8, "elapsed_time": "1:22:55", "remaining_time": "1:26:59"} | |
| {"current_steps": 1230, "total_steps": 2500, "loss": 0.26335647106170657, "lr": 6.0122273488291304e-05, "epoch": 4.92, "percentage": 49.2, "elapsed_time": "1:23:34", "remaining_time": "1:26:17"} | |
| {"current_steps": 1240, "total_steps": 2500, "loss": 0.2614041090011597, "lr": 5.943763316116977e-05, "epoch": 4.96, "percentage": 49.6, "elapsed_time": "1:24:13", "remaining_time": "1:25:34"} | |
| {"current_steps": 1250, "total_steps": 2500, "loss": 0.24768717288970948, "lr": 5.875115294876381e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "1:24:52", "remaining_time": "1:24:52"} | |
| {"current_steps": 1260, "total_steps": 2500, "loss": 0.21707432270050048, "lr": 5.806296668175104e-05, "epoch": 5.04, "percentage": 50.4, "elapsed_time": "1:25:31", "remaining_time": "1:24:10"} | |
| {"current_steps": 1270, "total_steps": 2500, "loss": 0.2139519214630127, "lr": 5.737320852340775e-05, "epoch": 5.08, "percentage": 50.8, "elapsed_time": "1:26:06", "remaining_time": "1:23:23"} | |
| {"current_steps": 1280, "total_steps": 2500, "loss": 0.20998594760894776, "lr": 5.668201294345363e-05, "epoch": 5.12, "percentage": 51.2, "elapsed_time": "1:26:39", "remaining_time": "1:22:35"} | |
| {"current_steps": 1290, "total_steps": 2500, "loss": 0.23306002616882324, "lr": 5.598951469183649e-05, "epoch": 5.16, "percentage": 51.6, "elapsed_time": "1:27:14", "remaining_time": "1:21:49"} | |
| {"current_steps": 1300, "total_steps": 2500, "loss": 0.2262401580810547, "lr": 5.52958487724626e-05, "epoch": 5.2, "percentage": 52.0, "elapsed_time": "1:27:49", "remaining_time": "1:21:04"} | |
| {"current_steps": 1300, "total_steps": 2500, "eval_loss": 0.49972543120384216, "epoch": 5.2, "percentage": 52.0, "elapsed_time": "1:28:08", "remaining_time": "1:21:22"} | |
| {"current_steps": 1310, "total_steps": 2500, "loss": 0.21100988388061523, "lr": 5.4601150416877367e-05, "epoch": 5.24, "percentage": 52.4, "elapsed_time": "1:28:47", "remaining_time": "1:20:39"} | |
| {"current_steps": 1320, "total_steps": 2500, "loss": 0.23542592525482178, "lr": 5.390555505790168e-05, "epoch": 5.28, "percentage": 52.8, "elapsed_time": "1:29:20", "remaining_time": "1:19:52"} | |
| {"current_steps": 1330, "total_steps": 2500, "loss": 0.2095633029937744, "lr": 5.3209198303229027e-05, "epoch": 5.32, "percentage": 53.2, "elapsed_time": "1:29:54", "remaining_time": "1:19:05"} | |
| {"current_steps": 1340, "total_steps": 2500, "loss": 0.21693904399871827, "lr": 5.2512215908988484e-05, "epoch": 5.36, "percentage": 53.6, "elapsed_time": "1:30:31", "remaining_time": "1:18:21"} | |
| {"current_steps": 1350, "total_steps": 2500, "loss": 0.2076347827911377, "lr": 5.1814743753278795e-05, "epoch": 5.4, "percentage": 54.0, "elapsed_time": "1:31:11", "remaining_time": "1:17:40"} | |
| {"current_steps": 1360, "total_steps": 2500, "loss": 0.22539749145507812, "lr": 5.111691780967869e-05, "epoch": 5.44, "percentage": 54.4, "elapsed_time": "1:31:50", "remaining_time": "1:16:58"} | |
| {"current_steps": 1370, "total_steps": 2500, "loss": 0.2077547550201416, "lr": 5.041887412073854e-05, "epoch": 5.48, "percentage": 54.8, "elapsed_time": "1:32:27", "remaining_time": "1:16:15"} | |
| {"current_steps": 1380, "total_steps": 2500, "loss": 0.21558783054351807, "lr": 4.97207487714586e-05, "epoch": 5.52, "percentage": 55.2, "elapsed_time": "1:33:04", "remaining_time": "1:15:32"} | |
| {"current_steps": 1390, "total_steps": 2500, "loss": 0.21069679260253907, "lr": 4.9022677862758945e-05, "epoch": 5.5600000000000005, "percentage": 55.6, "elapsed_time": "1:33:39", "remaining_time": "1:14:47"} | |
| {"current_steps": 1400, "total_steps": 2500, "loss": 0.21843309402465821, "lr": 4.832479748494643e-05, "epoch": 5.6, "percentage": 56.0, "elapsed_time": "1:34:13", "remaining_time": "1:14:02"} | |
| {"current_steps": 1400, "total_steps": 2500, "eval_loss": 0.49576279520988464, "epoch": 5.6, "percentage": 56.0, "elapsed_time": "1:34:31", "remaining_time": "1:14:16"} | |
| {"current_steps": 1410, "total_steps": 2500, "loss": 0.22310276031494142, "lr": 4.7627243691183453e-05, "epoch": 5.64, "percentage": 56.4, "elapsed_time": "1:35:09", "remaining_time": "1:13:33"} | |
| {"current_steps": 1420, "total_steps": 2500, "loss": 0.22056117057800292, "lr": 4.693015247096423e-05, "epoch": 5.68, "percentage": 56.8, "elapsed_time": "1:35:47", "remaining_time": "1:12:51"} | |
| {"current_steps": 1430, "total_steps": 2500, "loss": 0.2241537094116211, "lr": 4.623365972360337e-05, "epoch": 5.72, "percentage": 57.2, "elapsed_time": "1:36:25", "remaining_time": "1:12:09"} | |
| {"current_steps": 1440, "total_steps": 2500, "loss": 0.21514451503753662, "lr": 4.553790123174197e-05, "epoch": 5.76, "percentage": 57.6, "elapsed_time": "1:37:04", "remaining_time": "1:11:27"} | |
| {"current_steps": 1450, "total_steps": 2500, "loss": 0.21031346321105956, "lr": 4.484301263487665e-05, "epoch": 5.8, "percentage": 58.0, "elapsed_time": "1:37:42", "remaining_time": "1:10:45"} | |
| {"current_steps": 1460, "total_steps": 2500, "loss": 0.2312474489212036, "lr": 4.414912940291613e-05, "epoch": 5.84, "percentage": 58.4, "elapsed_time": "1:38:21", "remaining_time": "1:10:03"} | |
| {"current_steps": 1470, "total_steps": 2500, "loss": 0.22380952835083007, "lr": 4.345638680977139e-05, "epoch": 5.88, "percentage": 58.8, "elapsed_time": "1:39:00", "remaining_time": "1:09:22"} | |
| {"current_steps": 1480, "total_steps": 2500, "loss": 0.22706894874572753, "lr": 4.276491990698355e-05, "epoch": 5.92, "percentage": 59.2, "elapsed_time": "1:39:39", "remaining_time": "1:08:40"} | |
| {"current_steps": 1490, "total_steps": 2500, "loss": 0.2103546142578125, "lr": 4.2074863497395377e-05, "epoch": 5.96, "percentage": 59.6, "elapsed_time": "1:40:15", "remaining_time": "1:07:57"} | |
| {"current_steps": 1500, "total_steps": 2500, "loss": 0.2276217222213745, "lr": 4.1386352108871174e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "1:40:50", "remaining_time": "1:07:13"} | |
| {"current_steps": 1500, "total_steps": 2500, "eval_loss": 0.4966464042663574, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "1:41:07", "remaining_time": "1:07:25"} | |
| {"current_steps": 1510, "total_steps": 2500, "loss": 0.16540236473083497, "lr": 4.069951996807034e-05, "epoch": 6.04, "percentage": 60.4, "elapsed_time": "1:41:49", "remaining_time": "1:06:45"} | |
| {"current_steps": 1520, "total_steps": 2500, "loss": 0.1638352394104004, "lr": 4.001450097427966e-05, "epoch": 6.08, "percentage": 60.8, "elapsed_time": "1:42:26", "remaining_time": "1:06:03"} | |
| {"current_steps": 1530, "total_steps": 2500, "loss": 0.1719011664390564, "lr": 3.9331428673309204e-05, "epoch": 6.12, "percentage": 61.2, "elapsed_time": "1:43:05", "remaining_time": "1:05:21"} | |
| {"current_steps": 1540, "total_steps": 2500, "loss": 0.1651092290878296, "lr": 3.865043623145751e-05, "epoch": 6.16, "percentage": 61.6, "elapsed_time": "1:43:41", "remaining_time": "1:04:38"} | |
| {"current_steps": 1550, "total_steps": 2500, "loss": 0.1746900796890259, "lr": 3.797165640955041e-05, "epoch": 6.2, "percentage": 62.0, "elapsed_time": "1:44:21", "remaining_time": "1:03:57"} | |
| {"current_steps": 1560, "total_steps": 2500, "loss": 0.16637682914733887, "lr": 3.729522153705916e-05, "epoch": 6.24, "percentage": 62.4, "elapsed_time": "1:44:59", "remaining_time": "1:03:15"} | |
| {"current_steps": 1570, "total_steps": 2500, "loss": 0.1709848165512085, "lr": 3.662126348630237e-05, "epoch": 6.28, "percentage": 62.8, "elapsed_time": "1:45:38", "remaining_time": "1:02:34"} | |
| {"current_steps": 1580, "total_steps": 2500, "loss": 0.18107957839965821, "lr": 3.594991364673745e-05, "epoch": 6.32, "percentage": 63.2, "elapsed_time": "1:46:17", "remaining_time": "1:01:53"} | |
| {"current_steps": 1590, "total_steps": 2500, "loss": 0.16225044727325438, "lr": 3.528130289934583e-05, "epoch": 6.36, "percentage": 63.6, "elapsed_time": "1:46:54", "remaining_time": "1:01:11"} | |
| {"current_steps": 1600, "total_steps": 2500, "loss": 0.17544152736663818, "lr": 3.461556159111748e-05, "epoch": 6.4, "percentage": 64.0, "elapsed_time": "1:47:32", "remaining_time": "1:00:29"} | |
| {"current_steps": 1600, "total_steps": 2500, "eval_loss": 0.5342507362365723, "epoch": 6.4, "percentage": 64.0, "elapsed_time": "1:47:52", "remaining_time": "1:00:40"} | |
| {"current_steps": 1610, "total_steps": 2500, "loss": 0.17091144323349, "lr": 3.3952819509639534e-05, "epoch": 6.44, "percentage": 64.4, "elapsed_time": "1:48:32", "remaining_time": "0:59:59"} | |
| {"current_steps": 1620, "total_steps": 2500, "loss": 0.17765278816223146, "lr": 3.329320585779393e-05, "epoch": 6.48, "percentage": 64.8, "elapsed_time": "1:49:11", "remaining_time": "0:59:18"} | |
| {"current_steps": 1630, "total_steps": 2500, "loss": 0.16475566625595092, "lr": 3.263684922856905e-05, "epoch": 6.52, "percentage": 65.2, "elapsed_time": "1:49:51", "remaining_time": "0:58:38"} | |
| {"current_steps": 1640, "total_steps": 2500, "loss": 0.172060227394104, "lr": 3.1983877579990274e-05, "epoch": 6.5600000000000005, "percentage": 65.6, "elapsed_time": "1:50:30", "remaining_time": "0:57:57"} | |
| {"current_steps": 1650, "total_steps": 2500, "loss": 0.16673840284347535, "lr": 3.1334418210174263e-05, "epoch": 6.6, "percentage": 66.0, "elapsed_time": "1:51:09", "remaining_time": "0:57:15"} | |
| {"current_steps": 1660, "total_steps": 2500, "loss": 0.17414634227752684, "lr": 3.0688597732512e-05, "epoch": 6.64, "percentage": 66.4, "elapsed_time": "1:51:47", "remaining_time": "0:56:34"} | |
| {"current_steps": 1670, "total_steps": 2500, "loss": 0.1620783567428589, "lr": 3.0046542050985237e-05, "epoch": 6.68, "percentage": 66.8, "elapsed_time": "1:52:28", "remaining_time": "0:55:53"} | |
| {"current_steps": 1680, "total_steps": 2500, "loss": 0.17428462505340575, "lr": 2.940837633562127e-05, "epoch": 6.72, "percentage": 67.2, "elapsed_time": "1:53:08", "remaining_time": "0:55:13"} | |
| {"current_steps": 1690, "total_steps": 2500, "loss": 0.19050977230072022, "lr": 2.877422499809072e-05, "epoch": 6.76, "percentage": 67.6, "elapsed_time": "1:53:46", "remaining_time": "0:54:31"} | |
| {"current_steps": 1700, "total_steps": 2500, "loss": 0.16926174163818358, "lr": 2.8144211667453368e-05, "epoch": 6.8, "percentage": 68.0, "elapsed_time": "1:54:23", "remaining_time": "0:53:50"} | |
| {"current_steps": 1700, "total_steps": 2500, "eval_loss": 0.5441356301307678, "epoch": 6.8, "percentage": 68.0, "elapsed_time": "1:54:41", "remaining_time": "0:53:58"} | |
| {"current_steps": 1710, "total_steps": 2500, "loss": 0.1793771743774414, "lr": 2.75184591660563e-05, "epoch": 6.84, "percentage": 68.4, "elapsed_time": "1:55:20", "remaining_time": "0:53:17"} | |
| {"current_steps": 1720, "total_steps": 2500, "loss": 0.1647491931915283, "lr": 2.6897089485589583e-05, "epoch": 6.88, "percentage": 68.8, "elapsed_time": "1:55:56", "remaining_time": "0:52:34"} | |
| {"current_steps": 1730, "total_steps": 2500, "loss": 0.17397019863128663, "lr": 2.6280223763303546e-05, "epoch": 6.92, "percentage": 69.2, "elapsed_time": "1:56:35", "remaining_time": "0:51:53"} | |
| {"current_steps": 1740, "total_steps": 2500, "loss": 0.17107686996459961, "lr": 2.5667982258393014e-05, "epoch": 6.96, "percentage": 69.6, "elapsed_time": "1:57:11", "remaining_time": "0:51:11"} | |
| {"current_steps": 1750, "total_steps": 2500, "loss": 0.1730511426925659, "lr": 2.506048432855247e-05, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "1:57:50", "remaining_time": "0:50:30"} | |
| {"current_steps": 1760, "total_steps": 2500, "loss": 0.13950222730636597, "lr": 2.4457848406707013e-05, "epoch": 7.04, "percentage": 70.4, "elapsed_time": "1:58:29", "remaining_time": "0:49:49"} | |
| {"current_steps": 1770, "total_steps": 2500, "loss": 0.1326605796813965, "lr": 2.3860191977923672e-05, "epoch": 7.08, "percentage": 70.8, "elapsed_time": "1:59:08", "remaining_time": "0:49:08"} | |
| {"current_steps": 1780, "total_steps": 2500, "loss": 0.1265331983566284, "lr": 2.326763155650744e-05, "epoch": 7.12, "percentage": 71.2, "elapsed_time": "1:59:47", "remaining_time": "0:48:27"} | |
| {"current_steps": 1790, "total_steps": 2500, "loss": 0.12731509208679198, "lr": 2.2680282663286552e-05, "epoch": 7.16, "percentage": 71.6, "elapsed_time": "2:00:26", "remaining_time": "0:47:46"} | |
| {"current_steps": 1800, "total_steps": 2500, "loss": 0.13114826679229735, "lr": 2.209825980309151e-05, "epoch": 7.2, "percentage": 72.0, "elapsed_time": "2:01:03", "remaining_time": "0:47:04"} | |
| {"current_steps": 1800, "total_steps": 2500, "eval_loss": 0.5847110748291016, "epoch": 7.2, "percentage": 72.0, "elapsed_time": "2:01:22", "remaining_time": "0:47:12"} | |
| {"current_steps": 1810, "total_steps": 2500, "loss": 0.12906957864761354, "lr": 2.152167644243213e-05, "epoch": 7.24, "percentage": 72.4, "elapsed_time": "2:02:00", "remaining_time": "0:46:30"} | |
| {"current_steps": 1820, "total_steps": 2500, "loss": 0.133590030670166, "lr": 2.095064498737701e-05, "epoch": 7.28, "percentage": 72.8, "elapsed_time": "2:02:38", "remaining_time": "0:45:49"} | |
| {"current_steps": 1830, "total_steps": 2500, "loss": 0.13653848171234131, "lr": 2.0385276761639765e-05, "epoch": 7.32, "percentage": 73.2, "elapsed_time": "2:03:18", "remaining_time": "0:45:08"} | |
| {"current_steps": 1840, "total_steps": 2500, "loss": 0.12472724914550781, "lr": 1.9825681984876172e-05, "epoch": 7.36, "percentage": 73.6, "elapsed_time": "2:03:56", "remaining_time": "0:44:27"} | |
| {"current_steps": 1850, "total_steps": 2500, "loss": 0.13255125284194946, "lr": 1.9271969751196776e-05, "epoch": 7.4, "percentage": 74.0, "elapsed_time": "2:04:32", "remaining_time": "0:43:45"} | |
| {"current_steps": 1860, "total_steps": 2500, "loss": 0.13693161010742189, "lr": 1.8724248007898647e-05, "epoch": 7.44, "percentage": 74.4, "elapsed_time": "2:05:09", "remaining_time": "0:43:03"} | |
| {"current_steps": 1870, "total_steps": 2500, "loss": 0.13425672054290771, "lr": 1.8182623534420907e-05, "epoch": 7.48, "percentage": 74.8, "elapsed_time": "2:05:43", "remaining_time": "0:42:21"} | |
| {"current_steps": 1880, "total_steps": 2500, "loss": 0.13668575286865234, "lr": 1.76472019215278e-05, "epoch": 7.52, "percentage": 75.2, "elapsed_time": "2:06:19", "remaining_time": "0:41:39"} | |
| {"current_steps": 1890, "total_steps": 2500, "loss": 0.1317702889442444, "lr": 1.7118087550723633e-05, "epoch": 7.5600000000000005, "percentage": 75.6, "elapsed_time": "2:06:53", "remaining_time": "0:40:57"} | |
| {"current_steps": 1900, "total_steps": 2500, "loss": 0.14458621740341188, "lr": 1.659538357390341e-05, "epoch": 7.6, "percentage": 76.0, "elapsed_time": "2:07:26", "remaining_time": "0:40:14"} | |
| {"current_steps": 1900, "total_steps": 2500, "eval_loss": 0.5830516219139099, "epoch": 7.6, "percentage": 76.0, "elapsed_time": "2:07:44", "remaining_time": "0:40:20"} | |
| {"current_steps": 1910, "total_steps": 2500, "loss": 0.13126691579818725, "lr": 1.60791918932431e-05, "epoch": 7.64, "percentage": 76.4, "elapsed_time": "2:08:25", "remaining_time": "0:39:40"} | |
| {"current_steps": 1920, "total_steps": 2500, "loss": 0.12600460052490234, "lr": 1.556961314133359e-05, "epoch": 7.68, "percentage": 76.8, "elapsed_time": "2:09:04", "remaining_time": "0:38:59"} | |
| {"current_steps": 1930, "total_steps": 2500, "loss": 0.12453792095184327, "lr": 1.5066746661562253e-05, "epoch": 7.72, "percentage": 77.2, "elapsed_time": "2:09:40", "remaining_time": "0:38:17"} | |
| {"current_steps": 1940, "total_steps": 2500, "loss": 0.14839541912078857, "lr": 1.4570690488745687e-05, "epoch": 7.76, "percentage": 77.6, "elapsed_time": "2:10:17", "remaining_time": "0:37:36"} | |
| {"current_steps": 1950, "total_steps": 2500, "loss": 0.1321096420288086, "lr": 1.4081541330017705e-05, "epoch": 7.8, "percentage": 78.0, "elapsed_time": "2:10:53", "remaining_time": "0:36:55"} | |
| {"current_steps": 1960, "total_steps": 2500, "loss": 0.1317069411277771, "lr": 1.3599394545975951e-05, "epoch": 7.84, "percentage": 78.4, "elapsed_time": "2:11:29", "remaining_time": "0:36:13"} | |
| {"current_steps": 1970, "total_steps": 2500, "loss": 0.13362932205200195, "lr": 1.312434413209131e-05, "epoch": 7.88, "percentage": 78.8, "elapsed_time": "2:12:06", "remaining_time": "0:35:32"} | |
| {"current_steps": 1980, "total_steps": 2500, "loss": 0.12677763700485228, "lr": 1.2656482700383237e-05, "epoch": 7.92, "percentage": 79.2, "elapsed_time": "2:12:43", "remaining_time": "0:34:51"} | |
| {"current_steps": 1990, "total_steps": 2500, "loss": 0.1382434129714966, "lr": 1.219590146136485e-05, "epoch": 7.96, "percentage": 79.6, "elapsed_time": "2:13:22", "remaining_time": "0:34:10"} | |
| {"current_steps": 2000, "total_steps": 2500, "loss": 0.12519369125366211, "lr": 1.1742690206261292e-05, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "2:13:59", "remaining_time": "0:33:29"} | |
| {"current_steps": 2000, "total_steps": 2500, "eval_loss": 0.5840195417404175, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "2:14:18", "remaining_time": "0:33:34"} | |
| {"current_steps": 2010, "total_steps": 2500, "loss": 0.10409053564071655, "lr": 1.129693728950474e-05, "epoch": 8.04, "percentage": 80.4, "elapsed_time": "2:15:02", "remaining_time": "0:32:55"} | |
| {"current_steps": 2020, "total_steps": 2500, "loss": 0.10310100317001343, "lr": 1.0858729611509516e-05, "epoch": 8.08, "percentage": 80.8, "elapsed_time": "2:15:43", "remaining_time": "0:32:15"} | |
| {"current_steps": 2030, "total_steps": 2500, "loss": 0.09960774183273316, "lr": 1.0428152601730718e-05, "epoch": 8.12, "percentage": 81.2, "elapsed_time": "2:16:20", "remaining_time": "0:31:34"} | |
| {"current_steps": 2040, "total_steps": 2500, "loss": 0.09982571601867676, "lr": 1.0005290202009531e-05, "epoch": 8.16, "percentage": 81.6, "elapsed_time": "2:16:58", "remaining_time": "0:30:53"} | |
| {"current_steps": 2050, "total_steps": 2500, "loss": 0.11322143077850341, "lr": 9.590224850208646e-06, "epoch": 8.2, "percentage": 82.0, "elapsed_time": "2:17:36", "remaining_time": "0:30:12"} | |
| {"current_steps": 2060, "total_steps": 2500, "loss": 0.10006082057952881, "lr": 9.183037464140804e-06, "epoch": 8.24, "percentage": 82.4, "elapsed_time": "2:18:13", "remaining_time": "0:29:31"} | |
| {"current_steps": 2070, "total_steps": 2500, "loss": 0.11560235023498536, "lr": 8.783807425793721e-06, "epoch": 8.28, "percentage": 82.8, "elapsed_time": "2:18:46", "remaining_time": "0:28:49"} | |
| {"current_steps": 2080, "total_steps": 2500, "loss": 0.10931503772735596, "lr": 8.392612565854375e-06, "epoch": 8.32, "percentage": 83.2, "elapsed_time": "2:19:21", "remaining_time": "0:28:08"} | |
| {"current_steps": 2090, "total_steps": 2500, "loss": 0.10900030136108399, "lr": 8.009529148535855e-06, "epoch": 8.36, "percentage": 83.6, "elapsed_time": "2:19:58", "remaining_time": "0:27:27"} | |
| {"current_steps": 2100, "total_steps": 2500, "loss": 0.1069128155708313, "lr": 7.63463185670939e-06, "epoch": 8.4, "percentage": 84.0, "elapsed_time": "2:20:34", "remaining_time": "0:26:46"} | |
| {"current_steps": 2100, "total_steps": 2500, "eval_loss": 0.6247864961624146, "epoch": 8.4, "percentage": 84.0, "elapsed_time": "2:20:53", "remaining_time": "0:26:50"} | |
| {"current_steps": 2110, "total_steps": 2500, "loss": 0.09856721758842468, "lr": 7.267993777344856e-06, "epoch": 8.44, "percentage": 84.4, "elapsed_time": "2:21:31", "remaining_time": "0:26:09"} | |
| {"current_steps": 2120, "total_steps": 2500, "loss": 0.10609345436096192, "lr": 6.909686387262254e-06, "epoch": 8.48, "percentage": 84.8, "elapsed_time": "2:22:07", "remaining_time": "0:25:28"} | |
| {"current_steps": 2130, "total_steps": 2500, "loss": 0.105103600025177, "lr": 6.559779539197231e-06, "epoch": 8.52, "percentage": 85.2, "elapsed_time": "2:22:41", "remaining_time": "0:24:47"} | |
| {"current_steps": 2140, "total_steps": 2500, "loss": 0.10853493213653564, "lr": 6.21834144818314e-06, "epoch": 8.56, "percentage": 85.6, "elapsed_time": "2:23:18", "remaining_time": "0:24:06"} | |
| {"current_steps": 2150, "total_steps": 2500, "loss": 0.11464111804962158, "lr": 5.885438678252342e-06, "epoch": 8.6, "percentage": 86.0, "elapsed_time": "2:23:56", "remaining_time": "0:23:25"} | |
| {"current_steps": 2160, "total_steps": 2500, "loss": 0.10765299797058106, "lr": 5.5611361294594325e-06, "epoch": 8.64, "percentage": 86.4, "elapsed_time": "2:24:33", "remaining_time": "0:22:45"} | |
| {"current_steps": 2170, "total_steps": 2500, "loss": 0.10699164867401123, "lr": 5.245497025228874e-06, "epoch": 8.68, "percentage": 86.8, "elapsed_time": "2:25:12", "remaining_time": "0:22:04"} | |
| {"current_steps": 2180, "total_steps": 2500, "loss": 0.10728691816329956, "lr": 4.938582900029437e-06, "epoch": 8.72, "percentage": 87.2, "elapsed_time": "2:25:52", "remaining_time": "0:21:24"} | |
| {"current_steps": 2190, "total_steps": 2500, "loss": 0.11177785396575927, "lr": 4.640453587377957e-06, "epoch": 8.76, "percentage": 87.6, "elapsed_time": "2:26:32", "remaining_time": "0:20:44"} | |
| {"current_steps": 2200, "total_steps": 2500, "loss": 0.11041848659515381, "lr": 4.351167208174639e-06, "epoch": 8.8, "percentage": 88.0, "elapsed_time": "2:27:11", "remaining_time": "0:20:04"} | |
| {"current_steps": 2200, "total_steps": 2500, "eval_loss": 0.6235533356666565, "epoch": 8.8, "percentage": 88.0, "elapsed_time": "2:27:30", "remaining_time": "0:20:06"} | |
| {"current_steps": 2210, "total_steps": 2500, "loss": 0.1085782766342163, "lr": 4.0707801593723e-06, "epoch": 8.84, "percentage": 88.4, "elapsed_time": "2:28:10", "remaining_time": "0:19:26"} | |
| {"current_steps": 2220, "total_steps": 2500, "loss": 0.11138873100280762, "lr": 3.799347102981665e-06, "epoch": 8.88, "percentage": 88.8, "elapsed_time": "2:28:48", "remaining_time": "0:18:46"} | |
| {"current_steps": 2230, "total_steps": 2500, "loss": 0.10770895481109619, "lr": 3.536920955414885e-06, "epoch": 8.92, "percentage": 89.2, "elapsed_time": "2:29:26", "remaining_time": "0:18:05"} | |
| {"current_steps": 2240, "total_steps": 2500, "loss": 0.11167995929718018, "lr": 3.2835528771693992e-06, "epoch": 8.96, "percentage": 89.6, "elapsed_time": "2:30:02", "remaining_time": "0:17:24"} | |
| {"current_steps": 2250, "total_steps": 2500, "loss": 0.11738998889923095, "lr": 3.039292262854088e-06, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "2:30:38", "remaining_time": "0:16:44"} | |
| {"current_steps": 2260, "total_steps": 2500, "loss": 0.10072145462036133, "lr": 2.804186731559677e-06, "epoch": 9.04, "percentage": 90.4, "elapsed_time": "2:31:15", "remaining_time": "0:16:03"} | |
| {"current_steps": 2270, "total_steps": 2500, "loss": 0.09228388667106628, "lr": 2.5782821175753422e-06, "epoch": 9.08, "percentage": 90.8, "elapsed_time": "2:31:51", "remaining_time": "0:15:23"} | |
| {"current_steps": 2280, "total_steps": 2500, "loss": 0.09626876711845397, "lr": 2.361622461453178e-06, "epoch": 9.12, "percentage": 91.2, "elapsed_time": "2:32:28", "remaining_time": "0:14:42"} | |
| {"current_steps": 2290, "total_steps": 2500, "loss": 0.0960278868675232, "lr": 2.154250001422431e-06, "epoch": 9.16, "percentage": 91.6, "elapsed_time": "2:33:07", "remaining_time": "0:14:02"} | |
| {"current_steps": 2300, "total_steps": 2500, "loss": 0.0941778838634491, "lr": 1.956205165155078e-06, "epoch": 9.2, "percentage": 92.0, "elapsed_time": "2:33:45", "remaining_time": "0:13:22"} | |
| {"current_steps": 2300, "total_steps": 2500, "eval_loss": 0.6419874429702759, "epoch": 9.2, "percentage": 92.0, "elapsed_time": "2:34:05", "remaining_time": "0:13:23"} | |
| {"current_steps": 2310, "total_steps": 2500, "loss": 0.09725146293640137, "lr": 1.7675265618843362e-06, "epoch": 9.24, "percentage": 92.4, "elapsed_time": "2:34:46", "remaining_time": "0:12:43"} | |
| {"current_steps": 2320, "total_steps": 2500, "loss": 0.09353782534599304, "lr": 1.5882509748777808e-06, "epoch": 9.28, "percentage": 92.8, "elapsed_time": "2:35:21", "remaining_time": "0:12:03"} | |
| {"current_steps": 2330, "total_steps": 2500, "loss": 0.09848537445068359, "lr": 1.4184133542663014e-06, "epoch": 9.32, "percentage": 93.2, "elapsed_time": "2:35:54", "remaining_time": "0:11:22"} | |
| {"current_steps": 2340, "total_steps": 2500, "loss": 0.10164464712142944, "lr": 1.258046810230562e-06, "epoch": 9.36, "percentage": 93.6, "elapsed_time": "2:36:32", "remaining_time": "0:10:42"} | |
| {"current_steps": 2350, "total_steps": 2500, "loss": 0.0934177041053772, "lr": 1.1071826065460588e-06, "epoch": 9.4, "percentage": 94.0, "elapsed_time": "2:37:08", "remaining_time": "0:10:01"} | |
| {"current_steps": 2360, "total_steps": 2500, "loss": 0.1012031078338623, "lr": 9.65850154488218e-07, "epoch": 9.44, "percentage": 94.4, "elapsed_time": "2:37:43", "remaining_time": "0:09:21"} | |
| {"current_steps": 2370, "total_steps": 2500, "loss": 0.09371918439865112, "lr": 8.340770070986214e-07, "epoch": 9.48, "percentage": 94.8, "elapsed_time": "2:38:22", "remaining_time": "0:08:41"} | |
| {"current_steps": 2380, "total_steps": 2500, "loss": 0.09450345039367676, "lr": 7.11888853813436e-07, "epoch": 9.52, "percentage": 95.2, "elapsed_time": "2:39:01", "remaining_time": "0:08:01"} | |
| {"current_steps": 2390, "total_steps": 2500, "loss": 0.09499152898788452, "lr": 5.993095154552431e-07, "epoch": 9.56, "percentage": 95.6, "elapsed_time": "2:39:40", "remaining_time": "0:07:20"} | |
| {"current_steps": 2400, "total_steps": 2500, "loss": 0.10716021060943604, "lr": 4.963609395891299e-07, "epoch": 9.6, "percentage": 96.0, "elapsed_time": "2:40:19", "remaining_time": "0:06:40"} | |
| {"current_steps": 2400, "total_steps": 2500, "eval_loss": 0.6402375102043152, "epoch": 9.6, "percentage": 96.0, "elapsed_time": "2:40:38", "remaining_time": "0:06:41"} | |
| {"current_steps": 2410, "total_steps": 2500, "loss": 0.09596163630485535, "lr": 4.030631962439302e-07, "epoch": 9.64, "percentage": 96.4, "elapsed_time": "2:41:17", "remaining_time": "0:06:01"} | |
| {"current_steps": 2420, "total_steps": 2500, "loss": 0.09645589590072631, "lr": 3.1943447399958027e-07, "epoch": 9.68, "percentage": 96.8, "elapsed_time": "2:41:52", "remaining_time": "0:05:21"} | |
| {"current_steps": 2430, "total_steps": 2500, "loss": 0.09415926933288574, "lr": 2.4549107644117885e-07, "epoch": 9.72, "percentage": 97.2, "elapsed_time": "2:42:26", "remaining_time": "0:04:40"} | |
| {"current_steps": 2440, "total_steps": 2500, "loss": 0.10026730298995971, "lr": 1.8124741898058462e-07, "epoch": 9.76, "percentage": 97.6, "elapsed_time": "2:42:59", "remaining_time": "0:04:00"} | |
| {"current_steps": 2450, "total_steps": 2500, "loss": 0.09711679220199584, "lr": 1.267160260461253e-07, "epoch": 9.8, "percentage": 98.0, "elapsed_time": "2:43:33", "remaining_time": "0:03:20"} | |
| {"current_steps": 2460, "total_steps": 2500, "loss": 0.09345818758010864, "lr": 8.190752864088436e-08, "epoch": 9.84, "percentage": 98.4, "elapsed_time": "2:44:08", "remaining_time": "0:02:40"} | |
| {"current_steps": 2470, "total_steps": 2500, "loss": 0.102751624584198, "lr": 4.683066227023081e-08, "epoch": 9.88, "percentage": 98.8, "elapsed_time": "2:44:45", "remaining_time": "0:02:00"} | |
| {"current_steps": 2480, "total_steps": 2500, "loss": 0.0988599717617035, "lr": 2.1492265238748366e-08, "epoch": 9.92, "percentage": 99.2, "elapsed_time": "2:45:21", "remaining_time": "0:01:20"} | |
| {"current_steps": 2490, "total_steps": 2500, "loss": 0.09828301668167114, "lr": 5.897277317157279e-09, "epoch": 9.96, "percentage": 99.6, "elapsed_time": "2:45:56", "remaining_time": "0:00:39"} | |
| {"current_steps": 2500, "total_steps": 2500, "loss": 0.0937616467475891, "lr": 4.873877924582715e-11, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "2:46:32", "remaining_time": "0:00:00"} | |
| {"current_steps": 2500, "total_steps": 2500, "eval_loss": 0.6409608721733093, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "2:46:50", "remaining_time": "0:00:00"} | |
| {"current_steps": 2500, "total_steps": 2500, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "2:46:51", "remaining_time": "0:00:00"} | |