{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 6.2261097861441765, "learning_rate": 3.2258064516129035e-07, "loss": 0.7992, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.2717836628013774, "learning_rate": 6.451612903225807e-07, "loss": 0.8043, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.325651280368531, "learning_rate": 9.67741935483871e-07, "loss": 0.812, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.203002539855323, "learning_rate": 1.2903225806451614e-06, "loss": 0.8152, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 5.708794343076741, "learning_rate": 1.6129032258064516e-06, "loss": 0.7923, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.3538333660824975, "learning_rate": 1.935483870967742e-06, "loss": 0.7712, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.34441590427549, "learning_rate": 2.2580645161290324e-06, "loss": 0.7758, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 3.9697596815870253, "learning_rate": 2.580645161290323e-06, "loss": 0.7525, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.275750836758953, "learning_rate": 2.903225806451613e-06, "loss": 0.7218, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.0525032844656645, "learning_rate": 3.225806451612903e-06, "loss": 0.7083, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 1.947238950938309, "learning_rate": 3.548387096774194e-06, "loss": 0.729, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.6053075244387416, "learning_rate": 3.870967741935484e-06, "loss": 0.69, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.9684762544557057, "learning_rate": 4.193548387096774e-06, "loss": 0.7137, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.060083571765886, "learning_rate": 4.516129032258065e-06, "loss": 0.7021, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.016924874762021, "learning_rate": 4.838709677419355e-06, "loss": 0.7029, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.015595094072019, "learning_rate": 5.161290322580646e-06, "loss": 0.6526, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.740336152213742, "learning_rate": 5.483870967741935e-06, "loss": 0.6514, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.0539894794979805, "learning_rate": 5.806451612903226e-06, "loss": 0.6281, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.4012948299592567, "learning_rate": 6.129032258064517e-06, "loss": 0.6254, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.1918696867072713, "learning_rate": 6.451612903225806e-06, "loss": 0.6234, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.292986418244195, "learning_rate": 6.774193548387097e-06, "loss": 0.6019, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.2798497793068317, "learning_rate": 7.096774193548388e-06, "loss": 0.6078, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.0150256191234157, "learning_rate": 7.4193548387096784e-06, "loss": 0.5999, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.8043498463526109, "learning_rate": 7.741935483870968e-06, "loss": 0.5826, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.9052567195780795, "learning_rate": 8.064516129032258e-06, "loss": 0.5826, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.8141826047304964, "learning_rate": 8.387096774193549e-06, "loss": 0.5613, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.6701976183935249, "learning_rate": 8.70967741935484e-06, "loss": 0.561, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.7787803334979648, "learning_rate": 9.03225806451613e-06, "loss": 0.5543, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7545468906489995, "learning_rate": 9.35483870967742e-06, "loss": 0.5517, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.5533991956212235, "learning_rate": 9.67741935483871e-06, "loss": 0.5375, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.6357494196915167, "learning_rate": 1e-05, "loss": 0.5514, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.8157131742306958, "learning_rate": 1.0322580645161291e-05, "loss": 0.5432, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.6315571168287157, "learning_rate": 1.0645161290322582e-05, "loss": 0.5303, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.47863644832542324, "learning_rate": 1.096774193548387e-05, "loss": 0.5307, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.6453773442072431, "learning_rate": 1.1290322580645164e-05, "loss": 0.5281, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6264702829769256, "learning_rate": 1.1612903225806453e-05, "loss": 0.5359, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5156059375271903, "learning_rate": 1.1935483870967743e-05, "loss": 0.5219, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6025994268074982, "learning_rate": 1.2258064516129034e-05, "loss": 0.5218, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5058679953174398, "learning_rate": 1.2580645161290324e-05, "loss": 0.528, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.5966889388136908, "learning_rate": 1.2903225806451613e-05, "loss": 0.5283, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.548939549266992, "learning_rate": 1.3225806451612903e-05, "loss": 0.5281, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.4894061430107667, "learning_rate": 1.3548387096774194e-05, "loss": 0.5284, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.4647296526404282, "learning_rate": 1.3870967741935486e-05, "loss": 0.4942, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.485963084955271, "learning_rate": 1.4193548387096776e-05, "loss": 0.4865, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.4612536619275583, "learning_rate": 1.4516129032258066e-05, "loss": 0.5151, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.47583507774248096, "learning_rate": 1.4838709677419357e-05, "loss": 0.4967, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.40785646228009975, "learning_rate": 1.5161290322580646e-05, "loss": 0.5094, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.42088056038415456, "learning_rate": 1.5483870967741936e-05, "loss": 0.5048, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.42943491094084124, "learning_rate": 1.5806451612903226e-05, "loss": 0.5038, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.38190150470114076, "learning_rate": 1.6129032258064517e-05, "loss": 0.4951, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.3684706466576187, "learning_rate": 1.6451612903225807e-05, "loss": 0.4937, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.4502635045388667, "learning_rate": 1.6774193548387098e-05, "loss": 0.4921, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.4226850345822703, "learning_rate": 1.7096774193548388e-05, "loss": 0.5048, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.36742574580378295, "learning_rate": 1.741935483870968e-05, "loss": 0.4861, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.4464919018701757, "learning_rate": 1.774193548387097e-05, "loss": 0.4835, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.48207194948472243, "learning_rate": 1.806451612903226e-05, "loss": 0.511, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.5712171276559329, "learning_rate": 1.838709677419355e-05, "loss": 0.4826, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.5024077451411345, "learning_rate": 1.870967741935484e-05, "loss": 0.4789, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.45087213671996396, "learning_rate": 1.903225806451613e-05, "loss": 0.4733, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5755368427028855, "learning_rate": 1.935483870967742e-05, "loss": 0.478, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5189412885359231, "learning_rate": 1.967741935483871e-05, "loss": 0.495, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.5920175005644891, "learning_rate": 2e-05, "loss": 0.4854, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.522207504419153, "learning_rate": 2.0322580645161292e-05, "loss": 0.485, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.46186605958339244, "learning_rate": 2.0645161290322582e-05, "loss": 0.4719, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.4947568316116691, "learning_rate": 2.0967741935483873e-05, "loss": 0.4848, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.786574644464834, "learning_rate": 2.1290322580645163e-05, "loss": 0.4906, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 1.018961364782763, "learning_rate": 2.161290322580645e-05, "loss": 0.4816, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.8655113993332554, "learning_rate": 2.193548387096774e-05, "loss": 0.4733, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 1.024663718681665, "learning_rate": 2.225806451612903e-05, "loss": 0.4708, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 1.2743266816139396, "learning_rate": 2.2580645161290328e-05, "loss": 0.4994, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7893266552999105, "learning_rate": 2.2903225806451615e-05, "loss": 0.4672, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 1.1869318973656515, "learning_rate": 2.3225806451612906e-05, "loss": 0.4967, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.8313004673377109, "learning_rate": 2.3548387096774196e-05, "loss": 0.4843, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.8505863655349873, "learning_rate": 2.3870967741935486e-05, "loss": 0.473, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.851383129856202, "learning_rate": 2.4193548387096777e-05, "loss": 0.4788, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.631617892286867, "learning_rate": 2.4516129032258067e-05, "loss": 0.4727, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.6631688720289463, "learning_rate": 2.4838709677419358e-05, "loss": 0.4879, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.7278069558779597, "learning_rate": 2.5161290322580648e-05, "loss": 0.4765, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.615381879321262, "learning_rate": 2.548387096774194e-05, "loss": 0.4585, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.7119028500444586, "learning_rate": 2.5806451612903226e-05, "loss": 0.4816, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.8450029312369092, "learning_rate": 2.6129032258064516e-05, "loss": 0.4733, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.7703129606040241, "learning_rate": 2.6451612903225806e-05, "loss": 0.4619, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.6019639660232513, "learning_rate": 2.6774193548387097e-05, "loss": 0.4635, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.9389798231832055, "learning_rate": 2.7096774193548387e-05, "loss": 0.4802, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 1.2709199843703791, "learning_rate": 2.7419354838709678e-05, "loss": 0.4656, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.9977242157909181, "learning_rate": 2.774193548387097e-05, "loss": 0.4725, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.9373767814786491, "learning_rate": 2.8064516129032262e-05, "loss": 0.463, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.92198544273846, "learning_rate": 2.8387096774193552e-05, "loss": 0.4848, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.123322518257047, "learning_rate": 2.8709677419354843e-05, "loss": 0.4569, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.8238961161608216, "learning_rate": 2.9032258064516133e-05, "loss": 0.4783, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.3591280267498453, "learning_rate": 2.9354838709677423e-05, "loss": 0.4714, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.8737795943399969, "learning_rate": 2.9677419354838714e-05, "loss": 0.4704, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.165120023073424, "learning_rate": 3.0000000000000004e-05, "loss": 0.4669, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.0268173764072372, "learning_rate": 3.032258064516129e-05, "loss": 0.4687, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.8275963297796262, "learning_rate": 3.0645161290322585e-05, "loss": 0.4533, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.918778497427167, "learning_rate": 3.096774193548387e-05, "loss": 0.4516, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.1960843905402212, "learning_rate": 3.1290322580645166e-05, "loss": 0.4653, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.8028221806195716, "learning_rate": 3.161290322580645e-05, "loss": 0.4521, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 1.1904336593652118, "learning_rate": 3.193548387096774e-05, "loss": 0.4659, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.7223054295643014, "learning_rate": 3.2258064516129034e-05, "loss": 0.453, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.8448173434205684, "learning_rate": 3.258064516129033e-05, "loss": 0.4652, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.1180959334315552, "learning_rate": 3.2903225806451614e-05, "loss": 0.4735, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.7747042799256035, "learning_rate": 3.322580645161291e-05, "loss": 0.4496, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.7836333695786769, "learning_rate": 3.3548387096774195e-05, "loss": 0.4484, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.9259738504924802, "learning_rate": 3.387096774193549e-05, "loss": 0.4684, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.1781249299978627, "learning_rate": 3.4193548387096776e-05, "loss": 0.4705, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 1.4167926791114924, "learning_rate": 3.451612903225807e-05, "loss": 0.4654, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.8355836310698508, "learning_rate": 3.483870967741936e-05, "loss": 0.454, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.5302950468266525, "learning_rate": 3.516129032258065e-05, "loss": 0.4816, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 1.383863077159545, "learning_rate": 3.548387096774194e-05, "loss": 0.4693, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.7773201361293582, "learning_rate": 3.5806451612903225e-05, "loss": 0.4668, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.6654715907905624, "learning_rate": 3.612903225806452e-05, "loss": 0.4675, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.944531558422689, "learning_rate": 3.6451612903225805e-05, "loss": 0.4525, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.6027910849573919, "learning_rate": 3.67741935483871e-05, "loss": 0.4585, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.331396734040665, "learning_rate": 3.7096774193548386e-05, "loss": 0.4749, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.5138106084787444, "learning_rate": 3.741935483870968e-05, "loss": 0.4701, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.348790622214385, "learning_rate": 3.7741935483870974e-05, "loss": 0.464, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.2273786145722314, "learning_rate": 3.806451612903226e-05, "loss": 0.4571, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.1700932236971764, "learning_rate": 3.8387096774193555e-05, "loss": 0.4629, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 1.0248079447378022, "learning_rate": 3.870967741935484e-05, "loss": 0.4499, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.951967934120823, "learning_rate": 3.9032258064516135e-05, "loss": 0.4428, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 1.2124240873278926, "learning_rate": 3.935483870967742e-05, "loss": 0.4626, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 1.0354231076704887, "learning_rate": 3.9677419354838716e-05, "loss": 0.4648, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.1605489218073655, "learning_rate": 4e-05, "loss": 0.4613, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 1.145369668084183, "learning_rate": 3.9999920040266474e-05, "loss": 0.4417, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.022564405063952, "learning_rate": 3.999968016170525e-05, "loss": 0.4642, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.9652532205216916, "learning_rate": 3.9999280366234394e-05, "loss": 0.4725, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.1996774368222909, "learning_rate": 3.999872065705065e-05, "loss": 0.4604, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 1.2839341716838242, "learning_rate": 3.999800103862945e-05, "loss": 0.4542, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.9462834274943882, "learning_rate": 3.9997121516724834e-05, "loss": 0.4588, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 1.007802766977578, "learning_rate": 3.999608209836944e-05, "loss": 0.457, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.3966706533943465, "learning_rate": 3.999488279187443e-05, "loss": 0.4571, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.8420734477126186, "learning_rate": 3.9993523606829425e-05, "loss": 0.448, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 1.387455782191252, "learning_rate": 3.9992004554102435e-05, "loss": 0.4683, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 1.1481419466458667, "learning_rate": 3.999032564583976e-05, "loss": 0.4519, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.9317193080895807, "learning_rate": 3.998848689546591e-05, "loss": 0.4519, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 1.281419778050067, "learning_rate": 3.9986488317683496e-05, "loss": 0.4621, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.9656069213288737, "learning_rate": 3.9984329928473067e-05, "loss": 0.4472, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 1.1136273640320282, "learning_rate": 3.998201174509306e-05, "loss": 0.4526, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.933073598813819, "learning_rate": 3.997953378607961e-05, "loss": 0.446, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 1.1629101837431866, "learning_rate": 3.9976896071246403e-05, "loss": 0.4389, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.9599946801216442, "learning_rate": 3.997409862168454e-05, "loss": 0.4472, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.0312485716349844, "learning_rate": 3.997114145976237e-05, "loss": 0.445, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 1.0525691969032076, "learning_rate": 3.9968024609125245e-05, "loss": 0.4519, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 1.01752292220465, "learning_rate": 3.996474809469545e-05, "loss": 0.4457, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 1.0059366713828168, "learning_rate": 3.996131194267189e-05, "loss": 0.4509, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 1.0834602031158547, "learning_rate": 3.995771618052995e-05, "loss": 0.4353, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.8875167806609464, "learning_rate": 3.9953960837021256e-05, "loss": 0.4602, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.9931348205186209, "learning_rate": 3.995004594217343e-05, "loss": 0.4424, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7128321114756078, "learning_rate": 3.994597152728987e-05, "loss": 0.4489, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.7493540573883151, "learning_rate": 3.994173762494947e-05, "loss": 0.4418, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 1.0023345417449558, "learning_rate": 3.9937344269006424e-05, "loss": 0.4299, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7769414091367589, "learning_rate": 3.993279149458988e-05, "loss": 0.4462, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.7651477082535295, "learning_rate": 3.9928079338103695e-05, "loss": 0.4415, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.8403394571763393, "learning_rate": 3.992320783722616e-05, "loss": 0.4378, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.6871469089747201, "learning_rate": 3.991817703090965e-05, "loss": 0.4478, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.9230819774414982, "learning_rate": 3.991298695938038e-05, "loss": 0.4322, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.7821699468082606, "learning_rate": 3.9907637664138e-05, "loss": 0.4504, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.7235619867069933, "learning_rate": 3.990212918795534e-05, "loss": 0.4459, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.6657226527226077, "learning_rate": 3.9896461574878036e-05, "loss": 0.445, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6566265713669829, "learning_rate": 3.989063487022416e-05, "loss": 0.4429, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.7486502585269124, "learning_rate": 3.9884649120583903e-05, "loss": 0.4346, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.772206531957731, "learning_rate": 3.987850437381915e-05, "loss": 0.4521, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.761456191159745, "learning_rate": 3.987220067906313e-05, "loss": 0.4455, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.9661812637342855, "learning_rate": 3.986573808672002e-05, "loss": 0.4508, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 1.3210405877185971, "learning_rate": 3.9859116648464534e-05, "loss": 0.4585, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.7331283523478396, "learning_rate": 3.985233641724152e-05, "loss": 0.4327, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7701622531784398, "learning_rate": 3.984539744726554e-05, "loss": 0.4403, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.733769304393686, "learning_rate": 3.983829979402038e-05, "loss": 0.4461, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 1.2039913276488763, "learning_rate": 3.983104351425871e-05, "loss": 0.4616, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.9632330139351646, "learning_rate": 3.982362866600154e-05, "loss": 0.4499, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.6068690637519466, "learning_rate": 3.9816055308537806e-05, "loss": 0.4344, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.6022814696648962, "learning_rate": 3.980832350242388e-05, "loss": 0.4455, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.6383863419027256, "learning_rate": 3.980043330948306e-05, "loss": 0.4329, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.6666154498837851, "learning_rate": 3.9792384792805124e-05, "loss": 0.4263, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.6663383951750069, "learning_rate": 3.978417801674579e-05, "loss": 0.4341, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.5304844459959736, "learning_rate": 3.9775813046926244e-05, "loss": 0.4339, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.5462281661468482, "learning_rate": 3.976728995023254e-05, "loss": 0.4344, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.7000533459315919, "learning_rate": 3.975860879481514e-05, "loss": 0.445, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.8804254424480921, "learning_rate": 3.974976965008833e-05, "loss": 0.4216, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.9073694156524174, "learning_rate": 3.9740772586729674e-05, "loss": 0.4473, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.689415447931239, "learning_rate": 3.973161767667946e-05, "loss": 0.4323, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6507168894766852, "learning_rate": 3.972230499314009e-05, "loss": 0.4325, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.6395931717214897, "learning_rate": 3.9712834610575545e-05, "loss": 0.4423, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.7034463169816023, "learning_rate": 3.9703206604710746e-05, "loss": 0.4442, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.8266323993924715, "learning_rate": 3.969342105253098e-05, "loss": 0.4477, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.834696690877527, "learning_rate": 3.9683478032281246e-05, "loss": 0.431, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.6560549821710195, "learning_rate": 3.967337762346568e-05, "loss": 0.431, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.612487419210545, "learning_rate": 3.9663119906846885e-05, "loss": 0.4266, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.4998349327401551, "learning_rate": 3.965270496444528e-05, "loss": 0.438, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6249349750271076, "learning_rate": 3.9642132879538465e-05, "loss": 0.4359, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5252097975893051, "learning_rate": 3.9631403736660566e-05, "loss": 0.425, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.6756075636711946, "learning_rate": 3.962051762160151e-05, "loss": 0.4323, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.8187016544993013, "learning_rate": 3.960947462140638e-05, "loss": 0.4264, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.6196578872255512, "learning_rate": 3.959827482437472e-05, "loss": 0.4207, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.5825171647383087, "learning_rate": 3.958691832005981e-05, "loss": 0.4304, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5514489199407867, "learning_rate": 3.9575405199267944e-05, "loss": 0.4242, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.6432079151576783, "learning_rate": 3.956373555405774e-05, "loss": 0.4389, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.672511395304782, "learning_rate": 3.955190947773937e-05, "loss": 0.4442, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.6386265890980478, "learning_rate": 3.9539927064873824e-05, "loss": 0.425, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.6763824806056511, "learning_rate": 3.952778841127214e-05, "loss": 0.4338, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.6723986366850315, "learning_rate": 3.95154936139947e-05, "loss": 0.4577, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.5942000622104338, "learning_rate": 3.950304277135034e-05, "loss": 0.4278, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.6781043856943778, "learning_rate": 3.94904359828957e-05, "loss": 0.43, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.7067983630679934, "learning_rate": 3.94776733494343e-05, "loss": 0.4372, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.6227442727322821, "learning_rate": 3.9464754973015826e-05, "loss": 0.4311, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.6672472512383744, "learning_rate": 3.9451680956935275e-05, "loss": 0.428, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.767733102777411, "learning_rate": 3.943845140573213e-05, "loss": 0.4381, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.6149134049500559, "learning_rate": 3.942506642518952e-05, "loss": 0.4329, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.6418938596480572, "learning_rate": 3.9411526122333396e-05, "loss": 0.4302, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.9711161189885225, "learning_rate": 3.939783060543167e-05, "loss": 0.4393, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.9936095751066949, "learning_rate": 3.938397998399333e-05, "loss": 0.4275, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.8186790383682524, "learning_rate": 3.936997436876756e-05, "loss": 0.4568, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6568891482868405, "learning_rate": 3.935581387174289e-05, "loss": 0.4279, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.6996668024453528, "learning_rate": 3.9341498606146295e-05, "loss": 0.4305, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.7812308852731097, "learning_rate": 3.932702868644224e-05, "loss": 0.4344, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.5615747544242249, "learning_rate": 3.931240422833181e-05, "loss": 0.432, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.7051196877679892, "learning_rate": 3.9297625348751806e-05, "loss": 0.4279, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.7587868279128983, "learning_rate": 3.9282692165873744e-05, "loss": 0.4344, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.7499366159535814, "learning_rate": 3.9267604799102945e-05, "loss": 0.4288, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.6326782234860102, "learning_rate": 3.9252363369077615e-05, "loss": 0.4299, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5525922378611929, "learning_rate": 3.9236967997667796e-05, "loss": 0.4253, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.5289116278838981, "learning_rate": 3.9221418807974496e-05, "loss": 0.4296, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5323285190555165, "learning_rate": 3.92057159243286e-05, "loss": 0.4288, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.5296962771227676, "learning_rate": 3.9189859472289956e-05, "loss": 0.4263, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.6218295455919403, "learning_rate": 3.9173849578646324e-05, "loss": 0.4271, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.6934560489315307, "learning_rate": 3.9157686371412395e-05, "loss": 0.4191, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5300878813490233, "learning_rate": 3.914136997982874e-05, "loss": 0.4323, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5660507253268235, "learning_rate": 3.912490053436079e-05, "loss": 0.4329, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5420855270957574, "learning_rate": 3.9108278166697805e-05, "loss": 0.4302, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.6980931298940509, "learning_rate": 3.909150300975178e-05, "loss": 0.4394, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.6944067068488942, "learning_rate": 3.907457519765642e-05, "loss": 0.4333, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.6576966463827559, "learning_rate": 3.905749486576607e-05, "loss": 0.4225, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.7790848867683634, "learning_rate": 3.90402621506546e-05, "loss": 0.4114, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.5298159264360089, "learning_rate": 3.902287719011435e-05, "loss": 0.4297, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.49883274679515155, "learning_rate": 3.900534012315499e-05, "loss": 0.444, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5561970651561554, "learning_rate": 3.8987651090002454e-05, "loss": 0.4266, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.7101132230743977, "learning_rate": 3.896981023209777e-05, "loss": 0.42, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.753166983675595, "learning_rate": 3.8951817692095966e-05, "loss": 0.4321, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.67549127991895, "learning_rate": 3.893367361386491e-05, "loss": 0.4358, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.5072485184944172, "learning_rate": 3.891537814248417e-05, "loss": 0.4271, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4409616272921719, "learning_rate": 3.889693142424384e-05, "loss": 0.4395, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.4973218862669857, "learning_rate": 3.8878333606643405e-05, "loss": 0.417, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.5654299520733814, "learning_rate": 3.885958483839049e-05, "loss": 0.4131, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.6834089665856187, "learning_rate": 3.8840685269399786e-05, "loss": 0.4206, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.7264701157448912, "learning_rate": 3.882163505079171e-05, "loss": 0.4216, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.6969155124911476, "learning_rate": 3.880243433489132e-05, "loss": 0.4235, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5745666274215253, "learning_rate": 3.878308327522702e-05, "loss": 0.3987, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.4844681249330372, "learning_rate": 3.876358202652936e-05, "loss": 0.3896, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.538124783125258, "learning_rate": 3.8743930744729835e-05, "loss": 0.3939, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.5514346863265672, "learning_rate": 3.8724129586959535e-05, "loss": 0.3924, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.4806077732281162, "learning_rate": 3.870417871154801e-05, "loss": 0.3842, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.5023250957691602, "learning_rate": 3.868407827802192e-05, "loss": 0.3751, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.551863161889452, "learning_rate": 3.8663828447103804e-05, "loss": 0.3889, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.6276392225009089, "learning_rate": 3.8643429380710765e-05, "loss": 0.3934, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.6388433668379547, "learning_rate": 3.862288124195319e-05, "loss": 0.3959, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.4714233761737193, "learning_rate": 3.8602184195133464e-05, "loss": 0.3812, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5291411004223132, "learning_rate": 3.8581338405744604e-05, "loss": 0.3874, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.65330891185458, "learning_rate": 3.8560344040468996e-05, "loss": 0.3867, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5455886162726942, "learning_rate": 3.853920126717703e-05, "loss": 0.3812, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.5822776293913925, "learning_rate": 3.851791025492574e-05, "loss": 0.4003, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.6880756924712844, "learning_rate": 3.8496471173957515e-05, "loss": 0.3922, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.4951756045981264, "learning_rate": 3.847488419569866e-05, "loss": 0.3855, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.9811678939606828, "learning_rate": 3.8453149492758077e-05, "loss": 0.3959, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.9894067080344762, "learning_rate": 3.8431267238925886e-05, "loss": 0.3917, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.4983808998932081, "learning_rate": 3.840923760917199e-05, "loss": 0.3934, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.7981228784100288, "learning_rate": 3.838706077964473e-05, "loss": 0.4005, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.5657345592780465, "learning_rate": 3.836473692766944e-05, "loss": 0.376, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.4911098860071859, "learning_rate": 3.834226623174705e-05, "loss": 0.3995, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.588277347043334, "learning_rate": 3.831964887155264e-05, "loss": 0.4024, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.42426087879361074, "learning_rate": 3.829688502793403e-05, "loss": 0.3851, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5234266058656396, "learning_rate": 3.827397488291029e-05, "loss": 0.3992, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.6009820291549427, "learning_rate": 3.8250918619670343e-05, "loss": 0.3872, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.525803726567273, "learning_rate": 3.822771642257145e-05, "loss": 0.4015, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.5959520823536482, "learning_rate": 3.820436847713776e-05, "loss": 0.4027, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.5964150779358477, "learning_rate": 3.8180874970058826e-05, "loss": 0.3666, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5433953489016419, "learning_rate": 3.8157236089188103e-05, "loss": 0.3843, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.4295287620130814, "learning_rate": 3.813345202354145e-05, "loss": 0.4038, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.6001870166745928, "learning_rate": 3.810952296329563e-05, "loss": 0.4007, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.6672521777836111, "learning_rate": 3.808544909978676e-05, "loss": 0.3867, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.626875049590781, "learning_rate": 3.806123062550882e-05, "loss": 0.3833, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.5221672525226306, "learning_rate": 3.803686773411208e-05, "loss": 0.38, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.5144961398475812, "learning_rate": 3.801236062040158e-05, "loss": 0.3956, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.4597225492688166, "learning_rate": 3.798770948033553e-05, "loss": 0.3709, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5692653605399516, "learning_rate": 3.796291451102381e-05, "loss": 0.3967, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.4476107117886192, "learning_rate": 3.793797591072631e-05, "loss": 0.392, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.4051109786040723, "learning_rate": 3.791289387885144e-05, "loss": 0.3913, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.46198358199540507, "learning_rate": 3.788766861595443e-05, "loss": 0.3846, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5594996814707078, "learning_rate": 3.7862300323735835e-05, "loss": 0.3919, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.5007196274520902, "learning_rate": 3.783678920503983e-05, "loss": 0.4077, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.5309054122090887, "learning_rate": 3.781113546385265e-05, "loss": 0.3841, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.6656795150985277, "learning_rate": 3.7785339305300916e-05, "loss": 0.3908, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6380398307020223, "learning_rate": 3.7759400935650025e-05, "loss": 0.3843, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.5992823438424286, "learning_rate": 3.77333205623025e-05, "loss": 0.4, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.7312277556457971, "learning_rate": 3.7707098393796295e-05, "loss": 0.3785, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.528898359340593, "learning_rate": 3.7680734639803185e-05, "loss": 0.3849, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.47962304059096694, "learning_rate": 3.765422951112704e-05, "loss": 0.3796, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.5081275769437719, "learning_rate": 3.762758321970216e-05, "loss": 0.3926, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.604394973461617, "learning_rate": 3.7600795978591584e-05, "loss": 0.4011, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.5918675112543058, "learning_rate": 3.757386800198538e-05, "loss": 0.4046, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.7259492512080126, "learning_rate": 3.7546799505198925e-05, "loss": 0.3911, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.6867822850398075, "learning_rate": 3.7519590704671197e-05, "loss": 0.3718, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.4071008282689887, "learning_rate": 3.749224181796305e-05, "loss": 0.3833, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.5548281939923068, "learning_rate": 3.746475306375545e-05, "loss": 0.3931, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.5348844301067888, "learning_rate": 3.743712466184774e-05, "loss": 0.3814, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 1.5056014903473869, "learning_rate": 3.7409356833155885e-05, "loss": 0.4065, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.5579464670686761, "learning_rate": 3.73814497997107e-05, "loss": 0.398, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 1.058683193086143, "learning_rate": 3.7353403784656095e-05, "loss": 0.3784, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 1.1289081775805834, "learning_rate": 3.732521901224724e-05, "loss": 0.4084, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6970830327081544, "learning_rate": 3.7296895707848844e-05, "loss": 0.3934, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.51795995284662, "learning_rate": 3.7268434097933275e-05, "loss": 0.3961, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.6909057263798679, "learning_rate": 3.723983441007882e-05, "loss": 0.3787, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.8669541576496338, "learning_rate": 3.721109687296781e-05, "loss": 0.3943, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.8077956527057318, "learning_rate": 3.718222171638484e-05, "loss": 0.3935, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5484147851233626, "learning_rate": 3.715320917121488e-05, "loss": 0.3939, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.5483193531862545, "learning_rate": 3.712405946944149e-05, "loss": 0.3819, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.6886590947173884, "learning_rate": 3.709477284414488e-05, "loss": 0.39, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.8123552945382145, "learning_rate": 3.7065349529500136e-05, "loss": 0.407, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.7206285743866094, "learning_rate": 3.7035789760775305e-05, "loss": 0.3812, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.5301523577073225, "learning_rate": 3.70060937743295e-05, "loss": 0.3763, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.4760745414105602, "learning_rate": 3.6976261807611045e-05, "loss": 0.393, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.6873400827854519, "learning_rate": 3.694629409915555e-05, "loss": 0.3921, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.7425055497330607, "learning_rate": 3.691619088858401e-05, "loss": 0.3734, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.47971771685951053, "learning_rate": 3.68859524166009e-05, "loss": 0.3843, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.8761196494969224, "learning_rate": 3.6855578924992226e-05, "loss": 0.394, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.9237742505013397, "learning_rate": 3.6825070656623626e-05, "loss": 0.3869, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.735913985539214, "learning_rate": 3.67944278554384e-05, "loss": 0.3795, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.5323339003545412, "learning_rate": 3.676365076645557e-05, "loss": 0.3865, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.7067610320465401, "learning_rate": 3.673273963576791e-05, "loss": 0.3738, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.6549403780255703, "learning_rate": 3.670169471054001e-05, "loss": 0.3826, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.6369136112479608, "learning_rate": 3.6670516239006254e-05, "loss": 0.3798, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.5357740100798015, "learning_rate": 3.663920447046888e-05, "loss": 0.3881, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.5484242459655476, "learning_rate": 3.6607759655295954e-05, "loss": 0.3913, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.5639993412540062, "learning_rate": 3.657618204491937e-05, "loss": 0.3933, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.5379712855916269, "learning_rate": 3.6544471891832875e-05, "loss": 0.3819, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.5018230645903432, "learning_rate": 3.6512629449589983e-05, "loss": 0.3879, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.6835174001363935, "learning_rate": 3.6480654972802045e-05, "loss": 0.3907, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.6648129029063596, "learning_rate": 3.644854871713611e-05, "loss": 0.3903, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.5093636252569471, "learning_rate": 3.6416310939312924e-05, "loss": 0.3979, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.652189584232788, "learning_rate": 3.638394189710493e-05, "loss": 0.397, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.7712117083723115, "learning_rate": 3.635144184933412e-05, "loss": 0.3913, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.6708204343552145, "learning_rate": 3.6318811055869994e-05, "loss": 0.3853, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.4734203394900249, "learning_rate": 3.628604977762752e-05, "loss": 0.3924, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.6838534276105479, "learning_rate": 3.6253158276565004e-05, "loss": 0.3943, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.6372041142976433, "learning_rate": 3.6220136815682016e-05, "loss": 0.3906, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.5788226608142896, "learning_rate": 3.618698565901727e-05, "loss": 0.3957, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.7548477653118822, "learning_rate": 3.615370507164654e-05, "loss": 0.3818, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.631292354999809, "learning_rate": 3.61202953196805e-05, "loss": 0.3882, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.8014924384096284, "learning_rate": 3.6086756670262654e-05, "loss": 0.3925, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.46956244290532256, "learning_rate": 3.6053089391567135e-05, "loss": 0.3831, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.6429782144943578, "learning_rate": 3.601929375279662e-05, "loss": 0.3843, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.6340509692633481, "learning_rate": 3.598537002418012e-05, "loss": 0.3768, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.4606858382923839, "learning_rate": 3.5951318476970885e-05, "loss": 0.3778, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5595777745657181, "learning_rate": 3.591713938344416e-05, "loss": 0.3986, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.4906579321387629, "learning_rate": 3.588283301689507e-05, "loss": 0.3982, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.4985763436483905, "learning_rate": 3.5848399651636424e-05, "loss": 0.3961, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.48755956559439045, "learning_rate": 3.5813839562996473e-05, "loss": 0.3863, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.484286084924765, "learning_rate": 3.5779153027316775e-05, "loss": 0.3867, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.595708477626769, "learning_rate": 3.574434032194994e-05, "loss": 0.3857, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.47216302984368913, "learning_rate": 3.5709401725257436e-05, "loss": 0.4051, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.44811459094712713, "learning_rate": 3.5674337516607346e-05, "loss": 0.3818, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.5098670895107178, "learning_rate": 3.563914797637216e-05, "loss": 0.3992, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.48592905802492375, "learning_rate": 3.560383338592649e-05, "loss": 0.3885, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5133904704669686, "learning_rate": 3.556839402764487e-05, "loss": 0.3811, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.459922256386911, "learning_rate": 3.553283018489946e-05, "loss": 0.3772, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5415066837152517, "learning_rate": 3.54971421420578e-05, "loss": 0.3789, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.4487319475668654, "learning_rate": 3.5461330184480524e-05, "loss": 0.3683, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.4151218665874673, "learning_rate": 3.54253945985191e-05, "loss": 0.3855, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.5551474804245674, "learning_rate": 3.5389335671513524e-05, "loss": 0.3942, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.3955236441382353, "learning_rate": 3.5353153691789986e-05, "loss": 0.3784, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.5189795526569946, "learning_rate": 3.531684894865866e-05, "loss": 0.3917, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.4498708262779881, "learning_rate": 3.528042173241128e-05, "loss": 0.3961, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4261044356569846, "learning_rate": 3.524387233431892e-05, "loss": 0.3843, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.39180047322135886, "learning_rate": 3.520720104662958e-05, "loss": 0.3788, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.4577864077743075, "learning_rate": 3.5170408162565904e-05, "loss": 0.3734, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.49126962019268583, "learning_rate": 3.513349397632281e-05, "loss": 0.3962, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.5206393383467205, "learning_rate": 3.5096458783065145e-05, "loss": 0.3864, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.5380988136555684, "learning_rate": 3.505930287892533e-05, "loss": 0.3801, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.49948332849877564, "learning_rate": 3.502202656100099e-05, "loss": 0.3859, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.5512191883000351, "learning_rate": 3.498463012735256e-05, "loss": 0.3894, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.5801801273612543, "learning_rate": 3.494711387700094e-05, "loss": 0.3852, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.5624341901043877, "learning_rate": 3.490947810992505e-05, "loss": 0.3895, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.4454322639982269, "learning_rate": 3.48717231270595e-05, "loss": 0.3918, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.6297101321372556, "learning_rate": 3.483384923029211e-05, "loss": 0.3905, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.6470142110244017, "learning_rate": 3.479585672246156e-05, "loss": 0.3861, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.4646418833813086, "learning_rate": 3.4757745907354924e-05, "loss": 0.3792, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.49869015543374134, "learning_rate": 3.471951708970527e-05, "loss": 0.392, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.664399694801895, "learning_rate": 3.468117057518921e-05, "loss": 0.3888, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.5013010389724175, "learning_rate": 3.4642706670424426e-05, "loss": 0.3875, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.4382202827281309, "learning_rate": 3.460412568296731e-05, "loss": 0.3822, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.632095263897543, "learning_rate": 3.456542792131039e-05, "loss": 0.3866, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.5657850397599766, "learning_rate": 3.4526613694879936e-05, "loss": 0.3804, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.3667771416378925, "learning_rate": 3.448768331403348e-05, "loss": 0.3818, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.5076756469131105, "learning_rate": 3.44486370900573e-05, "loss": 0.3783, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.5459984160655014, "learning_rate": 3.440947533516396e-05, "loss": 0.3791, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.5048147627363347, "learning_rate": 3.4370198362489816e-05, "loss": 0.392, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.46510609725250973, "learning_rate": 3.43308064860925e-05, "loss": 0.3709, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.5538026765062621, "learning_rate": 3.4291300020948393e-05, "loss": 0.3946, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.5473692284690739, "learning_rate": 3.425167928295015e-05, "loss": 0.3772, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.3945679558772016, "learning_rate": 3.421194458890411e-05, "loss": 0.3766, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.5448043298337327, "learning_rate": 3.4172096256527865e-05, "loss": 0.3927, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.6254194203756326, "learning_rate": 3.4132134604447595e-05, "loss": 0.3908, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.3820404518991928, "learning_rate": 3.409205995219561e-05, "loss": 0.3801, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.5568455085158146, "learning_rate": 3.4051872620207765e-05, "loss": 0.382, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.43552823003164937, "learning_rate": 3.40115729298209e-05, "loss": 0.3874, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.42976562926595574, "learning_rate": 3.397116120327025e-05, "loss": 0.379, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.4480113316850934, "learning_rate": 3.3930637763686916e-05, "loss": 0.3742, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.5761278981702768, "learning_rate": 3.389000293509524e-05, "loss": 0.3885, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.5539550913391287, "learning_rate": 3.3849257042410225e-05, "loss": 0.3689, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.523737687195207, "learning_rate": 3.380840041143494e-05, "loss": 0.3769, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.5432736680898252, "learning_rate": 3.376743336885792e-05, "loss": 0.3878, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4684899938909767, "learning_rate": 3.372635624225055e-05, "loss": 0.3874, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.48570358626866794, "learning_rate": 3.3685169360064445e-05, "loss": 0.3777, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.47469316676178536, "learning_rate": 3.3643873051628804e-05, "loss": 0.3829, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.42318250765629944, "learning_rate": 3.3602467647147814e-05, "loss": 0.3858, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.4045170870003658, "learning_rate": 3.356095347769799e-05, "loss": 0.3892, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.5210704279946063, "learning_rate": 3.351933087522552e-05, "loss": 0.3785, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.384879473126043, "learning_rate": 3.3477600172543626e-05, "loss": 0.3734, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.4328401321955483, "learning_rate": 3.3435761703329894e-05, "loss": 0.3854, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.4375194647272637, "learning_rate": 3.3393815802123606e-05, "loss": 0.394, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.4183723365977529, "learning_rate": 3.335176280432308e-05, "loss": 0.3744, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.5276127143977974, "learning_rate": 3.330960304618295e-05, "loss": 0.3851, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.5059994660139095, "learning_rate": 3.326733686481153e-05, "loss": 0.3718, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.4758069715158602, "learning_rate": 3.3224964598168084e-05, "loss": 0.387, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.49506093818858, "learning_rate": 3.318248658506012e-05, "loss": 0.3872, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.4187129620110788, "learning_rate": 3.313990316514069e-05, "loss": 0.3827, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.4404118454120631, "learning_rate": 3.309721467890571e-05, "loss": 0.3924, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.3800062069478053, "learning_rate": 3.305442146769115e-05, "loss": 0.3974, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.4274988998504963, "learning_rate": 3.30115238736704e-05, "loss": 0.3708, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.42808407911163443, "learning_rate": 3.296852223985148e-05, "loss": 0.3826, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.4699548151028978, "learning_rate": 3.2925416910074315e-05, "loss": 0.369, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.4685529909278573, "learning_rate": 3.288220822900796e-05, "loss": 0.3794, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.47764422141883234, "learning_rate": 3.283889654214788e-05, "loss": 0.3879, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.4302990554506411, "learning_rate": 3.279548219581317e-05, "loss": 0.3805, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.43128404843363916, "learning_rate": 3.275196553714379e-05, "loss": 0.3746, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.48655297335992015, "learning_rate": 3.270834691409778e-05, "loss": 0.393, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.39287258759071514, "learning_rate": 3.266462667544849e-05, "loss": 0.3744, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.45032195298342576, "learning_rate": 3.262080517078178e-05, "loss": 0.396, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.6185801332036531, "learning_rate": 3.257688275049323e-05, "loss": 0.3927, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.5239773504261022, "learning_rate": 3.253285976578535e-05, "loss": 0.3769, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.46805299208971624, "learning_rate": 3.2488736568664756e-05, "loss": 0.3822, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.6087079772791385, "learning_rate": 3.244451351193935e-05, "loss": 0.3831, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.43251836584948455, "learning_rate": 3.240019094921551e-05, "loss": 0.3748, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.4952679677792668, "learning_rate": 3.235576923489527e-05, "loss": 0.3832, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.41155131619268726, "learning_rate": 3.2311248724173476e-05, "loss": 0.3751, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.4752421813095128, "learning_rate": 3.226662977303494e-05, "loss": 0.3803, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.38950017545427307, "learning_rate": 3.2221912738251626e-05, "loss": 0.3886, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.5181225585050684, "learning_rate": 3.2177097977379736e-05, "loss": 0.3773, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.4333136670829311, "learning_rate": 3.21321858487569e-05, "loss": 0.3879, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.4486443277034727, "learning_rate": 3.208717671149931e-05, "loss": 0.3706, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.4025734749603414, "learning_rate": 3.204207092549882e-05, "loss": 0.3763, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.4274361803012289, "learning_rate": 3.19968688514201e-05, "loss": 0.3986, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.6470426959375326, "learning_rate": 3.195157085069774e-05, "loss": 0.3829, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.6083213968696388, "learning_rate": 3.190617728553332e-05, "loss": 0.385, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.4141674137508911, "learning_rate": 3.1860688518892606e-05, "loss": 0.3729, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.5109260154037814, "learning_rate": 3.181510491450254e-05, "loss": 0.38, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.7327956158117686, "learning_rate": 3.176942683684842e-05, "loss": 0.3752, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.6274318569294633, "learning_rate": 3.1723654651170934e-05, "loss": 0.3849, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.3591628542903483, "learning_rate": 3.167778872346327e-05, "loss": 0.3836, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.5605802008967226, "learning_rate": 3.163182942046815e-05, "loss": 0.3825, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.5100308001306669, "learning_rate": 3.158577710967494e-05, "loss": 0.3793, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.659761258057112, "learning_rate": 3.153963215931669e-05, "loss": 0.3776, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.7494910484958914, "learning_rate": 3.14933949383672e-05, "loss": 0.3758, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.5236319690928617, "learning_rate": 3.144706581653805e-05, "loss": 0.3821, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.5425287911280672, "learning_rate": 3.140064516427566e-05, "loss": 0.3836, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.5440948214587358, "learning_rate": 3.135413335275833e-05, "loss": 0.3847, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.48387916687927396, "learning_rate": 3.130753075389327e-05, "loss": 0.3697, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.4174383098618729, "learning_rate": 3.1260837740313625e-05, "loss": 0.3752, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.49661899219585365, "learning_rate": 3.121405468537547e-05, "loss": 0.3824, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.4494781547069374, "learning_rate": 3.116718196315488e-05, "loss": 0.3731, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.5548090581836521, "learning_rate": 3.1120219948444894e-05, "loss": 0.3666, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.6070358893439504, "learning_rate": 3.107316901675252e-05, "loss": 0.394, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.46572324489354483, "learning_rate": 3.1026029544295745e-05, "loss": 0.393, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.5493422479068988, "learning_rate": 3.097880190800057e-05, "loss": 0.3839, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.4932928023677151, "learning_rate": 3.093148648549788e-05, "loss": 0.3997, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.4367826060378638, "learning_rate": 3.088408365512055e-05, "loss": 0.3919, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.4762404128163616, "learning_rate": 3.083659379590034e-05, "loss": 0.3841, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.4145953164113427, "learning_rate": 3.0789017287564913e-05, "loss": 0.3798, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.3505900526223974, "learning_rate": 3.074135451053475e-05, "loss": 0.3711, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.3842525220553451, "learning_rate": 3.069360584592015e-05, "loss": 0.3839, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.42916323722642563, "learning_rate": 3.064577167551816e-05, "loss": 0.3789, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.39822867056685923, "learning_rate": 3.059785238180953e-05, "loss": 0.3803, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.3475613822173484, "learning_rate": 3.054984834795566e-05, "loss": 0.378, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.4606341567439486, "learning_rate": 3.0501759957795537e-05, "loss": 0.3867, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.4064279348356458, "learning_rate": 3.0453587595842627e-05, "loss": 0.3875, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4192805263830732, "learning_rate": 3.0405331647281856e-05, "loss": 0.3819, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.40447326697793223, "learning_rate": 3.0356992497966508e-05, "loss": 0.3689, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.49550977518538175, "learning_rate": 3.0308570534415137e-05, "loss": 0.3831, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.5410340830407806, "learning_rate": 3.0260066143808467e-05, "loss": 0.3855, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.41716306216045107, "learning_rate": 3.021147971398632e-05, "loss": 0.3803, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.45796465571132094, "learning_rate": 3.0162811633444478e-05, "loss": 0.3858, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.5137745034332498, "learning_rate": 3.0114062291331635e-05, "loss": 0.3718, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.4079677947483675, "learning_rate": 3.0065232077446217e-05, "loss": 0.368, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.5124224267720536, "learning_rate": 3.001632138223332e-05, "loss": 0.3745, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.5213826409628545, "learning_rate": 2.9967330596781565e-05, "loss": 0.3317, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.4560363647995602, "learning_rate": 2.9918260112819952e-05, "loss": 0.3335, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.42991320388823806, "learning_rate": 2.9869110322714778e-05, "loss": 0.3301, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5273059107667628, "learning_rate": 2.9819881619466447e-05, "loss": 0.3268, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.511024079554745, "learning_rate": 2.9770574396706364e-05, "loss": 0.3443, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5853415627925488, "learning_rate": 2.972118904869376e-05, "loss": 0.3216, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.44138362544443105, "learning_rate": 2.9671725970312563e-05, "loss": 0.3331, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.70931333025428, "learning_rate": 2.9622185557068238e-05, "loss": 0.3252, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.6069168347490355, "learning_rate": 2.95725682050846e-05, "loss": 0.3366, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.48747858430114643, "learning_rate": 2.9522874311100684e-05, "loss": 0.321, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.520089849608399, "learning_rate": 2.9473104272467526e-05, "loss": 0.3232, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.5886515834134605, "learning_rate": 2.942325848714505e-05, "loss": 0.335, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.552768466457189, "learning_rate": 2.9373337353698804e-05, "loss": 0.3305, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.367479384926514, "learning_rate": 2.932334127129686e-05, "loss": 0.3189, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.47789296512398, "learning_rate": 2.9273270639706547e-05, "loss": 0.3301, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.41864884112207107, "learning_rate": 2.922312585929131e-05, "loss": 0.3278, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.37431821652714575, "learning_rate": 2.9172907331007478e-05, "loss": 0.3206, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.34994745564794755, "learning_rate": 2.9122615456401053e-05, "loss": 0.3202, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.3897160335406495, "learning_rate": 2.9072250637604535e-05, "loss": 0.3304, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.3792350257639845, "learning_rate": 2.9021813277333667e-05, "loss": 0.318, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.4891276878923638, "learning_rate": 2.8971303778884244e-05, "loss": 0.3403, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.3999915273867046, "learning_rate": 2.8920722546128863e-05, "loss": 0.3412, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.4147213305976618, "learning_rate": 2.887006998351372e-05, "loss": 0.3347, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3688742962569892, "learning_rate": 2.881934649605535e-05, "loss": 0.334, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.3626961218415493, "learning_rate": 2.8768552489337408e-05, "loss": 0.3247, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.3301311041747866, "learning_rate": 2.8717688369507425e-05, "loss": 0.3322, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.4745567835792035, "learning_rate": 2.8666754543273535e-05, "loss": 0.3301, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.4142707816635897, "learning_rate": 2.8615751417901273e-05, "loss": 0.3314, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.3777586856728137, "learning_rate": 2.856467940121025e-05, "loss": 0.3274, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.4115877967613032, "learning_rate": 2.8513538901570964e-05, "loss": 0.325, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.4493904520653939, "learning_rate": 2.846233032790149e-05, "loss": 0.3344, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.3528048662515778, "learning_rate": 2.84110540896642e-05, "loss": 0.3349, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.39292822478576694, "learning_rate": 2.8359710596862555e-05, "loss": 0.3339, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.45503097526777814, "learning_rate": 2.8308300260037734e-05, "loss": 0.3299, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3543197200902583, "learning_rate": 2.8256823490265424e-05, "loss": 0.3162, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3832202264521118, "learning_rate": 2.8205280699152515e-05, "loss": 0.3299, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.41032526496695787, "learning_rate": 2.8153672298833777e-05, "loss": 0.3355, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3853068189850333, "learning_rate": 2.8101998701968615e-05, "loss": 0.3297, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.41995552921694623, "learning_rate": 2.805026032173773e-05, "loss": 0.3395, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3655919057176836, "learning_rate": 2.7998457571839832e-05, "loss": 0.3275, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.31446045572593667, "learning_rate": 2.7946590866488322e-05, "loss": 0.3225, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.4073064258159972, "learning_rate": 2.7894660620408e-05, "loss": 0.3373, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.4226268660863442, "learning_rate": 2.784266724883173e-05, "loss": 0.3416, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3134035623238087, "learning_rate": 2.7790611167497128e-05, "loss": 0.3238, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.4207529419489319, "learning_rate": 2.7738492792643224e-05, "loss": 0.3342, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.37966518543120015, "learning_rate": 2.768631254100716e-05, "loss": 0.3406, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.3623521717757906, "learning_rate": 2.7634070829820836e-05, "loss": 0.3275, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.33876385332430514, "learning_rate": 2.7581768076807592e-05, "loss": 0.3299, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.36090421348254104, "learning_rate": 2.7529404700178832e-05, "loss": 0.335, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3207980495609672, "learning_rate": 2.7476981118630735e-05, "loss": 0.332, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.36452758621920417, "learning_rate": 2.742449775134085e-05, "loss": 0.3269, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.32636973335490665, "learning_rate": 2.7371955017964788e-05, "loss": 0.3298, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.36787155579822806, "learning_rate": 2.7319353338632845e-05, "loss": 0.3271, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3330446645857325, "learning_rate": 2.7266693133946645e-05, "loss": 0.3328, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.3854320611506621, "learning_rate": 2.7213974824975785e-05, "loss": 0.3296, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.33851789379213326, "learning_rate": 2.7161198833254464e-05, "loss": 0.3304, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.31788667947945615, "learning_rate": 2.7108365580778095e-05, "loss": 0.3255, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.2962845500056351, "learning_rate": 2.705547548999996e-05, "loss": 0.3312, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.32325217692641145, "learning_rate": 2.7002528983827817e-05, "loss": 0.3291, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.35535467483589667, "learning_rate": 2.6949526485620517e-05, "loss": 0.3338, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.3284635076150435, "learning_rate": 2.6896468419184623e-05, "loss": 0.3316, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.37458651226594464, "learning_rate": 2.6843355208771024e-05, "loss": 0.3374, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.30665998206846673, "learning_rate": 2.6790187279071536e-05, "loss": 0.3295, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.3594769634634411, "learning_rate": 2.67369650552155e-05, "loss": 0.329, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.34069460037518007, "learning_rate": 2.6683688962766407e-05, "loss": 0.335, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.34987047121630405, "learning_rate": 2.6630359427718468e-05, "loss": 0.3289, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.2993011464251092, "learning_rate": 2.6576976876493225e-05, "loss": 0.3258, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.3895002062663446, "learning_rate": 2.652354173593614e-05, "loss": 0.3402, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.35572180258705055, "learning_rate": 2.647005443331317e-05, "loss": 0.3362, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.33907713645592125, "learning_rate": 2.6416515396307354e-05, "loss": 0.3375, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.35486611630701714, "learning_rate": 2.636292505301542e-05, "loss": 0.3394, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.3698070364923052, "learning_rate": 2.630928383194431e-05, "loss": 0.33, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.3818165373363919, "learning_rate": 2.625559216200781e-05, "loss": 0.3347, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.38453648336797663, "learning_rate": 2.620185047252308e-05, "loss": 0.3374, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.3291689345652599, "learning_rate": 2.614805919320723e-05, "loss": 0.3257, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3429305079926836, "learning_rate": 2.6094218754173895e-05, "loss": 0.3273, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.35834276118949404, "learning_rate": 2.60403295859298e-05, "loss": 0.3287, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3743737821310122, "learning_rate": 2.5986392119371297e-05, "loss": 0.3395, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.38686366025024493, "learning_rate": 2.5932406785780928e-05, "loss": 0.324, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3532466206328132, "learning_rate": 2.5878374016823987e-05, "loss": 0.3384, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.35543146068382625, "learning_rate": 2.5824294244545045e-05, "loss": 0.3315, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.3697301032670907, "learning_rate": 2.577016790136453e-05, "loss": 0.336, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3986892746497814, "learning_rate": 2.5715995420075225e-05, "loss": 0.3323, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.3526947595888307, "learning_rate": 2.5661777233838864e-05, "loss": 0.3239, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3509631682632769, "learning_rate": 2.5607513776182616e-05, "loss": 0.3247, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.3659620747313324, "learning_rate": 2.5553205480995633e-05, "loss": 0.3284, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.4173823640621538, "learning_rate": 2.5498852782525604e-05, "loss": 0.333, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.35599315992483044, "learning_rate": 2.5444456115375252e-05, "loss": 0.3274, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.4641410188802057, "learning_rate": 2.539001591449889e-05, "loss": 0.3372, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.35320504325834745, "learning_rate": 2.53355326151989e-05, "loss": 0.325, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.37816465812801797, "learning_rate": 2.5281006653122288e-05, "loss": 0.3266, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.33976880825343975, "learning_rate": 2.5226438464257217e-05, "loss": 0.3456, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3705889755986993, "learning_rate": 2.5171828484929447e-05, "loss": 0.3322, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.3034195678148419, "learning_rate": 2.5117177151798934e-05, "loss": 0.3293, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.38015125929365606, "learning_rate": 2.506248490185627e-05, "loss": 0.3391, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.40665401992739214, "learning_rate": 2.500775217241923e-05, "loss": 0.3294, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3089533271299827, "learning_rate": 2.4952979401129266e-05, "loss": 0.3235, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.4577191409821041, "learning_rate": 2.4898167025948e-05, "loss": 0.3366, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.31327413085393424, "learning_rate": 2.4843315485153703e-05, "loss": 0.3332, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.4655001902890136, "learning_rate": 2.4788425217337856e-05, "loss": 0.3355, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.31920945172618265, "learning_rate": 2.4733496661401572e-05, "loss": 0.3377, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.3775783810901616, "learning_rate": 2.4678530256552114e-05, "loss": 0.3327, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.29640114764025993, "learning_rate": 2.46235264422994e-05, "loss": 0.3235, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.4078826877497936, "learning_rate": 2.4568485658452452e-05, "loss": 0.3267, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.36210808259411736, "learning_rate": 2.451340834511592e-05, "loss": 0.327, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.33874600279540446, "learning_rate": 2.4458294942686528e-05, "loss": 0.3323, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.350728848485844, "learning_rate": 2.440314589184958e-05, "loss": 0.3258, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.3610310474381399, "learning_rate": 2.434796163357541e-05, "loss": 0.3397, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.34281923303212364, "learning_rate": 2.429274260911588e-05, "loss": 0.332, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.4030523189891252, "learning_rate": 2.423748926000084e-05, "loss": 0.3326, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.32556117899890935, "learning_rate": 2.418220202803459e-05, "loss": 0.3347, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3803263282452234, "learning_rate": 2.412688135529237e-05, "loss": 0.3377, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.4272863773498727, "learning_rate": 2.4071527684116807e-05, "loss": 0.3359, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.38571651899011605, "learning_rate": 2.4016141457114372e-05, "loss": 0.3276, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.3291707517717791, "learning_rate": 2.396072311715187e-05, "loss": 0.3312, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.35513823165372116, "learning_rate": 2.3905273107352863e-05, "loss": 0.33, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.35501697771029983, "learning_rate": 2.3849791871094157e-05, "loss": 0.3303, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.44695463506717187, "learning_rate": 2.379427985200223e-05, "loss": 0.3325, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.31634379402054197, "learning_rate": 2.373873749394972e-05, "loss": 0.334, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.4074470985700305, "learning_rate": 2.3683165241051836e-05, "loss": 0.3339, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.33628351636126796, "learning_rate": 2.3627563537662823e-05, "loss": 0.3227, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.3503523112073845, "learning_rate": 2.3571932828372433e-05, "loss": 0.3258, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.33642902342964953, "learning_rate": 2.351627355800233e-05, "loss": 0.3285, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.31580536316972, "learning_rate": 2.346058617160256e-05, "loss": 0.3198, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.4882912980231789, "learning_rate": 2.3404871114447976e-05, "loss": 0.3389, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3722199502768517, "learning_rate": 2.334912883203469e-05, "loss": 0.3354, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.4838750334600524, "learning_rate": 2.3293359770076505e-05, "loss": 0.3339, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.2970134460130801, "learning_rate": 2.323756437450136e-05, "loss": 0.3221, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.4487477720203529, "learning_rate": 2.3181743091447754e-05, "loss": 0.3303, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.2836658664763772, "learning_rate": 2.3125896367261164e-05, "loss": 0.3286, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.39878526074673576, "learning_rate": 2.307002464849052e-05, "loss": 0.3278, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.3402147846460814, "learning_rate": 2.30141283818846e-05, "loss": 0.3353, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3417404005949604, "learning_rate": 2.2958208014388462e-05, "loss": 0.331, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.35509968152528315, "learning_rate": 2.2902263993139857e-05, "loss": 0.3381, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.35795210181154896, "learning_rate": 2.2846296765465708e-05, "loss": 0.329, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.34560646686646185, "learning_rate": 2.2790306778878465e-05, "loss": 0.3308, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.3578819060055358, "learning_rate": 2.273429448107257e-05, "loss": 0.3134, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.39988932837012947, "learning_rate": 2.2678260319920868e-05, "loss": 0.3252, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.3739361590235061, "learning_rate": 2.262220474347102e-05, "loss": 0.3309, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.36216866678315474, "learning_rate": 2.2566128199941918e-05, "loss": 0.3255, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.37019193071118345, "learning_rate": 2.2510031137720104e-05, "loss": 0.3373, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.35582366571750484, "learning_rate": 2.2453914005356206e-05, "loss": 0.3292, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.3343684083795695, "learning_rate": 2.2397777251561302e-05, "loss": 0.3264, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.3181420516785811, "learning_rate": 2.2341621325203393e-05, "loss": 0.3314, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.32278742432339, "learning_rate": 2.2285446675303764e-05, "loss": 0.327, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.31199841886566626, "learning_rate": 2.2229253751033423e-05, "loss": 0.3155, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.3223259668360993, "learning_rate": 2.2173043001709492e-05, "loss": 0.3259, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.32912079429346497, "learning_rate": 2.2116814876791627e-05, "loss": 0.333, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.31375679340251444, "learning_rate": 2.2060569825878413e-05, "loss": 0.336, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.32857856038362493, "learning_rate": 2.2004308298703777e-05, "loss": 0.3324, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.3039480240493573, "learning_rate": 2.1948030745133396e-05, "loss": 0.3311, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.3075081402706174, "learning_rate": 2.1891737615161083e-05, "loss": 0.3257, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.34494683884992455, "learning_rate": 2.1835429358905218e-05, "loss": 0.3384, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3215808597785053, "learning_rate": 2.17791064266051e-05, "loss": 0.3316, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.393739870738204, "learning_rate": 2.172276926861741e-05, "loss": 0.3364, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.309069511342719, "learning_rate": 2.166641833541255e-05, "loss": 0.3373, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3612564976859204, "learning_rate": 2.161005407757109e-05, "loss": 0.3276, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3327952235785939, "learning_rate": 2.155367694578013e-05, "loss": 0.3405, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.299562509960106, "learning_rate": 2.1497287390829712e-05, "loss": 0.3375, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.3612865609393688, "learning_rate": 2.1440885863609208e-05, "loss": 0.3299, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.2741552923469152, "learning_rate": 2.1384472815103737e-05, "loss": 0.3318, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.30183378988115905, "learning_rate": 2.1328048696390534e-05, "loss": 0.3304, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.2774745653832324, "learning_rate": 2.1271613958635342e-05, "loss": 0.3263, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.3070656701025138, "learning_rate": 2.1215169053088825e-05, "loss": 0.3321, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.31582397598138334, "learning_rate": 2.1158714431082937e-05, "loss": 0.3271, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.27415708129051813, "learning_rate": 2.110225054402733e-05, "loss": 0.3319, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.3347915444142502, "learning_rate": 2.1045777843405747e-05, "loss": 0.3224, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.29556576559989545, "learning_rate": 2.09892967807724e-05, "loss": 0.3256, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.29873185804620794, "learning_rate": 2.093280780774835e-05, "loss": 0.341, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.2861584680209201, "learning_rate": 2.087631137601793e-05, "loss": 0.3397, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.2877649649997946, "learning_rate": 2.0819807937325104e-05, "loss": 0.318, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.323494454485772, "learning_rate": 2.0763297943469847e-05, "loss": 0.3333, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.28298062088626014, "learning_rate": 2.070678184630458e-05, "loss": 0.3225, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.27182263385777045, "learning_rate": 2.06502600977305e-05, "loss": 0.3269, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.31301918965255376, "learning_rate": 2.0593733149694008e-05, "loss": 0.3179, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.31065711816160063, "learning_rate": 2.0537201454183074e-05, "loss": 0.3271, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.2902276370250716, "learning_rate": 2.0480665463223626e-05, "loss": 0.3409, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.295915191038569, "learning_rate": 2.042412562887594e-05, "loss": 0.3319, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.3257658436483335, "learning_rate": 2.0367582403231033e-05, "loss": 0.333, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.3148852812300193, "learning_rate": 2.0311036238407023e-05, "loss": 0.327, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.3053015776367031, "learning_rate": 2.0254487586545534e-05, "loss": 0.3255, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.3575955807992751, "learning_rate": 2.0197936899808088e-05, "loss": 0.336, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.34367631985873826, "learning_rate": 2.0141384630372466e-05, "loss": 0.3291, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.33014704445394305, "learning_rate": 2.0084831230429106e-05, "loss": 0.3318, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.2873581058911794, "learning_rate": 2.0028277152177492e-05, "loss": 0.3368, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.287543522978766, "learning_rate": 1.9971722847822518e-05, "loss": 0.3255, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.25846816936652783, "learning_rate": 1.99151687695709e-05, "loss": 0.3211, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.2968249898091591, "learning_rate": 1.9858615369627537e-05, "loss": 0.3303, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.27852917195812454, "learning_rate": 1.9802063100191916e-05, "loss": 0.3324, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.2892480290450167, "learning_rate": 1.974551241345447e-05, "loss": 0.3199, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.31054819088280045, "learning_rate": 1.9688963761592984e-05, "loss": 0.3294, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.25596978875919973, "learning_rate": 1.963241759676897e-05, "loss": 0.3296, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.2988349482292453, "learning_rate": 1.9575874371124066e-05, "loss": 0.3285, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.2775906214225421, "learning_rate": 1.951933453677638e-05, "loss": 0.3217, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.28130477742190446, "learning_rate": 1.9462798545816932e-05, "loss": 0.3426, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.249942701088029, "learning_rate": 1.9406266850305996e-05, "loss": 0.3336, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.3124482506043465, "learning_rate": 1.9349739902269503e-05, "loss": 0.3186, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.254791228131245, "learning_rate": 1.9293218153695425e-05, "loss": 0.3248, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.2927604882979594, "learning_rate": 1.9236702056530153e-05, "loss": 0.3297, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.28546614299045237, "learning_rate": 1.9180192062674907e-05, "loss": 0.335, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.29505859786778504, "learning_rate": 1.9123688623982076e-05, "loss": 0.3315, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3678037213612779, "learning_rate": 1.906719219225165e-05, "loss": 0.3388, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.24724646200529599, "learning_rate": 1.9010703219227603e-05, "loss": 0.3224, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.3346173807943254, "learning_rate": 1.8954222156594256e-05, "loss": 0.3394, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.25340521607235167, "learning_rate": 1.8897749455972673e-05, "loss": 0.3203, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.2898304121363381, "learning_rate": 1.884128556891707e-05, "loss": 0.3286, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.29715205908776626, "learning_rate": 1.878483094691119e-05, "loss": 0.327, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.30334434582271164, "learning_rate": 1.8728386041364664e-05, "loss": 0.3331, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.3266491726182427, "learning_rate": 1.867195130360947e-05, "loss": 0.3374, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.2776433476181056, "learning_rate": 1.8615527184896263e-05, "loss": 0.3205, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.29416446971549604, "learning_rate": 1.8559114136390795e-05, "loss": 0.3313, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.33966771416382946, "learning_rate": 1.8502712609170298e-05, "loss": 0.3209, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.28638787844353203, "learning_rate": 1.8446323054219876e-05, "loss": 0.335, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.35360335844062807, "learning_rate": 1.838994592242891e-05, "loss": 0.3335, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.3003437046373217, "learning_rate": 1.8333581664587453e-05, "loss": 0.3266, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.32977599975031685, "learning_rate": 1.8277230731382593e-05, "loss": 0.3252, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.34061942173546467, "learning_rate": 1.82208935733949e-05, "loss": 0.3421, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.29489219253469534, "learning_rate": 1.8164570641094793e-05, "loss": 0.3385, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.30798648543462165, "learning_rate": 1.810826238483892e-05, "loss": 0.3337, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.2912190936312891, "learning_rate": 1.8051969254866608e-05, "loss": 0.3365, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.2847395784282535, "learning_rate": 1.7995691701296226e-05, "loss": 0.3312, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.25920528477183924, "learning_rate": 1.7939430174121593e-05, "loss": 0.323, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.2631826971246945, "learning_rate": 1.788318512320838e-05, "loss": 0.3311, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.30249614152342175, "learning_rate": 1.782695699829051e-05, "loss": 0.3259, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.2574525049516543, "learning_rate": 1.7770746248966587e-05, "loss": 0.3276, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.30596979459741747, "learning_rate": 1.7714553324696243e-05, "loss": 0.3348, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.29455281436594266, "learning_rate": 1.7658378674796614e-05, "loss": 0.3217, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.2516202759962299, "learning_rate": 1.76022227484387e-05, "loss": 0.3267, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.29912726926841005, "learning_rate": 1.7546085994643807e-05, "loss": 0.3362, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.2607608585647733, "learning_rate": 1.7489968862279902e-05, "loss": 0.3264, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.27470061825635467, "learning_rate": 1.743387180005809e-05, "loss": 0.3279, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.2952442632085356, "learning_rate": 1.737779525652899e-05, "loss": 0.3328, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.2747010139088515, "learning_rate": 1.732173968007914e-05, "loss": 0.3253, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2749220958308461, "learning_rate": 1.7265705518927437e-05, "loss": 0.3212, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.2760730978730554, "learning_rate": 1.7209693221121542e-05, "loss": 0.3261, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.2993565450773008, "learning_rate": 1.7153703234534302e-05, "loss": 0.3227, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.29739671751107094, "learning_rate": 1.709773600686015e-05, "loss": 0.3288, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.28370899229919655, "learning_rate": 1.7041791985611548e-05, "loss": 0.3313, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.29146283597586436, "learning_rate": 1.69858716181154e-05, "loss": 0.3292, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.2744613298474618, "learning_rate": 1.692997535150948e-05, "loss": 0.3146, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.28511907834154093, "learning_rate": 1.687410363273884e-05, "loss": 0.3361, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.29308948544972047, "learning_rate": 1.6818256908552257e-05, "loss": 0.3257, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.31036802959264026, "learning_rate": 1.6762435625498646e-05, "loss": 0.3368, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3143904020959225, "learning_rate": 1.67066402299235e-05, "loss": 0.3245, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.30490786151466626, "learning_rate": 1.6650871167965313e-05, "loss": 0.3263, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.36213604861962556, "learning_rate": 1.6595128885552028e-05, "loss": 0.3389, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.28434549129254255, "learning_rate": 1.653941382839745e-05, "loss": 0.3245, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.4639217718270056, "learning_rate": 1.6483726441997673e-05, "loss": 0.2752, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.3031398054055453, "learning_rate": 1.642806717162757e-05, "loss": 0.2785, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.522191144134054, "learning_rate": 1.637243646233718e-05, "loss": 0.2777, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.49997347326446945, "learning_rate": 1.6316834758948174e-05, "loss": 0.2865, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.40885401004728616, "learning_rate": 1.6261262506050282e-05, "loss": 0.2857, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.40173735361676555, "learning_rate": 1.620572014799777e-05, "loss": 0.2786, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.42952578917104733, "learning_rate": 1.6150208128905857e-05, "loss": 0.2859, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.3778730094756615, "learning_rate": 1.6094726892647147e-05, "loss": 0.2896, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.4178127413824748, "learning_rate": 1.6039276882848135e-05, "loss": 0.2808, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.36698714927787196, "learning_rate": 1.5983858542885635e-05, "loss": 0.2775, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.37890386925329356, "learning_rate": 1.5928472315883203e-05, "loss": 0.2667, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.32074496314989864, "learning_rate": 1.5873118644707633e-05, "loss": 0.2753, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.38313978051160835, "learning_rate": 1.5817797971965413e-05, "loss": 0.2801, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.3207123023789512, "learning_rate": 1.576251073999917e-05, "loss": 0.2798, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.34281183277840444, "learning_rate": 1.5707257390884126e-05, "loss": 0.2732, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.32360045627147704, "learning_rate": 1.5652038366424595e-05, "loss": 0.2766, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3082995896588431, "learning_rate": 1.5596854108150424e-05, "loss": 0.2744, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3259341471509848, "learning_rate": 1.5541705057313476e-05, "loss": 0.2713, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.29698232668494395, "learning_rate": 1.5486591654884086e-05, "loss": 0.2742, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.4064555223333744, "learning_rate": 1.543151434154755e-05, "loss": 0.289, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.32677887190206484, "learning_rate": 1.5376473557700615e-05, "loss": 0.2881, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.3403515632345309, "learning_rate": 1.5321469743447893e-05, "loss": 0.2715, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.32047140413618797, "learning_rate": 1.5266503338598434e-05, "loss": 0.2757, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.31470356059340926, "learning_rate": 1.5211574782662149e-05, "loss": 0.2792, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.29227486405774666, "learning_rate": 1.5156684514846307e-05, "loss": 0.2825, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.2810282238621462, "learning_rate": 1.5101832974052012e-05, "loss": 0.2718, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.2818598258602082, "learning_rate": 1.5047020598870737e-05, "loss": 0.2676, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.2795281408232774, "learning_rate": 1.4992247827580778e-05, "loss": 0.2818, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.26372705265196267, "learning_rate": 1.493751509814374e-05, "loss": 0.2786, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.2486892607246088, "learning_rate": 1.4882822848201073e-05, "loss": 0.2709, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.2519180983700985, "learning_rate": 1.4828171515070553e-05, "loss": 0.2735, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.2238768647427481, "learning_rate": 1.4773561535742793e-05, "loss": 0.2771, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.26423497732888757, "learning_rate": 1.4718993346877715e-05, "loss": 0.2725, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.255950174989913, "learning_rate": 1.466446738480111e-05, "loss": 0.2695, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.2608247962405235, "learning_rate": 1.460998408550112e-05, "loss": 0.2801, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.2885908037472601, "learning_rate": 1.4555543884624751e-05, "loss": 0.2806, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.2532919447439562, "learning_rate": 1.4501147217474402e-05, "loss": 0.2776, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.26996282257860105, "learning_rate": 1.444679451900437e-05, "loss": 0.274, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.2756545999696996, "learning_rate": 1.4392486223817397e-05, "loss": 0.2724, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.26420044555694633, "learning_rate": 1.4338222766161143e-05, "loss": 0.2862, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2523259659554382, "learning_rate": 1.4284004579924777e-05, "loss": 0.2748, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.2521335470000305, "learning_rate": 1.4229832098635479e-05, "loss": 0.2728, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.244954498496726, "learning_rate": 1.4175705755454963e-05, "loss": 0.2757, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.23704915501199023, "learning_rate": 1.412162598317602e-05, "loss": 0.2714, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.24604444132072337, "learning_rate": 1.406759321421907e-05, "loss": 0.2705, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.23687652646943422, "learning_rate": 1.401360788062871e-05, "loss": 0.2806, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.24156409236815393, "learning_rate": 1.3959670414070204e-05, "loss": 0.2748, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.2230342797120596, "learning_rate": 1.3905781245826108e-05, "loss": 0.2804, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.23182929750166623, "learning_rate": 1.3851940806792778e-05, "loss": 0.2814, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.21449800710568226, "learning_rate": 1.379814952747693e-05, "loss": 0.2737, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2190177634278557, "learning_rate": 1.3744407837992193e-05, "loss": 0.2691, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.2144402754322838, "learning_rate": 1.3690716168055692e-05, "loss": 0.2694, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.2293691902810277, "learning_rate": 1.363707494698459e-05, "loss": 0.2791, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.21338862070901385, "learning_rate": 1.358348460369265e-05, "loss": 0.2761, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.22978242525932607, "learning_rate": 1.352994556668684e-05, "loss": 0.2805, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.2365196177019313, "learning_rate": 1.3476458264063865e-05, "loss": 0.2796, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.21026176824181272, "learning_rate": 1.342302312350678e-05, "loss": 0.2805, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.2575791655611921, "learning_rate": 1.3369640572281537e-05, "loss": 0.2786, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.23023107921657895, "learning_rate": 1.3316311037233596e-05, "loss": 0.2807, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.2580839201055145, "learning_rate": 1.326303494478451e-05, "loss": 0.2766, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.24742111388018276, "learning_rate": 1.3209812720928472e-05, "loss": 0.2854, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2276547935455718, "learning_rate": 1.315664479122898e-05, "loss": 0.2789, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.24585527929791007, "learning_rate": 1.3103531580815378e-05, "loss": 0.277, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.22767077549550535, "learning_rate": 1.3050473514379488e-05, "loss": 0.2829, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.23725893586540717, "learning_rate": 1.2997471016172188e-05, "loss": 0.2803, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.2361783495850619, "learning_rate": 1.2944524510000042e-05, "loss": 0.2772, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.22835661292550008, "learning_rate": 1.2891634419221908e-05, "loss": 0.2841, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.2363119828113145, "learning_rate": 1.2838801166745545e-05, "loss": 0.281, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.21398254700677644, "learning_rate": 1.2786025175024216e-05, "loss": 0.2787, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.24068628814738216, "learning_rate": 1.2733306866053357e-05, "loss": 0.2777, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.22509212512637716, "learning_rate": 1.2680646661367163e-05, "loss": 0.2776, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.2617408935930581, "learning_rate": 1.2628044982035219e-05, "loss": 0.2844, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.21972422326626062, "learning_rate": 1.2575502248659155e-05, "loss": 0.2727, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.2536271400392804, "learning_rate": 1.2523018881369269e-05, "loss": 0.2804, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.23686385101751514, "learning_rate": 1.2470595299821176e-05, "loss": 0.2832, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.2519227076776149, "learning_rate": 1.2418231923192416e-05, "loss": 0.279, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.24751883463223523, "learning_rate": 1.2365929170179165e-05, "loss": 0.2737, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.22794218277437256, "learning_rate": 1.2313687458992848e-05, "loss": 0.2675, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.24424884448494846, "learning_rate": 1.2261507207356785e-05, "loss": 0.2793, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.23460803535584615, "learning_rate": 1.220938883250288e-05, "loss": 0.275, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.22822772289254817, "learning_rate": 1.215733275116827e-05, "loss": 0.2808, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.24802438810577127, "learning_rate": 1.2105339379592005e-05, "loss": 0.2731, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.2352846225993766, "learning_rate": 1.2053409133511681e-05, "loss": 0.2769, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.23749833643047524, "learning_rate": 1.2001542428160173e-05, "loss": 0.2762, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.24091068098451252, "learning_rate": 1.1949739678262278e-05, "loss": 0.2847, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.23231376373563575, "learning_rate": 1.189800129803139e-05, "loss": 0.2811, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.23500426124720086, "learning_rate": 1.1846327701166228e-05, "loss": 0.2738, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.2511202727259534, "learning_rate": 1.1794719300847493e-05, "loss": 0.2841, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.23469306174665117, "learning_rate": 1.1743176509734582e-05, "loss": 0.2877, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.23588994811963132, "learning_rate": 1.1691699739962275e-05, "loss": 0.2793, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.24766392775292848, "learning_rate": 1.1640289403137456e-05, "loss": 0.2731, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.2348760889071633, "learning_rate": 1.1588945910335802e-05, "loss": 0.2817, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.228913145356042, "learning_rate": 1.1537669672098517e-05, "loss": 0.2663, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.23634922017604248, "learning_rate": 1.1486461098429036e-05, "loss": 0.2813, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.22818143670713892, "learning_rate": 1.1435320598789747e-05, "loss": 0.2755, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.2261945662332709, "learning_rate": 1.1384248582098736e-05, "loss": 0.2823, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.23200519650079185, "learning_rate": 1.1333245456726467e-05, "loss": 0.2706, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2190870686086761, "learning_rate": 1.128231163049258e-05, "loss": 0.2783, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.22925228279257448, "learning_rate": 1.123144751066259e-05, "loss": 0.2796, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2374548894200329, "learning_rate": 1.1180653503944657e-05, "loss": 0.2812, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.24241830043949805, "learning_rate": 1.1129930016486287e-05, "loss": 0.2812, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.20727383210886763, "learning_rate": 1.107927745387114e-05, "loss": 0.274, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.22172027928052865, "learning_rate": 1.1028696221115766e-05, "loss": 0.2725, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.2350437303559192, "learning_rate": 1.0978186722666341e-05, "loss": 0.289, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.22231874406933774, "learning_rate": 1.0927749362395475e-05, "loss": 0.2813, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.22462418861017136, "learning_rate": 1.0877384543598954e-05, "loss": 0.2863, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2420389107335919, "learning_rate": 1.0827092668992529e-05, "loss": 0.2753, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.22262932166647198, "learning_rate": 1.077687414070869e-05, "loss": 0.2789, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.23598735072767468, "learning_rate": 1.0726729360293451e-05, "loss": 0.2803, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.24792289221658131, "learning_rate": 1.0676658728703147e-05, "loss": 0.2821, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.20003448795017756, "learning_rate": 1.0626662646301198e-05, "loss": 0.27, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.24317399644061113, "learning_rate": 1.0576741512854958e-05, "loss": 0.2754, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.23085708343182346, "learning_rate": 1.052689572753247e-05, "loss": 0.2734, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.21104206519733498, "learning_rate": 1.0477125688899328e-05, "loss": 0.2727, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.2299931781774496, "learning_rate": 1.0427431794915406e-05, "loss": 0.2782, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.2109996076828174, "learning_rate": 1.0377814442931769e-05, "loss": 0.2716, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2293546343390234, "learning_rate": 1.0328274029687439e-05, "loss": 0.2631, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.21248831869390905, "learning_rate": 1.0278810951306253e-05, "loss": 0.2837, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.22436821071674837, "learning_rate": 1.0229425603293647e-05, "loss": 0.2863, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.23328470250089622, "learning_rate": 1.0180118380533558e-05, "loss": 0.2786, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.22683569730556535, "learning_rate": 1.0130889677285225e-05, "loss": 0.2751, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.23156179205382832, "learning_rate": 1.008173988718005e-05, "loss": 0.2743, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2167785214864461, "learning_rate": 1.0032669403218439e-05, "loss": 0.2692, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.21970959509030452, "learning_rate": 9.983678617766677e-06, "loss": 0.2809, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.22157176028783132, "learning_rate": 9.934767922553788e-06, "loss": 0.2776, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.20510225954973985, "learning_rate": 9.885937708668371e-06, "loss": 0.2768, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.22114016414971294, "learning_rate": 9.837188366555524e-06, "loss": 0.2768, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.22227777249779046, "learning_rate": 9.788520286013691e-06, "loss": 0.2787, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.21215286416278506, "learning_rate": 9.739933856191537e-06, "loss": 0.2789, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.21653229411491542, "learning_rate": 9.691429465584866e-06, "loss": 0.2759, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.21497482601639525, "learning_rate": 9.643007502033492e-06, "loss": 0.2686, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.2087876314271648, "learning_rate": 9.594668352718152e-06, "loss": 0.2841, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.2262246955786178, "learning_rate": 9.546412404157383e-06, "loss": 0.2809, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.22023253631586587, "learning_rate": 9.498240042204471e-06, "loss": 0.2834, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.20602619821131324, "learning_rate": 9.450151652044339e-06, "loss": 0.2765, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.2233612528341099, "learning_rate": 9.402147618190472e-06, "loss": 0.2649, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.213126047812216, "learning_rate": 9.354228324481841e-06, "loss": 0.2798, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.21409637795331707, "learning_rate": 9.306394154079852e-06, "loss": 0.2794, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.19914053365099402, "learning_rate": 9.258645489465254e-06, "loss": 0.2746, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.20799559079625407, "learning_rate": 9.21098271243509e-06, "loss": 0.2776, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.22345564647015612, "learning_rate": 9.163406204099659e-06, "loss": 0.2777, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.19994445410826647, "learning_rate": 9.115916344879452e-06, "loss": 0.2804, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.21302625698333477, "learning_rate": 9.068513514502126e-06, "loss": 0.277, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.21050827381727114, "learning_rate": 9.021198091999439e-06, "loss": 0.2779, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.20568845821003143, "learning_rate": 8.973970455704251e-06, "loss": 0.2824, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.217690672951135, "learning_rate": 8.926830983247495e-06, "loss": 0.2803, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.20975042145248296, "learning_rate": 8.879780051555116e-06, "loss": 0.2764, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.2044086956919326, "learning_rate": 8.83281803684512e-06, "loss": 0.2721, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.22130712697848362, "learning_rate": 8.785945314624532e-06, "loss": 0.282, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.20973775835597622, "learning_rate": 8.739162259686385e-06, "loss": 0.2748, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2063408051356444, "learning_rate": 8.692469246106734e-06, "loss": 0.2819, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.21392173595279115, "learning_rate": 8.645866647241677e-06, "loss": 0.2798, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.21108985935918237, "learning_rate": 8.599354835724348e-06, "loss": 0.286, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2028788447888723, "learning_rate": 8.552934183461958e-06, "loss": 0.2774, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2009658462064052, "learning_rate": 8.506605061632805e-06, "loss": 0.2688, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.22711559500555148, "learning_rate": 8.460367840683308e-06, "loss": 0.2788, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2078593630335642, "learning_rate": 8.414222890325065e-06, "loss": 0.2748, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.2319863334597881, "learning_rate": 8.368170579531855e-06, "loss": 0.28, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.20549475525594976, "learning_rate": 8.322211276536733e-06, "loss": 0.2725, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.23432839914050604, "learning_rate": 8.27634534882907e-06, "loss": 0.2793, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.25636526871379, "learning_rate": 8.230573163151585e-06, "loss": 0.2869, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.23740751567460844, "learning_rate": 8.184895085497466e-06, "loss": 0.2786, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.22618844612676345, "learning_rate": 8.139311481107401e-06, "loss": 0.2756, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.24542217579794648, "learning_rate": 8.093822714466686e-06, "loss": 0.2808, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.22227491021755047, "learning_rate": 8.048429149302271e-06, "loss": 0.2671, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.22563320855921956, "learning_rate": 8.003131148579902e-06, "loss": 0.2796, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.22303156902189, "learning_rate": 7.957929074501182e-06, "loss": 0.2828, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.23029214116858654, "learning_rate": 7.912823288500695e-06, "loss": 0.2853, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.241484840966265, "learning_rate": 7.867814151243102e-06, "loss": 0.277, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.20198457127833994, "learning_rate": 7.822902022620267e-06, "loss": 0.2733, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.21644991827594745, "learning_rate": 7.778087261748377e-06, "loss": 0.2703, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.25252819942068916, "learning_rate": 7.733370226965056e-06, "loss": 0.275, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.20341414383376258, "learning_rate": 7.688751275826527e-06, "loss": 0.2708, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.20762432411697834, "learning_rate": 7.644230765104735e-06, "loss": 0.2841, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.21609007688131804, "learning_rate": 7.599809050784502e-06, "loss": 0.284, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.20466923515241323, "learning_rate": 7.555486488060661e-06, "loss": 0.2744, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2138506998467052, "learning_rate": 7.511263431335249e-06, "loss": 0.2756, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.2295010016346233, "learning_rate": 7.467140234214656e-06, "loss": 0.2728, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.21622223255860268, "learning_rate": 7.423117249506777e-06, "loss": 0.2802, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.21010404455896464, "learning_rate": 7.379194829218231e-06, "loss": 0.2861, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.20410499761031106, "learning_rate": 7.335373324551518e-06, "loss": 0.2768, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.22005679050088864, "learning_rate": 7.291653085902224e-06, "loss": 0.2899, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2105269866459844, "learning_rate": 7.248034462856213e-06, "loss": 0.2769, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2024795099251122, "learning_rate": 7.20451780418683e-06, "loss": 0.2759, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.20655798636212205, "learning_rate": 7.161103457852128e-06, "loss": 0.2774, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.2000927766227071, "learning_rate": 7.117791770992046e-06, "loss": 0.268, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.20059645919451619, "learning_rate": 7.074583089925688e-06, "loss": 0.274, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.2127981199444914, "learning_rate": 7.0314777601485155e-06, "loss": 0.2799, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.20045669461695614, "learning_rate": 6.988476126329604e-06, "loss": 0.275, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.21990974848032824, "learning_rate": 6.945578532308857e-06, "loss": 0.2773, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.19490224664040495, "learning_rate": 6.902785321094301e-06, "loss": 0.2707, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.19441406010588577, "learning_rate": 6.8600968348593115e-06, "loss": 0.2794, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.2032494135538002, "learning_rate": 6.817513414939892e-06, "loss": 0.2798, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.1976854818221208, "learning_rate": 6.775035401831924e-06, "loss": 0.2779, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.19409572891859514, "learning_rate": 6.732663135188473e-06, "loss": 0.2842, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.19977728877837303, "learning_rate": 6.690396953817055e-06, "loss": 0.2741, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.20404346593088665, "learning_rate": 6.648237195676927e-06, "loss": 0.277, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.19393372355085298, "learning_rate": 6.606184197876395e-06, "loss": 0.2745, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.1886377737282369, "learning_rate": 6.564238296670109e-06, "loss": 0.2726, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.20507260886317566, "learning_rate": 6.52239982745638e-06, "loss": 0.276, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.20322842239581645, "learning_rate": 6.480669124774484e-06, "loss": 0.276, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.19823314072531872, "learning_rate": 6.439046522302013e-06, "loss": 0.2822, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.19616658407651835, "learning_rate": 6.397532352852191e-06, "loss": 0.2713, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.18917535171616887, "learning_rate": 6.356126948371202e-06, "loss": 0.2669, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.19741965941836997, "learning_rate": 6.314830639935559e-06, "loss": 0.2811, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.18860316419987513, "learning_rate": 6.273643757749448e-06, "loss": 0.2675, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.2001151407305795, "learning_rate": 6.2325666311420856e-06, "loss": 0.2835, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.19642074715065927, "learning_rate": 6.1915995885650675e-06, "loss": 0.2731, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.20455081318063664, "learning_rate": 6.150742957589784e-06, "loss": 0.2702, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.2049649281524993, "learning_rate": 6.109997064904774e-06, "loss": 0.2755, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.19932763134152473, "learning_rate": 6.069362236313092e-06, "loss": 0.2743, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.19949826428715217, "learning_rate": 6.0288387967297565e-06, "loss": 0.2761, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.1988423600967208, "learning_rate": 5.988427070179108e-06, "loss": 0.2709, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.1950610219455824, "learning_rate": 5.948127379792234e-06, "loss": 0.2728, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.19324701925304036, "learning_rate": 5.90794004780439e-06, "loss": 0.2776, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.18421980439228075, "learning_rate": 5.867865395552405e-06, "loss": 0.2779, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.2161980913716608, "learning_rate": 5.8279037434721364e-06, "loss": 0.2743, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.19920892157347606, "learning_rate": 5.788055411095892e-06, "loss": 0.2777, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2055910855284108, "learning_rate": 5.7483207170498625e-06, "loss": 0.2784, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.198362158924191, "learning_rate": 5.708699979051613e-06, "loss": 0.2766, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.23073382633749745, "learning_rate": 5.66919351390751e-06, "loss": 0.2823, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.20649996688867767, "learning_rate": 5.629801637510188e-06, "loss": 0.2813, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.19251215004351824, "learning_rate": 5.590524664836043e-06, "loss": 0.2665, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.20427120655032932, "learning_rate": 5.551362909942708e-06, "loss": 0.2804, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.2002338769664395, "learning_rate": 5.51231668596653e-06, "loss": 0.2764, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.1999302514362599, "learning_rate": 5.47338630512007e-06, "loss": 0.2749, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.19448330638116584, "learning_rate": 5.434572078689617e-06, "loss": 0.2799, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.1915222017947595, "learning_rate": 5.395874317032694e-06, "loss": 0.2756, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.20017391789172573, "learning_rate": 5.357293329575573e-06, "loss": 0.2743, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.21120589505369963, "learning_rate": 5.318829424810797e-06, "loss": 0.2762, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.20191978417990966, "learning_rate": 5.280482910294728e-06, "loss": 0.277, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.2222614734525546, "learning_rate": 5.242254092645078e-06, "loss": 0.2777, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.20532747991294714, "learning_rate": 5.2041432775384445e-06, "loss": 0.2761, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.218992213270742, "learning_rate": 5.166150769707892e-06, "loss": 0.2818, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.195289288734148, "learning_rate": 5.128276872940503e-06, "loss": 0.2765, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.20567025426404867, "learning_rate": 5.090521890074953e-06, "loss": 0.2723, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.21388590888832182, "learning_rate": 5.0528861229990675e-06, "loss": 0.2835, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.19814712192941247, "learning_rate": 5.015369872647442e-06, "loss": 0.2795, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.19909688849916635, "learning_rate": 4.9779734389990195e-06, "loss": 0.271, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.18450089222783303, "learning_rate": 4.940697121074675e-06, "loss": 0.2832, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.18791033344465657, "learning_rate": 4.903541216934864e-06, "loss": 0.2764, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.20194434607779677, "learning_rate": 4.8665060236772e-06, "loss": 0.2777, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.1815572218389702, "learning_rate": 4.829591837434102e-06, "loss": 0.2768, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.20727303606546463, "learning_rate": 4.792798953370424e-06, "loss": 0.2741, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.18266458709454358, "learning_rate": 4.756127665681083e-06, "loss": 0.2738, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.1797595170618822, "learning_rate": 4.719578267588725e-06, "loss": 0.2695, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.18473956389895396, "learning_rate": 4.6831510513413525e-06, "loss": 0.2693, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3202245585952998, "learning_rate": 4.6468463082100176e-06, "loss": 0.2365, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.2612750702404506, "learning_rate": 4.610664328486485e-06, "loss": 0.2364, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.21529164657511768, "learning_rate": 4.5746054014809e-06, "loss": 0.2358, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.29392483645978773, "learning_rate": 4.5386698155194766e-06, "loss": 0.24, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3251536289534244, "learning_rate": 4.502857857942204e-06, "loss": 0.2447, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.24963352626366897, "learning_rate": 4.467169815100549e-06, "loss": 0.2362, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.25870723674040697, "learning_rate": 4.431605972355137e-06, "loss": 0.2324, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.26079576942304356, "learning_rate": 4.396166614073516e-06, "loss": 0.2365, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.26055051946713464, "learning_rate": 4.360852023627846e-06, "loss": 0.2403, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.23756695221346263, "learning_rate": 4.325662483392656e-06, "loss": 0.2403, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.25687704046526644, "learning_rate": 4.29059827474257e-06, "loss": 0.2366, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.23918780309982268, "learning_rate": 4.255659678050063e-06, "loss": 0.2481, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.22782527716967138, "learning_rate": 4.22084697268323e-06, "loss": 0.2348, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.24790433178428653, "learning_rate": 4.186160437003535e-06, "loss": 0.2377, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.2315137538902712, "learning_rate": 4.151600348363582e-06, "loss": 0.2386, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.22589145220887397, "learning_rate": 4.11716698310493e-06, "loss": 0.2477, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.1994624552714118, "learning_rate": 4.082860616555848e-06, "loss": 0.2369, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.22769165100568467, "learning_rate": 4.048681523029125e-06, "loss": 0.2319, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.2057604638461496, "learning_rate": 4.014629975819882e-06, "loss": 0.2289, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.22344497056583437, "learning_rate": 3.9807062472033855e-06, "loss": 0.2413, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.20650208675955453, "learning_rate": 3.94691060843287e-06, "loss": 0.2359, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.21207881096353853, "learning_rate": 3.913243329737353e-06, "loss": 0.2377, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.20946288757229092, "learning_rate": 3.879704680319503e-06, "loss": 0.237, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2107858290613827, "learning_rate": 3.846294928353471e-06, "loss": 0.2375, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.19437673136325584, "learning_rate": 3.8130143409827345e-06, "loss": 0.2324, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2017504530721483, "learning_rate": 3.7798631843179887e-06, "loss": 0.2391, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2173207709715705, "learning_rate": 3.7468417234349973e-06, "loss": 0.2399, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.19375943987276995, "learning_rate": 3.7139502223724823e-06, "loss": 0.2365, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.19634106214808433, "learning_rate": 3.6811889441300095e-06, "loss": 0.2373, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.19985908787814113, "learning_rate": 3.648558150665886e-06, "loss": 0.2418, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.20259966775520638, "learning_rate": 3.616058102895075e-06, "loss": 0.2412, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.1871358561789976, "learning_rate": 3.583689060687079e-06, "loss": 0.2354, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.1861030775312055, "learning_rate": 3.5514512828639023e-06, "loss": 0.2275, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.18530900884637147, "learning_rate": 3.51934502719796e-06, "loss": 0.2358, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.1912675653419767, "learning_rate": 3.4873705504100185e-06, "loss": 0.2397, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.20337975491600208, "learning_rate": 3.4555281081671345e-06, "loss": 0.25, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.18898837654198655, "learning_rate": 3.4238179550806326e-06, "loss": 0.2371, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.19028560091346636, "learning_rate": 3.3922403447040497e-06, "loss": 0.2403, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.18663562324189858, "learning_rate": 3.3607955295311247e-06, "loss": 0.2331, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.1846565630446262, "learning_rate": 3.32948376099375e-06, "loss": 0.2427, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.18703818272240488, "learning_rate": 3.2983052894599976e-06, "loss": 0.236, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.18636718487997245, "learning_rate": 3.2672603642320945e-06, "loss": 0.2359, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.18298254469400446, "learning_rate": 3.236349233544438e-06, "loss": 0.2369, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.1913266155214946, "learning_rate": 3.205572144561604e-06, "loss": 0.2321, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.19138403487702013, "learning_rate": 3.174929343376374e-06, "loss": 0.2415, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.1906539513768421, "learning_rate": 3.1444210750077777e-06, "loss": 0.2383, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.1805363326284445, "learning_rate": 3.1140475833991046e-06, "loss": 0.2437, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.19086988007792136, "learning_rate": 3.0838091114159895e-06, "loss": 0.239, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.18970248535965945, "learning_rate": 3.0537059008444524e-06, "loss": 0.2399, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.1770620962169806, "learning_rate": 3.0237381923889563e-06, "loss": 0.2357, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.18663046962484262, "learning_rate": 2.9939062256704997e-06, "loss": 0.2402, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.17771212052708138, "learning_rate": 2.964210239224696e-06, "loss": 0.2278, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.18194855431711268, "learning_rate": 2.934650470499869e-06, "loss": 0.2384, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.17643593529276067, "learning_rate": 2.905227155855128e-06, "loss": 0.2359, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.17840474228241596, "learning_rate": 2.875940530558519e-06, "loss": 0.2366, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.18904921655162168, "learning_rate": 2.8467908287851154e-06, "loss": 0.2383, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.1810531235410288, "learning_rate": 2.8177782836151603e-06, "loss": 0.2319, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.1720462965965786, "learning_rate": 2.7889031270321874e-06, "loss": 0.2385, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.18541132485526773, "learning_rate": 2.760165589921184e-06, "loss": 0.2446, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.17728155406354587, "learning_rate": 2.7315659020667305e-06, "loss": 0.239, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.18538753117982879, "learning_rate": 2.703104292151164e-06, "loss": 0.2425, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.18730889229256192, "learning_rate": 2.6747809877527607e-06, "loss": 0.2396, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.1812088760417518, "learning_rate": 2.6465962153439082e-06, "loss": 0.2343, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.1864243013492869, "learning_rate": 2.618550200289303e-06, "loss": 0.2402, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.1849878648931647, "learning_rate": 2.59064316684412e-06, "loss": 0.2467, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.1723301985453537, "learning_rate": 2.562875338152264e-06, "loss": 0.2329, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.17638792245322102, "learning_rate": 2.5352469362445552e-06, "loss": 0.2362, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.19635288138005746, "learning_rate": 2.5077581820369523e-06, "loss": 0.2503, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.17558768878148834, "learning_rate": 2.480409295328803e-06, "loss": 0.2377, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.17705253953045963, "learning_rate": 2.45320049480108e-06, "loss": 0.2342, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.18539095753552753, "learning_rate": 2.4261319980146293e-06, "loss": 0.2471, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.18515869102430416, "learning_rate": 2.399204021408421e-06, "loss": 0.2403, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.1809096620638504, "learning_rate": 2.3724167802978395e-06, "loss": 0.239, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.18966473788035454, "learning_rate": 2.3457704888729625e-06, "loss": 0.2328, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.18381948116162244, "learning_rate": 2.3192653601968162e-06, "loss": 0.2389, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.17548645056753198, "learning_rate": 2.2929016062037057e-06, "loss": 0.2351, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.18524326439134237, "learning_rate": 2.2666794376975055e-06, "loss": 0.2369, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.18150829143149264, "learning_rate": 2.24059906434998e-06, "loss": 0.2355, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.19448731509260186, "learning_rate": 2.214660694699091e-06, "loss": 0.2453, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.17863421951574224, "learning_rate": 2.188864536147355e-06, "loss": 0.2413, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.1745676835568738, "learning_rate": 2.1632107949601757e-06, "loss": 0.2381, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.1809333879327871, "learning_rate": 2.137699676264171e-06, "loss": 0.2368, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.17131659459598753, "learning_rate": 2.1123313840455738e-06, "loss": 0.2335, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.1795484623339474, "learning_rate": 2.08710612114857e-06, "loss": 0.2377, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.18170096104928174, "learning_rate": 2.0620240892736953e-06, "loss": 0.2394, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.17416772982590709, "learning_rate": 2.0370854889762e-06, "loss": 0.2375, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.182587694375979, "learning_rate": 2.0122905196644726e-06, "loss": 0.2306, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.18547317132740873, "learning_rate": 1.987639379598427e-06, "loss": 0.2411, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.18394025445293324, "learning_rate": 1.963132265887919e-06, "loss": 0.2398, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.1920187278730113, "learning_rate": 1.9387693744911784e-06, "loss": 0.2348, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.18090913356371274, "learning_rate": 1.9145509002132368e-06, "loss": 0.241, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.18029398239888905, "learning_rate": 1.8904770367043723e-06, "loss": 0.2398, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.17736647070887185, "learning_rate": 1.8665479764585504e-06, "loss": 0.2402, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.19266542739276346, "learning_rate": 1.8427639108118977e-06, "loss": 0.2394, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.17978826277855514, "learning_rate": 1.8191250299411755e-06, "loss": 0.2398, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.1760609308454715, "learning_rate": 1.7956315228622446e-06, "loss": 0.2357, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.1710452179240491, "learning_rate": 1.7722835774285553e-06, "loss": 0.2356, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.17728366954824076, "learning_rate": 1.7490813803296624e-06, "loss": 0.2362, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.18544686907173066, "learning_rate": 1.726025117089718e-06, "loss": 0.2397, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.18217144462457013, "learning_rate": 1.70311497206598e-06, "loss": 0.2295, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.18093506674461476, "learning_rate": 1.6803511284473638e-06, "loss": 0.2375, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.18526160723677823, "learning_rate": 1.6577337682529538e-06, "loss": 0.2466, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.18226376081401732, "learning_rate": 1.6352630723305617e-06, "loss": 0.2409, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.17817944611561962, "learning_rate": 1.612939220355272e-06, "loss": 0.2363, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.19258827653673066, "learning_rate": 1.5907623908280112e-06, "loss": 0.237, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.17544531007071176, "learning_rate": 1.568732761074121e-06, "loss": 0.2316, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.17960353884156513, "learning_rate": 1.5468505072419237e-06, "loss": 0.2465, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.17510423804580594, "learning_rate": 1.5251158043013448e-06, "loss": 0.2424, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.17622725527476937, "learning_rate": 1.5035288260424885e-06, "loss": 0.2344, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.17516884242423658, "learning_rate": 1.4820897450742623e-06, "loss": 0.2331, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.1821618582863437, "learning_rate": 1.4607987328229767e-06, "loss": 0.2345, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.18686798696396364, "learning_rate": 1.4396559595310056e-06, "loss": 0.2432, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.17053809888477964, "learning_rate": 1.4186615942553973e-06, "loss": 0.2309, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.17561095367595408, "learning_rate": 1.3978158048665424e-06, "loss": 0.2398, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.17788229439394554, "learning_rate": 1.3771187580468115e-06, "loss": 0.2423, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.17546422564873762, "learning_rate": 1.3565706192892392e-06, "loss": 0.2382, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.17245304980795387, "learning_rate": 1.3361715528961993e-06, "loss": 0.2328, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.17386826451575838, "learning_rate": 1.3159217219780817e-06, "loss": 0.2325, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.17586966791906633, "learning_rate": 1.2958212884519949e-06, "loss": 0.2451, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.17649425701029442, "learning_rate": 1.2758704130404675e-06, "loss": 0.2348, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.1747401425534685, "learning_rate": 1.2560692552701738e-06, "loss": 0.2411, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.17449151328947426, "learning_rate": 1.2364179734706382e-06, "loss": 0.2397, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.17961300865270946, "learning_rate": 1.2169167247729852e-06, "loss": 0.2416, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.17971148992080718, "learning_rate": 1.1975656651086864e-06, "loss": 0.2397, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.1888881729387754, "learning_rate": 1.1783649492082926e-06, "loss": 0.2401, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.1718593147498766, "learning_rate": 1.1593147306002183e-06, "loss": 0.2292, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.18428404211270544, "learning_rate": 1.140415161609505e-06, "loss": 0.2412, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.17567618625814435, "learning_rate": 1.121666393356604e-06, "loss": 0.2383, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.1696459901908342, "learning_rate": 1.1030685757561632e-06, "loss": 0.2385, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.17355987475126405, "learning_rate": 1.0846218575158373e-06, "loss": 0.2347, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.17196171070382776, "learning_rate": 1.066326386135097e-06, "loss": 0.2329, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.1719716776403984, "learning_rate": 1.0481823079040398e-06, "loss": 0.2362, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.17926735792991919, "learning_rate": 1.0301897679022344e-06, "loss": 0.2408, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.17818030553371406, "learning_rate": 1.0123489099975491e-06, "loss": 0.2389, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.17676142055733565, "learning_rate": 9.9465987684501e-07, "loss": 0.2435, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.17514899056278896, "learning_rate": 9.771228098856534e-07, "loss": 0.2437, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.17955484935411525, "learning_rate": 9.597378493454013e-07, "loss": 0.2457, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.17609267169331072, "learning_rate": 9.425051342339353e-07, "loss": 0.2393, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.17269899404323083, "learning_rate": 9.254248023435864e-07, "loss": 0.2379, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.1812084712055246, "learning_rate": 9.084969902482288e-07, "loss": 0.2425, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.17262936354129974, "learning_rate": 8.917218333021993e-07, "loss": 0.2351, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.1745342839226401, "learning_rate": 8.750994656392109e-07, "loss": 0.2326, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.17485656398034138, "learning_rate": 8.58630020171265e-07, "loss": 0.2295, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.17528201475533456, "learning_rate": 8.423136285876099e-07, "loss": 0.234, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.17810359772706938, "learning_rate": 8.26150421353682e-07, "loss": 0.2401, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.1766545300125588, "learning_rate": 8.101405277100549e-07, "loss": 0.239, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.17798192614227262, "learning_rate": 7.942840756714077e-07, "loss": 0.244, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.17476359206759007, "learning_rate": 7.785811920255093e-07, "loss": 0.238, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.17117872037896215, "learning_rate": 7.630320023322024e-07, "loss": 0.235, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.1745900766565171, "learning_rate": 7.476366309223903e-07, "loss": 0.2367, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.17346727170763743, "learning_rate": 7.323952008970537e-07, "loss": 0.2388, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.17378465166732077, "learning_rate": 7.173078341262618e-07, "loss": 0.2337, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.17575014002117056, "learning_rate": 7.023746512481989e-07, "loss": 0.2393, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.17878621301811676, "learning_rate": 6.875957716681902e-07, "loss": 0.2409, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.18215036978729554, "learning_rate": 6.729713135577687e-07, "loss": 0.2363, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.17860345507942188, "learning_rate": 6.585013938537143e-07, "loss": 0.243, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.17623902189059426, "learning_rate": 6.441861282571115e-07, "loss": 0.2365, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.19135396911508207, "learning_rate": 6.300256312324471e-07, "loss": 0.2346, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.1715375403472509, "learning_rate": 6.160200160066776e-07, "loss": 0.2356, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.17623844706718028, "learning_rate": 6.021693945683327e-07, "loss": 0.2389, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.1799756046237851, "learning_rate": 5.884738776666044e-07, "loss": 0.2326, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.176856473449362, "learning_rate": 5.749335748104878e-07, "loss": 0.238, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.17467815558481758, "learning_rate": 5.615485942678778e-07, "loss": 0.238, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.16746436111712412, "learning_rate": 5.483190430647289e-07, "loss": 0.2344, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.16997517037138068, "learning_rate": 5.352450269841747e-07, "loss": 0.2353, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.1754396069975056, "learning_rate": 5.22326650565701e-07, "loss": 0.2341, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.17389374267692806, "learning_rate": 5.095640171043048e-07, "loss": 0.2399, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.17459354605708255, "learning_rate": 4.969572286496594e-07, "loss": 0.2356, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.1689522856664325, "learning_rate": 4.845063860053079e-07, "loss": 0.2361, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.17167703345006247, "learning_rate": 4.7221158872785997e-07, "loss": 0.2317, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.18045036141485393, "learning_rate": 4.600729351261857e-07, "loss": 0.2389, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.1761885523537455, "learning_rate": 4.4809052226063355e-07, "loss": 0.241, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.17058085193585606, "learning_rate": 4.3626444594226046e-07, "loss": 0.2344, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.17766937484367407, "learning_rate": 4.245948007320588e-07, "loss": 0.2408, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.17459072593816252, "learning_rate": 4.130816799401971e-07, "loss": 0.2433, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.1679754163085146, "learning_rate": 4.017251756252827e-07, "loss": 0.2379, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.18170465483729717, "learning_rate": 3.9052537859362473e-07, "loss": 0.2464, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.17801212183933865, "learning_rate": 3.7948237839849687e-07, "loss": 0.2392, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.17112111677095534, "learning_rate": 3.6859626333943797e-07, "loss": 0.2379, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.17633684706563196, "learning_rate": 3.578671204615347e-07, "loss": 0.2326, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.16669655400087438, "learning_rate": 3.472950355547267e-07, "loss": 0.242, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.17198427909138983, "learning_rate": 3.3688009315312244e-07, "loss": 0.2348, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.17390841758499817, "learning_rate": 3.266223765343224e-07, "loss": 0.2398, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.17167367859275154, "learning_rate": 3.16521967718757e-07, "loss": 0.2399, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.17339729336746743, "learning_rate": 3.0657894746902726e-07, "loss": 0.2425, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.1695644706684447, "learning_rate": 2.9679339528925654e-07, "loss": 0.2366, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.17404499082949768, "learning_rate": 2.871653894244597e-07, "loss": 0.246, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.17448416009601736, "learning_rate": 2.7769500685991266e-07, "loss": 0.2324, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.1698067089937189, "learning_rate": 2.683823233205485e-07, "loss": 0.2381, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.17258947434664668, "learning_rate": 2.592274132703287e-07, "loss": 0.2417, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.1745746559587163, "learning_rate": 2.502303499116754e-07, "loss": 0.2419, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.1736737424279889, "learning_rate": 2.413912051848666e-07, "loss": 0.234, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.17427093927390794, "learning_rate": 2.3271004976746613e-07, "loss": 0.2334, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.17385018045407555, "learning_rate": 2.2418695307376393e-07, "loss": 0.2479, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.17391166521674598, "learning_rate": 2.1582198325420968e-07, "loss": 0.2364, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.1667799875362003, "learning_rate": 2.0761520719488447e-07, "loss": 0.2303, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.17887553510693308, "learning_rate": 1.9956669051694798e-07, "loss": 0.2403, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.1643796810591218, "learning_rate": 1.916764975761254e-07, "loss": 0.2335, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.17278545097158346, "learning_rate": 1.839446914621923e-07, "loss": 0.2442, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.176126936493936, "learning_rate": 1.7637133399845962e-07, "loss": 0.2425, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.17305427704623608, "learning_rate": 1.6895648574129397e-07, "loss": 0.2311, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.1710097803205307, "learning_rate": 1.6170020597962465e-07, "loss": 0.2381, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.17233643058864295, "learning_rate": 1.5460255273447078e-07, "loss": 0.2325, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.1683127059380481, "learning_rate": 1.4766358275847715e-07, "loss": 0.2343, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.16461285570305634, "learning_rate": 1.4088335153546573e-07, "loss": 0.2319, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.18151387298105426, "learning_rate": 1.3426191327998496e-07, "loss": 0.2419, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.16401075293500317, "learning_rate": 1.277993209368744e-07, "loss": 0.235, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.17682912909767748, "learning_rate": 1.214956261808542e-07, "loss": 0.2409, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.16951926314794882, "learning_rate": 1.1535087941609846e-07, "loss": 0.2403, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.16744214153855366, "learning_rate": 1.0936512977583802e-07, "loss": 0.2369, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.17446696331843214, "learning_rate": 1.0353842512196732e-07, "loss": 0.2365, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.17434643085463739, "learning_rate": 9.787081204466253e-08, "loss": 0.2434, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.1756253973553314, "learning_rate": 9.236233586200627e-08, "loss": 0.2424, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.17375717651999648, "learning_rate": 8.70130406196279e-08, "loss": 0.2478, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.16370895254599876, "learning_rate": 8.182296909035047e-08, "loss": 0.2288, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.1746419027369903, "learning_rate": 7.679216277384439e-08, "loss": 0.2347, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.17759795420321345, "learning_rate": 7.19206618963053e-08, "loss": 0.2349, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.17346809776738353, "learning_rate": 6.720850541012347e-08, "loss": 0.2369, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.1684152898740747, "learning_rate": 6.265573099357714e-08, "loss": 0.2391, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.17520213140213572, "learning_rate": 5.826237505053067e-08, "loss": 0.2418, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.177117973628676, "learning_rate": 5.4028472710137e-08, "loss": 0.2414, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.1766808647888417, "learning_rate": 4.9954057826571146e-08, "loss": 0.2317, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.17786957145618734, "learning_rate": 4.6039162978743776e-08, "loss": 0.2427, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.1725049751276308, "learning_rate": 4.228381947004812e-08, "loss": 0.2425, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.17501625614608315, "learning_rate": 3.868805732811343e-08, "loss": 0.2426, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.1754549995449676, "learning_rate": 3.525190530455636e-08, "loss": 0.2426, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.17231006306542476, "learning_rate": 3.197539087475887e-08, "loss": 0.2445, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.16893394039124482, "learning_rate": 2.8858540237641786e-08, "loss": 0.24, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.16559765423330278, "learning_rate": 2.5901378315458247e-08, "loss": 0.2331, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.1680446309833421, "learning_rate": 2.3103928753598347e-08, "loss": 0.2405, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.1655559154940124, "learning_rate": 2.0466213920393718e-08, "loss": 0.2395, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.17213946952362183, "learning_rate": 1.7988254906942115e-08, "loss": 0.2396, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.1686412259108814, "learning_rate": 1.5670071526936447e-08, "loss": 0.2346, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.17516067558565385, "learning_rate": 1.3511682316509344e-08, "loss": 0.2375, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.16789848629395, "learning_rate": 1.1513104534086605e-08, "loss": 0.2307, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.16748497755568964, "learning_rate": 9.67435416023843e-09, "loss": 0.2307, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.1697676421945325, "learning_rate": 7.995445897566178e-09, "loss": 0.2342, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.1767690916000606, "learning_rate": 6.476393170578021e-09, "loss": 0.2443, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.1725770625682362, "learning_rate": 5.11720812557348e-09, "loss": 0.2357, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.1752653167426694, "learning_rate": 3.917901630563492e-09, "loss": 0.2398, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.1692660334122324, "learning_rate": 2.878483275170485e-09, "loss": 0.2412, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.17139256344304135, "learning_rate": 1.998961370555108e-09, "loss": 0.2455, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.16529708564499263, "learning_rate": 1.2793429493518361e-09, "loss": 0.2394, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.16705919657168333, "learning_rate": 7.196337656112384e-10, "loss": 0.2323, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.17219942825559245, "learning_rate": 3.198382947511292e-10, "loss": 0.2351, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.16981318428587966, "learning_rate": 7.995973352770137e-11, "loss": 0.2369, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.1682514197872799, "learning_rate": 0.0, "loss": 0.2334, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 4.90203692596514e+18, "train_loss": 0.34299286624439335, "train_runtime": 58019.4787, "train_samples_per_second": 2.723, "train_steps_per_second": 0.021 } ], "logging_steps": 1.0, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.90203692596514e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }