| { | |
| "best_metric": 0.08071564882993698, | |
| "best_model_checkpoint": "saves/psy-course-info-chain/Llama-3.1-8B-Instruct/train/fold8/checkpoint-60", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 1.8975050449371338, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.5535, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 1.685721755027771, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.4777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 1.813672661781311, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.5486, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 1.8253041505813599, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.5644, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 1.6894313097000122, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.5447, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 1.828792691230774, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.5201, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 1.8088443279266357, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.4355, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 2.232731342315674, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.3477, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.2492733001708984, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.2323, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.8256329894065857, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.14744111895561218, | |
| "eval_runtime": 22.8857, | |
| "eval_samples_per_second": 1.966, | |
| "eval_steps_per_second": 1.966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.6204838156700134, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1431, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.6980053186416626, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1735, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.919075608253479, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1897, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.7102231383323669, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1398, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.6234557628631592, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.1547, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.5208286643028259, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.5619456171989441, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1944, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.46780818700790405, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.181, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.42069298028945923, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1154, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.45726099610328674, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1389, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.12015388160943985, | |
| "eval_runtime": 22.6946, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.4607139825820923, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1201, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.40011414885520935, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1046, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.4767753481864929, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1122, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.48444610834121704, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1752, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.4876687824726105, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1399, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.8903388381004333, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.3284, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.25991353392601013, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0741, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.363349586725235, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1348, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.3166600465774536, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0876, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.40176066756248474, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0991, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.10131536424160004, | |
| "eval_runtime": 22.6749, | |
| "eval_samples_per_second": 1.985, | |
| "eval_steps_per_second": 1.985, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.3381379544734955, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0876, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.5212336778640747, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1302, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.639557957649231, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1517, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.5579487681388855, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1055, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.48373380303382874, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1054, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.429056316614151, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0881, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.3923807740211487, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1011, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.4976230263710022, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1182, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.34380602836608887, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0822, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.3771078586578369, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0993, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.09595522284507751, | |
| "eval_runtime": 22.6934, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.5000609755516052, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1215, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.3169495165348053, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0767, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.3422163426876068, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0873, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.34192079305648804, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0661, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.3956718146800995, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.085, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.46730583906173706, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.095, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.40540656447410583, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0957, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.542033314704895, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1261, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.48119983077049255, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0703, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.32339000701904297, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.08799542486667633, | |
| "eval_runtime": 22.6986, | |
| "eval_samples_per_second": 1.982, | |
| "eval_steps_per_second": 1.982, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.6669144630432129, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1174, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.3366815745830536, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0608, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.4924454092979431, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.1025, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.41088971495628357, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0856, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.27872180938720703, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0789, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.2806490361690521, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0487, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.38126903772354126, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0667, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.3622308373451233, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.1034, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.4423893988132477, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0618, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.3973909616470337, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0569, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.08071564882993698, | |
| "eval_runtime": 22.6906, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.4315108060836792, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.07, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.4396975040435791, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0715, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.40260976552963257, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0648, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.5236598253250122, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0833, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.5737664699554443, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.078, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.2913729250431061, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0444, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.4558725357055664, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0947, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.31693553924560547, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0437, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.5158818960189819, | |
| "learning_rate": 5e-05, | |
| "loss": 0.088, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.45348548889160156, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0851, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.08390659093856812, | |
| "eval_runtime": 22.6822, | |
| "eval_samples_per_second": 1.984, | |
| "eval_steps_per_second": 1.984, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.5833895206451416, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0796, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.41326600313186646, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0534, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.4611353278160095, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0656, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.48883384466171265, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0625, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.29011398553848267, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0469, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.9229749441146851, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.146, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.42856061458587646, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0401, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.34011030197143555, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0468, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.3267209827899933, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0537, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.35374563932418823, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0454, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.0821903869509697, | |
| "eval_runtime": 22.6885, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.45855477452278137, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.062, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.3995332419872284, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0684, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.34111762046813965, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0473, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.47038137912750244, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0627, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.3913915753364563, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0782, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.4883895516395569, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0667, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.294202983379364, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0415, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.4939901828765869, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.065, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.4949710965156555, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0799, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.44213947653770447, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0687, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.08131466060876846, | |
| "eval_runtime": 22.6975, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.48285290598869324, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0599, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.3591051399707794, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0406, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.4646325409412384, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0338, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.43579134345054626, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0487, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.6243188977241516, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0641, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.34514120221138, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0448, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.3839885890483856, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0468, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.43585655093193054, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0524, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.510970413684845, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0524, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.4718784689903259, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0553, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.0824190154671669, | |
| "eval_runtime": 22.6878, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.45389047265052795, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0692, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 1.3573462963104248, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1234, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.2730891704559326, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0364, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.45728424191474915, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0389, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.32674726843833923, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.036, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.37260979413986206, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0658, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.39876478910446167, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.054, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.3188793957233429, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0382, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.46435898542404175, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0515, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.44302618503570557, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0514, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.08328327536582947, | |
| "eval_runtime": 22.703, | |
| "eval_samples_per_second": 1.982, | |
| "eval_steps_per_second": 1.982, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.28447964787483215, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0403, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.531129777431488, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0495, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.3604808449745178, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0394, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.45021384954452515, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0448, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.4472142457962036, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0436, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.40794333815574646, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0604, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.46008390188217163, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0504, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.3864462375640869, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0574, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.357191801071167, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0455, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.3680458068847656, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0357, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.08380993455648422, | |
| "eval_runtime": 22.6912, | |
| "eval_samples_per_second": 1.983, | |
| "eval_steps_per_second": 1.983, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.26838281750679016, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0194, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.43789878487586975, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0597, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.5413944721221924, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0653, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.5229392051696777, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0612, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.4239403307437897, | |
| "learning_rate": 0.0, | |
| "loss": 0.0575, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.3328024995882598e+17, | |
| "train_loss": 0.1108501496464014, | |
| "train_runtime": 3750.3463, | |
| "train_samples_per_second": 0.54, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3328024995882598e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |