| { |
| "best_metric": 0.10202746093273163, |
| "best_model_checkpoint": "saves/psy-course-info-chain/Llama3-OpenBioLLM-8B/train/fold4/checkpoint-80", |
| "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": 1.1397367715835571, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3765, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.0343598127365112, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3152, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 1.174424409866333, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.2912, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 1.1458992958068848, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.3076, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 1.2500667572021484, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.3917, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.4034178256988525, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.2683, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 1.1148568391799927, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.2606, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.9379229545593262, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.2331, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.0017644166946411, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2726, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.0871243476867676, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.1977, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.19604577124118805, |
| "eval_runtime": 23.396, |
| "eval_samples_per_second": 1.923, |
| "eval_steps_per_second": 1.923, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.0499131679534912, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.1788, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.9944149255752563, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.1909, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.8811809420585632, |
| "learning_rate": 0.0001, |
| "loss": 0.2539, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.8236536979675293, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.1624, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.708342432975769, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1887, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.8178593516349792, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1923, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.6386023759841919, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1326, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.6949962973594666, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.2051, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.48018312454223633, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.0942, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.5926098227500916, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1713, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.12425671517848969, |
| "eval_runtime": 23.346, |
| "eval_samples_per_second": 1.928, |
| "eval_steps_per_second": 1.928, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.48318570852279663, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.128, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.5449168682098389, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1089, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.5118151903152466, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1084, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.6431940197944641, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1171, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.4453395903110504, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1006, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 1.0043201446533203, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.1622, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.4652407765388489, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0939, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.5098345875740051, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.088, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.5490687489509583, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.0965, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.44616246223449707, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.0999, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.11493782699108124, |
| "eval_runtime": 23.2796, |
| "eval_samples_per_second": 1.933, |
| "eval_steps_per_second": 1.933, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.5870193839073181, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0892, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.8277015089988708, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1186, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.7107386589050293, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0806, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.5558963418006897, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0712, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.5010335445404053, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0855, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.8736300468444824, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1319, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.7057644724845886, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1132, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.5595960021018982, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1235, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.700205385684967, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0958, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.5269560217857361, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0629, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.10979632288217545, |
| "eval_runtime": 23.2108, |
| "eval_samples_per_second": 1.939, |
| "eval_steps_per_second": 1.939, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.4388459622859955, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.06, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.6417354345321655, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1295, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.4556141495704651, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0812, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.45949292182922363, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0793, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.39352497458457947, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0511, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.41997867822647095, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0839, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.5700072646141052, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.112, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.3185150623321533, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0708, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.6814136505126953, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1254, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5683565139770508, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1162, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.10616640746593475, |
| "eval_runtime": 23.2301, |
| "eval_samples_per_second": 1.937, |
| "eval_steps_per_second": 1.937, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.7697029709815979, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1362, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.38404616713523865, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0932, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.4210062026977539, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0609, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.3112558424472809, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0368, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.41806361079216003, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0708, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.43115636706352234, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0603, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.5658217668533325, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.1141, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.5961173176765442, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0701, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.5112624168395996, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0591, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.39993372559547424, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0527, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.10550259798765182, |
| "eval_runtime": 23.204, |
| "eval_samples_per_second": 1.939, |
| "eval_steps_per_second": 1.939, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.5047454237937927, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0733, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5371226072311401, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0634, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.7455381751060486, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0939, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.5078282952308655, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0406, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.46094533801078796, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0766, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.4235560894012451, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0574, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.3579745590686798, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0406, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.41921454668045044, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0638, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.6163402795791626, |
| "learning_rate": 5e-05, |
| "loss": 0.0503, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.49867355823516846, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.055, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.10488604754209518, |
| "eval_runtime": 23.2566, |
| "eval_samples_per_second": 1.935, |
| "eval_steps_per_second": 1.935, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.514280378818512, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0627, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.40522271394729614, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0476, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.47451409697532654, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.078, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.4638388454914093, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0688, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.4866134822368622, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0868, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.8423274159431458, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1166, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.3533177673816681, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.042, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.4623727798461914, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0556, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.3292884826660156, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0454, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.4475354254245758, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0352, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.10202746093273163, |
| "eval_runtime": 23.268, |
| "eval_samples_per_second": 1.934, |
| "eval_steps_per_second": 1.934, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.4370597302913666, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0502, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.3436806797981262, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0278, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.28942734003067017, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0389, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.5907009243965149, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.075, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.41526731848716736, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0463, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.6353158354759216, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0766, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.3979648947715759, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0409, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.44404664635658264, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0611, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.5780859589576721, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0588, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.3209652900695801, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0339, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.1038849800825119, |
| "eval_runtime": 23.1953, |
| "eval_samples_per_second": 1.94, |
| "eval_steps_per_second": 1.94, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.377836674451828, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.046, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.5361688137054443, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0765, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.40771806240081787, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0401, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.5302116870880127, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0475, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.4853723645210266, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0277, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.37974801659584045, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0351, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.49550458788871765, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0434, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.7367110848426819, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0534, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.41934946179389954, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0431, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.4090460240840912, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0328, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.10538610070943832, |
| "eval_runtime": 23.1482, |
| "eval_samples_per_second": 1.944, |
| "eval_steps_per_second": 1.944, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.7280628085136414, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0776, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.9631427526473999, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0759, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.3840622901916504, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0345, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.35214847326278687, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0346, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.5144171118736267, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0455, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.3269506096839905, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.018, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.37571755051612854, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0477, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.36377057433128357, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0375, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.46875059604644775, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0465, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.47391244769096375, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0519, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.10474657267332077, |
| "eval_runtime": 23.3369, |
| "eval_samples_per_second": 1.928, |
| "eval_steps_per_second": 1.928, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.5079701542854309, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0491, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.5678668022155762, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0334, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.4205664396286011, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0369, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.4578480124473572, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0363, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.4161450266838074, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0307, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.48821282386779785, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0432, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.3613753020763397, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0461, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.41897493600845337, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0253, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.32371440529823303, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0373, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.6042532920837402, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0705, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.1061079129576683, |
| "eval_runtime": 23.2715, |
| "eval_samples_per_second": 1.934, |
| "eval_steps_per_second": 1.934, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.4437013864517212, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0383, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.4564840793609619, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0381, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.4598064720630646, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0304, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.419933557510376, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.032, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.2525017261505127, |
| "learning_rate": 0.0, |
| "loss": 0.0189, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.3302485114565427e+17, |
| "train_loss": 0.09335103625059128, |
| "train_runtime": 3944.0954, |
| "train_samples_per_second": 0.513, |
| "train_steps_per_second": 0.032 |
| } |
| ], |
| "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": 1.3302485114565427e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
