| { |
| "best_metric": 0.11938976496458054, |
| "best_model_checkpoint": "saves/psy-course-info/Ministral-8B-Instruct-2410/train/fold7/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": 2.022390365600586, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.8365, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 2.2239491939544678, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 1.0631, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 1.9871013164520264, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.937, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.06746244430542, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.8887, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 2.116649866104126, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.8601, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.9861055612564087, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.8327, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 2.2386155128479004, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.7172, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 1.5947870016098022, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.5418, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.3133420944213867, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.4373, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.1003928184509277, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.3969, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.34402453899383545, |
| "eval_runtime": 23.1536, |
| "eval_samples_per_second": 1.944, |
| "eval_steps_per_second": 1.944, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.4169647693634033, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.4151, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.284870982170105, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2895, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.7745369672775269, |
| "learning_rate": 0.0001, |
| "loss": 0.2762, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.8304974436759949, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.3222, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.8633395433425903, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.2954, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.8543188571929932, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2512, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.7053364515304565, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.2108, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.6881051659584045, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1919, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.6324135661125183, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1525, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.5455204248428345, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1803, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.17951227724552155, |
| "eval_runtime": 22.918, |
| "eval_samples_per_second": 1.964, |
| "eval_steps_per_second": 1.964, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.6378706097602844, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.2085, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.7083904147148132, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1266, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.7334399819374084, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1801, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.521269679069519, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1494, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.778774082660675, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.202, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.6234628558158875, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.1586, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.5797760486602783, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1473, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.7433450818061829, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1667, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.6499334573745728, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1218, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.7856629490852356, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1319, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.1497059017419815, |
| "eval_runtime": 22.9057, |
| "eval_samples_per_second": 1.965, |
| "eval_steps_per_second": 1.965, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.6869418025016785, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1476, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.6118039488792419, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1485, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.7574868202209473, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1299, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.6238383054733276, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.1478, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.7682011723518372, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.128, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.6644240617752075, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1575, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.6031039357185364, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1212, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.5895079970359802, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1095, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.5690909624099731, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1242, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.5504185557365417, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.1265, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.14007125794887543, |
| "eval_runtime": 22.9073, |
| "eval_samples_per_second": 1.964, |
| "eval_steps_per_second": 1.964, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.5086302161216736, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1051, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.6894351243972778, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1149, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.847445011138916, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.1246, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.7746707201004028, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1307, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.60562664270401, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1113, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.7388084530830383, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.1427, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.6047436594963074, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.1237, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.6416733264923096, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.138, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.46748948097229004, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0799, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5877372622489929, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0994, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.1287231147289276, |
| "eval_runtime": 22.9013, |
| "eval_samples_per_second": 1.965, |
| "eval_steps_per_second": 1.965, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.5067760944366455, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.0986, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.6477751731872559, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.1197, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.47074922919273376, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0887, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.5839120745658875, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.1233, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.48237642645835876, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0632, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.5187559723854065, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0733, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.5357832908630371, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.098, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.42861276865005493, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0814, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.6599748134613037, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.1014, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.6289940476417542, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0749, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.12497540563344955, |
| "eval_runtime": 22.9107, |
| "eval_samples_per_second": 1.964, |
| "eval_steps_per_second": 1.964, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.6579391956329346, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.1128, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.536950409412384, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0825, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.6302985548973083, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0888, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.5579256415367126, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0578, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.5780500769615173, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0849, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.5653601884841919, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0757, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.4165619909763336, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0637, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.5682859420776367, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0819, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.7044422626495361, |
| "learning_rate": 5e-05, |
| "loss": 0.0682, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.5883644223213196, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.081, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.12497829645872116, |
| "eval_runtime": 22.9011, |
| "eval_samples_per_second": 1.965, |
| "eval_steps_per_second": 1.965, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.6911253929138184, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0856, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.7134124040603638, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0991, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.45771825313568115, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0703, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.6937627792358398, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0743, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.7038816213607788, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0667, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.47139880061149597, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0585, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.4809420704841614, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0536, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.4967633783817291, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0501, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.4364219605922699, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0506, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.4572148025035858, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0606, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.11938976496458054, |
| "eval_runtime": 22.8933, |
| "eval_samples_per_second": 1.966, |
| "eval_steps_per_second": 1.966, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.41270697116851807, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.037, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.703535258769989, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0777, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.45016127824783325, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0521, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.6479594111442566, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0629, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.6253299117088318, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0587, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.662324070930481, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0551, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.6179029941558838, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0738, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.4176694452762604, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0423, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.4821168780326843, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0466, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.7948113679885864, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0657, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.12137798964977264, |
| "eval_runtime": 22.8981, |
| "eval_samples_per_second": 1.965, |
| "eval_steps_per_second": 1.965, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.415885329246521, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0278, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.6542827486991882, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0902, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.5916126370429993, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0704, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.8161066174507141, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0554, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.5390156507492065, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0691, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.4960595369338989, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0438, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.5204513669013977, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.047, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.6652653813362122, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0715, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.6120516061782837, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.064, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.43140730261802673, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.041, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.12451139837503433, |
| "eval_runtime": 22.8988, |
| "eval_samples_per_second": 1.965, |
| "eval_steps_per_second": 1.965, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.6394028663635254, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0642, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.5395355820655823, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0642, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.5384740233421326, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0482, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.4767075777053833, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0372, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.5522722005844116, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0432, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.44300949573516846, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0352, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.4249274730682373, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0406, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.4833020269870758, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0471, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.5739688277244568, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0505, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.5418300628662109, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0555, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.12479380518198013, |
| "eval_runtime": 22.9091, |
| "eval_samples_per_second": 1.964, |
| "eval_steps_per_second": 1.964, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.45070841908454895, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0422, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.6511685252189636, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0847, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.5008986592292786, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0432, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.40296921133995056, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0449, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.4708488881587982, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.027, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.40455782413482666, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0323, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.39391109347343445, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0273, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.389161616563797, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0447, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.46511298418045044, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0356, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.516966700553894, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0391, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.12486810982227325, |
| "eval_runtime": 22.9009, |
| "eval_samples_per_second": 1.965, |
| "eval_steps_per_second": 1.965, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.465669721364975, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0315, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.5697471499443054, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0567, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.4099237024784088, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0436, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.6466348767280579, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0573, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.5930317640304565, |
| "learning_rate": 0.0, |
| "loss": 0.0393, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.2904754452483277e+17, |
| "train_loss": 0.15101532430946826, |
| "train_runtime": 3648.9816, |
| "train_samples_per_second": 0.555, |
| "train_steps_per_second": 0.034 |
| } |
| ], |
| "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": 1.2904754452483277e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
