| { |
| "best_metric": 0.13164517283439636, |
| "best_model_checkpoint": "saves/psy-course-info/Ministral-8B-Instruct-2410/train/fold3/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": 1.88387930393219, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.9163, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 2.0437674522399902, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.8912, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 2.0551068782806396, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.9307, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.005868911743164, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.8355, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 1.9968656301498413, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.9521, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 2.0808393955230713, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.7275, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 2.0151429176330566, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.7777, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 1.6804784536361694, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.6113, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.192612886428833, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.4848, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.1536256074905396, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.4189, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.37848058342933655, |
| "eval_runtime": 21.4279, |
| "eval_samples_per_second": 2.1, |
| "eval_steps_per_second": 2.1, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.2359048128128052, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.3495, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.2226791381835938, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.3017, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.8974970579147339, |
| "learning_rate": 0.0001, |
| "loss": 0.2361, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.8545649647712708, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.2562, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.9259800910949707, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.2354, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 1.0612022876739502, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2459, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.8645911812782288, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.2035, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.6097703576087952, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1792, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.652665376663208, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1695, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.6387906074523926, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1604, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.19103586673736572, |
| "eval_runtime": 21.2745, |
| "eval_samples_per_second": 2.115, |
| "eval_steps_per_second": 2.115, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.9285987019538879, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.2201, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.8993455171585083, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1808, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.6245130300521851, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1396, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.7214536666870117, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1926, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.7997086644172668, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1981, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.7039807438850403, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.1953, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.6352254152297974, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1279, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.5867531299591064, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1645, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.5474146008491516, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1519, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.649555504322052, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1496, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.15950791537761688, |
| "eval_runtime": 21.2955, |
| "eval_samples_per_second": 2.113, |
| "eval_steps_per_second": 2.113, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.5549101233482361, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1121, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.588964581489563, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.134, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.5350345969200134, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.113, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.6418925523757935, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.1586, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.6536703705787659, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1285, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.5942428708076477, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1425, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.6391817331314087, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1372, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.6921087503433228, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1249, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.5099162459373474, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.097, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.6329302191734314, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.129, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.1433192640542984, |
| "eval_runtime": 21.2877, |
| "eval_samples_per_second": 2.114, |
| "eval_steps_per_second": 2.114, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.5236812829971313, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0902, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.6952739357948303, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1324, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.746796727180481, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.1193, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.6901694536209106, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1136, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.529670000076294, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1172, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.5925005674362183, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.1178, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.6129519939422607, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.1319, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.6355108022689819, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1468, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.5077322125434875, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0959, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.6017586588859558, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0951, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.1401616483926773, |
| "eval_runtime": 21.288, |
| "eval_samples_per_second": 2.114, |
| "eval_steps_per_second": 2.114, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.6097234487533569, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1238, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.4967862367630005, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0644, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.49397993087768555, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0986, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.47185176610946655, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0846, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.5109013915061951, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.1011, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.6786739826202393, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.1124, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.6182302236557007, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0837, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.525033175945282, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0958, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.5250701308250427, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0893, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.45738929510116577, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.073, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.14132848381996155, |
| "eval_runtime": 21.2664, |
| "eval_samples_per_second": 2.116, |
| "eval_steps_per_second": 2.116, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.5111187100410461, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0931, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5760725736618042, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0938, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.45572230219841003, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0752, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.43041902780532837, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0649, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.39944151043891907, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0454, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.7070135474205017, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.1181, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.8437821865081787, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.1, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.5093618631362915, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0687, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.6310197114944458, |
| "learning_rate": 5e-05, |
| "loss": 0.0886, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.5495316982269287, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0654, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.13377071917057037, |
| "eval_runtime": 21.2694, |
| "eval_samples_per_second": 2.116, |
| "eval_steps_per_second": 2.116, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.7269087433815002, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.117, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.6060029864311218, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0778, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.6334003210067749, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0784, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.611452579498291, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.077, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.6560848951339722, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.1086, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.6053079962730408, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.068, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.6017114520072937, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0734, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.6089465618133545, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0792, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.48159003257751465, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0611, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.6468281149864197, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0608, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.13164517283439636, |
| "eval_runtime": 21.2768, |
| "eval_samples_per_second": 2.115, |
| "eval_steps_per_second": 2.115, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.5581164956092834, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0727, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.5522684454917908, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0867, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.6064017415046692, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.069, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.45766428112983704, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0526, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.5743669867515564, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0518, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.6011852025985718, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0474, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.5489234328269958, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.051, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.5288805365562439, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0352, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.7551547288894653, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0478, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.6781327724456787, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0642, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.13698329031467438, |
| "eval_runtime": 21.2693, |
| "eval_samples_per_second": 2.116, |
| "eval_steps_per_second": 2.116, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.658314049243927, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0658, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.704215943813324, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0537, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.5954383611679077, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0528, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.6946048736572266, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0734, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.7986078858375549, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0841, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.5556001663208008, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0651, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.6038070917129517, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0586, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.5463442206382751, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.07, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.7392358779907227, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0458, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.48301032185554504, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0397, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.133963480591774, |
| "eval_runtime": 21.2761, |
| "eval_samples_per_second": 2.115, |
| "eval_steps_per_second": 2.115, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.5791436433792114, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0556, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.5720934271812439, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0524, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.5098394751548767, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0462, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.4873999357223511, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0382, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.44167429208755493, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0288, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.5804839134216309, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0632, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.40340307354927063, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0335, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.4408301115036011, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.047, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.49245479702949524, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0346, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.547877311706543, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0606, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.13484035432338715, |
| "eval_runtime": 21.2761, |
| "eval_samples_per_second": 2.115, |
| "eval_steps_per_second": 2.115, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.5615519285202026, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0515, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.5062819719314575, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0507, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.4328884184360504, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0329, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.5657582879066467, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0407, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.5019187927246094, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0389, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.43167033791542053, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0292, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.6004226207733154, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0676, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.5526849031448364, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0541, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.49565309286117554, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0307, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.5426778197288513, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0551, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.13495521247386932, |
| "eval_runtime": 21.2881, |
| "eval_samples_per_second": 2.114, |
| "eval_steps_per_second": 2.114, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.4021456837654114, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0443, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.4804547131061554, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0509, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.5332744717597961, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0454, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.6498481631278992, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0513, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.5680502653121948, |
| "learning_rate": 0.0, |
| "loss": 0.0514, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.3179392676082483e+17, |
| "train_loss": 0.1513957921117544, |
| "train_runtime": 3799.4443, |
| "train_samples_per_second": 0.533, |
| "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": 1.3179392676082483e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
