| { | |
| "best_metric": 0.16459199786186218, | |
| "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold5/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": 3.1609537601470947, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.8257, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 3.4778194427490234, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.0196, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 3.41058611869812, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.9767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 3.332434892654419, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.9277, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 3.2479190826416016, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.97, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 3.3888728618621826, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.8208, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 2.8832502365112305, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.7344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 2.049940824508667, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.6459, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 2.399707078933716, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.8352, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 1.6917188167572021, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.5193, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.4231546223163605, | |
| "eval_runtime": 21.3917, | |
| "eval_samples_per_second": 2.104, | |
| "eval_steps_per_second": 2.104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 1.3795276880264282, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.5075, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 1.3883271217346191, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.5233, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.9566529393196106, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3608, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 1.0591416358947754, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.4391, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.9402590394020081, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.3174, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.8830267190933228, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.3084, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.7811403870582581, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.2395, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.7993518710136414, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.2883, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.889427125453949, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.3086, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.9078078866004944, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2655, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.24311862885951996, | |
| "eval_runtime": 21.2857, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 2.114, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.7216946482658386, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.2322, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.7100809216499329, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1369, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.7890493273735046, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.2252, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.8297878503799438, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.2049, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.7002233862876892, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1882, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 1.7222856283187866, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.3741, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.6407470107078552, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1521, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.775524914264679, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1723, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.7769914269447327, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.208, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.7448928952217102, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.1575, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.2011261135339737, | |
| "eval_runtime": 21.2941, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 2.113, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.5106372237205505, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1146, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.5387346744537354, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1291, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.6912793517112732, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1625, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.8624272346496582, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2176, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.7685644030570984, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1583, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.645549476146698, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1316, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.5016025900840759, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.9919281601905823, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1976, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.8780947327613831, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1453, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.8454704284667969, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.1529, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.17880217730998993, | |
| "eval_runtime": 21.3422, | |
| "eval_samples_per_second": 2.108, | |
| "eval_steps_per_second": 2.108, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.6084817051887512, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1399, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.7960084676742554, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.2002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.6951382160186768, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1534, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.8384109139442444, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1792, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.8313819169998169, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.1553, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.7282452583312988, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.1613, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.7107539176940918, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1308, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.6983649134635925, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1811, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.6983707547187805, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.1841, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.5776154398918152, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.1367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.1676388382911682, | |
| "eval_runtime": 21.3028, | |
| "eval_samples_per_second": 2.112, | |
| "eval_steps_per_second": 2.112, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 1.394680380821228, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.2843, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.5660679340362549, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.1196, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.44564926624298096, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0829, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.7316888570785522, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1363, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.5059979557991028, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0833, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.45145776867866516, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1158, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.5935726761817932, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.1015, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.5955262780189514, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.1343, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.7581863403320312, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.1372, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.567732572555542, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.1243, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.16937586665153503, | |
| "eval_runtime": 21.3112, | |
| "eval_samples_per_second": 2.112, | |
| "eval_steps_per_second": 2.112, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.601026177406311, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0959, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.6177619099617004, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0946, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.7292613983154297, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.1137, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.6076958775520325, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0769, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.629979133605957, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.1209, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.6063540577888489, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.1149, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.8434006571769714, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.1106, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.5540769696235657, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0738, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.7652309536933899, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1262, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.5797507166862488, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0943, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.1698533147573471, | |
| "eval_runtime": 21.2966, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 2.113, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.7467198371887207, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0974, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.7548785209655762, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.1262, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.6546044945716858, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0966, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.7426320910453796, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.1243, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.6800122857093811, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.1314, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 1.2498886585235596, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1636, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.60047847032547, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0714, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.5937264561653137, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.1082, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.5373544692993164, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0757, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.5356040596961975, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0697, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.16459199786186218, | |
| "eval_runtime": 21.337, | |
| "eval_samples_per_second": 2.109, | |
| "eval_steps_per_second": 2.109, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.588879406452179, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.081, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.48221874237060547, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0705, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.7139751315116882, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.077, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.4620410203933716, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0742, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.5212157368659973, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.085, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.4895257353782654, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0738, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.6054060459136963, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0885, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.4434739947319031, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0473, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.5287660360336304, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0871, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.45399925112724304, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.056, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.16687387228012085, | |
| "eval_runtime": 21.3193, | |
| "eval_samples_per_second": 2.111, | |
| "eval_steps_per_second": 2.111, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.43947917222976685, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0516, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.6417574286460876, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.062, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.40829816460609436, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0516, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.7315652370452881, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.085, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.6470200419425964, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.091, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.6585952043533325, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0698, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.5641435980796814, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1113, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.7359548807144165, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.111, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.5255526900291443, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0642, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.656811535358429, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0546, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.17240804433822632, | |
| "eval_runtime": 21.3162, | |
| "eval_samples_per_second": 2.111, | |
| "eval_steps_per_second": 2.111, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.7472591996192932, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0826, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 1.431636095046997, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1394, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.5793136358261108, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0666, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.4356386959552765, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0411, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.5856299996376038, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0566, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.5188583135604858, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0607, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.6742793917655945, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0568, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.5020348429679871, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0616, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.5859436392784119, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0655, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.4573688805103302, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0512, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.17236484587192535, | |
| "eval_runtime": 21.314, | |
| "eval_samples_per_second": 2.111, | |
| "eval_steps_per_second": 2.111, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.5039210915565491, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0475, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.7230071425437927, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0886, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.546083927154541, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0544, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.7178957462310791, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0666, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.5316588282585144, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0569, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.47381311655044556, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0471, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.5996780395507812, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0665, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.677655816078186, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0863, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.5139498710632324, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0526, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.5864439606666565, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0789, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.17115770280361176, | |
| "eval_runtime": 21.3634, | |
| "eval_samples_per_second": 2.106, | |
| "eval_steps_per_second": 2.106, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.4922991394996643, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0647, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.5744062662124634, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0594, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.7579936385154724, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0665, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.5928068161010742, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0844, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.43980729579925537, | |
| "learning_rate": 0.0, | |
| "loss": 0.0443, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.2544994631765197e+17, | |
| "train_loss": 0.1886660212278366, | |
| "train_runtime": 3412.1421, | |
| "train_samples_per_second": 0.593, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "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": 1.2544994631765197e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |