| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 2110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.226415094339623e-06, | |
| "loss": 1.1807, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.2452830188679246e-05, | |
| "loss": 1.1325, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.8679245283018867e-05, | |
| "loss": 0.9876, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.4905660377358492e-05, | |
| "loss": 0.873, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.994011976047904e-05, | |
| "loss": 0.7931, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.9610778443113774e-05, | |
| "loss": 0.7764, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.9281437125748504e-05, | |
| "loss": 0.7701, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.8952095808383233e-05, | |
| "loss": 0.739, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.8622754491017966e-05, | |
| "loss": 0.7644, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6429210134128167, | |
| "eval_loss": 1.0036486387252808, | |
| "eval_runtime": 6.1897, | |
| "eval_samples_per_second": 32.312, | |
| "eval_steps_per_second": 2.1, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 14.5, | |
| "eval_f1": 19.727380952380955, | |
| "eval_qa_bleu": 9.309381343075087, | |
| "eval_qa_exact_match": 0.14, | |
| "eval_recite_bleu": 15.818078125717689, | |
| "eval_recite_exact_match": 0.0, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.8293413173652696e-05, | |
| "loss": 0.6488, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.7964071856287425e-05, | |
| "loss": 0.5286, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.763473053892216e-05, | |
| "loss": 0.5157, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7305389221556884e-05, | |
| "loss": 0.4838, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.6976047904191617e-05, | |
| "loss": 0.5013, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.664670658682635e-05, | |
| "loss": 0.4649, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.6317365269461076e-05, | |
| "loss": 0.4604, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.598802395209581e-05, | |
| "loss": 0.5064, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.565868263473054e-05, | |
| "loss": 0.4732, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.5329341317365268e-05, | |
| "loss": 0.526, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6657600596125186, | |
| "eval_loss": 0.7350580096244812, | |
| "eval_runtime": 6.5425, | |
| "eval_samples_per_second": 30.569, | |
| "eval_steps_per_second": 1.987, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 12.5, | |
| "eval_f1": 19.69947691197691, | |
| "eval_qa_bleu": 9.452490656702446, | |
| "eval_qa_exact_match": 0.12, | |
| "eval_recite_bleu": 17.493375608153375, | |
| "eval_recite_exact_match": 0.0, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4741, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.467065868263473e-05, | |
| "loss": 0.4338, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2.4341317365269464e-05, | |
| "loss": 0.4451, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.4011976047904193e-05, | |
| "loss": 0.4312, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.3682634730538923e-05, | |
| "loss": 0.4363, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.3353293413173656e-05, | |
| "loss": 0.4302, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.302395209580838e-05, | |
| "loss": 0.4528, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.2694610778443115e-05, | |
| "loss": 0.4086, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.2365269461077847e-05, | |
| "loss": 0.4163, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6815499254843517, | |
| "eval_loss": 0.5743635296821594, | |
| "eval_runtime": 6.2699, | |
| "eval_samples_per_second": 31.898, | |
| "eval_steps_per_second": 2.073, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 13.0, | |
| "eval_f1": 20.81829004329004, | |
| "eval_qa_bleu": 7.245823931129993, | |
| "eval_qa_exact_match": 0.12, | |
| "eval_recite_bleu": 22.248138618982026, | |
| "eval_recite_exact_match": 0.0, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2.2035928143712574e-05, | |
| "loss": 0.3866, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2.1706586826347306e-05, | |
| "loss": 0.2789, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2.1377245508982036e-05, | |
| "loss": 0.2932, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 2.1047904191616766e-05, | |
| "loss": 0.2883, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.07185628742515e-05, | |
| "loss": 0.3048, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2.0389221556886228e-05, | |
| "loss": 0.28, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 2.0059880239520957e-05, | |
| "loss": 0.2847, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.9730538922155687e-05, | |
| "loss": 0.2949, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.940119760479042e-05, | |
| "loss": 0.3002, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.9071856287425153e-05, | |
| "loss": 0.2864, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.689903129657228, | |
| "eval_loss": 0.4952711760997772, | |
| "eval_runtime": 6.337, | |
| "eval_samples_per_second": 31.561, | |
| "eval_steps_per_second": 2.051, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 17.0, | |
| "eval_f1": 22.154761904761905, | |
| "eval_qa_bleu": 10.09488722739415, | |
| "eval_qa_exact_match": 0.155, | |
| "eval_recite_bleu": 27.91257178143564, | |
| "eval_recite_exact_match": 0.005, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.874251497005988e-05, | |
| "loss": 0.2368, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.8413173652694612e-05, | |
| "loss": 0.203, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 1.8083832335329345e-05, | |
| "loss": 0.2092, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 1.775449101796407e-05, | |
| "loss": 0.2188, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 1.7425149700598804e-05, | |
| "loss": 0.2092, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.7095808383233533e-05, | |
| "loss": 0.2144, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 1.6766467065868263e-05, | |
| "loss": 0.2061, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.6437125748502996e-05, | |
| "loss": 0.2161, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.6107784431137725e-05, | |
| "loss": 0.2118, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6943889716840537, | |
| "eval_loss": 0.45938587188720703, | |
| "eval_runtime": 6.2541, | |
| "eval_samples_per_second": 31.979, | |
| "eval_steps_per_second": 2.079, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 16.0, | |
| "eval_f1": 22.22857142857142, | |
| "eval_qa_bleu": 10.69246525438524, | |
| "eval_qa_exact_match": 0.14, | |
| "eval_recite_bleu": 33.64683237936858, | |
| "eval_recite_exact_match": 0.025, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.5778443113772455e-05, | |
| "loss": 0.2129, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.5449101796407184e-05, | |
| "loss": 0.1559, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 1.5119760479041917e-05, | |
| "loss": 0.1631, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1.4790419161676647e-05, | |
| "loss": 0.1614, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 1.4461077844311378e-05, | |
| "loss": 0.1636, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 1.4131736526946109e-05, | |
| "loss": 0.1645, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 1.3802395209580839e-05, | |
| "loss": 0.1613, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 1.3473053892215568e-05, | |
| "loss": 0.1724, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 1.31437125748503e-05, | |
| "loss": 0.1643, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 1.281437125748503e-05, | |
| "loss": 0.17, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6964456035767511, | |
| "eval_loss": 0.44896385073661804, | |
| "eval_runtime": 6.3718, | |
| "eval_samples_per_second": 31.389, | |
| "eval_steps_per_second": 2.04, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_exact_match": 15.0, | |
| "eval_f1": 21.070238095238086, | |
| "eval_qa_bleu": 11.294234950233255, | |
| "eval_qa_exact_match": 0.13, | |
| "eval_recite_bleu": 35.4728355349377, | |
| "eval_recite_exact_match": 0.025, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.2485029940119762e-05, | |
| "loss": 0.1441, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 1.2155688622754491e-05, | |
| "loss": 0.1356, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 1.182634730538922e-05, | |
| "loss": 0.1363, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 1.1497005988023954e-05, | |
| "loss": 0.137, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.1167664670658683e-05, | |
| "loss": 0.1382, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.0838323353293413e-05, | |
| "loss": 0.1416, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.0508982035928144e-05, | |
| "loss": 0.1389, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.0179640718562873e-05, | |
| "loss": 0.1392, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 9.850299401197606e-06, | |
| "loss": 0.1398, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 9.520958083832336e-06, | |
| "loss": 0.134, | |
| "step": 1474 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.697876304023845, | |
| "eval_loss": 0.43685418367385864, | |
| "eval_runtime": 6.2539, | |
| "eval_samples_per_second": 31.98, | |
| "eval_steps_per_second": 2.079, | |
| "step": 1477 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_exact_match": 16.5, | |
| "eval_f1": 22.119444444444444, | |
| "eval_qa_bleu": 13.989667861778496, | |
| "eval_qa_exact_match": 0.14, | |
| "eval_recite_bleu": 42.188868266934165, | |
| "eval_recite_exact_match": 0.04, | |
| "step": 1477 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 9.191616766467065e-06, | |
| "loss": 0.1188, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 8.862275449101796e-06, | |
| "loss": 0.1207, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 8.532934131736528e-06, | |
| "loss": 0.1223, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 8.203592814371257e-06, | |
| "loss": 0.115, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 7.874251497005988e-06, | |
| "loss": 0.1139, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 7.544910179640718e-06, | |
| "loss": 0.117, | |
| "step": 1606 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 7.215568862275449e-06, | |
| "loss": 0.1203, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 6.8862275449101795e-06, | |
| "loss": 0.1229, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 6.556886227544911e-06, | |
| "loss": 0.1206, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6986959761549926, | |
| "eval_loss": 0.43722403049468994, | |
| "eval_runtime": 6.191, | |
| "eval_samples_per_second": 32.305, | |
| "eval_steps_per_second": 2.1, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_exact_match": 20.0, | |
| "eval_f1": 25.83571428571428, | |
| "eval_qa_bleu": 8.333490045944334, | |
| "eval_qa_exact_match": 0.18, | |
| "eval_recite_bleu": 43.68492978075338, | |
| "eval_recite_exact_match": 0.065, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 6.22754491017964e-06, | |
| "loss": 0.1145, | |
| "step": 1694 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 5.898203592814371e-06, | |
| "loss": 0.1066, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 5.568862275449102e-06, | |
| "loss": 0.1064, | |
| "step": 1738 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 5.239520958083833e-06, | |
| "loss": 0.1077, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 4.9101796407185625e-06, | |
| "loss": 0.1108, | |
| "step": 1782 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.580838323353294e-06, | |
| "loss": 0.1078, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 4.251497005988024e-06, | |
| "loss": 0.1072, | |
| "step": 1826 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 3.922155688622755e-06, | |
| "loss": 0.1098, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 3.592814371257485e-06, | |
| "loss": 0.1093, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 3.2634730538922155e-06, | |
| "loss": 0.1081, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.698725782414307, | |
| "eval_loss": 0.44227516651153564, | |
| "eval_runtime": 6.2856, | |
| "eval_samples_per_second": 31.819, | |
| "eval_steps_per_second": 2.068, | |
| "step": 1899 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_exact_match": 17.5, | |
| "eval_f1": 22.30357142857143, | |
| "eval_qa_bleu": 10.817736383091892, | |
| "eval_qa_exact_match": 0.15, | |
| "eval_recite_bleu": 43.37666725316897, | |
| "eval_recite_exact_match": 0.06, | |
| "step": 1899 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 2.9341317365269463e-06, | |
| "loss": 0.1079, | |
| "step": 1914 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 2.6047904191616767e-06, | |
| "loss": 0.102, | |
| "step": 1936 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 2.2754491017964075e-06, | |
| "loss": 0.1003, | |
| "step": 1958 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 1.9461077844311374e-06, | |
| "loss": 0.1023, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 1.6167664670658684e-06, | |
| "loss": 0.1003, | |
| "step": 2002 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 1.287425149700599e-06, | |
| "loss": 0.1058, | |
| "step": 2024 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 9.580838323353293e-07, | |
| "loss": 0.1067, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 6.287425149700599e-07, | |
| "loss": 0.1047, | |
| "step": 2068 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 2.994011976047904e-07, | |
| "loss": 0.1053, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6988971684053651, | |
| "eval_loss": 0.4435840845108032, | |
| "eval_runtime": 6.3653, | |
| "eval_samples_per_second": 31.42, | |
| "eval_steps_per_second": 2.042, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_exact_match": 20.5, | |
| "eval_f1": 25.95833333333333, | |
| "eval_qa_bleu": 12.082719988904218, | |
| "eval_qa_exact_match": 0.18, | |
| "eval_recite_bleu": 44.74289478974747, | |
| "eval_recite_exact_match": 0.075, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 2110, | |
| "total_flos": 9.64020042848256e+16, | |
| "train_loss": 0.29445283661521443, | |
| "train_runtime": 3197.9615, | |
| "train_samples_per_second": 10.547, | |
| "train_steps_per_second": 0.66 | |
| } | |
| ], | |
| "logging_steps": 22, | |
| "max_steps": 2110, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 9.64020042848256e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |