| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 49.99777942264989, | |
| "global_step": 16850, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.8119, | |
| "eval_gen_len": 15.295, | |
| "eval_loss": 3.3328945636749268, | |
| "eval_runtime": 64.1416, | |
| "eval_samples_per_second": 88.102, | |
| "eval_steps_per_second": 4.412, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.851632047477745e-05, | |
| "loss": 3.528, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.9197, | |
| "eval_gen_len": 15.3056, | |
| "eval_loss": 3.283737897872925, | |
| "eval_runtime": 63.9504, | |
| "eval_samples_per_second": 88.365, | |
| "eval_steps_per_second": 4.425, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.70326409495549e-05, | |
| "loss": 3.3932, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.9536, | |
| "eval_gen_len": 15.6238, | |
| "eval_loss": 3.2553622722625732, | |
| "eval_runtime": 62.6609, | |
| "eval_samples_per_second": 90.184, | |
| "eval_steps_per_second": 4.516, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 1.0082, | |
| "eval_gen_len": 15.5254, | |
| "eval_loss": 3.236884117126465, | |
| "eval_runtime": 62.9428, | |
| "eval_samples_per_second": 89.78, | |
| "eval_steps_per_second": 4.496, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.554896142433235e-05, | |
| "loss": 3.3394, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 1.088, | |
| "eval_gen_len": 15.7466, | |
| "eval_loss": 3.222892999649048, | |
| "eval_runtime": 64.2741, | |
| "eval_samples_per_second": 87.92, | |
| "eval_steps_per_second": 4.403, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 4.4065281899109794e-05, | |
| "loss": 3.2982, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 1.1295, | |
| "eval_gen_len": 15.7866, | |
| "eval_loss": 3.210378885269165, | |
| "eval_runtime": 64.1493, | |
| "eval_samples_per_second": 88.091, | |
| "eval_steps_per_second": 4.412, | |
| "step": 2022 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 1.1648, | |
| "eval_gen_len": 15.6852, | |
| "eval_loss": 3.200908899307251, | |
| "eval_runtime": 63.0315, | |
| "eval_samples_per_second": 89.654, | |
| "eval_steps_per_second": 4.49, | |
| "step": 2359 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 4.258160237388724e-05, | |
| "loss": 3.2658, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 1.1548, | |
| "eval_gen_len": 15.9358, | |
| "eval_loss": 3.191558361053467, | |
| "eval_runtime": 64.0034, | |
| "eval_samples_per_second": 88.292, | |
| "eval_steps_per_second": 4.422, | |
| "step": 2696 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 4.109792284866469e-05, | |
| "loss": 3.2397, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 1.0651, | |
| "eval_gen_len": 16.0241, | |
| "eval_loss": 3.1847681999206543, | |
| "eval_runtime": 64.3166, | |
| "eval_samples_per_second": 87.862, | |
| "eval_steps_per_second": 4.4, | |
| "step": 3033 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 1.1443, | |
| "eval_gen_len": 16.0409, | |
| "eval_loss": 3.1797027587890625, | |
| "eval_runtime": 62.6803, | |
| "eval_samples_per_second": 90.156, | |
| "eval_steps_per_second": 4.515, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 3.961424332344214e-05, | |
| "loss": 3.2203, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 1.1562, | |
| "eval_gen_len": 15.9648, | |
| "eval_loss": 3.1735124588012695, | |
| "eval_runtime": 64.1808, | |
| "eval_samples_per_second": 88.048, | |
| "eval_steps_per_second": 4.409, | |
| "step": 3707 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 3.8130563798219586e-05, | |
| "loss": 3.1935, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 1.145, | |
| "eval_gen_len": 15.7811, | |
| "eval_loss": 3.1689915657043457, | |
| "eval_runtime": 62.6765, | |
| "eval_samples_per_second": 90.161, | |
| "eval_steps_per_second": 4.515, | |
| "step": 4044 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 1.1534, | |
| "eval_gen_len": 15.9582, | |
| "eval_loss": 3.1667888164520264, | |
| "eval_runtime": 64.2839, | |
| "eval_samples_per_second": 87.907, | |
| "eval_steps_per_second": 4.402, | |
| "step": 4381 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 3.664688427299703e-05, | |
| "loss": 3.1791, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 1.1476, | |
| "eval_gen_len": 15.9605, | |
| "eval_loss": 3.1629080772399902, | |
| "eval_runtime": 63.0085, | |
| "eval_samples_per_second": 89.686, | |
| "eval_steps_per_second": 4.491, | |
| "step": 4718 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 3.516320474777448e-05, | |
| "loss": 3.1562, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 1.1504, | |
| "eval_gen_len": 15.9747, | |
| "eval_loss": 3.1592817306518555, | |
| "eval_runtime": 63.8036, | |
| "eval_samples_per_second": 88.569, | |
| "eval_steps_per_second": 4.435, | |
| "step": 5055 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 1.2003, | |
| "eval_gen_len": 15.6548, | |
| "eval_loss": 3.1569018363952637, | |
| "eval_runtime": 63.7567, | |
| "eval_samples_per_second": 88.634, | |
| "eval_steps_per_second": 4.439, | |
| "step": 5392 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 3.3679525222551934e-05, | |
| "loss": 3.1461, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 1.187, | |
| "eval_gen_len": 16.2831, | |
| "eval_loss": 3.1528096199035645, | |
| "eval_runtime": 62.8317, | |
| "eval_samples_per_second": 89.939, | |
| "eval_steps_per_second": 4.504, | |
| "step": 5729 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 3.219584569732938e-05, | |
| "loss": 3.1301, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 1.1908, | |
| "eval_gen_len": 16.2078, | |
| "eval_loss": 3.15116024017334, | |
| "eval_runtime": 62.7949, | |
| "eval_samples_per_second": 89.991, | |
| "eval_steps_per_second": 4.507, | |
| "step": 6066 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 1.2164, | |
| "eval_gen_len": 16.1816, | |
| "eval_loss": 3.149709463119507, | |
| "eval_runtime": 63.3277, | |
| "eval_samples_per_second": 89.234, | |
| "eval_steps_per_second": 4.469, | |
| "step": 6403 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 3.071216617210683e-05, | |
| "loss": 3.1199, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 1.2493, | |
| "eval_gen_len": 16.0138, | |
| "eval_loss": 3.147409200668335, | |
| "eval_runtime": 62.5603, | |
| "eval_samples_per_second": 90.329, | |
| "eval_steps_per_second": 4.524, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "learning_rate": 2.9228486646884274e-05, | |
| "loss": 3.1012, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_bleu": 1.2189, | |
| "eval_gen_len": 15.9667, | |
| "eval_loss": 3.1471338272094727, | |
| "eval_runtime": 62.6224, | |
| "eval_samples_per_second": 90.239, | |
| "eval_steps_per_second": 4.519, | |
| "step": 7077 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_bleu": 1.2535, | |
| "eval_gen_len": 16.0239, | |
| "eval_loss": 3.145897150039673, | |
| "eval_runtime": 62.7278, | |
| "eval_samples_per_second": 90.088, | |
| "eval_steps_per_second": 4.512, | |
| "step": 7414 | |
| }, | |
| { | |
| "epoch": 22.25, | |
| "learning_rate": 2.774480712166172e-05, | |
| "loss": 3.0953, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_bleu": 1.2554, | |
| "eval_gen_len": 15.7225, | |
| "eval_loss": 3.143968343734741, | |
| "eval_runtime": 63.12, | |
| "eval_samples_per_second": 89.528, | |
| "eval_steps_per_second": 4.484, | |
| "step": 7751 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "learning_rate": 2.6261127596439174e-05, | |
| "loss": 3.0761, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_bleu": 1.2086, | |
| "eval_gen_len": 16.0069, | |
| "eval_loss": 3.141495943069458, | |
| "eval_runtime": 62.7045, | |
| "eval_samples_per_second": 90.121, | |
| "eval_steps_per_second": 4.513, | |
| "step": 8088 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_bleu": 1.305, | |
| "eval_gen_len": 15.9912, | |
| "eval_loss": 3.1416375637054443, | |
| "eval_runtime": 62.5621, | |
| "eval_samples_per_second": 90.326, | |
| "eval_steps_per_second": 4.524, | |
| "step": 8425 | |
| }, | |
| { | |
| "epoch": 25.22, | |
| "learning_rate": 2.4777448071216618e-05, | |
| "loss": 3.0822, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_bleu": 1.248, | |
| "eval_gen_len": 15.8406, | |
| "eval_loss": 3.1405673027038574, | |
| "eval_runtime": 62.6069, | |
| "eval_samples_per_second": 90.262, | |
| "eval_steps_per_second": 4.52, | |
| "step": 8762 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 2.3293768545994066e-05, | |
| "loss": 3.0614, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_bleu": 1.2888, | |
| "eval_gen_len": 16.3189, | |
| "eval_loss": 3.140249252319336, | |
| "eval_runtime": 62.6544, | |
| "eval_samples_per_second": 90.193, | |
| "eval_steps_per_second": 4.517, | |
| "step": 9099 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_bleu": 1.3016, | |
| "eval_gen_len": 16.0096, | |
| "eval_loss": 3.1379010677337646, | |
| "eval_runtime": 62.5617, | |
| "eval_samples_per_second": 90.327, | |
| "eval_steps_per_second": 4.524, | |
| "step": 9436 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 2.1810089020771514e-05, | |
| "loss": 3.0594, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_bleu": 1.2268, | |
| "eval_gen_len": 16.3702, | |
| "eval_loss": 3.139193058013916, | |
| "eval_runtime": 62.7397, | |
| "eval_samples_per_second": 90.071, | |
| "eval_steps_per_second": 4.511, | |
| "step": 9773 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "learning_rate": 2.0326409495548962e-05, | |
| "loss": 3.0453, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_bleu": 1.278, | |
| "eval_gen_len": 15.9722, | |
| "eval_loss": 3.1378531455993652, | |
| "eval_runtime": 62.634, | |
| "eval_samples_per_second": 90.223, | |
| "eval_steps_per_second": 4.518, | |
| "step": 10110 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_bleu": 1.2832, | |
| "eval_gen_len": 15.9759, | |
| "eval_loss": 3.136270046234131, | |
| "eval_runtime": 62.6958, | |
| "eval_samples_per_second": 90.134, | |
| "eval_steps_per_second": 4.514, | |
| "step": 10447 | |
| }, | |
| { | |
| "epoch": 31.16, | |
| "learning_rate": 1.884272997032641e-05, | |
| "loss": 3.0425, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_bleu": 1.3089, | |
| "eval_gen_len": 16.1499, | |
| "eval_loss": 3.136704206466675, | |
| "eval_runtime": 62.6194, | |
| "eval_samples_per_second": 90.244, | |
| "eval_steps_per_second": 4.519, | |
| "step": 10784 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 1.7359050445103858e-05, | |
| "loss": 3.0339, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_bleu": 1.2718, | |
| "eval_gen_len": 16.1051, | |
| "eval_loss": 3.1367685794830322, | |
| "eval_runtime": 62.5638, | |
| "eval_samples_per_second": 90.324, | |
| "eval_steps_per_second": 4.523, | |
| "step": 11121 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_bleu": 1.2683, | |
| "eval_gen_len": 16.0159, | |
| "eval_loss": 3.1349706649780273, | |
| "eval_runtime": 62.675, | |
| "eval_samples_per_second": 90.164, | |
| "eval_steps_per_second": 4.515, | |
| "step": 11458 | |
| }, | |
| { | |
| "epoch": 34.12, | |
| "learning_rate": 1.5875370919881306e-05, | |
| "loss": 3.0301, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_bleu": 1.286, | |
| "eval_gen_len": 16.1807, | |
| "eval_loss": 3.135624408721924, | |
| "eval_runtime": 62.61, | |
| "eval_samples_per_second": 90.257, | |
| "eval_steps_per_second": 4.52, | |
| "step": 11795 | |
| }, | |
| { | |
| "epoch": 35.61, | |
| "learning_rate": 1.4391691394658754e-05, | |
| "loss": 3.0197, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_bleu": 1.267, | |
| "eval_gen_len": 16.0966, | |
| "eval_loss": 3.1348326206207275, | |
| "eval_runtime": 62.637, | |
| "eval_samples_per_second": 90.218, | |
| "eval_steps_per_second": 4.518, | |
| "step": 12132 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_bleu": 1.3013, | |
| "eval_gen_len": 15.9283, | |
| "eval_loss": 3.1351914405822754, | |
| "eval_runtime": 62.7389, | |
| "eval_samples_per_second": 90.072, | |
| "eval_steps_per_second": 4.511, | |
| "step": 12469 | |
| }, | |
| { | |
| "epoch": 37.09, | |
| "learning_rate": 1.29080118694362e-05, | |
| "loss": 3.0204, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_bleu": 1.282, | |
| "eval_gen_len": 16.0099, | |
| "eval_loss": 3.1345412731170654, | |
| "eval_runtime": 62.6541, | |
| "eval_samples_per_second": 90.194, | |
| "eval_steps_per_second": 4.517, | |
| "step": 12806 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 1.142433234421365e-05, | |
| "loss": 3.0169, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_bleu": 1.3076, | |
| "eval_gen_len": 16.1136, | |
| "eval_loss": 3.1348047256469727, | |
| "eval_runtime": 62.7366, | |
| "eval_samples_per_second": 90.075, | |
| "eval_steps_per_second": 4.511, | |
| "step": 13143 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_bleu": 1.2947, | |
| "eval_gen_len": 16.0117, | |
| "eval_loss": 3.135272979736328, | |
| "eval_runtime": 62.894, | |
| "eval_samples_per_second": 89.85, | |
| "eval_steps_per_second": 4.5, | |
| "step": 13480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 9.940652818991098e-06, | |
| "loss": 3.0093, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_bleu": 1.3047, | |
| "eval_gen_len": 16.0662, | |
| "eval_loss": 3.134445905685425, | |
| "eval_runtime": 62.7291, | |
| "eval_samples_per_second": 90.086, | |
| "eval_steps_per_second": 4.511, | |
| "step": 13817 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 8.456973293768548e-06, | |
| "loss": 3.0009, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_bleu": 1.3017, | |
| "eval_gen_len": 16.1531, | |
| "eval_loss": 3.134453535079956, | |
| "eval_runtime": 62.7311, | |
| "eval_samples_per_second": 90.083, | |
| "eval_steps_per_second": 4.511, | |
| "step": 14154 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_bleu": 1.2762, | |
| "eval_gen_len": 16.0741, | |
| "eval_loss": 3.1347758769989014, | |
| "eval_runtime": 62.6827, | |
| "eval_samples_per_second": 90.152, | |
| "eval_steps_per_second": 4.515, | |
| "step": 14491 | |
| }, | |
| { | |
| "epoch": 43.03, | |
| "learning_rate": 6.973293768545995e-06, | |
| "loss": 3.0066, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_bleu": 1.2743, | |
| "eval_gen_len": 16.069, | |
| "eval_loss": 3.1343321800231934, | |
| "eval_runtime": 62.7369, | |
| "eval_samples_per_second": 90.075, | |
| "eval_steps_per_second": 4.511, | |
| "step": 14828 | |
| }, | |
| { | |
| "epoch": 44.51, | |
| "learning_rate": 5.489614243323442e-06, | |
| "loss": 3.0014, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_bleu": 1.264, | |
| "eval_gen_len": 16.0232, | |
| "eval_loss": 3.1345059871673584, | |
| "eval_runtime": 62.8103, | |
| "eval_samples_per_second": 89.969, | |
| "eval_steps_per_second": 4.506, | |
| "step": 15165 | |
| }, | |
| { | |
| "epoch": 45.99, | |
| "learning_rate": 4.005934718100891e-06, | |
| "loss": 2.9948, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_bleu": 1.2856, | |
| "eval_gen_len": 16.1014, | |
| "eval_loss": 3.134138345718384, | |
| "eval_runtime": 62.6814, | |
| "eval_samples_per_second": 90.154, | |
| "eval_steps_per_second": 4.515, | |
| "step": 15502 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_bleu": 1.2889, | |
| "eval_gen_len": 16.0956, | |
| "eval_loss": 3.1343159675598145, | |
| "eval_runtime": 62.7663, | |
| "eval_samples_per_second": 90.032, | |
| "eval_steps_per_second": 4.509, | |
| "step": 15839 | |
| }, | |
| { | |
| "epoch": 47.48, | |
| "learning_rate": 2.5222551928783385e-06, | |
| "loss": 3.0016, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_bleu": 1.2823, | |
| "eval_gen_len": 16.0342, | |
| "eval_loss": 3.13439679145813, | |
| "eval_runtime": 62.7228, | |
| "eval_samples_per_second": 90.095, | |
| "eval_steps_per_second": 4.512, | |
| "step": 16176 | |
| }, | |
| { | |
| "epoch": 48.96, | |
| "learning_rate": 1.0385756676557863e-06, | |
| "loss": 2.992, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_bleu": 1.2903, | |
| "eval_gen_len": 16.0894, | |
| "eval_loss": 3.134230136871338, | |
| "eval_runtime": 62.7414, | |
| "eval_samples_per_second": 90.068, | |
| "eval_steps_per_second": 4.511, | |
| "step": 16513 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_bleu": 1.279, | |
| "eval_gen_len": 16.0568, | |
| "eval_loss": 3.1342360973358154, | |
| "eval_runtime": 62.8254, | |
| "eval_samples_per_second": 89.948, | |
| "eval_steps_per_second": 4.505, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 16850, | |
| "total_flos": 8.49568285776937e+16, | |
| "train_loss": 3.1156047950088093, | |
| "train_runtime": 18325.9577, | |
| "train_samples_per_second": 73.715, | |
| "train_steps_per_second": 0.919 | |
| } | |
| ], | |
| "max_steps": 16850, | |
| "num_train_epochs": 50, | |
| "total_flos": 8.49568285776937e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |