| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 3100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 38.730377197265625, | |
| "eval_runtime": 2.8841, | |
| "eval_samples_per_second": 41.955, | |
| "eval_steps_per_second": 5.548, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 37.18061828613281, | |
| "eval_runtime": 2.9537, | |
| "eval_samples_per_second": 40.966, | |
| "eval_steps_per_second": 5.417, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 33.34883499145508, | |
| "eval_runtime": 3.0329, | |
| "eval_samples_per_second": 39.895, | |
| "eval_steps_per_second": 5.275, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 28.77151870727539, | |
| "eval_runtime": 3.038, | |
| "eval_samples_per_second": 39.829, | |
| "eval_steps_per_second": 5.267, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 24.89649200439453, | |
| "eval_runtime": 3.1068, | |
| "eval_samples_per_second": 38.947, | |
| "eval_steps_per_second": 5.15, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 21.40663719177246, | |
| "eval_runtime": 3.1605, | |
| "eval_samples_per_second": 38.285, | |
| "eval_steps_per_second": 5.062, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 19.166534423828125, | |
| "eval_runtime": 3.191, | |
| "eval_samples_per_second": 37.919, | |
| "eval_steps_per_second": 5.014, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 17.308666229248047, | |
| "eval_runtime": 3.1957, | |
| "eval_samples_per_second": 37.863, | |
| "eval_steps_per_second": 5.007, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 1.6774193548387096e-07, | |
| "loss": 29.5022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 15.532267570495605, | |
| "eval_runtime": 3.0171, | |
| "eval_samples_per_second": 40.104, | |
| "eval_steps_per_second": 5.303, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 14.449665069580078, | |
| "eval_runtime": 3.0595, | |
| "eval_samples_per_second": 39.549, | |
| "eval_steps_per_second": 5.23, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 14.162155151367188, | |
| "eval_runtime": 3.1079, | |
| "eval_samples_per_second": 38.933, | |
| "eval_steps_per_second": 5.148, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 13.751199722290039, | |
| "eval_runtime": 3.1538, | |
| "eval_samples_per_second": 38.366, | |
| "eval_steps_per_second": 5.073, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 13.394129753112793, | |
| "eval_runtime": 3.1936, | |
| "eval_samples_per_second": 37.888, | |
| "eval_steps_per_second": 5.01, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 13.021451950073242, | |
| "eval_runtime": 3.2109, | |
| "eval_samples_per_second": 37.684, | |
| "eval_steps_per_second": 4.983, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 12.83625602722168, | |
| "eval_runtime": 3.2002, | |
| "eval_samples_per_second": 37.81, | |
| "eval_steps_per_second": 5.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 12.659578323364258, | |
| "eval_runtime": 3.1987, | |
| "eval_samples_per_second": 37.828, | |
| "eval_steps_per_second": 5.002, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 1.3548387096774192e-07, | |
| "loss": 13.2409, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 12.591437339782715, | |
| "eval_runtime": 3.1748, | |
| "eval_samples_per_second": 38.113, | |
| "eval_steps_per_second": 5.04, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 12.289512634277344, | |
| "eval_runtime": 3.1814, | |
| "eval_samples_per_second": 38.033, | |
| "eval_steps_per_second": 5.029, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 12.269988059997559, | |
| "eval_runtime": 3.2171, | |
| "eval_samples_per_second": 37.611, | |
| "eval_steps_per_second": 4.973, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 12.142666816711426, | |
| "eval_runtime": 3.202, | |
| "eval_samples_per_second": 37.789, | |
| "eval_steps_per_second": 4.997, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 12.13444995880127, | |
| "eval_runtime": 3.1974, | |
| "eval_samples_per_second": 37.843, | |
| "eval_steps_per_second": 5.004, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 12.062304496765137, | |
| "eval_runtime": 3.1989, | |
| "eval_samples_per_second": 37.825, | |
| "eval_steps_per_second": 5.002, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 12.063033103942871, | |
| "eval_runtime": 3.2187, | |
| "eval_samples_per_second": 37.593, | |
| "eval_steps_per_second": 4.971, | |
| "step": 1426 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 12.098295211791992, | |
| "eval_runtime": 3.1987, | |
| "eval_samples_per_second": 37.827, | |
| "eval_steps_per_second": 5.002, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 1.032258064516129e-07, | |
| "loss": 11.0242, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 11.790215492248535, | |
| "eval_runtime": 3.1841, | |
| "eval_samples_per_second": 38.002, | |
| "eval_steps_per_second": 5.025, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 11.862567901611328, | |
| "eval_runtime": 3.1927, | |
| "eval_samples_per_second": 37.899, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 11.915380477905273, | |
| "eval_runtime": 3.2213, | |
| "eval_samples_per_second": 37.562, | |
| "eval_steps_per_second": 4.967, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 11.648334503173828, | |
| "eval_runtime": 3.1958, | |
| "eval_samples_per_second": 37.862, | |
| "eval_steps_per_second": 5.007, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 11.861973762512207, | |
| "eval_runtime": 3.1992, | |
| "eval_samples_per_second": 37.822, | |
| "eval_steps_per_second": 5.001, | |
| "step": 1798 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 11.598742485046387, | |
| "eval_runtime": 3.2, | |
| "eval_samples_per_second": 37.812, | |
| "eval_steps_per_second": 5.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 11.763324737548828, | |
| "eval_runtime": 3.1997, | |
| "eval_samples_per_second": 37.817, | |
| "eval_steps_per_second": 5.001, | |
| "step": 1922 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 11.699971199035645, | |
| "eval_runtime": 3.1883, | |
| "eval_samples_per_second": 37.951, | |
| "eval_steps_per_second": 5.018, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 32.26, | |
| "learning_rate": 7.096774193548388e-08, | |
| "loss": 10.5931, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 11.6630859375, | |
| "eval_runtime": 3.1817, | |
| "eval_samples_per_second": 38.03, | |
| "eval_steps_per_second": 5.029, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 11.431499481201172, | |
| "eval_runtime": 3.1876, | |
| "eval_samples_per_second": 37.96, | |
| "eval_steps_per_second": 5.019, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 11.56187915802002, | |
| "eval_runtime": 3.1936, | |
| "eval_samples_per_second": 37.889, | |
| "eval_steps_per_second": 5.01, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 11.59299087524414, | |
| "eval_runtime": 3.1844, | |
| "eval_samples_per_second": 37.998, | |
| "eval_steps_per_second": 5.025, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 11.55374526977539, | |
| "eval_runtime": 3.2023, | |
| "eval_samples_per_second": 37.785, | |
| "eval_steps_per_second": 4.996, | |
| "step": 2294 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 11.67027473449707, | |
| "eval_runtime": 3.1993, | |
| "eval_samples_per_second": 37.821, | |
| "eval_steps_per_second": 5.001, | |
| "step": 2356 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 11.548821449279785, | |
| "eval_runtime": 3.1859, | |
| "eval_samples_per_second": 37.98, | |
| "eval_steps_per_second": 5.022, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 11.443954467773438, | |
| "eval_runtime": 3.1913, | |
| "eval_samples_per_second": 37.916, | |
| "eval_steps_per_second": 5.014, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 40.32, | |
| "learning_rate": 3.8709677419354835e-08, | |
| "loss": 10.4503, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 11.321048736572266, | |
| "eval_runtime": 3.1707, | |
| "eval_samples_per_second": 38.162, | |
| "eval_steps_per_second": 5.046, | |
| "step": 2542 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 11.437300682067871, | |
| "eval_runtime": 3.1784, | |
| "eval_samples_per_second": 38.07, | |
| "eval_steps_per_second": 5.034, | |
| "step": 2604 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 11.486796379089355, | |
| "eval_runtime": 3.187, | |
| "eval_samples_per_second": 37.967, | |
| "eval_steps_per_second": 5.02, | |
| "step": 2666 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 11.38952350616455, | |
| "eval_runtime": 3.1899, | |
| "eval_samples_per_second": 37.932, | |
| "eval_steps_per_second": 5.016, | |
| "step": 2728 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 11.409669876098633, | |
| "eval_runtime": 3.1917, | |
| "eval_samples_per_second": 37.911, | |
| "eval_steps_per_second": 5.013, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 11.556734085083008, | |
| "eval_runtime": 3.1934, | |
| "eval_samples_per_second": 37.891, | |
| "eval_steps_per_second": 5.01, | |
| "step": 2852 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 11.35185718536377, | |
| "eval_runtime": 3.1869, | |
| "eval_samples_per_second": 37.968, | |
| "eval_steps_per_second": 5.021, | |
| "step": 2914 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 11.326269149780273, | |
| "eval_runtime": 3.1877, | |
| "eval_samples_per_second": 37.959, | |
| "eval_steps_per_second": 5.019, | |
| "step": 2976 | |
| }, | |
| { | |
| "epoch": 48.39, | |
| "learning_rate": 6.451612903225806e-09, | |
| "loss": 10.4239, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 11.404916763305664, | |
| "eval_runtime": 3.3462, | |
| "eval_samples_per_second": 36.16, | |
| "eval_steps_per_second": 4.782, | |
| "step": 3038 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 11.230060577392578, | |
| "eval_runtime": 3.1439, | |
| "eval_samples_per_second": 38.487, | |
| "eval_steps_per_second": 5.089, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 3100, | |
| "total_flos": 1623561609830400.0, | |
| "train_loss": 14.082046567855343, | |
| "train_runtime": 2464.2419, | |
| "train_samples_per_second": 9.983, | |
| "train_steps_per_second": 1.258 | |
| } | |
| ], | |
| "max_steps": 3100, | |
| "num_train_epochs": 50, | |
| "total_flos": 1623561609830400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |