| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "./models/checkpoint-602", | |
| "epoch": 98.0, | |
| "global_step": 58996, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.99e-05, | |
| "loss": 9.7183, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.9950010776519775, | |
| "eval_runtime": 377.3539, | |
| "eval_samples_per_second": 12.24, | |
| "eval_steps_per_second": 0.154, | |
| "eval_wer": 1.0, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.966047297297298e-05, | |
| "loss": 2.4521, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.7947585582733154, | |
| "eval_runtime": 335.0691, | |
| "eval_samples_per_second": 13.785, | |
| "eval_steps_per_second": 0.173, | |
| "eval_wer": 0.7436259622854722, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.864358108108108e-05, | |
| "loss": 0.7245, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5130816698074341, | |
| "eval_runtime": 367.2509, | |
| "eval_samples_per_second": 12.577, | |
| "eval_steps_per_second": 0.158, | |
| "eval_wer": 0.6208418673635143, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.762668918918919e-05, | |
| "loss": 0.5488, | |
| "step": 2408 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.4323376417160034, | |
| "eval_runtime": 384.1184, | |
| "eval_samples_per_second": 12.025, | |
| "eval_steps_per_second": 0.151, | |
| "eval_wer": 0.5652941591920333, | |
| "step": 2408 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.66097972972973e-05, | |
| "loss": 0.4613, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.3905767500400543, | |
| "eval_runtime": 369.1827, | |
| "eval_samples_per_second": 12.511, | |
| "eval_steps_per_second": 0.157, | |
| "eval_wer": 0.5313934599901123, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.559290540540541e-05, | |
| "loss": 0.4138, | |
| "step": 3612 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.36640074849128723, | |
| "eval_runtime": 327.6142, | |
| "eval_samples_per_second": 14.099, | |
| "eval_steps_per_second": 0.177, | |
| "eval_wer": 0.5138074722791157, | |
| "step": 3612 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.457601351351352e-05, | |
| "loss": 0.3768, | |
| "step": 4214 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.34569260478019714, | |
| "eval_runtime": 320.036, | |
| "eval_samples_per_second": 14.433, | |
| "eval_steps_per_second": 0.181, | |
| "eval_wer": 0.49265484850625046, | |
| "step": 4214 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.355912162162163e-05, | |
| "loss": 0.3493, | |
| "step": 4816 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.3470996916294098, | |
| "eval_runtime": 322.8379, | |
| "eval_samples_per_second": 14.307, | |
| "eval_steps_per_second": 0.18, | |
| "eval_wer": 0.48280245780069214, | |
| "step": 4816 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.254222972972973e-05, | |
| "loss": 0.3278, | |
| "step": 5418 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.329658180475235, | |
| "eval_runtime": 351.53, | |
| "eval_samples_per_second": 13.14, | |
| "eval_steps_per_second": 0.165, | |
| "eval_wer": 0.4710431527650258, | |
| "step": 5418 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.152533783783784e-05, | |
| "loss": 0.3042, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.3340738117694855, | |
| "eval_runtime": 307.6844, | |
| "eval_samples_per_second": 15.012, | |
| "eval_steps_per_second": 0.189, | |
| "eval_wer": 0.4614732678861502, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.050844594594595e-05, | |
| "loss": 0.2902, | |
| "step": 6622 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.31241220235824585, | |
| "eval_runtime": 313.7253, | |
| "eval_samples_per_second": 14.723, | |
| "eval_steps_per_second": 0.185, | |
| "eval_wer": 0.4491842644254538, | |
| "step": 6622 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 8.949155405405406e-05, | |
| "loss": 0.2748, | |
| "step": 7224 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.3046228885650635, | |
| "eval_runtime": 310.6627, | |
| "eval_samples_per_second": 14.868, | |
| "eval_steps_per_second": 0.187, | |
| "eval_wer": 0.4424747510417402, | |
| "step": 7224 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 8.847466216216217e-05, | |
| "loss": 0.263, | |
| "step": 7826 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.3139520585536957, | |
| "eval_runtime": 306.886, | |
| "eval_samples_per_second": 15.051, | |
| "eval_steps_per_second": 0.189, | |
| "eval_wer": 0.4403206441132848, | |
| "step": 7826 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 8.745945945945946e-05, | |
| "loss": 0.2506, | |
| "step": 8428 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.3264484107494354, | |
| "eval_runtime": 314.9752, | |
| "eval_samples_per_second": 14.665, | |
| "eval_steps_per_second": 0.184, | |
| "eval_wer": 0.4372837064764461, | |
| "step": 8428 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.644256756756757e-05, | |
| "loss": 0.2395, | |
| "step": 9030 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.3298631012439728, | |
| "eval_runtime": 313.3642, | |
| "eval_samples_per_second": 14.74, | |
| "eval_steps_per_second": 0.185, | |
| "eval_wer": 0.4310332650610919, | |
| "step": 9030 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 8.542567567567568e-05, | |
| "loss": 0.2289, | |
| "step": 9632 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.32563555240631104, | |
| "eval_runtime": 316.6154, | |
| "eval_samples_per_second": 14.589, | |
| "eval_steps_per_second": 0.183, | |
| "eval_wer": 0.4247828236457377, | |
| "step": 9632 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 8.440878378378379e-05, | |
| "loss": 0.2229, | |
| "step": 10234 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.30847427248954773, | |
| "eval_runtime": 314.5985, | |
| "eval_samples_per_second": 14.682, | |
| "eval_steps_per_second": 0.184, | |
| "eval_wer": 0.4183205028603715, | |
| "step": 10234 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 8.339358108108109e-05, | |
| "loss": 0.2123, | |
| "step": 10836 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.32277214527130127, | |
| "eval_runtime": 319.0938, | |
| "eval_samples_per_second": 14.475, | |
| "eval_steps_per_second": 0.182, | |
| "eval_wer": 0.41549544459354476, | |
| "step": 10836 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 8.23766891891892e-05, | |
| "loss": 0.2059, | |
| "step": 11438 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.32871213555336, | |
| "eval_runtime": 322.1095, | |
| "eval_samples_per_second": 14.34, | |
| "eval_steps_per_second": 0.18, | |
| "eval_wer": 0.4104103397132566, | |
| "step": 11438 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 8.135979729729731e-05, | |
| "loss": 0.2011, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.3290630877017975, | |
| "eval_runtime": 327.3838, | |
| "eval_samples_per_second": 14.109, | |
| "eval_steps_per_second": 0.177, | |
| "eval_wer": 0.4098100148315559, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 8.03429054054054e-05, | |
| "loss": 0.1948, | |
| "step": 12642 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.3254837393760681, | |
| "eval_runtime": 343.6765, | |
| "eval_samples_per_second": 13.44, | |
| "eval_steps_per_second": 0.169, | |
| "eval_wer": 0.4006638886927043, | |
| "step": 12642 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 7.932770270270272e-05, | |
| "loss": 0.1884, | |
| "step": 13244 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.3118044137954712, | |
| "eval_runtime": 335.2687, | |
| "eval_samples_per_second": 13.777, | |
| "eval_steps_per_second": 0.173, | |
| "eval_wer": 0.39858040822091956, | |
| "step": 13244 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 7.831081081081081e-05, | |
| "loss": 0.1806, | |
| "step": 13846 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.3262838125228882, | |
| "eval_runtime": 390.3862, | |
| "eval_samples_per_second": 11.832, | |
| "eval_steps_per_second": 0.149, | |
| "eval_wer": 0.3974150716858535, | |
| "step": 13846 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 7.729391891891892e-05, | |
| "loss": 0.1782, | |
| "step": 14448 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.3207845687866211, | |
| "eval_runtime": 360.7865, | |
| "eval_samples_per_second": 12.803, | |
| "eval_steps_per_second": 0.161, | |
| "eval_wer": 0.39123525672717, | |
| "step": 14448 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 7.627702702702702e-05, | |
| "loss": 0.1729, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.3174630105495453, | |
| "eval_runtime": 356.0372, | |
| "eval_samples_per_second": 12.973, | |
| "eval_steps_per_second": 0.163, | |
| "eval_wer": 0.3948372060173741, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 7.526013513513513e-05, | |
| "loss": 0.1687, | |
| "step": 15652 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.3447326123714447, | |
| "eval_runtime": 369.502, | |
| "eval_samples_per_second": 12.501, | |
| "eval_steps_per_second": 0.157, | |
| "eval_wer": 0.38544388728017515, | |
| "step": 15652 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 7.424324324324324e-05, | |
| "loss": 0.167, | |
| "step": 16254 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.3525393605232239, | |
| "eval_runtime": 355.9444, | |
| "eval_samples_per_second": 12.977, | |
| "eval_steps_per_second": 0.163, | |
| "eval_wer": 0.3901052334204393, | |
| "step": 16254 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 7.322635135135135e-05, | |
| "loss": 0.1619, | |
| "step": 16856 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.3377859592437744, | |
| "eval_runtime": 331.4224, | |
| "eval_samples_per_second": 13.937, | |
| "eval_steps_per_second": 0.175, | |
| "eval_wer": 0.3853732608235045, | |
| "step": 16856 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 7.220945945945946e-05, | |
| "loss": 0.1549, | |
| "step": 17458 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.35701897740364075, | |
| "eval_runtime": 327.8021, | |
| "eval_samples_per_second": 14.091, | |
| "eval_steps_per_second": 0.177, | |
| "eval_wer": 0.3870682957836005, | |
| "step": 17458 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 7.119425675675676e-05, | |
| "loss": 0.1543, | |
| "step": 18060 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.3298207223415375, | |
| "eval_runtime": 329.7188, | |
| "eval_samples_per_second": 14.009, | |
| "eval_steps_per_second": 0.176, | |
| "eval_wer": 0.38085316759658167, | |
| "step": 18060 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 7.017736486486487e-05, | |
| "loss": 0.15, | |
| "step": 18662 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.34915244579315186, | |
| "eval_runtime": 362.9462, | |
| "eval_samples_per_second": 12.726, | |
| "eval_steps_per_second": 0.16, | |
| "eval_wer": 0.3779221696447489, | |
| "step": 18662 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 6.916047297297298e-05, | |
| "loss": 0.1459, | |
| "step": 19264 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.3343390226364136, | |
| "eval_runtime": 363.1934, | |
| "eval_samples_per_second": 12.718, | |
| "eval_steps_per_second": 0.16, | |
| "eval_wer": 0.37530899074793417, | |
| "step": 19264 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 6.814527027027028e-05, | |
| "loss": 0.1439, | |
| "step": 19866 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.3707464039325714, | |
| "eval_runtime": 319.1722, | |
| "eval_samples_per_second": 14.472, | |
| "eval_steps_per_second": 0.182, | |
| "eval_wer": 0.3783106151564376, | |
| "step": 19866 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 6.713006756756756e-05, | |
| "loss": 0.1386, | |
| "step": 20468 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.3442770838737488, | |
| "eval_runtime": 326.9396, | |
| "eval_samples_per_second": 14.128, | |
| "eval_steps_per_second": 0.177, | |
| "eval_wer": 0.3738964616145208, | |
| "step": 20468 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6.611317567567568e-05, | |
| "loss": 0.1374, | |
| "step": 21070 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.36009541153907776, | |
| "eval_runtime": 311.0687, | |
| "eval_samples_per_second": 14.849, | |
| "eval_steps_per_second": 0.186, | |
| "eval_wer": 0.37350801610283213, | |
| "step": 21070 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 6.509628378378379e-05, | |
| "loss": 0.1334, | |
| "step": 21672 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.37101128697395325, | |
| "eval_runtime": 289.3281, | |
| "eval_samples_per_second": 15.965, | |
| "eval_steps_per_second": 0.2, | |
| "eval_wer": 0.37138922240271205, | |
| "step": 21672 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 6.40793918918919e-05, | |
| "loss": 0.13, | |
| "step": 22274 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.3545927107334137, | |
| "eval_runtime": 291.5095, | |
| "eval_samples_per_second": 15.845, | |
| "eval_steps_per_second": 0.199, | |
| "eval_wer": 0.3684935376792146, | |
| "step": 22274 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 6.306250000000001e-05, | |
| "loss": 0.1266, | |
| "step": 22876 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.37049075961112976, | |
| "eval_runtime": 328.1134, | |
| "eval_samples_per_second": 14.077, | |
| "eval_steps_per_second": 0.177, | |
| "eval_wer": 0.367787273112508, | |
| "step": 22876 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 6.20456081081081e-05, | |
| "loss": 0.1253, | |
| "step": 23478 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.3741365373134613, | |
| "eval_runtime": 476.2923, | |
| "eval_samples_per_second": 9.698, | |
| "eval_steps_per_second": 0.122, | |
| "eval_wer": 0.37011794618264, | |
| "step": 23478 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 6.103040540540541e-05, | |
| "loss": 0.1221, | |
| "step": 24080 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.3850318491458893, | |
| "eval_runtime": 331.7813, | |
| "eval_samples_per_second": 13.922, | |
| "eval_steps_per_second": 0.175, | |
| "eval_wer": 0.37220142665442474, | |
| "step": 24080 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 6.001351351351352e-05, | |
| "loss": 0.1205, | |
| "step": 24682 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.3865145146846771, | |
| "eval_runtime": 328.7451, | |
| "eval_samples_per_second": 14.05, | |
| "eval_steps_per_second": 0.176, | |
| "eval_wer": 0.3651034677590225, | |
| "step": 24682 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 5.899662162162163e-05, | |
| "loss": 0.1179, | |
| "step": 25284 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.3818467855453491, | |
| "eval_runtime": 325.7829, | |
| "eval_samples_per_second": 14.178, | |
| "eval_steps_per_second": 0.178, | |
| "eval_wer": 0.36644537043576525, | |
| "step": 25284 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 5.7981418918918915e-05, | |
| "loss": 0.1185, | |
| "step": 25886 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.3811143636703491, | |
| "eval_runtime": 326.5779, | |
| "eval_samples_per_second": 14.144, | |
| "eval_steps_per_second": 0.178, | |
| "eval_wer": 0.36644537043576525, | |
| "step": 25886 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 5.6964527027027026e-05, | |
| "loss": 0.114, | |
| "step": 26488 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.3834444284439087, | |
| "eval_runtime": 335.6248, | |
| "eval_samples_per_second": 13.762, | |
| "eval_steps_per_second": 0.173, | |
| "eval_wer": 0.3639028179956212, | |
| "step": 26488 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 5.594763513513514e-05, | |
| "loss": 0.1147, | |
| "step": 27090 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.41083571314811707, | |
| "eval_runtime": 333.8024, | |
| "eval_samples_per_second": 13.838, | |
| "eval_steps_per_second": 0.174, | |
| "eval_wer": 0.3716364150010594, | |
| "step": 27090 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 5.493074324324324e-05, | |
| "loss": 0.1115, | |
| "step": 27692 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.39661291241645813, | |
| "eval_runtime": 339.3131, | |
| "eval_samples_per_second": 13.613, | |
| "eval_steps_per_second": 0.171, | |
| "eval_wer": 0.36227840949219575, | |
| "step": 27692 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 5.3915540540540545e-05, | |
| "loss": 0.109, | |
| "step": 28294 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.38050925731658936, | |
| "eval_runtime": 397.3812, | |
| "eval_samples_per_second": 11.624, | |
| "eval_steps_per_second": 0.146, | |
| "eval_wer": 0.358817713115333, | |
| "step": 28294 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 5.289864864864865e-05, | |
| "loss": 0.1072, | |
| "step": 28896 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.3901868164539337, | |
| "eval_runtime": 304.2685, | |
| "eval_samples_per_second": 15.181, | |
| "eval_steps_per_second": 0.191, | |
| "eval_wer": 0.35631047390352427, | |
| "step": 28896 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 5.188175675675676e-05, | |
| "loss": 0.1066, | |
| "step": 29498 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 0.41520482301712036, | |
| "eval_runtime": 344.9108, | |
| "eval_samples_per_second": 13.392, | |
| "eval_steps_per_second": 0.168, | |
| "eval_wer": 0.36079525390211176, | |
| "step": 29498 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 5.086486486486487e-05, | |
| "loss": 0.103, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.3830413520336151, | |
| "eval_runtime": 326.4997, | |
| "eval_samples_per_second": 14.147, | |
| "eval_steps_per_second": 0.178, | |
| "eval_wer": 0.3593120983120277, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 4.9847972972972975e-05, | |
| "loss": 0.1014, | |
| "step": 30702 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 0.40889114141464233, | |
| "eval_runtime": 440.9092, | |
| "eval_samples_per_second": 10.476, | |
| "eval_steps_per_second": 0.132, | |
| "eval_wer": 0.35578077547849424, | |
| "step": 30702 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 4.883108108108108e-05, | |
| "loss": 0.1012, | |
| "step": 31304 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 0.3804776668548584, | |
| "eval_runtime": 399.7783, | |
| "eval_samples_per_second": 11.554, | |
| "eval_steps_per_second": 0.145, | |
| "eval_wer": 0.3551098241401229, | |
| "step": 31304 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 4.781418918918919e-05, | |
| "loss": 0.0988, | |
| "step": 31906 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 0.38413405418395996, | |
| "eval_runtime": 402.2767, | |
| "eval_samples_per_second": 11.482, | |
| "eval_steps_per_second": 0.144, | |
| "eval_wer": 0.35320290981001484, | |
| "step": 31906 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 4.679898648648649e-05, | |
| "loss": 0.0984, | |
| "step": 32508 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 0.4035479724407196, | |
| "eval_runtime": 382.7739, | |
| "eval_samples_per_second": 12.067, | |
| "eval_steps_per_second": 0.152, | |
| "eval_wer": 0.3548273183134402, | |
| "step": 32508 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 4.5783783783783785e-05, | |
| "loss": 0.0961, | |
| "step": 33110 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 0.3776606619358063, | |
| "eval_runtime": 439.3383, | |
| "eval_samples_per_second": 10.514, | |
| "eval_steps_per_second": 0.132, | |
| "eval_wer": 0.3542269934317395, | |
| "step": 33110 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 4.4766891891891895e-05, | |
| "loss": 0.0949, | |
| "step": 33712 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 0.41516759991645813, | |
| "eval_runtime": 422.6534, | |
| "eval_samples_per_second": 10.929, | |
| "eval_steps_per_second": 0.137, | |
| "eval_wer": 0.35461543894342823, | |
| "step": 33712 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.0935, | |
| "step": 34314 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 0.3894650340080261, | |
| "eval_runtime": 423.1466, | |
| "eval_samples_per_second": 10.916, | |
| "eval_steps_per_second": 0.137, | |
| "eval_wer": 0.347729359418038, | |
| "step": 34314 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 4.273310810810811e-05, | |
| "loss": 0.0925, | |
| "step": 34916 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.4071078896522522, | |
| "eval_runtime": 435.5872, | |
| "eval_samples_per_second": 10.604, | |
| "eval_steps_per_second": 0.133, | |
| "eval_wer": 0.35087223673988277, | |
| "step": 34916 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 4.171621621621622e-05, | |
| "loss": 0.0922, | |
| "step": 35518 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 0.4226244390010834, | |
| "eval_runtime": 403.3952, | |
| "eval_samples_per_second": 11.45, | |
| "eval_steps_per_second": 0.144, | |
| "eval_wer": 0.35309697012500885, | |
| "step": 35518 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.070101351351351e-05, | |
| "loss": 0.0895, | |
| "step": 36120 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 0.43153172731399536, | |
| "eval_runtime": 398.9709, | |
| "eval_samples_per_second": 11.577, | |
| "eval_steps_per_second": 0.145, | |
| "eval_wer": 0.35094286319655343, | |
| "step": 36120 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 3.968412162162162e-05, | |
| "loss": 0.0897, | |
| "step": 36722 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 0.4538232386112213, | |
| "eval_runtime": 383.2903, | |
| "eval_samples_per_second": 12.051, | |
| "eval_steps_per_second": 0.151, | |
| "eval_wer": 0.3565929797302069, | |
| "step": 36722 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 3.8667229729729734e-05, | |
| "loss": 0.0873, | |
| "step": 37324 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 0.421456903219223, | |
| "eval_runtime": 398.9508, | |
| "eval_samples_per_second": 11.578, | |
| "eval_steps_per_second": 0.145, | |
| "eval_wer": 0.34794123878805, | |
| "step": 37324 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 3.765202702702703e-05, | |
| "loss": 0.0871, | |
| "step": 37926 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 0.42824164032936096, | |
| "eval_runtime": 403.2616, | |
| "eval_samples_per_second": 11.454, | |
| "eval_steps_per_second": 0.144, | |
| "eval_wer": 0.3506956705982061, | |
| "step": 37926 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.663682432432433e-05, | |
| "loss": 0.0862, | |
| "step": 38528 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 0.4110530912876129, | |
| "eval_runtime": 413.0672, | |
| "eval_samples_per_second": 11.182, | |
| "eval_steps_per_second": 0.14, | |
| "eval_wer": 0.3477999858747087, | |
| "step": 38528 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 3.561993243243243e-05, | |
| "loss": 0.0847, | |
| "step": 39130 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 0.4184618890285492, | |
| "eval_runtime": 401.9246, | |
| "eval_samples_per_second": 11.492, | |
| "eval_steps_per_second": 0.144, | |
| "eval_wer": 0.3505544176848647, | |
| "step": 39130 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 3.460304054054054e-05, | |
| "loss": 0.0843, | |
| "step": 39732 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 0.41128143668174744, | |
| "eval_runtime": 410.7955, | |
| "eval_samples_per_second": 11.244, | |
| "eval_steps_per_second": 0.141, | |
| "eval_wer": 0.3463168302846246, | |
| "step": 39732 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 3.3586148648648654e-05, | |
| "loss": 0.0829, | |
| "step": 40334 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 0.4144081771373749, | |
| "eval_runtime": 396.7416, | |
| "eval_samples_per_second": 11.642, | |
| "eval_steps_per_second": 0.146, | |
| "eval_wer": 0.3457871318595946, | |
| "step": 40334 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 3.256925675675676e-05, | |
| "loss": 0.0831, | |
| "step": 40936 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 0.4325215220451355, | |
| "eval_runtime": 401.3277, | |
| "eval_samples_per_second": 11.509, | |
| "eval_steps_per_second": 0.145, | |
| "eval_wer": 0.34493961437954657, | |
| "step": 40936 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 3.155236486486486e-05, | |
| "loss": 0.082, | |
| "step": 41538 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 0.4353320300579071, | |
| "eval_runtime": 266.5733, | |
| "eval_samples_per_second": 17.327, | |
| "eval_steps_per_second": 0.218, | |
| "eval_wer": 0.34246768839607317, | |
| "step": 41538 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 3.053547297297297e-05, | |
| "loss": 0.0802, | |
| "step": 42140 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 0.39984482526779175, | |
| "eval_runtime": 366.598, | |
| "eval_samples_per_second": 12.6, | |
| "eval_steps_per_second": 0.158, | |
| "eval_wer": 0.34059608729430046, | |
| "step": 42140 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 2.951858108108108e-05, | |
| "loss": 0.0792, | |
| "step": 42742 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 0.4112567901611328, | |
| "eval_runtime": 290.4304, | |
| "eval_samples_per_second": 15.904, | |
| "eval_steps_per_second": 0.2, | |
| "eval_wer": 0.3403488946959531, | |
| "step": 42742 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 2.850337837837838e-05, | |
| "loss": 0.0761, | |
| "step": 43344 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 0.422593891620636, | |
| "eval_runtime": 332.1718, | |
| "eval_samples_per_second": 13.905, | |
| "eval_steps_per_second": 0.175, | |
| "eval_wer": 0.3413376650893425, | |
| "step": 43344 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 2.7488175675675675e-05, | |
| "loss": 0.078, | |
| "step": 43946 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 0.420549213886261, | |
| "eval_runtime": 348.4845, | |
| "eval_samples_per_second": 13.255, | |
| "eval_steps_per_second": 0.166, | |
| "eval_wer": 0.3414436047743485, | |
| "step": 43946 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 2.6471283783783786e-05, | |
| "loss": 0.0771, | |
| "step": 44548 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.4529767334461212, | |
| "eval_runtime": 337.122, | |
| "eval_samples_per_second": 13.701, | |
| "eval_steps_per_second": 0.172, | |
| "eval_wer": 0.34349177201779785, | |
| "step": 44548 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 2.5454391891891894e-05, | |
| "loss": 0.0753, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 0.42464756965637207, | |
| "eval_runtime": 276.2812, | |
| "eval_samples_per_second": 16.718, | |
| "eval_steps_per_second": 0.21, | |
| "eval_wer": 0.33936012430256374, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 2.44375e-05, | |
| "loss": 0.0747, | |
| "step": 45752 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 0.4271426200866699, | |
| "eval_runtime": 305.7967, | |
| "eval_samples_per_second": 15.105, | |
| "eval_steps_per_second": 0.19, | |
| "eval_wer": 0.3410904724909951, | |
| "step": 45752 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 2.34222972972973e-05, | |
| "loss": 0.0744, | |
| "step": 46354 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 0.4557636082172394, | |
| "eval_runtime": 291.9496, | |
| "eval_samples_per_second": 15.821, | |
| "eval_steps_per_second": 0.199, | |
| "eval_wer": 0.34193798997104313, | |
| "step": 46354 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 2.2405405405405406e-05, | |
| "loss": 0.0735, | |
| "step": 46956 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 0.44490668177604675, | |
| "eval_runtime": 315.5036, | |
| "eval_samples_per_second": 14.64, | |
| "eval_steps_per_second": 0.184, | |
| "eval_wer": 0.34151423123101915, | |
| "step": 46956 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 2.1388513513513513e-05, | |
| "loss": 0.073, | |
| "step": 47558 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 0.431576669216156, | |
| "eval_runtime": 341.3029, | |
| "eval_samples_per_second": 13.533, | |
| "eval_steps_per_second": 0.17, | |
| "eval_wer": 0.33844198036584505, | |
| "step": 47558 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.0371621621621624e-05, | |
| "loss": 0.0735, | |
| "step": 48160 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 0.4496508538722992, | |
| "eval_runtime": 314.7178, | |
| "eval_samples_per_second": 14.677, | |
| "eval_steps_per_second": 0.184, | |
| "eval_wer": 0.33833604068083906, | |
| "step": 48160 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "learning_rate": 1.935641891891892e-05, | |
| "loss": 0.0721, | |
| "step": 48762 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 0.43915238976478577, | |
| "eval_runtime": 285.1559, | |
| "eval_samples_per_second": 16.198, | |
| "eval_steps_per_second": 0.203, | |
| "eval_wer": 0.33667631894907835, | |
| "step": 48762 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 1.8341216216216216e-05, | |
| "loss": 0.0705, | |
| "step": 49364 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 0.42993664741516113, | |
| "eval_runtime": 312.9699, | |
| "eval_samples_per_second": 14.759, | |
| "eval_steps_per_second": 0.185, | |
| "eval_wer": 0.33678225863408434, | |
| "step": 49364 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "learning_rate": 1.7324324324324326e-05, | |
| "loss": 0.0706, | |
| "step": 49966 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 0.442228227853775, | |
| "eval_runtime": 282.6844, | |
| "eval_samples_per_second": 16.34, | |
| "eval_steps_per_second": 0.205, | |
| "eval_wer": 0.33738258351578504, | |
| "step": 49966 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 1.6307432432432434e-05, | |
| "loss": 0.0707, | |
| "step": 50568 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 0.43407562375068665, | |
| "eval_runtime": 348.7351, | |
| "eval_samples_per_second": 13.245, | |
| "eval_steps_per_second": 0.166, | |
| "eval_wer": 0.33586411469736566, | |
| "step": 50568 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 1.529054054054054e-05, | |
| "loss": 0.0692, | |
| "step": 51170 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 0.44134435057640076, | |
| "eval_runtime": 326.8142, | |
| "eval_samples_per_second": 14.133, | |
| "eval_steps_per_second": 0.177, | |
| "eval_wer": 0.33568754855568894, | |
| "step": 51170 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "learning_rate": 1.4273648648648649e-05, | |
| "loss": 0.069, | |
| "step": 51772 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 0.4566088318824768, | |
| "eval_runtime": 315.2023, | |
| "eval_samples_per_second": 14.654, | |
| "eval_steps_per_second": 0.184, | |
| "eval_wer": 0.337912281940815, | |
| "step": 51772 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "learning_rate": 1.3256756756756758e-05, | |
| "loss": 0.0673, | |
| "step": 52374 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 0.4371909201145172, | |
| "eval_runtime": 288.747, | |
| "eval_samples_per_second": 15.997, | |
| "eval_steps_per_second": 0.201, | |
| "eval_wer": 0.33957200367257573, | |
| "step": 52374 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 1.2239864864864865e-05, | |
| "loss": 0.0678, | |
| "step": 52976 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 0.438821017742157, | |
| "eval_runtime": 399.7437, | |
| "eval_samples_per_second": 11.555, | |
| "eval_steps_per_second": 0.145, | |
| "eval_wer": 0.33819478776749773, | |
| "step": 52976 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "learning_rate": 1.1222972972972975e-05, | |
| "loss": 0.0679, | |
| "step": 53578 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 0.4385330379009247, | |
| "eval_runtime": 425.8088, | |
| "eval_samples_per_second": 10.848, | |
| "eval_steps_per_second": 0.136, | |
| "eval_wer": 0.33628787343738964, | |
| "step": 53578 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 1.0207770270270272e-05, | |
| "loss": 0.0676, | |
| "step": 54180 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 0.44581928849220276, | |
| "eval_runtime": 430.0001, | |
| "eval_samples_per_second": 10.742, | |
| "eval_steps_per_second": 0.135, | |
| "eval_wer": 0.3353344162723356, | |
| "step": 54180 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "learning_rate": 9.19087837837838e-06, | |
| "loss": 0.0661, | |
| "step": 54782 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 0.44878506660461426, | |
| "eval_runtime": 414.3814, | |
| "eval_samples_per_second": 11.147, | |
| "eval_steps_per_second": 0.14, | |
| "eval_wer": 0.3352284765873296, | |
| "step": 54782 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "learning_rate": 8.173986486486487e-06, | |
| "loss": 0.0667, | |
| "step": 55384 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 0.4502880275249481, | |
| "eval_runtime": 640.6777, | |
| "eval_samples_per_second": 7.21, | |
| "eval_steps_per_second": 0.091, | |
| "eval_wer": 0.33649975280740163, | |
| "step": 55384 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "learning_rate": 7.157094594594594e-06, | |
| "loss": 0.0668, | |
| "step": 55986 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 0.4470549523830414, | |
| "eval_runtime": 464.6555, | |
| "eval_samples_per_second": 9.941, | |
| "eval_steps_per_second": 0.125, | |
| "eval_wer": 0.33371000776891024, | |
| "step": 55986 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "learning_rate": 6.140202702702703e-06, | |
| "loss": 0.0663, | |
| "step": 56588 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 0.4470076858997345, | |
| "eval_runtime": 411.3931, | |
| "eval_samples_per_second": 11.228, | |
| "eval_steps_per_second": 0.141, | |
| "eval_wer": 0.3332862490288862, | |
| "step": 56588 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 5.123310810810811e-06, | |
| "loss": 0.0652, | |
| "step": 57190 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 0.4530947804450989, | |
| "eval_runtime": 429.7206, | |
| "eval_samples_per_second": 10.749, | |
| "eval_steps_per_second": 0.135, | |
| "eval_wer": 0.33476940461897026, | |
| "step": 57190 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "learning_rate": 4.108108108108108e-06, | |
| "loss": 0.0648, | |
| "step": 57792 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 0.44802409410476685, | |
| "eval_runtime": 456.6508, | |
| "eval_samples_per_second": 10.115, | |
| "eval_steps_per_second": 0.127, | |
| "eval_wer": 0.33346281517056287, | |
| "step": 57792 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "learning_rate": 3.0912162162162163e-06, | |
| "loss": 0.0638, | |
| "step": 58394 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 0.4479643702507019, | |
| "eval_runtime": 442.7361, | |
| "eval_samples_per_second": 10.433, | |
| "eval_steps_per_second": 0.131, | |
| "eval_wer": 0.33346281517056287, | |
| "step": 58394 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "learning_rate": 2.0743243243243246e-06, | |
| "loss": 0.0637, | |
| "step": 58996 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 0.4514257311820984, | |
| "eval_runtime": 447.5804, | |
| "eval_samples_per_second": 10.32, | |
| "eval_steps_per_second": 0.13, | |
| "eval_wer": 0.3328624902888622, | |
| "step": 58996 | |
| } | |
| ], | |
| "max_steps": 60200, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.2978795625125155e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |