| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "global_step": 9400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.5e-05, | |
| "loss": 15.9584, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 14.658380508422852, | |
| "eval_runtime": 249.5052, | |
| "eval_samples_per_second": 8.208, | |
| "eval_wer": 1.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5e-05, | |
| "loss": 6.3907, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 4.082584857940674, | |
| "eval_runtime": 247.9481, | |
| "eval_samples_per_second": 8.26, | |
| "eval_wer": 1.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.4412, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 3.1572635173797607, | |
| "eval_runtime": 251.7843, | |
| "eval_samples_per_second": 8.134, | |
| "eval_wer": 1.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001, | |
| "loss": 3.005, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 3.0201895236968994, | |
| "eval_runtime": 248.8764, | |
| "eval_samples_per_second": 8.229, | |
| "eval_wer": 1.0, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.000125, | |
| "loss": 2.9507, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 3.0097341537475586, | |
| "eval_runtime": 250.2451, | |
| "eval_samples_per_second": 8.184, | |
| "eval_wer": 1.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.9285, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 3.0145537853240967, | |
| "eval_runtime": 249.391, | |
| "eval_samples_per_second": 8.212, | |
| "eval_wer": 1.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.000175, | |
| "loss": 2.9081, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 2.889194965362549, | |
| "eval_runtime": 252.4706, | |
| "eval_samples_per_second": 8.112, | |
| "eval_wer": 1.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8141, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 3.1128151416778564, | |
| "eval_runtime": 249.3837, | |
| "eval_samples_per_second": 8.212, | |
| "eval_wer": 0.9997997196074504, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00019855985598559857, | |
| "loss": 1.9764, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.4347355365753174, | |
| "eval_runtime": 253.6868, | |
| "eval_samples_per_second": 8.073, | |
| "eval_wer": 0.9202884037652714, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001971197119711971, | |
| "loss": 1.171, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.1342754364013672, | |
| "eval_runtime": 252.7977, | |
| "eval_samples_per_second": 8.101, | |
| "eval_wer": 0.8585352827291541, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001956795679567957, | |
| "loss": 0.9986, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.0098124742507935, | |
| "eval_runtime": 254.0896, | |
| "eval_samples_per_second": 8.06, | |
| "eval_wer": 0.8405768075305428, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00019423942394239426, | |
| "loss": 0.8642, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.9640593528747559, | |
| "eval_runtime": 254.2048, | |
| "eval_samples_per_second": 8.056, | |
| "eval_wer": 0.8503905467654717, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0001927992799279928, | |
| "loss": 0.7951, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.8799329996109009, | |
| "eval_runtime": 255.0842, | |
| "eval_samples_per_second": 8.029, | |
| "eval_wer": 0.787903064290006, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00019135913591359136, | |
| "loss": 0.7317, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.8695712089538574, | |
| "eval_runtime": 253.1871, | |
| "eval_samples_per_second": 8.089, | |
| "eval_wer": 0.7686093864743975, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00018991899189918995, | |
| "loss": 0.6835, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.8140479326248169, | |
| "eval_runtime": 253.7263, | |
| "eval_samples_per_second": 8.072, | |
| "eval_wer": 0.7338941184324721, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00018847884788478848, | |
| "loss": 0.6188, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.8309915065765381, | |
| "eval_runtime": 254.0037, | |
| "eval_samples_per_second": 8.063, | |
| "eval_wer": 0.7473129047332933, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00018703870387038705, | |
| "loss": 0.6116, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.8404783010482788, | |
| "eval_runtime": 255.6119, | |
| "eval_samples_per_second": 8.012, | |
| "eval_wer": 0.7376326857600641, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0001855985598559856, | |
| "loss": 0.5654, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.7973554134368896, | |
| "eval_runtime": 253.93, | |
| "eval_samples_per_second": 8.065, | |
| "eval_wer": 0.7304893517591294, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00018415841584158417, | |
| "loss": 0.5697, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.7916511297225952, | |
| "eval_runtime": 255.1499, | |
| "eval_samples_per_second": 8.027, | |
| "eval_wer": 0.7420388543961546, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.00018271827182718273, | |
| "loss": 0.5621, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.773869514465332, | |
| "eval_runtime": 253.9689, | |
| "eval_samples_per_second": 8.064, | |
| "eval_wer": 0.7266840243006877, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0001812781278127813, | |
| "loss": 0.5646, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.7937338352203369, | |
| "eval_runtime": 254.2977, | |
| "eval_samples_per_second": 8.054, | |
| "eval_wer": 0.70698978569998, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00017983798379837983, | |
| "loss": 0.5266, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.738484263420105, | |
| "eval_runtime": 251.7487, | |
| "eval_samples_per_second": 8.135, | |
| "eval_wer": 0.6933707190066093, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00017839783978397842, | |
| "loss": 0.4719, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_loss": 0.7587714195251465, | |
| "eval_runtime": 253.339, | |
| "eval_samples_per_second": 8.084, | |
| "eval_wer": 0.6889645503705187, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00017695769576957698, | |
| "loss": 0.4479, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 0.7555954456329346, | |
| "eval_runtime": 252.6303, | |
| "eval_samples_per_second": 8.107, | |
| "eval_wer": 0.6807530542759864, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.00017551755175517552, | |
| "loss": 0.4614, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 0.7171066999435425, | |
| "eval_runtime": 252.5327, | |
| "eval_samples_per_second": 8.11, | |
| "eval_wer": 0.6792843313972895, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00017407740774077408, | |
| "loss": 0.4491, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 0.7290804386138916, | |
| "eval_runtime": 251.92, | |
| "eval_samples_per_second": 8.13, | |
| "eval_wer": 0.6693370719006609, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.00017263726372637264, | |
| "loss": 0.4355, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_loss": 0.7258065938949585, | |
| "eval_runtime": 251.8895, | |
| "eval_samples_per_second": 8.131, | |
| "eval_wer": 0.6802857333600374, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.0001711971197119712, | |
| "loss": 0.4217, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 0.7212890982627869, | |
| "eval_runtime": 251.4573, | |
| "eval_samples_per_second": 8.145, | |
| "eval_wer": 0.674878162761199, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00016975697569756977, | |
| "loss": 0.4466, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 0.7866759300231934, | |
| "eval_runtime": 252.4271, | |
| "eval_samples_per_second": 8.113, | |
| "eval_wer": 0.7039855798117365, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00016831683168316833, | |
| "loss": 0.4019, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.724478006362915, | |
| "eval_runtime": 252.8043, | |
| "eval_samples_per_second": 8.101, | |
| "eval_wer": 0.6720074771346551, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.0001668766876687669, | |
| "loss": 0.3812, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_loss": 0.7306143045425415, | |
| "eval_runtime": 252.5346, | |
| "eval_samples_per_second": 8.11, | |
| "eval_wer": 0.671206355564457, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00016543654365436546, | |
| "loss": 0.3662, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "eval_loss": 0.7334802150726318, | |
| "eval_runtime": 251.9822, | |
| "eval_samples_per_second": 8.128, | |
| "eval_wer": 0.6639295013018226, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.000163996399639964, | |
| "loss": 0.3684, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_loss": 0.7250552177429199, | |
| "eval_runtime": 251.8402, | |
| "eval_samples_per_second": 8.132, | |
| "eval_wer": 0.6481073502904066, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.00016255625562556255, | |
| "loss": 0.3809, | |
| "step": 2176 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 0.7295255064964294, | |
| "eval_runtime": 251.8173, | |
| "eval_samples_per_second": 8.133, | |
| "eval_wer": 0.666533146404967, | |
| "step": 2176 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.00016111611161116112, | |
| "loss": 0.3618, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_loss": 0.725806474685669, | |
| "eval_runtime": 251.7567, | |
| "eval_samples_per_second": 8.135, | |
| "eval_wer": 0.6467721476734094, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.00015967596759675968, | |
| "loss": 0.3896, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 0.6914154291152954, | |
| "eval_runtime": 253.233, | |
| "eval_samples_per_second": 8.087, | |
| "eval_wer": 0.6378262901395286, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.00015823582358235824, | |
| "loss": 0.3381, | |
| "step": 2368 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "eval_loss": 0.7252967357635498, | |
| "eval_runtime": 251.9208, | |
| "eval_samples_per_second": 8.13, | |
| "eval_wer": 0.6556512450764403, | |
| "step": 2368 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.0001567956795679568, | |
| "loss": 0.3385, | |
| "step": 2432 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 0.739501953125, | |
| "eval_runtime": 251.6871, | |
| "eval_samples_per_second": 8.137, | |
| "eval_wer": 0.6486414313372054, | |
| "step": 2432 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.00015535553555355537, | |
| "loss": 0.2991, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "eval_loss": 0.718348503112793, | |
| "eval_runtime": 252.6947, | |
| "eval_samples_per_second": 8.105, | |
| "eval_wer": 0.6476400293744575, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.00015391539153915393, | |
| "loss": 0.3219, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 0.6939400434494019, | |
| "eval_runtime": 252.3364, | |
| "eval_samples_per_second": 8.116, | |
| "eval_wer": 0.6454369450564124, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 0.0001524752475247525, | |
| "loss": 0.3212, | |
| "step": 2624 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "eval_loss": 0.723796010017395, | |
| "eval_runtime": 252.2722, | |
| "eval_samples_per_second": 8.118, | |
| "eval_wer": 0.6450363842713132, | |
| "step": 2624 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 0.00015103510351035103, | |
| "loss": 0.3152, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "eval_loss": 0.7430602312088013, | |
| "eval_runtime": 252.488, | |
| "eval_samples_per_second": 8.111, | |
| "eval_wer": 0.6561853261232392, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0001495949594959496, | |
| "loss": 0.3359, | |
| "step": 2752 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_loss": 0.7211728096008301, | |
| "eval_runtime": 252.04, | |
| "eval_samples_per_second": 8.126, | |
| "eval_wer": 0.6389612123639762, | |
| "step": 2752 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 0.00014815481548154818, | |
| "loss": 0.3171, | |
| "step": 2816 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_loss": 0.707861602306366, | |
| "eval_runtime": 253.0372, | |
| "eval_samples_per_second": 8.094, | |
| "eval_wer": 0.6495093130382535, | |
| "step": 2816 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00014671467146714671, | |
| "loss": 0.2806, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 0.6907961368560791, | |
| "eval_runtime": 254.422, | |
| "eval_samples_per_second": 8.05, | |
| "eval_wer": 0.6292142332598972, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.00014527452745274528, | |
| "loss": 0.2765, | |
| "step": 2944 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "eval_loss": 0.7019878029823303, | |
| "eval_runtime": 252.9804, | |
| "eval_samples_per_second": 8.095, | |
| "eval_wer": 0.6294145136524467, | |
| "step": 2944 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00014383438343834384, | |
| "loss": 0.2854, | |
| "step": 3008 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 0.811292290687561, | |
| "eval_runtime": 253.017, | |
| "eval_samples_per_second": 8.094, | |
| "eval_wer": 0.6774818078643434, | |
| "step": 3008 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 0.0001423942394239424, | |
| "loss": 0.2805, | |
| "step": 3072 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_loss": 0.7887662649154663, | |
| "eval_runtime": 251.6217, | |
| "eval_samples_per_second": 8.139, | |
| "eval_wer": 0.6378930502703786, | |
| "step": 3072 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00014095409540954096, | |
| "loss": 0.2861, | |
| "step": 3136 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 0.7010805606842041, | |
| "eval_runtime": 252.2814, | |
| "eval_samples_per_second": 8.118, | |
| "eval_wer": 0.635356165298084, | |
| "step": 3136 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00013951395139513953, | |
| "loss": 0.2903, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_loss": 0.7183523774147034, | |
| "eval_runtime": 253.427, | |
| "eval_samples_per_second": 8.081, | |
| "eval_wer": 0.6266105881567527, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.00013807380738073806, | |
| "loss": 0.2798, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_loss": 0.7161312699317932, | |
| "eval_runtime": 253.1259, | |
| "eval_samples_per_second": 8.091, | |
| "eval_wer": 0.6217370986047133, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.00013663366336633665, | |
| "loss": 0.2528, | |
| "step": 3328 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "eval_loss": 0.7560293674468994, | |
| "eval_runtime": 252.846, | |
| "eval_samples_per_second": 8.1, | |
| "eval_wer": 0.6506442352627011, | |
| "step": 3328 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.00013519351935193521, | |
| "loss": 0.2549, | |
| "step": 3392 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "eval_loss": 0.7602236270904541, | |
| "eval_runtime": 253.2296, | |
| "eval_samples_per_second": 8.088, | |
| "eval_wer": 0.6505774751318513, | |
| "step": 3392 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.00013375337533753375, | |
| "loss": 0.2431, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "eval_loss": 0.6875869035720825, | |
| "eval_runtime": 252.6805, | |
| "eval_samples_per_second": 8.105, | |
| "eval_wer": 0.61859937245477, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 0.0001323132313231323, | |
| "loss": 0.2506, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_loss": 0.7143360376358032, | |
| "eval_runtime": 253.2779, | |
| "eval_samples_per_second": 8.086, | |
| "eval_wer": 0.6345550437278857, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.00013087308730873087, | |
| "loss": 0.2497, | |
| "step": 3584 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.7228794693946838, | |
| "eval_runtime": 252.2511, | |
| "eval_samples_per_second": 8.119, | |
| "eval_wer": 0.6364910875225316, | |
| "step": 3584 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.00012943294329432944, | |
| "loss": 0.2492, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "eval_loss": 0.7050414085388184, | |
| "eval_runtime": 253.5665, | |
| "eval_samples_per_second": 8.077, | |
| "eval_wer": 0.6172641698377729, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 0.000127992799279928, | |
| "loss": 0.2444, | |
| "step": 3712 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "eval_loss": 0.7215788960456848, | |
| "eval_runtime": 252.8539, | |
| "eval_samples_per_second": 8.1, | |
| "eval_wer": 0.6314173175779425, | |
| "step": 3712 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 0.00012655265526552656, | |
| "loss": 0.2438, | |
| "step": 3776 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "eval_loss": 0.7077196836471558, | |
| "eval_runtime": 253.6898, | |
| "eval_samples_per_second": 8.073, | |
| "eval_wer": 0.6182655718005208, | |
| "step": 3776 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 0.0001251125112511251, | |
| "loss": 0.2083, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "eval_loss": 0.7524451613426208, | |
| "eval_runtime": 255.0333, | |
| "eval_samples_per_second": 8.03, | |
| "eval_wer": 0.6258762267174044, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 0.0001236723672367237, | |
| "loss": 0.204, | |
| "step": 3904 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "eval_loss": 0.7626018524169922, | |
| "eval_runtime": 253.5087, | |
| "eval_samples_per_second": 8.079, | |
| "eval_wer": 0.6330863208491888, | |
| "step": 3904 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.00012223222322232225, | |
| "loss": 0.2353, | |
| "step": 3968 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "eval_loss": 0.7177530527114868, | |
| "eval_runtime": 253.4757, | |
| "eval_samples_per_second": 8.08, | |
| "eval_wer": 0.6127244809399827, | |
| "step": 3968 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.0001207920792079208, | |
| "loss": 0.2208, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "eval_loss": 0.7555935382843018, | |
| "eval_runtime": 253.7282, | |
| "eval_samples_per_second": 8.072, | |
| "eval_wer": 0.6294812737832967, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.00011935193519351935, | |
| "loss": 0.2266, | |
| "step": 4096 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "eval_loss": 0.7341886162757874, | |
| "eval_runtime": 253.8255, | |
| "eval_samples_per_second": 8.069, | |
| "eval_wer": 0.6294812737832967, | |
| "step": 4096 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 0.00011791179117911792, | |
| "loss": 0.2188, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "eval_loss": 0.7594360709190369, | |
| "eval_runtime": 253.012, | |
| "eval_samples_per_second": 8.094, | |
| "eval_wer": 0.6449028640096135, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 0.00011647164716471647, | |
| "loss": 0.231, | |
| "step": 4224 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_loss": 0.6901054382324219, | |
| "eval_runtime": 253.458, | |
| "eval_samples_per_second": 8.08, | |
| "eval_wer": 0.6077842312570932, | |
| "step": 4224 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 0.00011503150315031504, | |
| "loss": 0.2063, | |
| "step": 4288 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "eval_loss": 0.7627975344657898, | |
| "eval_runtime": 253.6008, | |
| "eval_samples_per_second": 8.076, | |
| "eval_wer": 0.6116563188463849, | |
| "step": 4288 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 0.00011359135913591358, | |
| "loss": 0.1931, | |
| "step": 4352 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "eval_loss": 0.7425730228424072, | |
| "eval_runtime": 254.3179, | |
| "eval_samples_per_second": 8.053, | |
| "eval_wer": 0.6149943253888778, | |
| "step": 4352 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 0.00011215121512151216, | |
| "loss": 0.2189, | |
| "step": 4416 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "eval_loss": 0.7322723269462585, | |
| "eval_runtime": 254.9695, | |
| "eval_samples_per_second": 8.032, | |
| "eval_wer": 0.6066493090326457, | |
| "step": 4416 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 0.00011071107110711072, | |
| "loss": 0.1931, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_loss": 0.7253696918487549, | |
| "eval_runtime": 253.0608, | |
| "eval_samples_per_second": 8.093, | |
| "eval_wer": 0.613525602510181, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 0.00010927092709270927, | |
| "loss": 0.2017, | |
| "step": 4544 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 0.6984794735908508, | |
| "eval_runtime": 253.842, | |
| "eval_samples_per_second": 8.068, | |
| "eval_wer": 0.6072501502102944, | |
| "step": 4544 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 0.00010783078307830783, | |
| "loss": 0.2169, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 0.698683500289917, | |
| "eval_runtime": 253.2368, | |
| "eval_samples_per_second": 8.087, | |
| "eval_wer": 0.6078509913879431, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 0.00010639063906390641, | |
| "loss": 0.1956, | |
| "step": 4672 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_loss": 0.7127052545547485, | |
| "eval_runtime": 254.4368, | |
| "eval_samples_per_second": 8.049, | |
| "eval_wer": 0.6073836704719942, | |
| "step": 4672 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 0.00010495049504950496, | |
| "loss": 0.1972, | |
| "step": 4736 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "eval_loss": 0.7555835247039795, | |
| "eval_runtime": 253.4953, | |
| "eval_samples_per_second": 8.079, | |
| "eval_wer": 0.6094532345283397, | |
| "step": 4736 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 0.00010351035103510351, | |
| "loss": 0.1827, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "eval_loss": 0.7492347359657288, | |
| "eval_runtime": 255.7545, | |
| "eval_samples_per_second": 8.008, | |
| "eval_wer": 0.6165298083984244, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 0.00010207020702070207, | |
| "loss": 0.1798, | |
| "step": 4864 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "eval_loss": 0.7403519749641418, | |
| "eval_runtime": 254.7315, | |
| "eval_samples_per_second": 8.04, | |
| "eval_wer": 0.6058481874624474, | |
| "step": 4864 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 0.00010063006300630065, | |
| "loss": 0.1839, | |
| "step": 4928 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "eval_loss": 0.7588409185409546, | |
| "eval_runtime": 255.5749, | |
| "eval_samples_per_second": 8.013, | |
| "eval_wer": 0.60931971426664, | |
| "step": 4928 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 9.91899189918992e-05, | |
| "loss": 0.1823, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "eval_loss": 0.7923687696456909, | |
| "eval_runtime": 254.6347, | |
| "eval_samples_per_second": 8.043, | |
| "eval_wer": 0.621403297950464, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 9.774977497749776e-05, | |
| "loss": 0.1749, | |
| "step": 5056 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "eval_loss": 0.7493650913238525, | |
| "eval_runtime": 252.6472, | |
| "eval_samples_per_second": 8.106, | |
| "eval_wer": 0.6101875959676881, | |
| "step": 5056 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 9.630963096309631e-05, | |
| "loss": 0.1876, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "eval_loss": 0.7571142911911011, | |
| "eval_runtime": 253.4609, | |
| "eval_samples_per_second": 8.08, | |
| "eval_wer": 0.6097870351825889, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 9.486948694869487e-05, | |
| "loss": 0.2027, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 0.7235008478164673, | |
| "eval_runtime": 252.9146, | |
| "eval_samples_per_second": 8.098, | |
| "eval_wer": 0.6036451031444021, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 9.342934293429343e-05, | |
| "loss": 0.1699, | |
| "step": 5248 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "eval_loss": 0.7639468908309937, | |
| "eval_runtime": 253.3789, | |
| "eval_samples_per_second": 8.083, | |
| "eval_wer": 0.6093864743974898, | |
| "step": 5248 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 9.1989198919892e-05, | |
| "loss": 0.1556, | |
| "step": 5312 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "eval_loss": 0.7758333683013916, | |
| "eval_runtime": 255.9522, | |
| "eval_samples_per_second": 8.001, | |
| "eval_wer": 0.6128580012016823, | |
| "step": 5312 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 9.054905490549054e-05, | |
| "loss": 0.1679, | |
| "step": 5376 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "eval_loss": 0.7407320737838745, | |
| "eval_runtime": 253.1505, | |
| "eval_samples_per_second": 8.09, | |
| "eval_wer": 0.5980372521530142, | |
| "step": 5376 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 8.910891089108912e-05, | |
| "loss": 0.1681, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "eval_loss": 0.7515969276428223, | |
| "eval_runtime": 254.0821, | |
| "eval_samples_per_second": 8.06, | |
| "eval_wer": 0.6076507109953936, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 8.766876687668767e-05, | |
| "loss": 0.1814, | |
| "step": 5504 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "eval_loss": 0.7393285036087036, | |
| "eval_runtime": 255.9386, | |
| "eval_samples_per_second": 8.002, | |
| "eval_wer": 0.6063822685092463, | |
| "step": 5504 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 8.622862286228623e-05, | |
| "loss": 0.162, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "eval_loss": 0.7688995003700256, | |
| "eval_runtime": 255.0601, | |
| "eval_samples_per_second": 8.029, | |
| "eval_wer": 0.6063155083783964, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 8.47884788478848e-05, | |
| "loss": 0.1835, | |
| "step": 5632 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "eval_loss": 0.7229721546173096, | |
| "eval_runtime": 256.1311, | |
| "eval_samples_per_second": 7.996, | |
| "eval_wer": 0.6020428600040056, | |
| "step": 5632 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 8.334833483348336e-05, | |
| "loss": 0.1491, | |
| "step": 5696 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 0.7780319452285767, | |
| "eval_runtime": 253.9764, | |
| "eval_samples_per_second": 8.064, | |
| "eval_wer": 0.6079845116496428, | |
| "step": 5696 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 8.19081908190819e-05, | |
| "loss": 0.163, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "eval_loss": 0.7481300830841064, | |
| "eval_runtime": 255.5174, | |
| "eval_samples_per_second": 8.015, | |
| "eval_wer": 0.6035115828827025, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 8.046804680468047e-05, | |
| "loss": 0.1564, | |
| "step": 5824 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "eval_loss": 0.7477182149887085, | |
| "eval_runtime": 253.9361, | |
| "eval_samples_per_second": 8.065, | |
| "eval_wer": 0.6073169103411443, | |
| "step": 5824 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 7.902790279027903e-05, | |
| "loss": 0.1651, | |
| "step": 5888 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "eval_loss": 0.7700252532958984, | |
| "eval_runtime": 255.811, | |
| "eval_samples_per_second": 8.006, | |
| "eval_wer": 0.6119901195006342, | |
| "step": 5888 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 7.75877587758776e-05, | |
| "loss": 0.1406, | |
| "step": 5952 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "eval_loss": 0.7303926348686218, | |
| "eval_runtime": 255.3564, | |
| "eval_samples_per_second": 8.02, | |
| "eval_wer": 0.6010414580412577, | |
| "step": 5952 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 7.614761476147616e-05, | |
| "loss": 0.1454, | |
| "step": 6016 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "eval_loss": 0.7804365158081055, | |
| "eval_runtime": 258.3951, | |
| "eval_samples_per_second": 7.926, | |
| "eval_wer": 0.6108551972761866, | |
| "step": 6016 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 7.470747074707472e-05, | |
| "loss": 0.1405, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "eval_loss": 0.7660069465637207, | |
| "eval_runtime": 258.3136, | |
| "eval_samples_per_second": 7.928, | |
| "eval_wer": 0.5965017691434675, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 7.326732673267327e-05, | |
| "loss": 0.142, | |
| "step": 6144 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "eval_loss": 0.7802821397781372, | |
| "eval_runtime": 255.9638, | |
| "eval_samples_per_second": 8.001, | |
| "eval_wer": 0.6066493090326457, | |
| "step": 6144 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 7.182718271827183e-05, | |
| "loss": 0.1423, | |
| "step": 6208 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "eval_loss": 0.7940844297409058, | |
| "eval_runtime": 257.753, | |
| "eval_samples_per_second": 7.946, | |
| "eval_wer": 0.6061152279858468, | |
| "step": 6208 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 7.038703870387039e-05, | |
| "loss": 0.1494, | |
| "step": 6272 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "eval_loss": 0.7598519325256348, | |
| "eval_runtime": 257.9759, | |
| "eval_samples_per_second": 7.939, | |
| "eval_wer": 0.6009079377795581, | |
| "step": 6272 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 6.894689468946895e-05, | |
| "loss": 0.1459, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "eval_loss": 0.7658703327178955, | |
| "eval_runtime": 257.4947, | |
| "eval_samples_per_second": 7.954, | |
| "eval_wer": 0.6087188730889913, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 6.75067506750675e-05, | |
| "loss": 0.1316, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "eval_loss": 0.7935535311698914, | |
| "eval_runtime": 256.5247, | |
| "eval_samples_per_second": 7.984, | |
| "eval_wer": 0.6047132652379998, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 6.606660666066608e-05, | |
| "loss": 0.1428, | |
| "step": 6464 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "eval_loss": 0.782112181186676, | |
| "eval_runtime": 259.1672, | |
| "eval_samples_per_second": 7.902, | |
| "eval_wer": 0.5998397756859604, | |
| "step": 6464 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 6.462646264626463e-05, | |
| "loss": 0.1391, | |
| "step": 6528 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "eval_loss": 0.7535277605056763, | |
| "eval_runtime": 257.3279, | |
| "eval_samples_per_second": 7.959, | |
| "eval_wer": 0.5976366913679151, | |
| "step": 6528 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 6.318631863186318e-05, | |
| "loss": 0.138, | |
| "step": 6592 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "eval_loss": 0.7846142649650574, | |
| "eval_runtime": 257.0571, | |
| "eval_samples_per_second": 7.967, | |
| "eval_wer": 0.5956338874424194, | |
| "step": 6592 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 6.174617461746175e-05, | |
| "loss": 0.1299, | |
| "step": 6656 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "eval_loss": 0.7645628452301025, | |
| "eval_runtime": 259.0072, | |
| "eval_samples_per_second": 7.907, | |
| "eval_wer": 0.5987716135923626, | |
| "step": 6656 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 6.03060306030603e-05, | |
| "loss": 0.1287, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "eval_loss": 0.8099244832992554, | |
| "eval_runtime": 258.7408, | |
| "eval_samples_per_second": 7.915, | |
| "eval_wer": 0.612056879631484, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 5.886588658865887e-05, | |
| "loss": 0.1288, | |
| "step": 6784 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "eval_loss": 0.8042709231376648, | |
| "eval_runtime": 258.8574, | |
| "eval_samples_per_second": 7.912, | |
| "eval_wer": 0.6015755390880566, | |
| "step": 6784 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 5.742574257425742e-05, | |
| "loss": 0.131, | |
| "step": 6848 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "eval_loss": 0.7604876756668091, | |
| "eval_runtime": 256.5152, | |
| "eval_samples_per_second": 7.984, | |
| "eval_wer": 0.5951665665264704, | |
| "step": 6848 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 5.598559855985599e-05, | |
| "loss": 0.1353, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "eval_loss": 0.784662127494812, | |
| "eval_runtime": 256.9735, | |
| "eval_samples_per_second": 7.97, | |
| "eval_wer": 0.59997329594766, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.133, | |
| "step": 6976 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "eval_loss": 0.8255736827850342, | |
| "eval_runtime": 256.2102, | |
| "eval_samples_per_second": 7.993, | |
| "eval_wer": 0.6010414580412577, | |
| "step": 6976 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 5.310531053105311e-05, | |
| "loss": 0.1351, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_loss": 0.7962599992752075, | |
| "eval_runtime": 256.4813, | |
| "eval_samples_per_second": 7.985, | |
| "eval_wer": 0.5983710528072635, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 5.1665166516651664e-05, | |
| "loss": 0.1156, | |
| "step": 7104 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "eval_loss": 0.8220678567886353, | |
| "eval_runtime": 255.8959, | |
| "eval_samples_per_second": 8.003, | |
| "eval_wer": 0.6015087789572068, | |
| "step": 7104 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 5.022502250225023e-05, | |
| "loss": 0.1171, | |
| "step": 7168 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "eval_loss": 0.7746037840843201, | |
| "eval_runtime": 255.6563, | |
| "eval_samples_per_second": 8.011, | |
| "eval_wer": 0.592562921423326, | |
| "step": 7168 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 4.878487848784879e-05, | |
| "loss": 0.1213, | |
| "step": 7232 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "eval_loss": 0.8010141253471375, | |
| "eval_runtime": 256.8217, | |
| "eval_samples_per_second": 7.974, | |
| "eval_wer": 0.6013084985646572, | |
| "step": 7232 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 4.734473447344735e-05, | |
| "loss": 0.1175, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "eval_loss": 0.8121392726898193, | |
| "eval_runtime": 255.5954, | |
| "eval_samples_per_second": 8.013, | |
| "eval_wer": 0.6077174711262434, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 4.59045904590459e-05, | |
| "loss": 0.12, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "eval_loss": 0.7914840579032898, | |
| "eval_runtime": 256.4734, | |
| "eval_samples_per_second": 7.985, | |
| "eval_wer": 0.5952333266573202, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 4.4464446444644464e-05, | |
| "loss": 0.1147, | |
| "step": 7424 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "eval_loss": 0.7968710660934448, | |
| "eval_runtime": 255.805, | |
| "eval_samples_per_second": 8.006, | |
| "eval_wer": 0.5996394952934108, | |
| "step": 7424 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 4.3024302430243026e-05, | |
| "loss": 0.1217, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "eval_loss": 0.8240338563919067, | |
| "eval_runtime": 254.7962, | |
| "eval_samples_per_second": 8.038, | |
| "eval_wer": 0.6034448227518526, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 4.158415841584158e-05, | |
| "loss": 0.1088, | |
| "step": 7552 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "eval_loss": 0.8148845434188843, | |
| "eval_runtime": 255.3742, | |
| "eval_samples_per_second": 8.02, | |
| "eval_wer": 0.6006408972561587, | |
| "step": 7552 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 4.0144014401440144e-05, | |
| "loss": 0.1086, | |
| "step": 7616 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "eval_loss": 0.8434123992919922, | |
| "eval_runtime": 256.199, | |
| "eval_samples_per_second": 7.994, | |
| "eval_wer": 0.6020428600040056, | |
| "step": 7616 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 3.870387038703871e-05, | |
| "loss": 0.122, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "eval_loss": 0.8277792930603027, | |
| "eval_runtime": 255.246, | |
| "eval_samples_per_second": 8.024, | |
| "eval_wer": 0.5944989652179719, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 3.726372637263726e-05, | |
| "loss": 0.109, | |
| "step": 7744 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "eval_loss": 0.8119443655014038, | |
| "eval_runtime": 255.9109, | |
| "eval_samples_per_second": 8.003, | |
| "eval_wer": 0.5994392149008612, | |
| "step": 7744 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 3.5823582358235825e-05, | |
| "loss": 0.1159, | |
| "step": 7808 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "eval_loss": 0.8458046913146973, | |
| "eval_runtime": 255.3949, | |
| "eval_samples_per_second": 8.019, | |
| "eval_wer": 0.6047800253688497, | |
| "step": 7808 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 3.438343834383439e-05, | |
| "loss": 0.0992, | |
| "step": 7872 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "eval_loss": 0.8495743870735168, | |
| "eval_runtime": 255.6285, | |
| "eval_samples_per_second": 8.012, | |
| "eval_wer": 0.6048467854996996, | |
| "step": 7872 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 3.294329432943294e-05, | |
| "loss": 0.1078, | |
| "step": 7936 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "eval_loss": 0.8393277525901794, | |
| "eval_runtime": 255.6117, | |
| "eval_samples_per_second": 8.012, | |
| "eval_wer": 0.5990386541157621, | |
| "step": 7936 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.1503150315031506e-05, | |
| "loss": 0.1096, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_loss": 0.8454439640045166, | |
| "eval_runtime": 255.5979, | |
| "eval_samples_per_second": 8.013, | |
| "eval_wer": 0.5995059750317111, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 3.0063006300630065e-05, | |
| "loss": 0.0986, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "eval_loss": 0.8286423683166504, | |
| "eval_runtime": 257.011, | |
| "eval_samples_per_second": 7.969, | |
| "eval_wer": 0.6011082181721076, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 2.8622862286228624e-05, | |
| "loss": 0.1154, | |
| "step": 8128 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "eval_loss": 0.8368263244628906, | |
| "eval_runtime": 258.2275, | |
| "eval_samples_per_second": 7.931, | |
| "eval_wer": 0.5988383737232125, | |
| "step": 8128 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 2.7182718271827183e-05, | |
| "loss": 0.0927, | |
| "step": 8192 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "eval_loss": 0.861258864402771, | |
| "eval_runtime": 257.1554, | |
| "eval_samples_per_second": 7.964, | |
| "eval_wer": 0.6089191534815408, | |
| "step": 8192 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 2.5742574257425746e-05, | |
| "loss": 0.1056, | |
| "step": 8256 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "eval_loss": 0.8197841644287109, | |
| "eval_runtime": 256.4042, | |
| "eval_samples_per_second": 7.987, | |
| "eval_wer": 0.592562921423326, | |
| "step": 8256 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 2.4302430243024305e-05, | |
| "loss": 0.1112, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "eval_loss": 0.8646882772445679, | |
| "eval_runtime": 257.1754, | |
| "eval_samples_per_second": 7.963, | |
| "eval_wer": 0.5978369717604647, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 2.2862286228622864e-05, | |
| "loss": 0.0962, | |
| "step": 8384 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "eval_loss": 0.8387396335601807, | |
| "eval_runtime": 255.7406, | |
| "eval_samples_per_second": 8.008, | |
| "eval_wer": 0.5963014887509179, | |
| "step": 8384 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 2.1422142214221423e-05, | |
| "loss": 0.0973, | |
| "step": 8448 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "eval_loss": 0.8584703207015991, | |
| "eval_runtime": 256.391, | |
| "eval_samples_per_second": 7.988, | |
| "eval_wer": 0.5963682488817678, | |
| "step": 8448 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 1.9981998199819982e-05, | |
| "loss": 0.1013, | |
| "step": 8512 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "eval_loss": 0.8741297721862793, | |
| "eval_runtime": 257.1245, | |
| "eval_samples_per_second": 7.965, | |
| "eval_wer": 0.6001735763402096, | |
| "step": 8512 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 1.854185418541854e-05, | |
| "loss": 0.1037, | |
| "step": 8576 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "eval_loss": 0.8630872368812561, | |
| "eval_runtime": 257.6611, | |
| "eval_samples_per_second": 7.948, | |
| "eval_wer": 0.5943654449562721, | |
| "step": 8576 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 1.71017101710171e-05, | |
| "loss": 0.0947, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "eval_loss": 0.86741703748703, | |
| "eval_runtime": 257.8968, | |
| "eval_samples_per_second": 7.941, | |
| "eval_wer": 0.596768809666867, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "learning_rate": 1.5661566156615663e-05, | |
| "loss": 0.0884, | |
| "step": 8704 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "eval_loss": 0.8764230608940125, | |
| "eval_runtime": 256.705, | |
| "eval_samples_per_second": 7.978, | |
| "eval_wer": 0.5943654449562721, | |
| "step": 8704 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 1.4221422142214222e-05, | |
| "loss": 0.0997, | |
| "step": 8768 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "eval_loss": 0.8616538047790527, | |
| "eval_runtime": 256.2987, | |
| "eval_samples_per_second": 7.991, | |
| "eval_wer": 0.593030242339275, | |
| "step": 8768 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 1.2781278127812781e-05, | |
| "loss": 0.1066, | |
| "step": 8832 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "eval_loss": 0.8461120128631592, | |
| "eval_runtime": 255.9062, | |
| "eval_samples_per_second": 8.003, | |
| "eval_wer": 0.5889578743574337, | |
| "step": 8832 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 1.1341134113411342e-05, | |
| "loss": 0.0952, | |
| "step": 8896 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "eval_loss": 0.8545425534248352, | |
| "eval_runtime": 254.9463, | |
| "eval_samples_per_second": 8.033, | |
| "eval_wer": 0.5970358501902664, | |
| "step": 8896 | |
| }, | |
| { | |
| "epoch": 19.06, | |
| "learning_rate": 9.900990099009901e-06, | |
| "loss": 0.1094, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 19.06, | |
| "eval_loss": 0.8487824201583862, | |
| "eval_runtime": 255.9015, | |
| "eval_samples_per_second": 8.003, | |
| "eval_wer": 0.5928967220775753, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 8.46084608460846e-06, | |
| "loss": 0.1023, | |
| "step": 9024 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "eval_loss": 0.8481884002685547, | |
| "eval_runtime": 255.378, | |
| "eval_samples_per_second": 8.019, | |
| "eval_wer": 0.5924961612924762, | |
| "step": 9024 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 7.02070207020702e-06, | |
| "loss": 0.0896, | |
| "step": 9088 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "eval_loss": 0.8508026003837585, | |
| "eval_runtime": 258.1213, | |
| "eval_samples_per_second": 7.934, | |
| "eval_wer": 0.5942319246945724, | |
| "step": 9088 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "learning_rate": 5.58055805580558e-06, | |
| "loss": 0.1055, | |
| "step": 9152 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "eval_loss": 0.8545140027999878, | |
| "eval_runtime": 255.3836, | |
| "eval_samples_per_second": 8.019, | |
| "eval_wer": 0.5957674077041191, | |
| "step": 9152 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "learning_rate": 4.14041404140414e-06, | |
| "loss": 0.1102, | |
| "step": 9216 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "eval_loss": 0.8519406318664551, | |
| "eval_runtime": 255.7976, | |
| "eval_samples_per_second": 8.006, | |
| "eval_wer": 0.5952333266573202, | |
| "step": 9216 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 2.7002700270027004e-06, | |
| "loss": 0.1021, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "eval_loss": 0.8542845249176025, | |
| "eval_runtime": 255.9288, | |
| "eval_samples_per_second": 8.002, | |
| "eval_wer": 0.5940984044328727, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "learning_rate": 1.2601260126012601e-06, | |
| "loss": 0.0934, | |
| "step": 9344 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "eval_loss": 0.8573585748672485, | |
| "eval_runtime": 256.1564, | |
| "eval_samples_per_second": 7.995, | |
| "eval_wer": 0.5932305227318245, | |
| "step": 9344 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 9400, | |
| "total_flos": 5.3055511592602894e+19, | |
| "train_runtime": 80232.1889, | |
| "train_samples_per_second": 0.117 | |
| } | |
| ], | |
| "max_steps": 9400, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.3055511592602894e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |