| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.793780687397708, | |
| "global_step": 19300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001, | |
| "loss": 12.1859, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 3.897115468978882, | |
| "eval_runtime": 18.0759, | |
| "eval_samples_per_second": 5.532, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.997271487039564e-05, | |
| "loss": 3.3843, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 3.5120508670806885, | |
| "eval_runtime": 18.1777, | |
| "eval_samples_per_second": 5.501, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.994542974079127e-05, | |
| "loss": 3.3224, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 3.539235830307007, | |
| "eval_runtime": 18.2559, | |
| "eval_samples_per_second": 5.478, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.99181446111869e-05, | |
| "loss": 3.34, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 3.492466926574707, | |
| "eval_runtime": 18.4309, | |
| "eval_samples_per_second": 5.426, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.989085948158254e-05, | |
| "loss": 3.2825, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 3.376338481903076, | |
| "eval_runtime": 18.3713, | |
| "eval_samples_per_second": 5.443, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.986357435197817e-05, | |
| "loss": 3.2728, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 3.3126320838928223, | |
| "eval_runtime": 18.6895, | |
| "eval_samples_per_second": 5.351, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.983628922237382e-05, | |
| "loss": 3.2327, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 3.1550354957580566, | |
| "eval_runtime": 18.5514, | |
| "eval_samples_per_second": 5.39, | |
| "eval_wer": 1.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.980900409276944e-05, | |
| "loss": 2.7258, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.9835596084594727, | |
| "eval_runtime": 18.3986, | |
| "eval_samples_per_second": 5.435, | |
| "eval_wer": 0.9820554649265906, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.978171896316508e-05, | |
| "loss": 1.5581, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.2180073261260986, | |
| "eval_runtime": 18.413, | |
| "eval_samples_per_second": 5.431, | |
| "eval_wer": 1.0163132137030995, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.975443383356072e-05, | |
| "loss": 1.1164, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.966360867023468, | |
| "eval_runtime": 18.5352, | |
| "eval_samples_per_second": 5.395, | |
| "eval_wer": 0.8711256117455138, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.972714870395635e-05, | |
| "loss": 0.9322, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.8568554520606995, | |
| "eval_runtime": 18.1123, | |
| "eval_samples_per_second": 5.521, | |
| "eval_wer": 0.831973898858075, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.969986357435198e-05, | |
| "loss": 0.8174, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.8210877180099487, | |
| "eval_runtime": 18.2233, | |
| "eval_samples_per_second": 5.487, | |
| "eval_wer": 0.8058727569331158, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.967257844474762e-05, | |
| "loss": 0.7625, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.8484710454940796, | |
| "eval_runtime": 18.3237, | |
| "eval_samples_per_second": 5.457, | |
| "eval_wer": 0.8058727569331158, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 9.964529331514325e-05, | |
| "loss": 0.7211, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.7573192119598389, | |
| "eval_runtime": 18.7142, | |
| "eval_samples_per_second": 5.344, | |
| "eval_wer": 0.7732463295269169, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 9.96180081855389e-05, | |
| "loss": 0.6892, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.7421054244041443, | |
| "eval_runtime": 18.8747, | |
| "eval_samples_per_second": 5.298, | |
| "eval_wer": 0.768352365415987, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 9.959072305593452e-05, | |
| "loss": 0.6573, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.6711151599884033, | |
| "eval_runtime": 18.658, | |
| "eval_samples_per_second": 5.36, | |
| "eval_wer": 0.7422512234910277, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.956343792633015e-05, | |
| "loss": 0.6402, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.6495039463043213, | |
| "eval_runtime": 18.212, | |
| "eval_samples_per_second": 5.491, | |
| "eval_wer": 0.7161500815660685, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.95361527967258e-05, | |
| "loss": 0.6129, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.6313944458961487, | |
| "eval_runtime": 18.1993, | |
| "eval_samples_per_second": 5.495, | |
| "eval_wer": 0.6965742251223491, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.950886766712142e-05, | |
| "loss": 0.6074, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.6353416442871094, | |
| "eval_runtime": 18.4085, | |
| "eval_samples_per_second": 5.432, | |
| "eval_wer": 0.7030995106035889, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.948158253751706e-05, | |
| "loss": 0.5688, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.6229403018951416, | |
| "eval_runtime": 18.9507, | |
| "eval_samples_per_second": 5.277, | |
| "eval_wer": 0.6900489396411092, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 9.945429740791268e-05, | |
| "loss": 0.5522, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.6387014985084534, | |
| "eval_runtime": 18.1593, | |
| "eval_samples_per_second": 5.507, | |
| "eval_wer": 0.6916802610114192, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.942701227830833e-05, | |
| "loss": 0.5414, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.5740896463394165, | |
| "eval_runtime": 18.1093, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.6606851549755302, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.939972714870396e-05, | |
| "loss": 0.5227, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.5425416231155396, | |
| "eval_runtime": 18.0421, | |
| "eval_samples_per_second": 5.543, | |
| "eval_wer": 0.6427406199021207, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.93724420190996e-05, | |
| "loss": 0.5233, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.5257930755615234, | |
| "eval_runtime": 17.9989, | |
| "eval_samples_per_second": 5.556, | |
| "eval_wer": 0.6655791190864601, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.934515688949523e-05, | |
| "loss": 0.5019, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.5606628656387329, | |
| "eval_runtime": 18.0204, | |
| "eval_samples_per_second": 5.549, | |
| "eval_wer": 0.6427406199021207, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.931787175989086e-05, | |
| "loss": 0.472, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.5908198952674866, | |
| "eval_runtime": 18.0255, | |
| "eval_samples_per_second": 5.548, | |
| "eval_wer": 0.6378466557911908, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 9.92905866302865e-05, | |
| "loss": 0.4642, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.5597887635231018, | |
| "eval_runtime": 18.0187, | |
| "eval_samples_per_second": 5.55, | |
| "eval_wer": 0.6443719412724307, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 9.926330150068214e-05, | |
| "loss": 0.4331, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.5704432725906372, | |
| "eval_runtime": 18.1172, | |
| "eval_samples_per_second": 5.52, | |
| "eval_wer": 0.6264274061990212, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 9.923601637107776e-05, | |
| "loss": 0.4562, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.544298529624939, | |
| "eval_runtime": 17.9762, | |
| "eval_samples_per_second": 5.563, | |
| "eval_wer": 0.6199021207177814, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.920873124147341e-05, | |
| "loss": 0.4491, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.5418174266815186, | |
| "eval_runtime": 17.9099, | |
| "eval_samples_per_second": 5.584, | |
| "eval_wer": 0.6296900489396411, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 9.918144611186904e-05, | |
| "loss": 0.4278, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.5669529438018799, | |
| "eval_runtime": 18.1431, | |
| "eval_samples_per_second": 5.512, | |
| "eval_wer": 0.6280587275693311, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 9.915416098226466e-05, | |
| "loss": 0.4267, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 0.5152673721313477, | |
| "eval_runtime": 17.9853, | |
| "eval_samples_per_second": 5.56, | |
| "eval_wer": 0.6182707993474714, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.912687585266031e-05, | |
| "loss": 0.4056, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.5021263360977173, | |
| "eval_runtime": 17.9672, | |
| "eval_samples_per_second": 5.566, | |
| "eval_wer": 0.598694942903752, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 9.909959072305594e-05, | |
| "loss": 0.4121, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 0.5312536358833313, | |
| "eval_runtime": 17.8604, | |
| "eval_samples_per_second": 5.599, | |
| "eval_wer": 0.600326264274062, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.907230559345157e-05, | |
| "loss": 0.4357, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.5214389562606812, | |
| "eval_runtime": 18.0662, | |
| "eval_samples_per_second": 5.535, | |
| "eval_wer": 0.5954323001631321, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.904502046384721e-05, | |
| "loss": 0.4174, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.47309502959251404, | |
| "eval_runtime": 18.0379, | |
| "eval_samples_per_second": 5.544, | |
| "eval_wer": 0.5628058727569332, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.901773533424284e-05, | |
| "loss": 0.3911, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 0.46288207173347473, | |
| "eval_runtime": 17.9748, | |
| "eval_samples_per_second": 5.563, | |
| "eval_wer": 0.566068515497553, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 9.899045020463847e-05, | |
| "loss": 0.3817, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 0.5229946374893188, | |
| "eval_runtime": 18.101, | |
| "eval_samples_per_second": 5.525, | |
| "eval_wer": 0.5840130505709625, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.896316507503411e-05, | |
| "loss": 0.3504, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.459197074174881, | |
| "eval_runtime": 17.9054, | |
| "eval_samples_per_second": 5.585, | |
| "eval_wer": 0.5448613376835236, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 9.893587994542974e-05, | |
| "loss": 0.3741, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 0.4944967031478882, | |
| "eval_runtime": 18.5172, | |
| "eval_samples_per_second": 5.4, | |
| "eval_wer": 0.5562805872756933, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.890859481582539e-05, | |
| "loss": 0.3451, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.49022501707077026, | |
| "eval_runtime": 18.2792, | |
| "eval_samples_per_second": 5.471, | |
| "eval_wer": 0.5562805872756933, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 9.888130968622101e-05, | |
| "loss": 0.356, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 0.4645284414291382, | |
| "eval_runtime": 18.1691, | |
| "eval_samples_per_second": 5.504, | |
| "eval_wer": 0.5513866231647635, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.885402455661665e-05, | |
| "loss": 0.3679, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 0.4742129147052765, | |
| "eval_runtime": 18.0285, | |
| "eval_samples_per_second": 5.547, | |
| "eval_wer": 0.5791190864600326, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.882673942701229e-05, | |
| "loss": 0.343, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.45692238211631775, | |
| "eval_runtime": 18.0518, | |
| "eval_samples_per_second": 5.54, | |
| "eval_wer": 0.566068515497553, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 9.879945429740792e-05, | |
| "loss": 0.39, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_loss": 0.4621705114841461, | |
| "eval_runtime": 18.0928, | |
| "eval_samples_per_second": 5.527, | |
| "eval_wer": 0.5562805872756933, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 9.877216916780355e-05, | |
| "loss": 0.3434, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 0.5067647695541382, | |
| "eval_runtime": 18.1879, | |
| "eval_samples_per_second": 5.498, | |
| "eval_wer": 0.5693311582381729, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 9.874488403819919e-05, | |
| "loss": 0.3402, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_loss": 0.4918912947177887, | |
| "eval_runtime": 18.1428, | |
| "eval_samples_per_second": 5.512, | |
| "eval_wer": 0.5693311582381729, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 9.871759890859482e-05, | |
| "loss": 0.3493, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 0.4792294204235077, | |
| "eval_runtime": 18.131, | |
| "eval_samples_per_second": 5.515, | |
| "eval_wer": 0.5709624796084829, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.869031377899045e-05, | |
| "loss": 0.3367, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 0.5306392908096313, | |
| "eval_runtime": 18.1096, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.5774877650897227, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 9.866302864938609e-05, | |
| "loss": 0.3163, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.49867820739746094, | |
| "eval_runtime": 18.1564, | |
| "eval_samples_per_second": 5.508, | |
| "eval_wer": 0.5709624796084829, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.863574351978172e-05, | |
| "loss": 0.3025, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "eval_loss": 0.49608245491981506, | |
| "eval_runtime": 18.3468, | |
| "eval_samples_per_second": 5.451, | |
| "eval_wer": 0.5383360522022839, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 9.860845839017737e-05, | |
| "loss": 0.3017, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_loss": 0.519436776638031, | |
| "eval_runtime": 18.1576, | |
| "eval_samples_per_second": 5.507, | |
| "eval_wer": 0.5595432300163132, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 9.858117326057299e-05, | |
| "loss": 0.318, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "eval_loss": 0.49539458751678467, | |
| "eval_runtime": 18.1275, | |
| "eval_samples_per_second": 5.516, | |
| "eval_wer": 0.5530179445350734, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 9.855388813096863e-05, | |
| "loss": 0.3297, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_loss": 0.5326051115989685, | |
| "eval_runtime": 18.044, | |
| "eval_samples_per_second": 5.542, | |
| "eval_wer": 0.5595432300163132, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 9.852660300136425e-05, | |
| "loss": 0.3045, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 0.48108261823654175, | |
| "eval_runtime": 18.0697, | |
| "eval_samples_per_second": 5.534, | |
| "eval_wer": 0.5415986949429038, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 9.84993178717599e-05, | |
| "loss": 0.2975, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 0.5604788064956665, | |
| "eval_runtime": 18.1396, | |
| "eval_samples_per_second": 5.513, | |
| "eval_wer": 0.5725938009787929, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 9.847203274215553e-05, | |
| "loss": 0.2851, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "eval_loss": 0.52396559715271, | |
| "eval_runtime": 18.0267, | |
| "eval_samples_per_second": 5.547, | |
| "eval_wer": 0.5464926590538336, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 9.844474761255117e-05, | |
| "loss": 0.3037, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 0.4817478060722351, | |
| "eval_runtime": 18.1198, | |
| "eval_samples_per_second": 5.519, | |
| "eval_wer": 0.5415986949429038, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 9.84174624829468e-05, | |
| "loss": 0.3032, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.5403196215629578, | |
| "eval_runtime": 18.0777, | |
| "eval_samples_per_second": 5.532, | |
| "eval_wer": 0.5709624796084829, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 9.839017735334243e-05, | |
| "loss": 0.2947, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "eval_loss": 0.4690156877040863, | |
| "eval_runtime": 18.4111, | |
| "eval_samples_per_second": 5.432, | |
| "eval_wer": 0.5579119086460033, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 9.836289222373807e-05, | |
| "loss": 0.3041, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.5112998485565186, | |
| "eval_runtime": 18.0574, | |
| "eval_samples_per_second": 5.538, | |
| "eval_wer": 0.5595432300163132, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 9.83356070941337e-05, | |
| "loss": 0.2659, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_loss": 0.5093588829040527, | |
| "eval_runtime": 18.1339, | |
| "eval_samples_per_second": 5.515, | |
| "eval_wer": 0.5448613376835236, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 9.830832196452933e-05, | |
| "loss": 0.2621, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "eval_loss": 0.5168948173522949, | |
| "eval_runtime": 18.1269, | |
| "eval_samples_per_second": 5.517, | |
| "eval_wer": 0.5758564437194127, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 9.828103683492497e-05, | |
| "loss": 0.264, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_loss": 0.5183637142181396, | |
| "eval_runtime": 18.0896, | |
| "eval_samples_per_second": 5.528, | |
| "eval_wer": 0.5399673735725938, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 9.825375170532061e-05, | |
| "loss": 0.2725, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 0.5389344096183777, | |
| "eval_runtime": 18.0714, | |
| "eval_samples_per_second": 5.534, | |
| "eval_wer": 0.5415986949429038, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 9.822646657571623e-05, | |
| "loss": 0.273, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "eval_loss": 0.5070094466209412, | |
| "eval_runtime": 18.2125, | |
| "eval_samples_per_second": 5.491, | |
| "eval_wer": 0.5595432300163132, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 9.819918144611188e-05, | |
| "loss": 0.2889, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "eval_loss": 0.5503917932510376, | |
| "eval_runtime": 18.0283, | |
| "eval_samples_per_second": 5.547, | |
| "eval_wer": 0.5464926590538336, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 9.817189631650751e-05, | |
| "loss": 0.2728, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_loss": 0.6155907511711121, | |
| "eval_runtime": 18.1183, | |
| "eval_samples_per_second": 5.519, | |
| "eval_wer": 0.5889070146818923, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 9.814461118690314e-05, | |
| "loss": 0.2914, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "eval_loss": 0.521608293056488, | |
| "eval_runtime": 18.3112, | |
| "eval_samples_per_second": 5.461, | |
| "eval_wer": 0.5383360522022839, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 9.811732605729878e-05, | |
| "loss": 0.2639, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 0.6134706139564514, | |
| "eval_runtime": 18.0647, | |
| "eval_samples_per_second": 5.536, | |
| "eval_wer": 0.5481239804241436, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 9.809004092769441e-05, | |
| "loss": 0.2688, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "eval_loss": 0.5232261419296265, | |
| "eval_runtime": 18.1754, | |
| "eval_samples_per_second": 5.502, | |
| "eval_wer": 0.5464926590538336, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 9.806275579809004e-05, | |
| "loss": 0.2652, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_loss": 0.5219370126724243, | |
| "eval_runtime": 18.2531, | |
| "eval_samples_per_second": 5.479, | |
| "eval_wer": 0.533442088091354, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 9.803547066848569e-05, | |
| "loss": 0.2722, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_loss": 0.5088679790496826, | |
| "eval_runtime": 18.2641, | |
| "eval_samples_per_second": 5.475, | |
| "eval_wer": 0.5236541598694943, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 9.800818553888131e-05, | |
| "loss": 0.2575, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 0.509792149066925, | |
| "eval_runtime": 18.1448, | |
| "eval_samples_per_second": 5.511, | |
| "eval_wer": 0.5220228384991843, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 9.798090040927694e-05, | |
| "loss": 0.2397, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_loss": 0.5148301124572754, | |
| "eval_runtime": 18.0794, | |
| "eval_samples_per_second": 5.531, | |
| "eval_wer": 0.5579119086460033, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 9.795361527967258e-05, | |
| "loss": 0.2464, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_loss": 0.5043299198150635, | |
| "eval_runtime": 18.0544, | |
| "eval_samples_per_second": 5.539, | |
| "eval_wer": 0.5513866231647635, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 9.792633015006821e-05, | |
| "loss": 0.2485, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 0.5194571018218994, | |
| "eval_runtime": 18.0679, | |
| "eval_samples_per_second": 5.535, | |
| "eval_wer": 0.5823817292006526, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 9.789904502046386e-05, | |
| "loss": 0.2299, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_loss": 0.5433354377746582, | |
| "eval_runtime": 18.0004, | |
| "eval_samples_per_second": 5.555, | |
| "eval_wer": 0.5399673735725938, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 9.787175989085948e-05, | |
| "loss": 0.244, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "eval_loss": 0.5765259861946106, | |
| "eval_runtime": 18.2353, | |
| "eval_samples_per_second": 5.484, | |
| "eval_wer": 0.531810766721044, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 9.784447476125512e-05, | |
| "loss": 0.2394, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_loss": 0.6303309202194214, | |
| "eval_runtime": 18.0232, | |
| "eval_samples_per_second": 5.548, | |
| "eval_wer": 0.5530179445350734, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 9.781718963165076e-05, | |
| "loss": 0.2423, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "eval_loss": 0.5469087362289429, | |
| "eval_runtime": 18.1188, | |
| "eval_samples_per_second": 5.519, | |
| "eval_wer": 0.533442088091354, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 9.778990450204639e-05, | |
| "loss": 0.2363, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "eval_loss": 0.5919773578643799, | |
| "eval_runtime": 18.0302, | |
| "eval_samples_per_second": 5.546, | |
| "eval_wer": 0.567699836867863, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 9.776261937244202e-05, | |
| "loss": 0.231, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "eval_loss": 0.49973785877227783, | |
| "eval_runtime": 18.1196, | |
| "eval_samples_per_second": 5.519, | |
| "eval_wer": 0.5464926590538336, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 9.773533424283766e-05, | |
| "loss": 0.244, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_loss": 0.5464155673980713, | |
| "eval_runtime": 18.0797, | |
| "eval_samples_per_second": 5.531, | |
| "eval_wer": 0.5513866231647635, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 9.770804911323329e-05, | |
| "loss": 0.2332, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_loss": 0.526359498500824, | |
| "eval_runtime": 18.1851, | |
| "eval_samples_per_second": 5.499, | |
| "eval_wer": 0.5709624796084829, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 9.768076398362894e-05, | |
| "loss": 0.2421, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 0.5105239748954773, | |
| "eval_runtime": 18.1953, | |
| "eval_samples_per_second": 5.496, | |
| "eval_wer": 0.5562805872756933, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 9.765347885402456e-05, | |
| "loss": 0.2236, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_loss": 0.5103984475135803, | |
| "eval_runtime": 18.0762, | |
| "eval_samples_per_second": 5.532, | |
| "eval_wer": 0.5367047308319739, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 9.76261937244202e-05, | |
| "loss": 0.2075, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_loss": 0.5242435336112976, | |
| "eval_runtime": 18.142, | |
| "eval_samples_per_second": 5.512, | |
| "eval_wer": 0.5106035889070146, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 9.759890859481584e-05, | |
| "loss": 0.2322, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "eval_loss": 0.5415535569190979, | |
| "eval_runtime": 18.1455, | |
| "eval_samples_per_second": 5.511, | |
| "eval_wer": 0.5350734094616639, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 9.757162346521146e-05, | |
| "loss": 0.209, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "eval_loss": 0.45015835762023926, | |
| "eval_runtime": 18.2899, | |
| "eval_samples_per_second": 5.467, | |
| "eval_wer": 0.5154975530179445, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 9.75443383356071e-05, | |
| "loss": 0.2161, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "eval_loss": 0.435876727104187, | |
| "eval_runtime": 18.1085, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.5203915171288744, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 9.751705320600272e-05, | |
| "loss": 0.2239, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "eval_loss": 0.5517589449882507, | |
| "eval_runtime": 18.1314, | |
| "eval_samples_per_second": 5.515, | |
| "eval_wer": 0.5513866231647635, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 9.748976807639837e-05, | |
| "loss": 0.2135, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 0.5722827315330505, | |
| "eval_runtime": 18.2661, | |
| "eval_samples_per_second": 5.475, | |
| "eval_wer": 0.5383360522022839, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 9.7462482946794e-05, | |
| "loss": 0.2193, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "eval_loss": 0.5303468704223633, | |
| "eval_runtime": 18.1001, | |
| "eval_samples_per_second": 5.525, | |
| "eval_wer": 0.5073409461663948, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 9.743519781718964e-05, | |
| "loss": 0.239, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "eval_loss": 0.5649023056030273, | |
| "eval_runtime": 18.115, | |
| "eval_samples_per_second": 5.52, | |
| "eval_wer": 0.5089722675367048, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 9.740791268758527e-05, | |
| "loss": 0.2266, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "eval_loss": 0.4942982792854309, | |
| "eval_runtime": 18.1724, | |
| "eval_samples_per_second": 5.503, | |
| "eval_wer": 0.5187601957585645, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 9.73806275579809e-05, | |
| "loss": 0.2328, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_loss": 0.4808942377567291, | |
| "eval_runtime": 18.123, | |
| "eval_samples_per_second": 5.518, | |
| "eval_wer": 0.5171288743882545, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.735334242837654e-05, | |
| "loss": 0.2219, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_loss": 0.5041812062263489, | |
| "eval_runtime": 18.2686, | |
| "eval_samples_per_second": 5.474, | |
| "eval_wer": 0.5220228384991843, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 9.732605729877218e-05, | |
| "loss": 0.2166, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_loss": 0.49035871028900146, | |
| "eval_runtime": 18.2214, | |
| "eval_samples_per_second": 5.488, | |
| "eval_wer": 0.533442088091354, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 9.72987721691678e-05, | |
| "loss": 0.2036, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "eval_loss": 0.4532802104949951, | |
| "eval_runtime": 18.0465, | |
| "eval_samples_per_second": 5.541, | |
| "eval_wer": 0.5154975530179445, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 9.727148703956345e-05, | |
| "loss": 0.2056, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "eval_loss": 0.49766284227371216, | |
| "eval_runtime": 18.3478, | |
| "eval_samples_per_second": 5.45, | |
| "eval_wer": 0.5220228384991843, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 9.724420190995908e-05, | |
| "loss": 0.1897, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "eval_loss": 0.5390677452087402, | |
| "eval_runtime": 18.1818, | |
| "eval_samples_per_second": 5.5, | |
| "eval_wer": 0.5269168026101142, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 9.721691678035471e-05, | |
| "loss": 0.1957, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "eval_loss": 0.5764414072036743, | |
| "eval_runtime": 18.1005, | |
| "eval_samples_per_second": 5.525, | |
| "eval_wer": 0.533442088091354, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 9.718963165075035e-05, | |
| "loss": 0.1985, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "eval_loss": 0.5892696976661682, | |
| "eval_runtime": 18.12, | |
| "eval_samples_per_second": 5.519, | |
| "eval_wer": 0.5399673735725938, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 9.716234652114598e-05, | |
| "loss": 0.208, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 0.46923932433128357, | |
| "eval_runtime": 18.0696, | |
| "eval_samples_per_second": 5.534, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 9.713506139154161e-05, | |
| "loss": 0.2055, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "eval_loss": 0.5385192036628723, | |
| "eval_runtime": 18.086, | |
| "eval_samples_per_second": 5.529, | |
| "eval_wer": 0.5220228384991843, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 9.710777626193725e-05, | |
| "loss": 0.205, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 0.5977317690849304, | |
| "eval_runtime": 18.0762, | |
| "eval_samples_per_second": 5.532, | |
| "eval_wer": 0.5252854812398042, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 9.708049113233288e-05, | |
| "loss": 0.2153, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_loss": 0.5502565503120422, | |
| "eval_runtime": 18.0402, | |
| "eval_samples_per_second": 5.543, | |
| "eval_wer": 0.5350734094616639, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 9.705320600272851e-05, | |
| "loss": 0.2221, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_loss": 0.5062658786773682, | |
| "eval_runtime": 18.1668, | |
| "eval_samples_per_second": 5.505, | |
| "eval_wer": 0.5057096247960848, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.702592087312416e-05, | |
| "loss": 0.2228, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.4952687919139862, | |
| "eval_runtime": 18.0738, | |
| "eval_samples_per_second": 5.533, | |
| "eval_wer": 0.5187601957585645, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 9.699863574351978e-05, | |
| "loss": 0.1888, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "eval_loss": 0.5036348700523376, | |
| "eval_runtime": 18.1191, | |
| "eval_samples_per_second": 5.519, | |
| "eval_wer": 0.5089722675367048, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 9.697135061391543e-05, | |
| "loss": 0.1827, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "eval_loss": 0.5076143741607666, | |
| "eval_runtime": 18.3508, | |
| "eval_samples_per_second": 5.449, | |
| "eval_wer": 0.5008156606851549, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 9.694406548431105e-05, | |
| "loss": 0.1881, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "eval_loss": 0.48387715220451355, | |
| "eval_runtime": 18.1083, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.49592169657422513, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 9.69167803547067e-05, | |
| "loss": 0.1889, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_loss": 0.5388205051422119, | |
| "eval_runtime": 18.0209, | |
| "eval_samples_per_second": 5.549, | |
| "eval_wer": 0.5008156606851549, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 9.688949522510233e-05, | |
| "loss": 0.1845, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "eval_loss": 0.4822709262371063, | |
| "eval_runtime": 18.0517, | |
| "eval_samples_per_second": 5.54, | |
| "eval_wer": 0.4893964110929853, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 9.686221009549796e-05, | |
| "loss": 0.2032, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "eval_loss": 0.50101637840271, | |
| "eval_runtime": 18.1112, | |
| "eval_samples_per_second": 5.521, | |
| "eval_wer": 0.5350734094616639, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 9.68349249658936e-05, | |
| "loss": 0.2148, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 0.49152928590774536, | |
| "eval_runtime": 18.1082, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 9.680763983628923e-05, | |
| "loss": 0.2014, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 0.490098774433136, | |
| "eval_runtime": 18.2244, | |
| "eval_samples_per_second": 5.487, | |
| "eval_wer": 0.5187601957585645, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 9.678035470668486e-05, | |
| "loss": 0.2006, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "eval_loss": 0.5543618202209473, | |
| "eval_runtime": 18.1457, | |
| "eval_samples_per_second": 5.511, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 9.675306957708049e-05, | |
| "loss": 0.2015, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "eval_loss": 0.46993693709373474, | |
| "eval_runtime": 18.1108, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.49755301794453505, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 9.672578444747613e-05, | |
| "loss": 0.1955, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 0.5119531750679016, | |
| "eval_runtime": 18.1088, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.5171288743882545, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 9.669849931787176e-05, | |
| "loss": 0.1992, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_loss": 0.5462976098060608, | |
| "eval_runtime": 18.1437, | |
| "eval_samples_per_second": 5.512, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 9.66712141882674e-05, | |
| "loss": 0.1858, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "eval_loss": 0.5365936756134033, | |
| "eval_runtime": 18.1212, | |
| "eval_samples_per_second": 5.518, | |
| "eval_wer": 0.5057096247960848, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 9.664392905866303e-05, | |
| "loss": 0.1695, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "eval_loss": 0.5218992829322815, | |
| "eval_runtime": 18.1427, | |
| "eval_samples_per_second": 5.512, | |
| "eval_wer": 0.5138662316476346, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 9.661664392905867e-05, | |
| "loss": 0.198, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "eval_loss": 0.5381004214286804, | |
| "eval_runtime": 18.0861, | |
| "eval_samples_per_second": 5.529, | |
| "eval_wer": 0.5220228384991843, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 9.65893587994543e-05, | |
| "loss": 0.1741, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "eval_loss": 0.549069344997406, | |
| "eval_runtime": 18.1945, | |
| "eval_samples_per_second": 5.496, | |
| "eval_wer": 0.5171288743882545, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 9.656207366984994e-05, | |
| "loss": 0.1941, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "eval_loss": 0.5582250356674194, | |
| "eval_runtime": 18.1284, | |
| "eval_samples_per_second": 5.516, | |
| "eval_wer": 0.5187601957585645, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 9.653478854024557e-05, | |
| "loss": 0.197, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "eval_loss": 0.5502349138259888, | |
| "eval_runtime": 18.1653, | |
| "eval_samples_per_second": 5.505, | |
| "eval_wer": 0.5040783034257749, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 9.65075034106412e-05, | |
| "loss": 0.1758, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "eval_loss": 0.5512282848358154, | |
| "eval_runtime": 18.1381, | |
| "eval_samples_per_second": 5.513, | |
| "eval_wer": 0.49592169657422513, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 9.648021828103684e-05, | |
| "loss": 0.1795, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "eval_loss": 0.5705503225326538, | |
| "eval_runtime": 18.1085, | |
| "eval_samples_per_second": 5.522, | |
| "eval_wer": 0.4926590538336052, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 9.645293315143247e-05, | |
| "loss": 0.1908, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "eval_loss": 0.5005561113357544, | |
| "eval_runtime": 18.2399, | |
| "eval_samples_per_second": 5.482, | |
| "eval_wer": 0.499184339314845, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 9.64256480218281e-05, | |
| "loss": 0.1849, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "eval_loss": 0.4815738797187805, | |
| "eval_runtime": 18.0612, | |
| "eval_samples_per_second": 5.537, | |
| "eval_wer": 0.49755301794453505, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 9.639836289222375e-05, | |
| "loss": 0.1746, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "eval_loss": 0.5251672863960266, | |
| "eval_runtime": 18.1744, | |
| "eval_samples_per_second": 5.502, | |
| "eval_wer": 0.5057096247960848, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 9.637107776261937e-05, | |
| "loss": 0.1805, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "eval_loss": 0.6231664419174194, | |
| "eval_runtime": 18.1307, | |
| "eval_samples_per_second": 5.515, | |
| "eval_wer": 0.5301794453507341, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 9.6343792633015e-05, | |
| "loss": 0.1585, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "eval_loss": 0.639666736125946, | |
| "eval_runtime": 18.0378, | |
| "eval_samples_per_second": 5.544, | |
| "eval_wer": 0.5024469820554649, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 9.631650750341065e-05, | |
| "loss": 0.1676, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "eval_loss": 0.5459147095680237, | |
| "eval_runtime": 18.1234, | |
| "eval_samples_per_second": 5.518, | |
| "eval_wer": 0.5008156606851549, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 9.628922237380627e-05, | |
| "loss": 0.1797, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "eval_loss": 0.542678952217102, | |
| "eval_runtime": 18.1227, | |
| "eval_samples_per_second": 5.518, | |
| "eval_wer": 0.5089722675367048, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 9.626193724420192e-05, | |
| "loss": 0.1587, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "eval_loss": 0.5375781059265137, | |
| "eval_runtime": 18.0437, | |
| "eval_samples_per_second": 5.542, | |
| "eval_wer": 0.5106035889070146, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 9.623465211459755e-05, | |
| "loss": 0.1786, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "eval_loss": 0.5375598669052124, | |
| "eval_runtime": 18.3192, | |
| "eval_samples_per_second": 5.459, | |
| "eval_wer": 0.5008156606851549, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 9.620736698499318e-05, | |
| "loss": 0.1771, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "eval_loss": 0.5227739214897156, | |
| "eval_runtime": 18.3436, | |
| "eval_samples_per_second": 5.452, | |
| "eval_wer": 0.4910277324632953, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 9.618008185538882e-05, | |
| "loss": 0.1668, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "eval_loss": 0.54190593957901, | |
| "eval_runtime": 18.2145, | |
| "eval_samples_per_second": 5.49, | |
| "eval_wer": 0.499184339314845, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 9.615279672578445e-05, | |
| "loss": 0.1628, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "eval_loss": 0.49297595024108887, | |
| "eval_runtime": 18.1064, | |
| "eval_samples_per_second": 5.523, | |
| "eval_wer": 0.48613376835236544, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 9.612551159618008e-05, | |
| "loss": 0.1728, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "eval_loss": 0.4872676432132721, | |
| "eval_runtime": 18.2245, | |
| "eval_samples_per_second": 5.487, | |
| "eval_wer": 0.48776508972267535, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 9.609822646657573e-05, | |
| "loss": 0.1876, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "eval_loss": 0.5935976505279541, | |
| "eval_runtime": 18.1277, | |
| "eval_samples_per_second": 5.516, | |
| "eval_wer": 0.5220228384991843, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 9.607094133697135e-05, | |
| "loss": 0.1732, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "eval_loss": 0.5435391068458557, | |
| "eval_runtime": 18.2852, | |
| "eval_samples_per_second": 5.469, | |
| "eval_wer": 0.49429037520391517, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 9.6043656207367e-05, | |
| "loss": 0.1794, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "eval_loss": 0.5519204139709473, | |
| "eval_runtime": 18.2453, | |
| "eval_samples_per_second": 5.481, | |
| "eval_wer": 0.5138662316476346, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 9.601637107776262e-05, | |
| "loss": 0.1696, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "eval_loss": 0.5955798029899597, | |
| "eval_runtime": 18.1714, | |
| "eval_samples_per_second": 5.503, | |
| "eval_wer": 0.5252854812398042, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 9.598908594815826e-05, | |
| "loss": 0.1665, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "eval_loss": 0.5391552448272705, | |
| "eval_runtime": 18.128, | |
| "eval_samples_per_second": 5.516, | |
| "eval_wer": 0.49592169657422513, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 9.59618008185539e-05, | |
| "loss": 0.1668, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "eval_loss": 0.523460865020752, | |
| "eval_runtime": 18.2149, | |
| "eval_samples_per_second": 5.49, | |
| "eval_wer": 0.499184339314845, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 9.593451568894952e-05, | |
| "loss": 0.1656, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "eval_loss": 0.6226036548614502, | |
| "eval_runtime": 18.3111, | |
| "eval_samples_per_second": 5.461, | |
| "eval_wer": 0.5089722675367048, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 9.590723055934516e-05, | |
| "loss": 0.1652, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "eval_loss": 0.6167003512382507, | |
| "eval_runtime": 18.2279, | |
| "eval_samples_per_second": 5.486, | |
| "eval_wer": 0.5138662316476346, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 9.58799454297408e-05, | |
| "loss": 0.1576, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "eval_loss": 0.561502993106842, | |
| "eval_runtime": 18.1886, | |
| "eval_samples_per_second": 5.498, | |
| "eval_wer": 0.5106035889070146, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 9.585266030013643e-05, | |
| "loss": 0.1483, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "eval_loss": 0.5715560913085938, | |
| "eval_runtime": 18.3019, | |
| "eval_samples_per_second": 5.464, | |
| "eval_wer": 0.5252854812398042, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 9.582537517053206e-05, | |
| "loss": 0.1713, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "eval_loss": 0.5943311452865601, | |
| "eval_runtime": 18.2667, | |
| "eval_samples_per_second": 5.474, | |
| "eval_wer": 0.5024469820554649, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 9.57980900409277e-05, | |
| "loss": 0.1496, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "eval_loss": 0.5450413227081299, | |
| "eval_runtime": 19.1731, | |
| "eval_samples_per_second": 5.216, | |
| "eval_wer": 0.49755301794453505, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 9.577080491132333e-05, | |
| "loss": 0.1673, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "eval_loss": 0.5580278635025024, | |
| "eval_runtime": 18.1472, | |
| "eval_samples_per_second": 5.51, | |
| "eval_wer": 0.49429037520391517, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 9.574351978171898e-05, | |
| "loss": 0.1596, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "eval_loss": 0.5721789002418518, | |
| "eval_runtime": 18.2542, | |
| "eval_samples_per_second": 5.478, | |
| "eval_wer": 0.5073409461663948, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 9.57162346521146e-05, | |
| "loss": 0.1588, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "eval_loss": 0.5455964803695679, | |
| "eval_runtime": 18.234, | |
| "eval_samples_per_second": 5.484, | |
| "eval_wer": 0.5073409461663948, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 9.568894952251024e-05, | |
| "loss": 0.1737, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "eval_loss": 0.5726311206817627, | |
| "eval_runtime": 18.2177, | |
| "eval_samples_per_second": 5.489, | |
| "eval_wer": 0.5040783034257749, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 9.566166439290588e-05, | |
| "loss": 0.1571, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "eval_loss": 0.579778790473938, | |
| "eval_runtime": 18.1586, | |
| "eval_samples_per_second": 5.507, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 9.563437926330151e-05, | |
| "loss": 0.1486, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "eval_loss": 0.5972344279289246, | |
| "eval_runtime": 18.1733, | |
| "eval_samples_per_second": 5.503, | |
| "eval_wer": 0.5106035889070146, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 9.560709413369714e-05, | |
| "loss": 0.1551, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "eval_loss": 0.6507982015609741, | |
| "eval_runtime": 18.1445, | |
| "eval_samples_per_second": 5.511, | |
| "eval_wer": 0.5171288743882545, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 9.557980900409276e-05, | |
| "loss": 0.1655, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "eval_loss": 0.5814386606216431, | |
| "eval_runtime": 18.3148, | |
| "eval_samples_per_second": 5.46, | |
| "eval_wer": 0.5154975530179445, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 9.555252387448841e-05, | |
| "loss": 0.1673, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "eval_loss": 0.5608506202697754, | |
| "eval_runtime": 18.1216, | |
| "eval_samples_per_second": 5.518, | |
| "eval_wer": 0.49429037520391517, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 9.552523874488404e-05, | |
| "loss": 0.1453, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "eval_loss": 0.5696703195571899, | |
| "eval_runtime": 18.192, | |
| "eval_samples_per_second": 5.497, | |
| "eval_wer": 0.499184339314845, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 9.549795361527968e-05, | |
| "loss": 0.1497, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "eval_loss": 0.5988049507141113, | |
| "eval_runtime": 18.1244, | |
| "eval_samples_per_second": 5.517, | |
| "eval_wer": 0.5057096247960848, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 9.547066848567531e-05, | |
| "loss": 0.1648, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "eval_loss": 0.5495877861976624, | |
| "eval_runtime": 18.2527, | |
| "eval_samples_per_second": 5.479, | |
| "eval_wer": 0.4926590538336052, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 9.544338335607094e-05, | |
| "loss": 0.1521, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "eval_loss": 0.5653265118598938, | |
| "eval_runtime": 18.0473, | |
| "eval_samples_per_second": 5.541, | |
| "eval_wer": 0.49592169657422513, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 9.541609822646657e-05, | |
| "loss": 0.1485, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "eval_loss": 0.5756533145904541, | |
| "eval_runtime": 18.163, | |
| "eval_samples_per_second": 5.506, | |
| "eval_wer": 0.5040783034257749, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 9.538881309686222e-05, | |
| "loss": 0.1662, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "eval_loss": 0.5320442318916321, | |
| "eval_runtime": 18.1679, | |
| "eval_samples_per_second": 5.504, | |
| "eval_wer": 0.5040783034257749, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 9.536152796725784e-05, | |
| "loss": 0.167, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_loss": 0.5141332745552063, | |
| "eval_runtime": 18.227, | |
| "eval_samples_per_second": 5.486, | |
| "eval_wer": 0.5008156606851549, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 9.533424283765349e-05, | |
| "loss": 0.1588, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "eval_loss": 0.5980657339096069, | |
| "eval_runtime": 18.0668, | |
| "eval_samples_per_second": 5.535, | |
| "eval_wer": 0.5089722675367048, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 9.530695770804912e-05, | |
| "loss": 0.1512, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "eval_loss": 0.5132100582122803, | |
| "eval_runtime": 18.2884, | |
| "eval_samples_per_second": 5.468, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 9.527967257844475e-05, | |
| "loss": 0.1407, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "eval_loss": 0.5253714919090271, | |
| "eval_runtime": 18.1261, | |
| "eval_samples_per_second": 5.517, | |
| "eval_wer": 0.49592169657422513, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 9.525238744884039e-05, | |
| "loss": 0.1385, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "eval_loss": 0.516293466091156, | |
| "eval_runtime": 18.1921, | |
| "eval_samples_per_second": 5.497, | |
| "eval_wer": 0.48613376835236544, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 9.522510231923602e-05, | |
| "loss": 0.1454, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "eval_loss": 0.5024062991142273, | |
| "eval_runtime": 18.1823, | |
| "eval_samples_per_second": 5.5, | |
| "eval_wer": 0.4698205546492659, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 9.519781718963165e-05, | |
| "loss": 0.1574, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_loss": 0.5171040296554565, | |
| "eval_runtime": 18.1815, | |
| "eval_samples_per_second": 5.5, | |
| "eval_wer": 0.4926590538336052, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 9.517053206002729e-05, | |
| "loss": 0.1481, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "eval_loss": 0.5247868895530701, | |
| "eval_runtime": 18.1938, | |
| "eval_samples_per_second": 5.496, | |
| "eval_wer": 0.48776508972267535, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 9.514324693042292e-05, | |
| "loss": 0.1382, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "eval_loss": 0.5333756804466248, | |
| "eval_runtime": 18.3407, | |
| "eval_samples_per_second": 5.452, | |
| "eval_wer": 0.47797716150081565, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 9.511596180081855e-05, | |
| "loss": 0.1557, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "eval_loss": 0.5148436427116394, | |
| "eval_runtime": 18.1439, | |
| "eval_samples_per_second": 5.511, | |
| "eval_wer": 0.4893964110929853, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 9.50886766712142e-05, | |
| "loss": 0.1559, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "eval_loss": 0.5419223308563232, | |
| "eval_runtime": 18.3072, | |
| "eval_samples_per_second": 5.462, | |
| "eval_wer": 0.5024469820554649, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 9.506139154160982e-05, | |
| "loss": 0.1412, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_loss": 0.5893602967262268, | |
| "eval_runtime": 18.1299, | |
| "eval_samples_per_second": 5.516, | |
| "eval_wer": 0.49592169657422513, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 9.503410641200547e-05, | |
| "loss": 0.1508, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_loss": 0.5416052937507629, | |
| "eval_runtime": 18.2068, | |
| "eval_samples_per_second": 5.492, | |
| "eval_wer": 0.5057096247960848, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 9.500682128240109e-05, | |
| "loss": 0.1461, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "eval_loss": 0.5962003469467163, | |
| "eval_runtime": 18.1627, | |
| "eval_samples_per_second": 5.506, | |
| "eval_wer": 0.49755301794453505, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 9.497953615279673e-05, | |
| "loss": 0.1503, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "eval_loss": 0.59946209192276, | |
| "eval_runtime": 18.2979, | |
| "eval_samples_per_second": 5.465, | |
| "eval_wer": 0.5073409461663948, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 9.495225102319237e-05, | |
| "loss": 0.148, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "eval_loss": 0.615426778793335, | |
| "eval_runtime": 18.13, | |
| "eval_samples_per_second": 5.516, | |
| "eval_wer": 0.5057096247960848, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 9.4924965893588e-05, | |
| "loss": 0.1427, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "eval_loss": 0.6145089864730835, | |
| "eval_runtime": 18.1833, | |
| "eval_samples_per_second": 5.5, | |
| "eval_wer": 0.5106035889070146, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 9.489768076398363e-05, | |
| "loss": 0.1456, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "eval_loss": 0.6026967763900757, | |
| "eval_runtime": 18.3448, | |
| "eval_samples_per_second": 5.451, | |
| "eval_wer": 0.5040783034257749, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 9.487039563437927e-05, | |
| "loss": 0.1463, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "eval_loss": 0.6294275522232056, | |
| "eval_runtime": 18.1136, | |
| "eval_samples_per_second": 5.521, | |
| "eval_wer": 0.48613376835236544, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 9.48431105047749e-05, | |
| "loss": 0.1534, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "eval_loss": 0.656607449054718, | |
| "eval_runtime": 18.1552, | |
| "eval_samples_per_second": 5.508, | |
| "eval_wer": 0.5171288743882545, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 9.481582537517055e-05, | |
| "loss": 0.1508, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "eval_loss": 0.6075925827026367, | |
| "eval_runtime": 18.1522, | |
| "eval_samples_per_second": 5.509, | |
| "eval_wer": 0.49755301794453505, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 9.478854024556617e-05, | |
| "loss": 0.1403, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "eval_loss": 0.5606480836868286, | |
| "eval_runtime": 18.178, | |
| "eval_samples_per_second": 5.501, | |
| "eval_wer": 0.4893964110929853, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 9.47612551159618e-05, | |
| "loss": 0.1483, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "eval_loss": 0.5454413890838623, | |
| "eval_runtime": 18.1743, | |
| "eval_samples_per_second": 5.502, | |
| "eval_wer": 0.5122349102773246, | |
| "step": 19300 | |
| } | |
| ], | |
| "max_steps": 366600, | |
| "num_train_epochs": 300, | |
| "total_flos": 2.1672229688161493e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |