| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 34.0, | |
| "global_step": 70346, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.69758337361044e-05, | |
| "loss": 0.3202, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6951667472208798e-05, | |
| "loss": 0.2924, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.6927501208313194e-05, | |
| "loss": 0.3137, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6903334944417593e-05, | |
| "loss": 0.2914, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.687941034316095e-05, | |
| "loss": 0.434, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.1704005002975464, | |
| "eval_runtime": 546.3501, | |
| "eval_samples_per_second": 9.951, | |
| "eval_steps_per_second": 0.831, | |
| "eval_wer": 0.13782148705227137, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.6855244079265344e-05, | |
| "loss": 0.2905, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.6831077815369744e-05, | |
| "loss": 0.2807, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.6806911551474143e-05, | |
| "loss": 0.3051, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.678274528757854e-05, | |
| "loss": 0.2663, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6758579023682938e-05, | |
| "loss": 0.2833, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.16379164159297943, | |
| "eval_runtime": 540.8282, | |
| "eval_samples_per_second": 10.053, | |
| "eval_steps_per_second": 0.839, | |
| "eval_wer": 0.13242864286624767, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.6734412759787337e-05, | |
| "loss": 0.2632, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.6710246495891733e-05, | |
| "loss": 0.2705, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.6686080231996132e-05, | |
| "loss": 0.2541, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.666191396810053e-05, | |
| "loss": 0.2762, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.663774770420493e-05, | |
| "loss": 0.2478, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.16061988472938538, | |
| "eval_runtime": 543.4613, | |
| "eval_samples_per_second": 10.004, | |
| "eval_steps_per_second": 0.835, | |
| "eval_wer": 0.12399619559355604, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.661358144030933e-05, | |
| "loss": 0.2515, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.6589415176413726e-05, | |
| "loss": 0.2477, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.6565248912518125e-05, | |
| "loss": 0.2514, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6541082648622524e-05, | |
| "loss": 0.2431, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.651691638472692e-05, | |
| "loss": 0.2276, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.1561962068080902, | |
| "eval_runtime": 547.2093, | |
| "eval_samples_per_second": 9.936, | |
| "eval_steps_per_second": 0.83, | |
| "eval_wer": 0.12123113730181298, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.649275012083132e-05, | |
| "loss": 0.2148, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.6468583856935718e-05, | |
| "loss": 0.2291, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.6444417593040114e-05, | |
| "loss": 0.2076, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.6420251329144513e-05, | |
| "loss": 0.225, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.6396085065248912e-05, | |
| "loss": 0.2208, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.15758563578128815, | |
| "eval_runtime": 541.7393, | |
| "eval_samples_per_second": 10.036, | |
| "eval_steps_per_second": 0.838, | |
| "eval_wer": 0.11715218606292958, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.637191880135331e-05, | |
| "loss": 0.2242, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.6347994200096664e-05, | |
| "loss": 0.245, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.6323827936201063e-05, | |
| "loss": 0.2192, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.6299661672305462e-05, | |
| "loss": 0.1945, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.627549540840986e-05, | |
| "loss": 0.2148, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.1502295583486557, | |
| "eval_runtime": 539.5134, | |
| "eval_samples_per_second": 10.078, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.11193583495935756, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.6251329144514257e-05, | |
| "loss": 0.2043, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.6227404543257612e-05, | |
| "loss": 0.3319, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.620323827936201e-05, | |
| "loss": 0.2109, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.617907201546641e-05, | |
| "loss": 0.1961, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.6154905751570807e-05, | |
| "loss": 0.1994, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.1409340798854828, | |
| "eval_runtime": 545.8219, | |
| "eval_samples_per_second": 9.961, | |
| "eval_steps_per_second": 0.832, | |
| "eval_wer": 0.11102395403335719, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.6130739487675206e-05, | |
| "loss": 0.2171, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.6106573223779605e-05, | |
| "loss": 0.2102, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.6082406959884e-05, | |
| "loss": 0.2027, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.60582406959884e-05, | |
| "loss": 0.1979, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.60340744320928e-05, | |
| "loss": 0.1932, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.14319856464862823, | |
| "eval_runtime": 539.2664, | |
| "eval_samples_per_second": 10.082, | |
| "eval_steps_per_second": 0.842, | |
| "eval_wer": 0.11120044711580888, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.6009908168197195e-05, | |
| "loss": 0.2413, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5985741904301594e-05, | |
| "loss": 0.2414, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.5961575640405993e-05, | |
| "loss": 0.2287, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.5937409376510393e-05, | |
| "loss": 0.2179, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.591324311261479e-05, | |
| "loss": 0.2122, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.14428170025348663, | |
| "eval_runtime": 537.2993, | |
| "eval_samples_per_second": 10.119, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.10977869728494809, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.5889076848719188e-05, | |
| "loss": 0.2187, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.5864910584823587e-05, | |
| "loss": 0.1976, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.5840744320927986e-05, | |
| "loss": 0.2173, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.5816578057032382e-05, | |
| "loss": 0.2094, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.579241179313678e-05, | |
| "loss": 0.2177, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.13294020295143127, | |
| "eval_runtime": 536.1048, | |
| "eval_samples_per_second": 10.142, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.11017090413484071, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.576824552924118e-05, | |
| "loss": 0.2215, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.5744079265345576e-05, | |
| "loss": 0.2139, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.5719913001449975e-05, | |
| "loss": 0.2119, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.5695746737554375e-05, | |
| "loss": 0.2149, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.5671580473658774e-05, | |
| "loss": 0.2058, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.1402895301580429, | |
| "eval_runtime": 536.0517, | |
| "eval_samples_per_second": 10.143, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.10704305450694697, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.564741420976317e-05, | |
| "loss": 0.2223, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.562324794586757e-05, | |
| "loss": 0.2028, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.5599081681971968e-05, | |
| "loss": 0.2216, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5575157080715323e-05, | |
| "loss": 0.3608, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.555099081681972e-05, | |
| "loss": 0.2216, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.1341892033815384, | |
| "eval_runtime": 534.1744, | |
| "eval_samples_per_second": 10.178, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.10667045799954897, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.5526824552924118e-05, | |
| "loss": 0.2144, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.5502658289028518e-05, | |
| "loss": 0.1997, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.5478492025132913e-05, | |
| "loss": 0.1848, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.5454325761237313e-05, | |
| "loss": 0.1904, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.5430159497341712e-05, | |
| "loss": 0.1984, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 0.1369849145412445, | |
| "eval_runtime": 536.2744, | |
| "eval_samples_per_second": 10.138, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.10296410326806357, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.5405993233446108e-05, | |
| "loss": 0.2003, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.5381826969550507e-05, | |
| "loss": 0.1895, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.5357660705654906e-05, | |
| "loss": 0.1905, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.5333494441759305e-05, | |
| "loss": 0.1844, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.53093281778637e-05, | |
| "loss": 0.2056, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 0.13709090650081635, | |
| "eval_runtime": 535.6926, | |
| "eval_samples_per_second": 10.149, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.10407208761901027, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 1.52851619139681e-05, | |
| "loss": 0.1998, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.52609956500725e-05, | |
| "loss": 0.2027, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.5236829386176895e-05, | |
| "loss": 0.1931, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.5212663122281296e-05, | |
| "loss": 0.1769, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.5188496858385694e-05, | |
| "loss": 0.1735, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_loss": 0.12957297265529633, | |
| "eval_runtime": 533.0901, | |
| "eval_samples_per_second": 10.199, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.10028729151754635, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.5164330594490091e-05, | |
| "loss": 0.1912, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.514016433059449e-05, | |
| "loss": 0.2043, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.5115998066698888e-05, | |
| "loss": 0.1785, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.5091831802803287e-05, | |
| "loss": 0.2036, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.5067665538907685e-05, | |
| "loss": 0.203, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 0.13005520403385162, | |
| "eval_runtime": 537.2934, | |
| "eval_samples_per_second": 10.119, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.10054222596997657, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.5043499275012082e-05, | |
| "loss": 0.1794, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.5019333011116481e-05, | |
| "loss": 0.2061, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.4995408409859835e-05, | |
| "loss": 0.3276, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.4971242145964234e-05, | |
| "loss": 0.335, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 1.4947075882068632e-05, | |
| "loss": 0.1835, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.13098418712615967, | |
| "eval_runtime": 534.5971, | |
| "eval_samples_per_second": 10.17, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.10036573288752489, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.492290961817303e-05, | |
| "loss": 0.1809, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 1.489874335427743e-05, | |
| "loss": 0.1726, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1.4874577090381828e-05, | |
| "loss": 0.1826, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 1.4850410826486225e-05, | |
| "loss": 0.1925, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 1.4826244562590624e-05, | |
| "loss": 0.178, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.12995637953281403, | |
| "eval_runtime": 536.3946, | |
| "eval_samples_per_second": 10.136, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.09591418514124349, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 1.4802078298695022e-05, | |
| "loss": 0.1815, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 1.477791203479942e-05, | |
| "loss": 0.1874, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.4753745770903819e-05, | |
| "loss": 0.1651, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.4729579507008216e-05, | |
| "loss": 0.1813, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.4705413243112614e-05, | |
| "loss": 0.1585, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 0.1276778280735016, | |
| "eval_runtime": 536.9673, | |
| "eval_samples_per_second": 10.125, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.09657113161481365, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 1.4681246979217013e-05, | |
| "loss": 0.166, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 1.465708071532141e-05, | |
| "loss": 0.1768, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.463291445142581e-05, | |
| "loss": 0.1764, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.4608748187530209e-05, | |
| "loss": 0.1827, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.4584581923634606e-05, | |
| "loss": 0.1848, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.1260216385126114, | |
| "eval_runtime": 535.0378, | |
| "eval_samples_per_second": 10.162, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.09744379185582476, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 1.4560415659739004e-05, | |
| "loss": 0.1766, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.4536249395843403e-05, | |
| "loss": 0.1644, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 1.45120831319478e-05, | |
| "loss": 0.1728, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.4487916868052198e-05, | |
| "loss": 0.1745, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.4463750604156597e-05, | |
| "loss": 0.169, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_loss": 0.12812106311321259, | |
| "eval_runtime": 533.3633, | |
| "eval_samples_per_second": 10.194, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.09692411777971702, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 1.4439584340260995e-05, | |
| "loss": 0.1698, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 1.4415418076365394e-05, | |
| "loss": 0.1713, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 1.4391251812469793e-05, | |
| "loss": 0.1509, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 1.436708554857419e-05, | |
| "loss": 0.1837, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1.434291928467859e-05, | |
| "loss": 0.1666, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 0.12905415892601013, | |
| "eval_runtime": 536.1065, | |
| "eval_samples_per_second": 10.142, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.10030690186004099, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 1.4318753020782987e-05, | |
| "loss": 0.1684, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 1.4294586756887385e-05, | |
| "loss": 0.1611, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.4270420492991784e-05, | |
| "loss": 0.1661, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 1.4246254229096182e-05, | |
| "loss": 0.1712, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 1.4222087965200579e-05, | |
| "loss": 0.1552, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_loss": 0.12709665298461914, | |
| "eval_runtime": 538.6615, | |
| "eval_samples_per_second": 10.094, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.09592399031249081, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.4197921701304978e-05, | |
| "loss": 0.1493, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 1.4173755437409376e-05, | |
| "loss": 0.1659, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 1.4149589173513773e-05, | |
| "loss": 0.1652, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 1.4125422909618174e-05, | |
| "loss": 0.1531, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 1.4101498308361526e-05, | |
| "loss": 0.2736, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_loss": 0.13202722370624542, | |
| "eval_runtime": 533.0403, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.09354133369939306, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 1.4077332044465925e-05, | |
| "loss": 0.1616, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 1.4053165780570323e-05, | |
| "loss": 0.1712, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 1.4028999516674722e-05, | |
| "loss": 0.1582, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 1.4004833252779121e-05, | |
| "loss": 0.149, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.3980666988883519e-05, | |
| "loss": 0.2845, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "eval_loss": 0.12987647950649261, | |
| "eval_runtime": 537.4862, | |
| "eval_samples_per_second": 10.116, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.09205094766980106, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 1.3956500724987916e-05, | |
| "loss": 0.1444, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1.3932334461092316e-05, | |
| "loss": 0.1405, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.3908168197196713e-05, | |
| "loss": 0.1661, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 1.388400193330111e-05, | |
| "loss": 0.1481, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.385983566940551e-05, | |
| "loss": 0.1536, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "eval_loss": 0.12819713354110718, | |
| "eval_runtime": 534.4732, | |
| "eval_samples_per_second": 10.173, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.09267847862962926, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.3835669405509907e-05, | |
| "loss": 0.1461, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 1.3811503141614305e-05, | |
| "loss": 0.1441, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.3787336877718706e-05, | |
| "loss": 0.1461, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 1.3763170613823103e-05, | |
| "loss": 0.1512, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 1.37390043499275e-05, | |
| "loss": 0.1491, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_loss": 0.12403933703899384, | |
| "eval_runtime": 535.3779, | |
| "eval_samples_per_second": 10.155, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.09064880818143489, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.37148380860319e-05, | |
| "loss": 0.1501, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.3690671822136297e-05, | |
| "loss": 0.1455, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.3666505558240697e-05, | |
| "loss": 0.1506, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 1.3642339294345094e-05, | |
| "loss": 0.164, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1.3618173030449492e-05, | |
| "loss": 0.1579, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_loss": 0.12084199488162994, | |
| "eval_runtime": 538.825, | |
| "eval_samples_per_second": 10.09, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.0921391942110269, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 1.3594006766553891e-05, | |
| "loss": 0.1601, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 1.3569840502658288e-05, | |
| "loss": 0.1507, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 1.3545674238762686e-05, | |
| "loss": 0.1499, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.3521507974867087e-05, | |
| "loss": 0.1475, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.3497341710971484e-05, | |
| "loss": 0.16, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 0.118172787129879, | |
| "eval_runtime": 533.288, | |
| "eval_samples_per_second": 10.195, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.09033504270152078, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.3473417109714838e-05, | |
| "loss": 0.2721, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.3449250845819237e-05, | |
| "loss": 0.143, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 1.3425084581923635e-05, | |
| "loss": 0.1665, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.3400918318028034e-05, | |
| "loss": 0.1462, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.3376752054132431e-05, | |
| "loss": 0.1367, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "eval_loss": 0.12139006704092026, | |
| "eval_runtime": 534.1889, | |
| "eval_samples_per_second": 10.178, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.09224705109474737, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.3352585790236829e-05, | |
| "loss": 0.1441, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.3328419526341228e-05, | |
| "loss": 0.1536, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.3304253262445626e-05, | |
| "loss": 0.1373, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.3280086998550023e-05, | |
| "loss": 0.1425, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.3255920734654422e-05, | |
| "loss": 0.1499, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_loss": 0.12317845225334167, | |
| "eval_runtime": 533.7448, | |
| "eval_samples_per_second": 10.187, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.09159010462117721, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 1.323175447075882e-05, | |
| "loss": 0.1487, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.3207588206863217e-05, | |
| "loss": 0.1375, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 1.3183421942967618e-05, | |
| "loss": 0.1297, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.3159255679072016e-05, | |
| "loss": 0.1493, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 1.3135089415176413e-05, | |
| "loss": 0.148, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "eval_loss": 0.11843948066234589, | |
| "eval_runtime": 537.4799, | |
| "eval_samples_per_second": 10.116, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.08962907037171404, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 1.3110923151280813e-05, | |
| "loss": 0.1345, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.308675688738521e-05, | |
| "loss": 0.1462, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.3062590623489608e-05, | |
| "loss": 0.1387, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 1.3038424359594007e-05, | |
| "loss": 0.1346, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.3014258095698404e-05, | |
| "loss": 0.1426, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "eval_loss": 0.12005690485239029, | |
| "eval_runtime": 534.4862, | |
| "eval_samples_per_second": 10.172, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.0888544618431761, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 1.2990091831802802e-05, | |
| "loss": 0.1409, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.2965925567907201e-05, | |
| "loss": 0.1325, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.2941759304011599e-05, | |
| "loss": 0.1358, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 1.2917593040116e-05, | |
| "loss": 0.1375, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 1.2893426776220397e-05, | |
| "loss": 0.1471, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 0.12563009560108185, | |
| "eval_runtime": 534.1976, | |
| "eval_samples_per_second": 10.178, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.08820732054085324, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 1.2869260512324794e-05, | |
| "loss": 0.129, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 1.2845094248429194e-05, | |
| "loss": 0.1231, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 1.2820927984533591e-05, | |
| "loss": 0.1264, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 1.2796761720637989e-05, | |
| "loss": 0.1339, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 1.2772595456742388e-05, | |
| "loss": 0.1358, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_loss": 0.12654127180576324, | |
| "eval_runtime": 536.6902, | |
| "eval_samples_per_second": 10.131, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.09087432712012315, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 1.2748429192846785e-05, | |
| "loss": 0.1338, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 1.2724262928951183e-05, | |
| "loss": 0.1255, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 1.2700096665055584e-05, | |
| "loss": 0.1365, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 1.2676172063798936e-05, | |
| "loss": 0.2927, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 1.2652005799903335e-05, | |
| "loss": 0.1245, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_loss": 0.12634220719337463, | |
| "eval_runtime": 530.9611, | |
| "eval_samples_per_second": 10.24, | |
| "eval_steps_per_second": 0.855, | |
| "eval_wer": 0.08857011187700393, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 1.2627839536007732e-05, | |
| "loss": 0.1293, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 1.260367327211213e-05, | |
| "loss": 0.1399, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 1.2579507008216531e-05, | |
| "loss": 0.1403, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 1.2555340744320928e-05, | |
| "loss": 0.1441, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 1.2531174480425326e-05, | |
| "loss": 0.1407, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_loss": 0.12264178693294525, | |
| "eval_runtime": 530.7763, | |
| "eval_samples_per_second": 10.243, | |
| "eval_steps_per_second": 0.855, | |
| "eval_wer": 0.08845244982203614, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 1.2507008216529725e-05, | |
| "loss": 0.1403, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 1.2482841952634123e-05, | |
| "loss": 0.1296, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 1.245867568873852e-05, | |
| "loss": 0.1319, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.243450942484292e-05, | |
| "loss": 0.2732, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 1.2410343160947317e-05, | |
| "loss": 0.1289, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "eval_loss": 0.13154181838035583, | |
| "eval_runtime": 537.8319, | |
| "eval_samples_per_second": 10.109, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.08732485512859482, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 1.2386176897051714e-05, | |
| "loss": 0.1232, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 1.2362010633156114e-05, | |
| "loss": 0.122, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 1.2337844369260513e-05, | |
| "loss": 0.1233, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 1.231367810536491e-05, | |
| "loss": 0.1298, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 1.228951184146931e-05, | |
| "loss": 0.1326, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "eval_loss": 0.12328499555587769, | |
| "eval_runtime": 531.7435, | |
| "eval_samples_per_second": 10.225, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.08676596036749781, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 1.2265345577573707e-05, | |
| "loss": 0.1199, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 1.2241179313678106e-05, | |
| "loss": 0.1215, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 1.2217013049782504e-05, | |
| "loss": 0.1193, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.2192846785886901e-05, | |
| "loss": 0.1208, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.21686805219913e-05, | |
| "loss": 0.1305, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 0.12366868555545807, | |
| "eval_runtime": 535.288, | |
| "eval_samples_per_second": 10.157, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.08696206379244413, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.2144514258095698e-05, | |
| "loss": 0.1291, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 1.2120347994200095e-05, | |
| "loss": 0.1208, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 1.2096181730304496e-05, | |
| "loss": 0.1297, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 1.2072015466408894e-05, | |
| "loss": 0.1329, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 1.2047849202513291e-05, | |
| "loss": 0.1432, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_loss": 0.12335643172264099, | |
| "eval_runtime": 535.9161, | |
| "eval_samples_per_second": 10.145, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.08573641738652965, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 1.202368293861769e-05, | |
| "loss": 0.1325, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.1999758337361043e-05, | |
| "loss": 0.1434, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 1.1975592073465443e-05, | |
| "loss": 0.11, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 1.1951425809569841e-05, | |
| "loss": 0.1253, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 1.1927259545674238e-05, | |
| "loss": 0.1205, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "eval_loss": 0.13027793169021606, | |
| "eval_runtime": 533.5508, | |
| "eval_samples_per_second": 10.19, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.08577563807151892, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 1.1903093281778638e-05, | |
| "loss": 0.1245, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 1.1878927017883035e-05, | |
| "loss": 0.1171, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 1.1854760753987433e-05, | |
| "loss": 0.1091, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 1.1830594490091832e-05, | |
| "loss": 0.1186, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 1.180642822619623e-05, | |
| "loss": 0.1248, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "eval_loss": 0.12523461878299713, | |
| "eval_runtime": 530.7909, | |
| "eval_samples_per_second": 10.243, | |
| "eval_steps_per_second": 0.855, | |
| "eval_wer": 0.08582466392775549, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 1.1782261962300627e-05, | |
| "loss": 0.1273, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 1.1758095698405028e-05, | |
| "loss": 0.1223, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 1.1733929434509425e-05, | |
| "loss": 0.1345, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 1.1709763170613823e-05, | |
| "loss": 0.12, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 1.1685596906718222e-05, | |
| "loss": 0.1251, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "eval_loss": 0.12534739077091217, | |
| "eval_runtime": 533.4769, | |
| "eval_samples_per_second": 10.192, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.08687381725121829, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 1.166143064282262e-05, | |
| "loss": 0.1167, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 1.1637264378927017e-05, | |
| "loss": 0.2585, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 1.1613098115031416e-05, | |
| "loss": 0.1145, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 1.1588931851135814e-05, | |
| "loss": 0.1299, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 1.1564765587240211e-05, | |
| "loss": 0.1143, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "eval_loss": 0.12656624615192413, | |
| "eval_runtime": 535.5717, | |
| "eval_samples_per_second": 10.152, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.08596193632521792, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 1.154059932334461e-05, | |
| "loss": 0.1238, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 1.1516433059449008e-05, | |
| "loss": 0.1402, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 1.1492266795553409e-05, | |
| "loss": 0.1105, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 1.1468100531657806e-05, | |
| "loss": 0.1059, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 1.1443934267762204e-05, | |
| "loss": 0.1155, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "eval_loss": 0.12192143499851227, | |
| "eval_runtime": 533.9241, | |
| "eval_samples_per_second": 10.183, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.08622667594889545, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 1.1419768003866603e-05, | |
| "loss": 0.1184, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 1.1395601739971e-05, | |
| "loss": 0.1224, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 1.1371435476075398e-05, | |
| "loss": 0.1153, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 1.1347269212179797e-05, | |
| "loss": 0.115, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 1.1323102948284195e-05, | |
| "loss": 0.1227, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "eval_loss": 0.1329466998577118, | |
| "eval_runtime": 534.046, | |
| "eval_samples_per_second": 10.181, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.08641297420259444, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 1.1298936684388592e-05, | |
| "loss": 0.1047, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 1.1275012083131948e-05, | |
| "loss": 0.109, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 1.1250845819236345e-05, | |
| "loss": 0.1167, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 1.1226679555340744e-05, | |
| "loss": 0.236, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 1.1202513291445142e-05, | |
| "loss": 0.1229, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "eval_loss": 0.12436678260564804, | |
| "eval_runtime": 532.5696, | |
| "eval_samples_per_second": 10.209, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.08545206742035749, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 1.117834702754954e-05, | |
| "loss": 0.1105, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 1.115418076365394e-05, | |
| "loss": 0.1144, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 1.1130014499758338e-05, | |
| "loss": 0.1126, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 1.1105848235862735e-05, | |
| "loss": 0.116, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 1.1081681971967135e-05, | |
| "loss": 0.1112, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "eval_loss": 0.135575070977211, | |
| "eval_runtime": 531.7639, | |
| "eval_samples_per_second": 10.224, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.08505986057046486, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 1.1057515708071532e-05, | |
| "loss": 0.1224, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 1.103334944417593e-05, | |
| "loss": 0.1083, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 1.1009183180280329e-05, | |
| "loss": 0.1236, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 1.0985016916384726e-05, | |
| "loss": 0.1127, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 1.0960850652489124e-05, | |
| "loss": 0.2163, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "eval_loss": 0.1251877397298813, | |
| "eval_runtime": 532.3352, | |
| "eval_samples_per_second": 10.213, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.08473628991930345, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 1.0936684388593523e-05, | |
| "loss": 0.1127, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 1.091251812469792e-05, | |
| "loss": 0.0953, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 1.0888351860802318e-05, | |
| "loss": 0.1191, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 1.0864185596906719e-05, | |
| "loss": 0.1064, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 1.0840019333011117e-05, | |
| "loss": 0.1146, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "eval_loss": 0.12111415714025497, | |
| "eval_runtime": 531.5635, | |
| "eval_samples_per_second": 10.228, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.08371655210958259, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 1.0815853069115514e-05, | |
| "loss": 0.1168, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 1.0791686805219913e-05, | |
| "loss": 0.11, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 1.076752054132431e-05, | |
| "loss": 0.1098, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 1.074335427742871e-05, | |
| "loss": 0.1149, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 1.0719188013533108e-05, | |
| "loss": 0.1058, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "eval_loss": 0.12474307417869568, | |
| "eval_runtime": 531.5706, | |
| "eval_samples_per_second": 10.228, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.08430486238442154, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 1.0695021749637505e-05, | |
| "loss": 0.1121, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 1.0670855485741904e-05, | |
| "loss": 0.1157, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 1.0646689221846303e-05, | |
| "loss": 0.1128, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 1.0622522957950701e-05, | |
| "loss": 0.1085, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 1.05983566940551e-05, | |
| "loss": 0.1099, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "eval_loss": 0.11886163800954819, | |
| "eval_runtime": 532.2632, | |
| "eval_samples_per_second": 10.215, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.08326551423220606, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.0574190430159498e-05, | |
| "loss": 0.1089, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 1.0550024166263895e-05, | |
| "loss": 0.0996, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 1.0525857902368294e-05, | |
| "loss": 0.118, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.0501691638472692e-05, | |
| "loss": 0.1186, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.047752537457709e-05, | |
| "loss": 0.1028, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "eval_loss": 0.13030289113521576, | |
| "eval_runtime": 534.5757, | |
| "eval_samples_per_second": 10.171, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.08151038857893653, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 1.0453359110681489e-05, | |
| "loss": 0.1158, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 1.0429192846785886e-05, | |
| "loss": 0.1087, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 1.0405268245529241e-05, | |
| "loss": 0.2071, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 1.0381101981633639e-05, | |
| "loss": 0.1049, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 1.0356935717738037e-05, | |
| "loss": 0.1092, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "eval_loss": 0.13048675656318665, | |
| "eval_runtime": 536.1532, | |
| "eval_samples_per_second": 10.141, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.08381460382205576, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 1.0332769453842436e-05, | |
| "loss": 0.113, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 1.0308603189946833e-05, | |
| "loss": 0.1085, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 1.0284436926051232e-05, | |
| "loss": 0.1044, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 1.0260270662155632e-05, | |
| "loss": 0.1038, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 1.023610439826003e-05, | |
| "loss": 0.1076, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "eval_loss": 0.12758177518844604, | |
| "eval_runtime": 536.4295, | |
| "eval_samples_per_second": 10.136, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.08422642101444301, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 1.0211938134364427e-05, | |
| "loss": 0.1003, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 1.0187771870468826e-05, | |
| "loss": 0.1066, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 1.0163605606573223e-05, | |
| "loss": 0.1138, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 1.0139439342677621e-05, | |
| "loss": 0.1054, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 1.011527307878202e-05, | |
| "loss": 0.1074, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "eval_loss": 0.12682940065860748, | |
| "eval_runtime": 536.2203, | |
| "eval_samples_per_second": 10.139, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.08438330375440008, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 1.0091106814886418e-05, | |
| "loss": 0.1063, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 1.0066940550990817e-05, | |
| "loss": 0.1069, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 1.0042774287095216e-05, | |
| "loss": 0.103, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 1.0018608023199614e-05, | |
| "loss": 0.111, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 9.994441759304013e-06, | |
| "loss": 0.0971, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_loss": 0.13224470615386963, | |
| "eval_runtime": 535.3009, | |
| "eval_samples_per_second": 10.157, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.08387343484953964, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 9.97027549540841e-06, | |
| "loss": 0.0954, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 9.946109231512808e-06, | |
| "loss": 0.1067, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 9.921942967617207e-06, | |
| "loss": 0.0997, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 9.897776703721605e-06, | |
| "loss": 0.1001, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 9.873610439826002e-06, | |
| "loss": 0.1109, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "eval_loss": 0.12869225442409515, | |
| "eval_runtime": 536.6211, | |
| "eval_samples_per_second": 10.132, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.0821085040250228, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 9.849444175930401e-06, | |
| "loss": 0.0918, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 9.825277912034799e-06, | |
| "loss": 0.1051, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 9.801111648139196e-06, | |
| "loss": 0.093, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "learning_rate": 9.776945384243597e-06, | |
| "loss": 0.1025, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 9.752779120347995e-06, | |
| "loss": 0.0991, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "eval_loss": 0.1289302110671997, | |
| "eval_runtime": 643.4222, | |
| "eval_samples_per_second": 8.45, | |
| "eval_steps_per_second": 0.706, | |
| "eval_wer": 0.08313804700599096, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 9.728612856452392e-06, | |
| "loss": 0.1068, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 9.704688255195747e-06, | |
| "loss": 0.1959, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 9.680763653939101e-06, | |
| "loss": 0.1014, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 9.656597390043499e-06, | |
| "loss": 0.1021, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 9.632431126147896e-06, | |
| "loss": 0.1095, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "eval_loss": 0.1272599995136261, | |
| "eval_runtime": 545.0718, | |
| "eval_samples_per_second": 9.975, | |
| "eval_steps_per_second": 0.833, | |
| "eval_wer": 0.08217714022375401, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 9.608264862252297e-06, | |
| "loss": 0.0965, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 9.584098598356695e-06, | |
| "loss": 0.1024, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 9.559932334461092e-06, | |
| "loss": 0.1004, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 9.535766070565491e-06, | |
| "loss": 0.1019, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 9.511599806669889e-06, | |
| "loss": 0.1015, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_loss": 0.13261932134628296, | |
| "eval_runtime": 533.8882, | |
| "eval_samples_per_second": 10.184, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.08159863512016237, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 9.487433542774286e-06, | |
| "loss": 0.1012, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 9.463267278878685e-06, | |
| "loss": 0.0825, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 9.439101014983083e-06, | |
| "loss": 0.0957, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 9.41493475108748e-06, | |
| "loss": 0.0905, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 9.39076848719188e-06, | |
| "loss": 0.1051, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "eval_loss": 0.1337267905473709, | |
| "eval_runtime": 530.4506, | |
| "eval_samples_per_second": 10.25, | |
| "eval_steps_per_second": 0.856, | |
| "eval_wer": 0.08141233686646338, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 9.366602223296277e-06, | |
| "loss": 0.1076, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 15.32, | |
| "learning_rate": 9.342435959400676e-06, | |
| "loss": 0.096, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 9.318269695505076e-06, | |
| "loss": 0.0968, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 9.294103431609473e-06, | |
| "loss": 0.0998, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 9.269937167713872e-06, | |
| "loss": 0.0894, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "eval_loss": 0.13310810923576355, | |
| "eval_runtime": 528.9377, | |
| "eval_samples_per_second": 10.279, | |
| "eval_steps_per_second": 0.858, | |
| "eval_wer": 0.0802455214880328, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 15.51, | |
| "learning_rate": 9.24577090381827e-06, | |
| "loss": 0.0916, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 9.221604639922667e-06, | |
| "loss": 0.0989, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 15.61, | |
| "learning_rate": 9.197438376027067e-06, | |
| "loss": 0.094, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 9.173272112131464e-06, | |
| "loss": 0.1084, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 9.149105848235862e-06, | |
| "loss": 0.1, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "eval_loss": 0.1304289698600769, | |
| "eval_runtime": 532.0673, | |
| "eval_samples_per_second": 10.219, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.0798238991243982, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 9.124939584340261e-06, | |
| "loss": 0.2271, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 9.10077332044466e-06, | |
| "loss": 0.1039, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 9.076607056549058e-06, | |
| "loss": 0.102, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 9.052440792653457e-06, | |
| "loss": 0.0941, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 9.028274528757854e-06, | |
| "loss": 0.0957, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "eval_loss": 0.12928777933120728, | |
| "eval_runtime": 535.6178, | |
| "eval_samples_per_second": 10.151, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.0823536333062057, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 9.004108264862252e-06, | |
| "loss": 0.1037, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 8.979942000966651e-06, | |
| "loss": 0.0861, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "learning_rate": 8.955775737071049e-06, | |
| "loss": 0.0892, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 8.931609473175446e-06, | |
| "loss": 0.093, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 8.907443209279845e-06, | |
| "loss": 0.0921, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "eval_loss": 0.13820573687553406, | |
| "eval_runtime": 532.0135, | |
| "eval_samples_per_second": 10.22, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.08076519556414052, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 8.883276945384243e-06, | |
| "loss": 0.0936, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 8.85911068148864e-06, | |
| "loss": 0.0884, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 8.834944417593041e-06, | |
| "loss": 0.0914, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 8.810778153697439e-06, | |
| "loss": 0.1037, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 8.786611889801836e-06, | |
| "loss": 0.0986, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "eval_loss": 0.13009332120418549, | |
| "eval_runtime": 535.3827, | |
| "eval_samples_per_second": 10.155, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.07883357682841931, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 8.762445625906235e-06, | |
| "loss": 0.0974, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 8.738279362010633e-06, | |
| "loss": 0.0908, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 8.71411309811503e-06, | |
| "loss": 0.1573, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 16.63, | |
| "learning_rate": 8.68994683421943e-06, | |
| "loss": 0.0936, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 8.665780570323827e-06, | |
| "loss": 0.098, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "eval_loss": 0.13050219416618347, | |
| "eval_runtime": 534.8267, | |
| "eval_samples_per_second": 10.166, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.07953954915822604, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 8.641614306428225e-06, | |
| "loss": 0.0962, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 8.617448042532624e-06, | |
| "loss": 0.0912, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 16.82, | |
| "learning_rate": 8.593281778637023e-06, | |
| "loss": 0.0884, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 8.569115514741422e-06, | |
| "loss": 0.0905, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 8.54494925084582e-06, | |
| "loss": 0.0974, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_loss": 0.13248874247074127, | |
| "eval_runtime": 531.6237, | |
| "eval_samples_per_second": 10.227, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.07960818535695725, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 8.520782986950217e-06, | |
| "loss": 0.0878, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 8.496616723054615e-06, | |
| "loss": 0.0879, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 8.472450459159014e-06, | |
| "loss": 0.0868, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 8.448284195263413e-06, | |
| "loss": 0.0887, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 8.42411793136781e-06, | |
| "loss": 0.0886, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "eval_loss": 0.133157879114151, | |
| "eval_runtime": 532.3943, | |
| "eval_samples_per_second": 10.212, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.07963760087069921, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 8.399951667472208e-06, | |
| "loss": 0.0823, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 8.375785403576608e-06, | |
| "loss": 0.0995, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 17.3, | |
| "learning_rate": 8.351619139681005e-06, | |
| "loss": 0.0898, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 8.32769453842436e-06, | |
| "loss": 0.177, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "learning_rate": 8.303528274528758e-06, | |
| "loss": 0.0892, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "eval_loss": 0.13265499472618103, | |
| "eval_runtime": 531.671, | |
| "eval_samples_per_second": 10.226, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.07853942169099984, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 8.279362010633155e-06, | |
| "loss": 0.0868, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 8.255195746737555e-06, | |
| "loss": 0.0847, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 8.231029482841952e-06, | |
| "loss": 0.0898, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 8.206863218946351e-06, | |
| "loss": 0.0935, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 8.182696955050749e-06, | |
| "loss": 0.0917, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "eval_loss": 0.13038352131843567, | |
| "eval_runtime": 533.0136, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.0793238353907851, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 8.158530691155146e-06, | |
| "loss": 0.09, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 8.134364427259546e-06, | |
| "loss": 0.0965, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 8.110198163363945e-06, | |
| "loss": 0.0843, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 17.83, | |
| "learning_rate": 8.086031899468342e-06, | |
| "loss": 0.0858, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 17.88, | |
| "learning_rate": 8.06186563557274e-06, | |
| "loss": 0.0919, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 17.88, | |
| "eval_loss": 0.1353004425764084, | |
| "eval_runtime": 536.1738, | |
| "eval_samples_per_second": 10.14, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.07910812162334416, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 8.037699371677139e-06, | |
| "loss": 0.0845, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "learning_rate": 8.013533107781536e-06, | |
| "loss": 0.0859, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 7.989366843885936e-06, | |
| "loss": 0.082, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 7.965200579990333e-06, | |
| "loss": 0.0784, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 7.941034316094732e-06, | |
| "loss": 0.1007, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "eval_loss": 0.13400490581989288, | |
| "eval_runtime": 533.0551, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.07914734230833341, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 7.91686805219913e-06, | |
| "loss": 0.0952, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 7.892701788303527e-06, | |
| "loss": 0.0878, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 7.868535524407927e-06, | |
| "loss": 0.0799, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 7.844369260512324e-06, | |
| "loss": 0.0798, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "learning_rate": 7.820202996616723e-06, | |
| "loss": 0.0831, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "eval_loss": 0.13274520635604858, | |
| "eval_runtime": 531.7091, | |
| "eval_samples_per_second": 10.226, | |
| "eval_steps_per_second": 0.854, | |
| "eval_wer": 0.07859825271848372, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 7.796036732721121e-06, | |
| "loss": 0.0785, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 7.771870468825518e-06, | |
| "loss": 0.0902, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 7.747704204929918e-06, | |
| "loss": 0.0834, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 7.723537941034317e-06, | |
| "loss": 0.0888, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 7.699371677138714e-06, | |
| "loss": 0.0862, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "eval_loss": 0.1343163102865219, | |
| "eval_runtime": 539.9261, | |
| "eval_samples_per_second": 10.07, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.07915714747958073, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 7.675205413243112e-06, | |
| "loss": 0.0782, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "learning_rate": 7.651039149347511e-06, | |
| "loss": 0.0883, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 7.627114548090865e-06, | |
| "loss": 0.1613, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "learning_rate": 7.602948284195263e-06, | |
| "loss": 0.089, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 7.578782020299662e-06, | |
| "loss": 0.0837, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "eval_loss": 0.13338808715343475, | |
| "eval_runtime": 536.3645, | |
| "eval_samples_per_second": 10.137, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.07772559247747261, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 7.55461575640406e-06, | |
| "loss": 0.0941, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 7.530449492508458e-06, | |
| "loss": 0.0789, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 7.5062832286128565e-06, | |
| "loss": 0.0959, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 7.482116964717254e-06, | |
| "loss": 0.1284, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 7.457950700821653e-06, | |
| "loss": 0.0771, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "eval_loss": 0.14555354416370392, | |
| "eval_runtime": 532.5061, | |
| "eval_samples_per_second": 10.21, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.07781383901869846, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 7.4337844369260515e-06, | |
| "loss": 0.0829, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 7.409618173030449e-06, | |
| "loss": 0.0835, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 7.3854519091348474e-06, | |
| "loss": 0.0762, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 19.28, | |
| "learning_rate": 7.361285645239246e-06, | |
| "loss": 0.079, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "learning_rate": 7.337119381343645e-06, | |
| "loss": 0.0841, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "eval_loss": 0.13647744059562683, | |
| "eval_runtime": 535.6134, | |
| "eval_samples_per_second": 10.151, | |
| "eval_steps_per_second": 0.848, | |
| "eval_wer": 0.07841195446478473, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 7.3129531174480425e-06, | |
| "loss": 0.078, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 7.288786853552441e-06, | |
| "loss": 0.0806, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 7.264620589656839e-06, | |
| "loss": 0.0902, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 19.53, | |
| "learning_rate": 7.240454325761237e-06, | |
| "loss": 0.0786, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 7.216288061865636e-06, | |
| "loss": 0.0874, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "eval_loss": 0.13786283135414124, | |
| "eval_runtime": 532.3776, | |
| "eval_samples_per_second": 10.213, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.07786286487493504, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 7.192121797970034e-06, | |
| "loss": 0.079, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 7.167955534074432e-06, | |
| "loss": 0.082, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 7.14378927017883e-06, | |
| "loss": 0.0861, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 19.77, | |
| "learning_rate": 7.1196230062832286e-06, | |
| "loss": 0.0699, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 7.095456742387626e-06, | |
| "loss": 0.0773, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "eval_loss": 0.13585713505744934, | |
| "eval_runtime": 534.0258, | |
| "eval_samples_per_second": 10.181, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.07759812525125752, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 7.071290478492025e-06, | |
| "loss": 0.0831, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 7.047124214596424e-06, | |
| "loss": 0.0803, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "learning_rate": 7.022957950700821e-06, | |
| "loss": 0.0901, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 6.9987916868052195e-06, | |
| "loss": 0.0858, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 20.06, | |
| "learning_rate": 6.974625422909618e-06, | |
| "loss": 0.0771, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 20.06, | |
| "eval_loss": 0.13920992612838745, | |
| "eval_runtime": 532.6574, | |
| "eval_samples_per_second": 10.207, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.07762754076499946, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 20.11, | |
| "learning_rate": 6.950459159014017e-06, | |
| "loss": 0.0726, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 20.15, | |
| "learning_rate": 6.926292895118415e-06, | |
| "loss": 0.0856, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "learning_rate": 6.902126631222813e-06, | |
| "loss": 0.081, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 6.877960367327211e-06, | |
| "loss": 0.0765, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "learning_rate": 6.853794103431609e-06, | |
| "loss": 0.0861, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "eval_loss": 0.13946381211280823, | |
| "eval_runtime": 532.9507, | |
| "eval_samples_per_second": 10.202, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.07738241148381657, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 20.35, | |
| "learning_rate": 6.829627839536008e-06, | |
| "loss": 0.0785, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 6.805461575640406e-06, | |
| "loss": 0.0884, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 6.781295311744804e-06, | |
| "loss": 0.0889, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 20.49, | |
| "learning_rate": 6.757129047849202e-06, | |
| "loss": 0.0777, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "learning_rate": 6.732962783953601e-06, | |
| "loss": 0.0773, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "eval_loss": 0.1356438547372818, | |
| "eval_runtime": 530.8168, | |
| "eval_samples_per_second": 10.243, | |
| "eval_steps_per_second": 0.855, | |
| "eval_wer": 0.0775294890525263, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 20.59, | |
| "learning_rate": 6.709038182696955e-06, | |
| "loss": 0.1599, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 6.6848719188013534e-06, | |
| "loss": 0.0795, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 6.660705654905751e-06, | |
| "loss": 0.0842, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 6.636539391010149e-06, | |
| "loss": 0.0748, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 20.78, | |
| "learning_rate": 6.6123731271145485e-06, | |
| "loss": 0.069, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 20.78, | |
| "eval_loss": 0.13994921743869781, | |
| "eval_runtime": 532.1861, | |
| "eval_samples_per_second": 10.216, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.07649014090031082, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 6.588206863218947e-06, | |
| "loss": 0.075, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 20.88, | |
| "learning_rate": 6.564040599323344e-06, | |
| "loss": 0.0742, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 20.93, | |
| "learning_rate": 6.539874335427743e-06, | |
| "loss": 0.0727, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "learning_rate": 6.515708071532141e-06, | |
| "loss": 0.0813, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 6.491541807636539e-06, | |
| "loss": 0.0823, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "eval_loss": 0.14689351618289948, | |
| "eval_runtime": 536.4496, | |
| "eval_samples_per_second": 10.135, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.07741182699755851, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 21.07, | |
| "learning_rate": 6.467375543740938e-06, | |
| "loss": 0.0745, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 6.443209279845336e-06, | |
| "loss": 0.0895, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 21.17, | |
| "learning_rate": 6.419043015949734e-06, | |
| "loss": 0.0833, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 21.22, | |
| "learning_rate": 6.394876752054132e-06, | |
| "loss": 0.0797, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 6.3707104881585305e-06, | |
| "loss": 0.0747, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "eval_loss": 0.1414875090122223, | |
| "eval_runtime": 534.8494, | |
| "eval_samples_per_second": 10.165, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.07676468569523567, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 21.31, | |
| "learning_rate": 6.346544224262929e-06, | |
| "loss": 0.0728, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "learning_rate": 6.322377960367327e-06, | |
| "loss": 0.0762, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 21.41, | |
| "learning_rate": 6.2982116964717255e-06, | |
| "loss": 0.0751, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 6.274045432576124e-06, | |
| "loss": 0.0766, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "learning_rate": 6.249879168680521e-06, | |
| "loss": 0.0703, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "eval_loss": 0.1404789239168167, | |
| "eval_runtime": 537.6324, | |
| "eval_samples_per_second": 10.113, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.07775500799121457, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 21.56, | |
| "learning_rate": 6.225712904784921e-06, | |
| "loss": 0.0789, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 6.201546640889319e-06, | |
| "loss": 0.0759, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 21.65, | |
| "learning_rate": 6.1773803769937165e-06, | |
| "loss": 0.0804, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "learning_rate": 6.153455775737072e-06, | |
| "loss": 0.1452, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 21.75, | |
| "learning_rate": 6.129289511841469e-06, | |
| "loss": 0.0776, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 21.75, | |
| "eval_loss": 0.14924485981464386, | |
| "eval_runtime": 540.2911, | |
| "eval_samples_per_second": 10.063, | |
| "eval_steps_per_second": 0.84, | |
| "eval_wer": 0.07781383901869846, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 6.105123247945868e-06, | |
| "loss": 0.0825, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 6.080956984050266e-06, | |
| "loss": 0.0757, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "learning_rate": 6.0567907201546635e-06, | |
| "loss": 0.0766, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 6.032624456259062e-06, | |
| "loss": 0.0768, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "learning_rate": 6.008458192363461e-06, | |
| "loss": 0.0833, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "eval_loss": 0.14477114379405975, | |
| "eval_runtime": 530.9416, | |
| "eval_samples_per_second": 10.24, | |
| "eval_steps_per_second": 0.855, | |
| "eval_wer": 0.07668624432525714, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 22.04, | |
| "learning_rate": 5.984291928467859e-06, | |
| "loss": 0.0634, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 22.09, | |
| "learning_rate": 5.960125664572257e-06, | |
| "loss": 0.0714, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 5.935959400676655e-06, | |
| "loss": 0.0728, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 5.911793136781054e-06, | |
| "loss": 0.0824, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 22.23, | |
| "learning_rate": 5.887626872885452e-06, | |
| "loss": 0.0796, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 22.23, | |
| "eval_loss": 0.1434243619441986, | |
| "eval_runtime": 534.545, | |
| "eval_samples_per_second": 10.171, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.07610773922166551, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 5.8634606089898504e-06, | |
| "loss": 0.0771, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 5.839294345094249e-06, | |
| "loss": 0.0735, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "learning_rate": 5.815128081198646e-06, | |
| "loss": 0.0743, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 22.43, | |
| "learning_rate": 5.790961817303045e-06, | |
| "loss": 0.0746, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "learning_rate": 5.766795553407444e-06, | |
| "loss": 0.0613, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "eval_loss": 0.14463861286640167, | |
| "eval_runtime": 537.9928, | |
| "eval_samples_per_second": 10.106, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.07675488052398835, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 22.52, | |
| "learning_rate": 5.742629289511841e-06, | |
| "loss": 0.0698, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 5.71846302561624e-06, | |
| "loss": 0.0726, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 5.694296761720638e-06, | |
| "loss": 0.0722, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "learning_rate": 5.670130497825036e-06, | |
| "loss": 0.075, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 5.646205896568391e-06, | |
| "loss": 0.0753, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "eval_loss": 0.14392878115177155, | |
| "eval_runtime": 537.6965, | |
| "eval_samples_per_second": 10.112, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.07573514271426751, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "learning_rate": 5.6220396326727884e-06, | |
| "loss": 0.0668, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 22.81, | |
| "learning_rate": 5.597873368777187e-06, | |
| "loss": 0.099, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 5.573707104881585e-06, | |
| "loss": 0.0775, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 5.549540840985983e-06, | |
| "loss": 0.1401, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "learning_rate": 5.525374577090382e-06, | |
| "loss": 0.076, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "eval_loss": 0.1402006894350052, | |
| "eval_runtime": 536.9033, | |
| "eval_samples_per_second": 10.127, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.0759116357967192, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 5.50120831319478e-06, | |
| "loss": 0.0738, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 23.05, | |
| "learning_rate": 5.477042049299179e-06, | |
| "loss": 0.0715, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 5.452875785403576e-06, | |
| "loss": 0.0755, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 23.15, | |
| "learning_rate": 5.4287095215079745e-06, | |
| "loss": 0.0694, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 5.404543257612374e-06, | |
| "loss": 0.0619, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "eval_loss": 0.14730505645275116, | |
| "eval_runtime": 550.4194, | |
| "eval_samples_per_second": 9.878, | |
| "eval_steps_per_second": 0.825, | |
| "eval_wer": 0.07674507535274104, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "learning_rate": 5.380376993716771e-06, | |
| "loss": 0.0695, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 23.3, | |
| "learning_rate": 5.3562107298211696e-06, | |
| "loss": 0.0666, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 23.34, | |
| "learning_rate": 5.332044465925568e-06, | |
| "loss": 0.0714, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 5.3078782020299654e-06, | |
| "loss": 0.0721, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 5.283711938134365e-06, | |
| "loss": 0.1322, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "eval_loss": 0.14308874309062958, | |
| "eval_runtime": 538.4366, | |
| "eval_samples_per_second": 10.098, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.07661760812652593, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 23.49, | |
| "learning_rate": 5.259545674238763e-06, | |
| "loss": 0.0622, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 23.54, | |
| "learning_rate": 5.2353794103431605e-06, | |
| "loss": 0.0742, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 23.59, | |
| "learning_rate": 5.211213146447559e-06, | |
| "loss": 0.0731, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "learning_rate": 5.187046882551957e-06, | |
| "loss": 0.0673, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 5.1628806186563565e-06, | |
| "loss": 0.0691, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "eval_loss": 0.145212322473526, | |
| "eval_runtime": 539.2239, | |
| "eval_samples_per_second": 10.083, | |
| "eval_steps_per_second": 0.842, | |
| "eval_wer": 0.07529391000813829, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "learning_rate": 5.138714354760754e-06, | |
| "loss": 0.0639, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 23.78, | |
| "learning_rate": 5.114548090865152e-06, | |
| "loss": 0.0635, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 5.090381826969551e-06, | |
| "loss": 0.0696, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 5.066215563073948e-06, | |
| "loss": 0.071, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 23.92, | |
| "learning_rate": 5.042049299178347e-06, | |
| "loss": 0.061, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 23.92, | |
| "eval_loss": 0.14517080783843994, | |
| "eval_runtime": 540.106, | |
| "eval_samples_per_second": 10.067, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.0752350789806544, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 5.017883035282746e-06, | |
| "loss": 0.0756, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 4.993716771387143e-06, | |
| "loss": 0.0689, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 24.07, | |
| "learning_rate": 4.969550507491542e-06, | |
| "loss": 0.0684, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 24.12, | |
| "learning_rate": 4.945625906234896e-06, | |
| "loss": 0.0687, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 4.9214596423392944e-06, | |
| "loss": 0.0716, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "eval_loss": 0.14293891191482544, | |
| "eval_runtime": 538.7233, | |
| "eval_samples_per_second": 10.092, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.07556845480306314, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 4.897293378443693e-06, | |
| "loss": 0.0753, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.87312711454809e-06, | |
| "loss": 0.0731, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 24.31, | |
| "learning_rate": 4.848960850652489e-06, | |
| "loss": 0.0639, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 24.36, | |
| "learning_rate": 4.824794586756888e-06, | |
| "loss": 0.0629, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "learning_rate": 4.800628322861286e-06, | |
| "loss": 0.074, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 24.41, | |
| "eval_loss": 0.14397481083869934, | |
| "eval_runtime": 538.7484, | |
| "eval_samples_per_second": 10.092, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.07462715836332082, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 24.46, | |
| "learning_rate": 4.776462058965684e-06, | |
| "loss": 0.0741, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 24.5, | |
| "learning_rate": 4.752295795070082e-06, | |
| "loss": 0.0782, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 4.7281295311744805e-06, | |
| "loss": 0.0683, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 24.6, | |
| "learning_rate": 4.703963267278878e-06, | |
| "loss": 0.0617, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 4.679797003383277e-06, | |
| "loss": 0.0696, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "eval_loss": 0.14590391516685486, | |
| "eval_runtime": 538.3684, | |
| "eval_samples_per_second": 10.099, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.07556845480306314, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "learning_rate": 4.655630739487676e-06, | |
| "loss": 0.0629, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 4.631464475592073e-06, | |
| "loss": 0.0676, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "learning_rate": 4.6072982116964715e-06, | |
| "loss": 0.0727, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 4.58313194780087e-06, | |
| "loss": 0.1067, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 4.558965683905268e-06, | |
| "loss": 0.081, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "eval_loss": 0.14432720839977264, | |
| "eval_runtime": 542.1883, | |
| "eval_samples_per_second": 10.028, | |
| "eval_steps_per_second": 0.837, | |
| "eval_wer": 0.07514683243942856, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 24.94, | |
| "learning_rate": 4.5347994200096665e-06, | |
| "loss": 0.0624, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "learning_rate": 4.510633156114065e-06, | |
| "loss": 0.0663, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 4.486466892218462e-06, | |
| "loss": 0.0703, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 25.08, | |
| "learning_rate": 4.462300628322861e-06, | |
| "loss": 0.0778, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 25.13, | |
| "learning_rate": 4.43813436442726e-06, | |
| "loss": 0.0754, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 25.13, | |
| "eval_loss": 0.14832191169261932, | |
| "eval_runtime": 546.1405, | |
| "eval_samples_per_second": 9.955, | |
| "eval_steps_per_second": 0.831, | |
| "eval_wer": 0.0755390392893212, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 4.413968100531658e-06, | |
| "loss": 0.0661, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 25.23, | |
| "learning_rate": 4.389801836636056e-06, | |
| "loss": 0.067, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 4.365635572740454e-06, | |
| "loss": 0.0646, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 4.341469308844853e-06, | |
| "loss": 0.0659, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 25.37, | |
| "learning_rate": 4.317544707588207e-06, | |
| "loss": 0.0864, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 25.37, | |
| "eval_loss": 0.14669360220432281, | |
| "eval_runtime": 544.2087, | |
| "eval_samples_per_second": 9.991, | |
| "eval_steps_per_second": 0.834, | |
| "eval_wer": 0.07566650651553629, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 4.293378443692605e-06, | |
| "loss": 0.063, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 25.47, | |
| "learning_rate": 4.269212179797003e-06, | |
| "loss": 0.0604, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 25.52, | |
| "learning_rate": 4.245045915901401e-06, | |
| "loss": 0.0671, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 4.2208796520058e-06, | |
| "loss": 0.0715, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "learning_rate": 4.196713388110198e-06, | |
| "loss": 0.0662, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "eval_loss": 0.1471155434846878, | |
| "eval_runtime": 541.2709, | |
| "eval_samples_per_second": 10.045, | |
| "eval_steps_per_second": 0.839, | |
| "eval_wer": 0.07475462558953593, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 25.66, | |
| "learning_rate": 4.172547124214596e-06, | |
| "loss": 0.0673, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 4.148380860318995e-06, | |
| "loss": 0.0731, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 4.124214596423393e-06, | |
| "loss": 0.0681, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 4.1000483325277914e-06, | |
| "loss": 0.0637, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "learning_rate": 4.07588206863219e-06, | |
| "loss": 0.109, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "eval_loss": 0.14721344411373138, | |
| "eval_runtime": 538.1361, | |
| "eval_samples_per_second": 10.103, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.07588222028297724, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "learning_rate": 4.051715804736587e-06, | |
| "loss": 0.0642, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 4.027549540840986e-06, | |
| "loss": 0.0717, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 4.003383276945384e-06, | |
| "loss": 0.0713, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 26.05, | |
| "learning_rate": 3.979217013049782e-06, | |
| "loss": 0.0638, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 26.1, | |
| "learning_rate": 3.955292411793137e-06, | |
| "loss": 0.0682, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 26.1, | |
| "eval_loss": 0.15388603508472443, | |
| "eval_runtime": 537.112, | |
| "eval_samples_per_second": 10.123, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.07482326178826713, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.931126147897535e-06, | |
| "loss": 0.0607, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 26.2, | |
| "learning_rate": 3.9069598840019336e-06, | |
| "loss": 0.0657, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 3.882793620106332e-06, | |
| "loss": 0.0694, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "learning_rate": 3.8586273562107294e-06, | |
| "loss": 0.0677, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 26.34, | |
| "learning_rate": 3.834461092315128e-06, | |
| "loss": 0.0655, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 26.34, | |
| "eval_loss": 0.146892249584198, | |
| "eval_runtime": 546.7383, | |
| "eval_samples_per_second": 9.944, | |
| "eval_steps_per_second": 0.83, | |
| "eval_wer": 0.07426436702717013, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 3.810294828419526e-06, | |
| "loss": 0.0646, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 26.44, | |
| "learning_rate": 3.786128564523925e-06, | |
| "loss": 0.0627, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 26.49, | |
| "learning_rate": 3.761962300628323e-06, | |
| "loss": 0.0641, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 3.737796036732721e-06, | |
| "loss": 0.0675, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "learning_rate": 3.7136297728371196e-06, | |
| "loss": 0.0651, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 26.58, | |
| "eval_loss": 0.1553058624267578, | |
| "eval_runtime": 539.8821, | |
| "eval_samples_per_second": 10.071, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.07484287213076177, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 26.63, | |
| "learning_rate": 3.6894635089415175e-06, | |
| "loss": 0.0637, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 26.68, | |
| "learning_rate": 3.6652972450459155e-06, | |
| "loss": 0.0674, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 26.73, | |
| "learning_rate": 3.6411309811503143e-06, | |
| "loss": 0.0839, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 26.78, | |
| "learning_rate": 3.616964717254712e-06, | |
| "loss": 0.0717, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 3.592798453359111e-06, | |
| "loss": 0.0666, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "eval_loss": 0.15197940170764923, | |
| "eval_runtime": 543.4408, | |
| "eval_samples_per_second": 10.005, | |
| "eval_steps_per_second": 0.835, | |
| "eval_wer": 0.07440163942463256, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "learning_rate": 3.568632189463509e-06, | |
| "loss": 0.0659, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "learning_rate": 3.544465925567907e-06, | |
| "loss": 0.0569, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 26.97, | |
| "learning_rate": 3.5205413243112613e-06, | |
| "loss": 0.0669, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 3.4963750604156597e-06, | |
| "loss": 0.0558, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 27.07, | |
| "learning_rate": 3.472208796520058e-06, | |
| "loss": 0.0724, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 27.07, | |
| "eval_loss": 0.152582049369812, | |
| "eval_runtime": 540.3039, | |
| "eval_samples_per_second": 10.063, | |
| "eval_steps_per_second": 0.84, | |
| "eval_wer": 0.07379371880729897, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 3.4480425326244564e-06, | |
| "loss": 0.0637, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 27.16, | |
| "learning_rate": 3.4238762687288547e-06, | |
| "loss": 0.0654, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "learning_rate": 3.3997100048332527e-06, | |
| "loss": 0.0661, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 27.26, | |
| "learning_rate": 3.375543740937651e-06, | |
| "loss": 0.0571, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 27.31, | |
| "learning_rate": 3.3513774770420494e-06, | |
| "loss": 0.067, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 27.31, | |
| "eval_loss": 0.14894814789295197, | |
| "eval_runtime": 537.7205, | |
| "eval_samples_per_second": 10.111, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.07383293949228824, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 3.3272112131464473e-06, | |
| "loss": 0.0646, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "learning_rate": 3.3030449492508457e-06, | |
| "loss": 0.0579, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 3.278878685355244e-06, | |
| "loss": 0.0698, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 3.2547124214596424e-06, | |
| "loss": 0.0595, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 3.230546157564041e-06, | |
| "loss": 0.0658, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "eval_loss": 0.15184684097766876, | |
| "eval_runtime": 536.8003, | |
| "eval_samples_per_second": 10.129, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.07376430329355702, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "learning_rate": 3.2063798936684387e-06, | |
| "loss": 0.0701, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 27.65, | |
| "learning_rate": 3.182213629772837e-06, | |
| "loss": 0.0605, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.1580473658772355e-06, | |
| "loss": 0.0565, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 27.74, | |
| "learning_rate": 3.1338811019816334e-06, | |
| "loss": 0.0662, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 27.79, | |
| "learning_rate": 3.1097148380860318e-06, | |
| "loss": 0.0581, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 27.79, | |
| "eval_loss": 0.15177908539772034, | |
| "eval_runtime": 545.0855, | |
| "eval_samples_per_second": 9.975, | |
| "eval_steps_per_second": 0.833, | |
| "eval_wer": 0.07392118603351408, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.08554857419043e-06, | |
| "loss": 0.0639, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "learning_rate": 3.0613823102948285e-06, | |
| "loss": 0.0644, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 27.94, | |
| "learning_rate": 3.037216046399227e-06, | |
| "loss": 0.0651, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 27.98, | |
| "learning_rate": 3.0130497825036248e-06, | |
| "loss": 0.0596, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 2.988883518608023e-06, | |
| "loss": 0.0639, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "eval_loss": 0.14953990280628204, | |
| "eval_runtime": 536.247, | |
| "eval_samples_per_second": 10.139, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.07356819986861071, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 28.08, | |
| "learning_rate": 2.9647172547124215e-06, | |
| "loss": 0.0581, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 28.13, | |
| "learning_rate": 2.94055099081682e-06, | |
| "loss": 0.07, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 28.18, | |
| "learning_rate": 2.916384726921218e-06, | |
| "loss": 0.0627, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 28.23, | |
| "learning_rate": 2.892218463025616e-06, | |
| "loss": 0.0692, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 28.27, | |
| "learning_rate": 2.8680521991300145e-06, | |
| "loss": 0.0606, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 28.27, | |
| "eval_loss": 0.15493559837341309, | |
| "eval_runtime": 535.7013, | |
| "eval_samples_per_second": 10.149, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.07394079637600871, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.843885935234413e-06, | |
| "loss": 0.0656, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 28.37, | |
| "learning_rate": 2.819719671338811e-06, | |
| "loss": 0.0676, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "learning_rate": 2.795553407443209e-06, | |
| "loss": 0.0584, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 2.7713871435476075e-06, | |
| "loss": 0.0725, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 2.747220879652006e-06, | |
| "loss": 0.0641, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "eval_loss": 0.151281476020813, | |
| "eval_runtime": 544.2585, | |
| "eval_samples_per_second": 9.99, | |
| "eval_steps_per_second": 0.834, | |
| "eval_wer": 0.07347995332738486, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 28.56, | |
| "learning_rate": 2.7230546157564043e-06, | |
| "loss": 0.0545, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 28.61, | |
| "learning_rate": 2.698888351860802e-06, | |
| "loss": 0.0677, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 2.6747220879652006e-06, | |
| "loss": 0.0621, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 28.71, | |
| "learning_rate": 2.650555824069599e-06, | |
| "loss": 0.0601, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "learning_rate": 2.626389560173997e-06, | |
| "loss": 0.0612, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "eval_loss": 0.15239545702934265, | |
| "eval_runtime": 535.9131, | |
| "eval_samples_per_second": 10.145, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.07391138086226676, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 28.81, | |
| "learning_rate": 2.6022232962783952e-06, | |
| "loss": 0.0611, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 2.5780570323827936e-06, | |
| "loss": 0.0533, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "learning_rate": 2.553890768487192e-06, | |
| "loss": 0.0571, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 2.5297245045915903e-06, | |
| "loss": 0.0571, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.5055582406959883e-06, | |
| "loss": 0.0536, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.15654411911964417, | |
| "eval_runtime": 540.584, | |
| "eval_samples_per_second": 10.058, | |
| "eval_steps_per_second": 0.84, | |
| "eval_wer": 0.07409767911596576, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 29.05, | |
| "learning_rate": 2.4813919768003866e-06, | |
| "loss": 0.0657, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 29.1, | |
| "learning_rate": 2.457225712904785e-06, | |
| "loss": 0.061, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 2.433059449009183e-06, | |
| "loss": 0.0596, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 29.19, | |
| "learning_rate": 2.4088931851135813e-06, | |
| "loss": 0.0591, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "learning_rate": 2.3847269212179796e-06, | |
| "loss": 0.0574, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "eval_loss": 0.15414078533649445, | |
| "eval_runtime": 538.274, | |
| "eval_samples_per_second": 10.101, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.0741172894584604, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 2.360560657322378e-06, | |
| "loss": 0.0585, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "learning_rate": 2.3363943934267764e-06, | |
| "loss": 0.0557, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 29.39, | |
| "learning_rate": 2.3122281295311743e-06, | |
| "loss": 0.061, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 29.43, | |
| "learning_rate": 2.2880618656355727e-06, | |
| "loss": 0.0682, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 29.48, | |
| "learning_rate": 2.263895601739971e-06, | |
| "loss": 0.057, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 29.48, | |
| "eval_loss": 0.15550018846988678, | |
| "eval_runtime": 545.4107, | |
| "eval_samples_per_second": 9.969, | |
| "eval_steps_per_second": 0.832, | |
| "eval_wer": 0.07412709462970771, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 29.53, | |
| "learning_rate": 2.2397293378443694e-06, | |
| "loss": 0.0579, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 2.2155630739487677e-06, | |
| "loss": 0.065, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 29.63, | |
| "learning_rate": 2.1913968100531657e-06, | |
| "loss": 0.0606, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 2.167230546157564e-06, | |
| "loss": 0.0605, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "learning_rate": 2.1430642822619624e-06, | |
| "loss": 0.0624, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "eval_loss": 0.15904855728149414, | |
| "eval_runtime": 537.848, | |
| "eval_samples_per_second": 10.109, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.0736270308960946, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 29.77, | |
| "learning_rate": 2.1188980183663603e-06, | |
| "loss": 0.0686, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 2.0947317544707587e-06, | |
| "loss": 0.0571, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 29.87, | |
| "learning_rate": 2.070565490575157e-06, | |
| "loss": 0.0555, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 29.92, | |
| "learning_rate": 2.0463992266795554e-06, | |
| "loss": 0.0547, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "learning_rate": 2.0222329627839534e-06, | |
| "loss": 0.0531, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "eval_loss": 0.1590205729007721, | |
| "eval_runtime": 544.0168, | |
| "eval_samples_per_second": 9.994, | |
| "eval_steps_per_second": 0.835, | |
| "eval_wer": 0.07340151195740634, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 1.9980666988883517e-06, | |
| "loss": 0.0591, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 30.06, | |
| "learning_rate": 1.97390043499275e-06, | |
| "loss": 0.0518, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 30.11, | |
| "learning_rate": 1.9497341710971485e-06, | |
| "loss": 0.0685, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "learning_rate": 1.9255679072015464e-06, | |
| "loss": 0.0583, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 1.901401643305945e-06, | |
| "loss": 0.0661, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "eval_loss": 0.15988512337207794, | |
| "eval_runtime": 538.3939, | |
| "eval_samples_per_second": 10.099, | |
| "eval_steps_per_second": 0.843, | |
| "eval_wer": 0.07318579818996539, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 30.26, | |
| "learning_rate": 1.8772353794103433e-06, | |
| "loss": 0.0522, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 30.3, | |
| "learning_rate": 1.8530691155147413e-06, | |
| "loss": 0.055, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 30.35, | |
| "learning_rate": 1.8289028516191396e-06, | |
| "loss": 0.0543, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 1.804736587723538e-06, | |
| "loss": 0.0588, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 1.7808119864668922e-06, | |
| "loss": 0.0641, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "eval_loss": 0.15761035680770874, | |
| "eval_runtime": 548.3745, | |
| "eval_samples_per_second": 9.915, | |
| "eval_steps_per_second": 0.828, | |
| "eval_wer": 0.0729504740800298, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 30.5, | |
| "learning_rate": 1.7566457225712904e-06, | |
| "loss": 0.0587, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 1.7324794586756887e-06, | |
| "loss": 0.0541, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 30.59, | |
| "learning_rate": 1.708313194780087e-06, | |
| "loss": 0.0571, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "learning_rate": 1.6841469308844852e-06, | |
| "loss": 0.0597, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 1.6599806669888836e-06, | |
| "loss": 0.0562, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "eval_loss": 0.15929917991161346, | |
| "eval_runtime": 542.8307, | |
| "eval_samples_per_second": 10.016, | |
| "eval_steps_per_second": 0.836, | |
| "eval_wer": 0.07335248610116976, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 30.74, | |
| "learning_rate": 1.6358144030932817e-06, | |
| "loss": 0.0569, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 30.79, | |
| "learning_rate": 1.6116481391976801e-06, | |
| "loss": 0.0559, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 30.84, | |
| "learning_rate": 1.5874818753020783e-06, | |
| "loss": 0.0638, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 30.88, | |
| "learning_rate": 1.5633156114064766e-06, | |
| "loss": 0.063, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "learning_rate": 1.5391493475108748e-06, | |
| "loss": 0.0527, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "eval_loss": 0.16035135090351105, | |
| "eval_runtime": 539.191, | |
| "eval_samples_per_second": 10.084, | |
| "eval_steps_per_second": 0.842, | |
| "eval_wer": 0.07301911027876101, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "learning_rate": 1.5149830836152731e-06, | |
| "loss": 0.0655, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 31.03, | |
| "learning_rate": 1.4908168197196713e-06, | |
| "loss": 0.0648, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 31.08, | |
| "learning_rate": 1.4666505558240696e-06, | |
| "loss": 0.0613, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 31.13, | |
| "learning_rate": 1.4424842919284678e-06, | |
| "loss": 0.0592, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 31.17, | |
| "learning_rate": 1.4183180280328662e-06, | |
| "loss": 0.0579, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 31.17, | |
| "eval_loss": 0.1570565551519394, | |
| "eval_runtime": 546.0461, | |
| "eval_samples_per_second": 9.957, | |
| "eval_steps_per_second": 0.831, | |
| "eval_wer": 0.0733819016149117, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 31.22, | |
| "learning_rate": 1.3941517641372643e-06, | |
| "loss": 0.0578, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 31.27, | |
| "learning_rate": 1.3699855002416627e-06, | |
| "loss": 0.0546, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 31.32, | |
| "learning_rate": 1.3458192363460608e-06, | |
| "loss": 0.0592, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 31.37, | |
| "learning_rate": 1.3216529724504592e-06, | |
| "loss": 0.0691, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 31.42, | |
| "learning_rate": 1.2977283711938134e-06, | |
| "loss": 0.0508, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 31.42, | |
| "eval_loss": 0.16027474403381348, | |
| "eval_runtime": 546.1186, | |
| "eval_samples_per_second": 9.956, | |
| "eval_steps_per_second": 0.831, | |
| "eval_wer": 0.07329365507368586, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 31.46, | |
| "learning_rate": 1.2735621072982118e-06, | |
| "loss": 0.0574, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 31.51, | |
| "learning_rate": 1.24939584340261e-06, | |
| "loss": 0.0479, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 31.56, | |
| "learning_rate": 1.225229579507008e-06, | |
| "loss": 0.0535, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 31.61, | |
| "learning_rate": 1.2010633156114064e-06, | |
| "loss": 0.0592, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 31.66, | |
| "learning_rate": 1.1768970517158048e-06, | |
| "loss": 0.0524, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 31.66, | |
| "eval_loss": 0.15882249176502228, | |
| "eval_runtime": 533.8193, | |
| "eval_samples_per_second": 10.185, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.07256807240138449, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 31.71, | |
| "learning_rate": 1.1527307878202031e-06, | |
| "loss": 0.0544, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 31.75, | |
| "learning_rate": 1.128564523924601e-06, | |
| "loss": 0.0608, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 1.1043982600289994e-06, | |
| "loss": 0.0549, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 31.85, | |
| "learning_rate": 1.0802319961333978e-06, | |
| "loss": 0.0619, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 31.9, | |
| "learning_rate": 1.056065732237796e-06, | |
| "loss": 0.0564, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 31.9, | |
| "eval_loss": 0.1570846140384674, | |
| "eval_runtime": 533.6853, | |
| "eval_samples_per_second": 10.188, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.07273476031258885, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 1.0318994683421943e-06, | |
| "loss": 0.0561, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.0077332044465925e-06, | |
| "loss": 0.0602, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 32.04, | |
| "learning_rate": 9.835669405509908e-07, | |
| "loss": 0.0521, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 32.09, | |
| "learning_rate": 9.59400676655389e-07, | |
| "loss": 0.0504, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "learning_rate": 9.352344127597873e-07, | |
| "loss": 0.0551, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "eval_loss": 0.15838252007961273, | |
| "eval_runtime": 534.3933, | |
| "eval_samples_per_second": 10.174, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.0728230068538147, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "learning_rate": 9.110681488641856e-07, | |
| "loss": 0.0527, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 32.24, | |
| "learning_rate": 8.869018849685839e-07, | |
| "loss": 0.0544, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "learning_rate": 8.627356210729821e-07, | |
| "loss": 0.0568, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "learning_rate": 8.385693571773804e-07, | |
| "loss": 0.0539, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 32.38, | |
| "learning_rate": 8.144030932817786e-07, | |
| "loss": 0.0564, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 32.38, | |
| "eval_loss": 0.15652470290660858, | |
| "eval_runtime": 533.2306, | |
| "eval_samples_per_second": 10.196, | |
| "eval_steps_per_second": 0.851, | |
| "eval_wer": 0.07255826723013717, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 32.43, | |
| "learning_rate": 7.90478492025133e-07, | |
| "loss": 0.0561, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 32.48, | |
| "learning_rate": 7.663122281295311e-07, | |
| "loss": 0.0597, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 32.53, | |
| "learning_rate": 7.421459642339295e-07, | |
| "loss": 0.055, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 32.58, | |
| "learning_rate": 7.179797003383277e-07, | |
| "loss": 0.0546, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 32.62, | |
| "learning_rate": 6.93813436442726e-07, | |
| "loss": 0.0628, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 32.62, | |
| "eval_loss": 0.1558191180229187, | |
| "eval_runtime": 536.6559, | |
| "eval_samples_per_second": 10.131, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.07252885171639523, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "learning_rate": 6.696471725471242e-07, | |
| "loss": 0.054, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 32.72, | |
| "learning_rate": 6.454809086515225e-07, | |
| "loss": 0.0562, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "learning_rate": 6.213146447559207e-07, | |
| "loss": 0.0589, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 32.82, | |
| "learning_rate": 5.97148380860319e-07, | |
| "loss": 0.0607, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 32.87, | |
| "learning_rate": 5.729821169647173e-07, | |
| "loss": 0.0561, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 32.87, | |
| "eval_loss": 0.15816724300384521, | |
| "eval_runtime": 537.9807, | |
| "eval_samples_per_second": 10.106, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.07271514997009423, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 5.488158530691155e-07, | |
| "loss": 0.0498, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 32.96, | |
| "learning_rate": 5.246495891735138e-07, | |
| "loss": 0.056, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 5.00483325277912e-07, | |
| "loss": 0.0597, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 33.06, | |
| "learning_rate": 4.763170613823103e-07, | |
| "loss": 0.063, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "learning_rate": 4.5215079748670853e-07, | |
| "loss": 0.0553, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "eval_loss": 0.1590672880411148, | |
| "eval_runtime": 542.9993, | |
| "eval_samples_per_second": 10.013, | |
| "eval_steps_per_second": 0.836, | |
| "eval_wer": 0.0725778775726318, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 4.2798453359110684e-07, | |
| "loss": 0.0509, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 33.2, | |
| "learning_rate": 4.038182696955051e-07, | |
| "loss": 0.0539, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 33.25, | |
| "learning_rate": 3.7965200579990335e-07, | |
| "loss": 0.0557, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "learning_rate": 3.554857419043016e-07, | |
| "loss": 0.0601, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 33.35, | |
| "learning_rate": 3.3131947800869987e-07, | |
| "loss": 0.0504, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 33.35, | |
| "eval_loss": 0.1590089201927185, | |
| "eval_runtime": 534.1043, | |
| "eval_samples_per_second": 10.18, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.07249943620265328, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 3.071532141130981e-07, | |
| "loss": 0.0503, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 33.45, | |
| "learning_rate": 2.829869502174964e-07, | |
| "loss": 0.0589, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 33.49, | |
| "learning_rate": 2.5882068632189463e-07, | |
| "loss": 0.0489, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 33.54, | |
| "learning_rate": 2.3465442242629292e-07, | |
| "loss": 0.0562, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 33.59, | |
| "learning_rate": 2.1048815853069117e-07, | |
| "loss": 0.0539, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 33.59, | |
| "eval_loss": 0.1581692099571228, | |
| "eval_runtime": 542.6631, | |
| "eval_samples_per_second": 10.019, | |
| "eval_steps_per_second": 0.837, | |
| "eval_wer": 0.07233274829144891, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 33.64, | |
| "learning_rate": 1.8632189463508943e-07, | |
| "loss": 0.0585, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 33.69, | |
| "learning_rate": 1.6215563073948768e-07, | |
| "loss": 0.0587, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 33.74, | |
| "learning_rate": 1.3798936684388594e-07, | |
| "loss": 0.0511, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 33.78, | |
| "learning_rate": 1.138231029482842e-07, | |
| "loss": 0.0563, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "learning_rate": 8.965683905268245e-08, | |
| "loss": 0.0576, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "eval_loss": 0.1579006165266037, | |
| "eval_runtime": 534.4556, | |
| "eval_samples_per_second": 10.173, | |
| "eval_steps_per_second": 0.849, | |
| "eval_wer": 0.07223469657897576, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 33.88, | |
| "learning_rate": 6.549057515708072e-08, | |
| "loss": 0.056, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 4.1324311261478975e-08, | |
| "loss": 0.0574, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 33.98, | |
| "learning_rate": 1.7158047365877234e-08, | |
| "loss": 0.05, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "step": 70346, | |
| "total_flos": 1.1180120186979425e+21, | |
| "train_loss": 0.11303290055127763, | |
| "train_runtime": 325332.1707, | |
| "train_samples_per_second": 5.188, | |
| "train_steps_per_second": 0.216 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "step": 70346, | |
| "total_flos": 1.1180120186979425e+21, | |
| "train_loss": 0.0, | |
| "train_runtime": 56.1914, | |
| "train_samples_per_second": 30038.954, | |
| "train_steps_per_second": 1251.9 | |
| } | |
| ], | |
| "max_steps": 70346, | |
| "num_train_epochs": 34, | |
| "total_flos": 1.1180120186979425e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |