| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.399048266485384, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.7125e-06, | |
| "loss": 17.1443, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 7.4625e-06, | |
| "loss": 11.1984, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.1212499999999998e-05, | |
| "loss": 8.1205, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.49625e-05, | |
| "loss": 6.904, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.8712499999999997e-05, | |
| "loss": 5.7531, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 5.456444263458252, | |
| "eval_runtime": 820.476, | |
| "eval_samples_per_second": 19.388, | |
| "eval_steps_per_second": 2.424, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.2462499999999997e-05, | |
| "loss": 4.5704, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.6212499999999997e-05, | |
| "loss": 3.686, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.99625e-05, | |
| "loss": 3.1914, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.37125e-05, | |
| "loss": 3.0347, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.7462499999999996e-05, | |
| "loss": 2.9882, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 3.00412654876709, | |
| "eval_runtime": 780.8978, | |
| "eval_samples_per_second": 20.37, | |
| "eval_steps_per_second": 2.547, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.12125e-05, | |
| "loss": 2.96, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.4962499999999995e-05, | |
| "loss": 2.9349, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.871249999999999e-05, | |
| "loss": 2.9093, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5.2462499999999994e-05, | |
| "loss": 2.7923, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5.62125e-05, | |
| "loss": 2.1953, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.1722890138626099, | |
| "eval_runtime": 780.9363, | |
| "eval_samples_per_second": 20.369, | |
| "eval_steps_per_second": 2.547, | |
| "eval_wer": 0.7120530803080308, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.9962499999999994e-05, | |
| "loss": 1.6768, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.37125e-05, | |
| "loss": 1.4414, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 6.746249999999999e-05, | |
| "loss": 1.3385, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.121249999999999e-05, | |
| "loss": 1.2697, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.49625e-05, | |
| "loss": 1.2406, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.3655729591846466, | |
| "eval_runtime": 784.9435, | |
| "eval_samples_per_second": 20.265, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 0.3622593509350935, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 7.498733799454298e-05, | |
| "loss": 1.1985, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 7.497454809004091e-05, | |
| "loss": 1.1829, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.496175818553888e-05, | |
| "loss": 1.1421, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.494896828103683e-05, | |
| "loss": 1.1478, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.493617837653478e-05, | |
| "loss": 1.1294, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.28432464599609375, | |
| "eval_runtime": 777.4526, | |
| "eval_samples_per_second": 20.46, | |
| "eval_steps_per_second": 2.558, | |
| "eval_wer": 0.29262926292629265, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.492338847203274e-05, | |
| "loss": 1.108, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.491059856753069e-05, | |
| "loss": 1.1031, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.489780866302864e-05, | |
| "loss": 1.0853, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.488501875852659e-05, | |
| "loss": 1.0775, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.487222885402455e-05, | |
| "loss": 1.0731, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.2553892731666565, | |
| "eval_runtime": 791.0753, | |
| "eval_samples_per_second": 20.108, | |
| "eval_steps_per_second": 2.514, | |
| "eval_wer": 0.2663641364136414, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.48594389495225e-05, | |
| "loss": 1.0511, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.484664904502046e-05, | |
| "loss": 1.0618, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.48338591405184e-05, | |
| "loss": 1.0504, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.482106923601637e-05, | |
| "loss": 1.0445, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.480827933151432e-05, | |
| "loss": 1.051, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.23866702616214752, | |
| "eval_runtime": 778.9178, | |
| "eval_samples_per_second": 20.422, | |
| "eval_steps_per_second": 2.554, | |
| "eval_wer": 0.25350660066006603, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.479548942701227e-05, | |
| "loss": 1.0441, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.478269952251022e-05, | |
| "loss": 1.0539, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.476990961800818e-05, | |
| "loss": 1.0458, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.475711971350613e-05, | |
| "loss": 1.0381, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.474432980900408e-05, | |
| "loss": 1.0479, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.23452000319957733, | |
| "eval_runtime": 783.957, | |
| "eval_samples_per_second": 20.291, | |
| "eval_steps_per_second": 2.537, | |
| "eval_wer": 0.2511619911991199, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.473153990450203e-05, | |
| "loss": 1.0221, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.471875e-05, | |
| "loss": 1.0272, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.470596009549795e-05, | |
| "loss": 1.0043, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.469329809004092e-05, | |
| "loss": 1.0019, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.468050818553888e-05, | |
| "loss": 1.0026, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.22704559564590454, | |
| "eval_runtime": 787.7831, | |
| "eval_samples_per_second": 20.192, | |
| "eval_steps_per_second": 2.525, | |
| "eval_wer": 0.245248899889989, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.466771828103683e-05, | |
| "loss": 0.994, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.465492837653478e-05, | |
| "loss": 1.0002, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7.464213847203273e-05, | |
| "loss": 0.9863, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.46293485675307e-05, | |
| "loss": 0.9988, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.461655866302864e-05, | |
| "loss": 0.9921, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.22116777300834656, | |
| "eval_runtime": 786.501, | |
| "eval_samples_per_second": 20.225, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.23532728272827283, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.46037687585266e-05, | |
| "loss": 0.9872, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 7.459110675306958e-05, | |
| "loss": 0.997, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.457831684856753e-05, | |
| "loss": 0.9853, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.456552694406548e-05, | |
| "loss": 0.9891, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.455273703956343e-05, | |
| "loss": 0.9839, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.21411563456058502, | |
| "eval_runtime": 788.0763, | |
| "eval_samples_per_second": 20.185, | |
| "eval_steps_per_second": 2.524, | |
| "eval_wer": 0.23299642464246426, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.453994713506138e-05, | |
| "loss": 0.9851, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.452715723055934e-05, | |
| "loss": 0.9925, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.451436732605729e-05, | |
| "loss": 0.9894, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 7.450157742155524e-05, | |
| "loss": 1.0026, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.448878751705319e-05, | |
| "loss": 0.9907, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.21215561032295227, | |
| "eval_runtime": 782.9841, | |
| "eval_samples_per_second": 20.316, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.23341584158415843, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.447599761255116e-05, | |
| "loss": 0.9939, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.44632077080491e-05, | |
| "loss": 0.9844, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 7.445041780354707e-05, | |
| "loss": 0.9783, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 7.4437627899045e-05, | |
| "loss": 0.9762, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.442483799454297e-05, | |
| "loss": 0.9788, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.2113770842552185, | |
| "eval_runtime": 788.5303, | |
| "eval_samples_per_second": 20.173, | |
| "eval_steps_per_second": 2.522, | |
| "eval_wer": 0.2269595709570957, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.441204809004092e-05, | |
| "loss": 0.9892, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.439925818553887e-05, | |
| "loss": 0.9902, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 7.438646828103683e-05, | |
| "loss": 0.9724, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.437367837653478e-05, | |
| "loss": 0.9789, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.436088847203273e-05, | |
| "loss": 0.9687, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.20659922063350677, | |
| "eval_runtime": 780.1295, | |
| "eval_samples_per_second": 20.39, | |
| "eval_steps_per_second": 2.55, | |
| "eval_wer": 0.23226760176017602, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.434809856753068e-05, | |
| "loss": 0.9756, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.433530866302865e-05, | |
| "loss": 0.9724, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.43225187585266e-05, | |
| "loss": 0.981, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.430972885402455e-05, | |
| "loss": 0.9703, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.42969389495225e-05, | |
| "loss": 0.9777, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.20326362550258636, | |
| "eval_runtime": 776.6863, | |
| "eval_samples_per_second": 20.481, | |
| "eval_steps_per_second": 2.561, | |
| "eval_wer": 0.22365924092409242, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.428427694406548e-05, | |
| "loss": 0.9631, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.427148703956343e-05, | |
| "loss": 0.979, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.425869713506138e-05, | |
| "loss": 0.9708, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.424590723055933e-05, | |
| "loss": 0.979, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.42331173260573e-05, | |
| "loss": 0.9476, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.2020493745803833, | |
| "eval_runtime": 772.9733, | |
| "eval_samples_per_second": 20.579, | |
| "eval_steps_per_second": 2.573, | |
| "eval_wer": 0.21941694169416942, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 7.422032742155525e-05, | |
| "loss": 0.9659, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 7.420753751705321e-05, | |
| "loss": 0.9559, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.419474761255115e-05, | |
| "loss": 0.9808, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.418195770804911e-05, | |
| "loss": 0.9678, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 7.416916780354706e-05, | |
| "loss": 0.9625, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.19774506986141205, | |
| "eval_runtime": 776.7494, | |
| "eval_samples_per_second": 20.479, | |
| "eval_steps_per_second": 2.561, | |
| "eval_wer": 0.2191144114411441, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.415637789904502e-05, | |
| "loss": 0.966, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.414358799454297e-05, | |
| "loss": 0.9713, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.413079809004092e-05, | |
| "loss": 0.9686, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.411800818553887e-05, | |
| "loss": 0.9609, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.410521828103682e-05, | |
| "loss": 0.9497, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.19759373366832733, | |
| "eval_runtime": 778.1447, | |
| "eval_samples_per_second": 20.442, | |
| "eval_steps_per_second": 2.556, | |
| "eval_wer": 0.21747112211221123, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.409242837653479e-05, | |
| "loss": 0.9637, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.407963847203274e-05, | |
| "loss": 0.9609, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 7.406684856753069e-05, | |
| "loss": 0.9628, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.405405866302864e-05, | |
| "loss": 0.9508, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 7.40412687585266e-05, | |
| "loss": 0.9781, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.19555576145648956, | |
| "eval_runtime": 780.7341, | |
| "eval_samples_per_second": 20.374, | |
| "eval_steps_per_second": 2.548, | |
| "eval_wer": 0.21591721672167216, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.402847885402455e-05, | |
| "loss": 0.9567, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.401581684856752e-05, | |
| "loss": 0.9514, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 7.400302694406547e-05, | |
| "loss": 0.9612, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.399023703956343e-05, | |
| "loss": 0.9702, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.397744713506138e-05, | |
| "loss": 0.9552, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.19579192996025085, | |
| "eval_runtime": 785.2228, | |
| "eval_samples_per_second": 20.258, | |
| "eval_steps_per_second": 2.533, | |
| "eval_wer": 0.2191144114411441, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.396465723055934e-05, | |
| "loss": 0.969, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.395186732605729e-05, | |
| "loss": 0.9607, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.393907742155525e-05, | |
| "loss": 0.9563, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.39262875170532e-05, | |
| "loss": 0.9601, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.391349761255116e-05, | |
| "loss": 0.9345, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.196384459733963, | |
| "eval_runtime": 782.7934, | |
| "eval_samples_per_second": 20.321, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.21577970297029703, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.39007077080491e-05, | |
| "loss": 0.9636, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.388791780354706e-05, | |
| "loss": 0.9453, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.387512789904501e-05, | |
| "loss": 0.9475, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.386233799454296e-05, | |
| "loss": 0.9527, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.384954809004093e-05, | |
| "loss": 0.9528, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.1925509124994278, | |
| "eval_runtime": 787.0057, | |
| "eval_samples_per_second": 20.212, | |
| "eval_steps_per_second": 2.527, | |
| "eval_wer": 0.21540154015401541, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.383675818553888e-05, | |
| "loss": 0.9517, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.382396828103683e-05, | |
| "loss": 0.9489, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.381117837653478e-05, | |
| "loss": 0.9652, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.379838847203274e-05, | |
| "loss": 0.9348, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.378559856753069e-05, | |
| "loss": 0.9502, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.19526860117912292, | |
| "eval_runtime": 785.5748, | |
| "eval_samples_per_second": 20.249, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.21489961496149615, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.377280866302864e-05, | |
| "loss": 0.945, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.376001875852659e-05, | |
| "loss": 0.941, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.374722885402455e-05, | |
| "loss": 0.9155, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.37344389495225e-05, | |
| "loss": 0.936, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.372177694406547e-05, | |
| "loss": 0.9358, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.19272169470787048, | |
| "eval_runtime": 794.4472, | |
| "eval_samples_per_second": 20.023, | |
| "eval_steps_per_second": 2.504, | |
| "eval_wer": 0.2167079207920792, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.370898703956342e-05, | |
| "loss": 0.9302, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.369619713506139e-05, | |
| "loss": 0.9437, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.368340723055934e-05, | |
| "loss": 0.9537, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.36706173260573e-05, | |
| "loss": 0.9364, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.365782742155524e-05, | |
| "loss": 0.941, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.19010405242443085, | |
| "eval_runtime": 786.4035, | |
| "eval_samples_per_second": 20.228, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.21145489548954896, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.36450375170532e-05, | |
| "loss": 0.9385, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.363224761255115e-05, | |
| "loss": 0.9386, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.361945770804912e-05, | |
| "loss": 0.956, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.360666780354705e-05, | |
| "loss": 0.9407, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.359387789904502e-05, | |
| "loss": 0.9287, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.1935959756374359, | |
| "eval_runtime": 778.5995, | |
| "eval_samples_per_second": 20.43, | |
| "eval_steps_per_second": 2.555, | |
| "eval_wer": 0.20895214521452146, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.358108799454297e-05, | |
| "loss": 0.9617, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.356829809004092e-05, | |
| "loss": 0.9321, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.355550818553888e-05, | |
| "loss": 0.9613, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 7.354271828103683e-05, | |
| "loss": 0.9436, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.352992837653478e-05, | |
| "loss": 0.9491, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.1899876892566681, | |
| "eval_runtime": 786.4087, | |
| "eval_samples_per_second": 20.227, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.2104097909790979, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.351713847203273e-05, | |
| "loss": 0.9486, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 7.35043485675307e-05, | |
| "loss": 0.9348, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 7.349155866302864e-05, | |
| "loss": 0.9542, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 7.34787687585266e-05, | |
| "loss": 0.9483, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.346597885402454e-05, | |
| "loss": 0.9478, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.19308479130268097, | |
| "eval_runtime": 780.4777, | |
| "eval_samples_per_second": 20.381, | |
| "eval_steps_per_second": 2.548, | |
| "eval_wer": 0.21197744774477448, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 7.345331684856753e-05, | |
| "loss": 0.9411, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 7.34406548431105e-05, | |
| "loss": 0.9335, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 7.342786493860845e-05, | |
| "loss": 0.9372, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 7.341507503410641e-05, | |
| "loss": 0.9339, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.340228512960436e-05, | |
| "loss": 0.946, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.1913636177778244, | |
| "eval_runtime": 795.396, | |
| "eval_samples_per_second": 19.999, | |
| "eval_steps_per_second": 2.501, | |
| "eval_wer": 0.21338696369636964, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 7.338949522510231e-05, | |
| "loss": 0.9447, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 7.337670532060026e-05, | |
| "loss": 0.929, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 7.336391541609821e-05, | |
| "loss": 0.9413, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 7.335112551159618e-05, | |
| "loss": 0.9292, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 7.333833560709413e-05, | |
| "loss": 0.9499, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.1930927187204361, | |
| "eval_runtime": 803.3902, | |
| "eval_samples_per_second": 19.8, | |
| "eval_steps_per_second": 2.476, | |
| "eval_wer": 0.21727172717271728, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 7.332554570259209e-05, | |
| "loss": 0.9406, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 7.331275579809003e-05, | |
| "loss": 0.9341, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 7.329996589358799e-05, | |
| "loss": 0.935, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 7.328717598908594e-05, | |
| "loss": 0.9426, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 7.32743860845839e-05, | |
| "loss": 0.9346, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.19133125245571136, | |
| "eval_runtime": 785.6947, | |
| "eval_samples_per_second": 20.246, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.2104716721672167, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 7.326159618008185e-05, | |
| "loss": 0.9499, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 7.32488062755798e-05, | |
| "loss": 0.9295, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 7.323601637107775e-05, | |
| "loss": 0.9459, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 7.32232264665757e-05, | |
| "loss": 0.9271, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 7.321043656207367e-05, | |
| "loss": 0.9509, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.19015146791934967, | |
| "eval_runtime": 782.4331, | |
| "eval_samples_per_second": 20.33, | |
| "eval_steps_per_second": 2.542, | |
| "eval_wer": 0.21373762376237623, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 7.319764665757162e-05, | |
| "loss": 0.938, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 7.318485675306957e-05, | |
| "loss": 0.9378, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 7.317206684856752e-05, | |
| "loss": 0.9266, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 7.315927694406548e-05, | |
| "loss": 0.9325, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.314648703956343e-05, | |
| "loss": 0.9294, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.18954087793827057, | |
| "eval_runtime": 786.5281, | |
| "eval_samples_per_second": 20.224, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.20861523652365235, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 7.31336971350614e-05, | |
| "loss": 0.9421, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 7.312103512960435e-05, | |
| "loss": 0.9453, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 7.310824522510231e-05, | |
| "loss": 0.9295, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 7.309545532060026e-05, | |
| "loss": 0.9347, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 7.308266541609823e-05, | |
| "loss": 0.9418, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.19125838577747345, | |
| "eval_runtime": 791.8538, | |
| "eval_samples_per_second": 20.088, | |
| "eval_steps_per_second": 2.512, | |
| "eval_wer": 0.2182549504950495, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 7.306987551159617e-05, | |
| "loss": 0.9383, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 7.305708560709413e-05, | |
| "loss": 0.923, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 7.304429570259208e-05, | |
| "loss": 0.9407, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 7.303150579809004e-05, | |
| "loss": 0.931, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.301871589358798e-05, | |
| "loss": 0.9302, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.18843084573745728, | |
| "eval_runtime": 784.6176, | |
| "eval_samples_per_second": 20.274, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.21144114411441145, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.300592598908594e-05, | |
| "loss": 0.9399, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.299313608458389e-05, | |
| "loss": 0.947, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.298034618008186e-05, | |
| "loss": 0.9468, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.29675562755798e-05, | |
| "loss": 0.9374, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.295476637107776e-05, | |
| "loss": 0.9418, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.1894412785768509, | |
| "eval_runtime": 794.6127, | |
| "eval_samples_per_second": 20.019, | |
| "eval_steps_per_second": 2.503, | |
| "eval_wer": 0.21082920792079207, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.294197646657571e-05, | |
| "loss": 0.9212, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 7.292918656207366e-05, | |
| "loss": 0.9321, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 7.291639665757162e-05, | |
| "loss": 0.9321, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 7.290360675306957e-05, | |
| "loss": 0.9203, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.289081684856752e-05, | |
| "loss": 0.9363, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.18861933052539825, | |
| "eval_runtime": 792.4762, | |
| "eval_samples_per_second": 20.073, | |
| "eval_steps_per_second": 2.51, | |
| "eval_wer": 0.21319444444444444, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.287802694406547e-05, | |
| "loss": 0.9392, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 7.286523703956343e-05, | |
| "loss": 0.9211, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 7.28525750341064e-05, | |
| "loss": 0.9245, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 7.283978512960435e-05, | |
| "loss": 0.9421, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 7.28269952251023e-05, | |
| "loss": 0.9338, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.18555332720279694, | |
| "eval_runtime": 790.487, | |
| "eval_samples_per_second": 20.123, | |
| "eval_steps_per_second": 2.516, | |
| "eval_wer": 0.20778327832783278, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.281420532060027e-05, | |
| "loss": 0.9221, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 7.280141541609822e-05, | |
| "loss": 0.9176, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.278862551159618e-05, | |
| "loss": 0.914, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 7.277583560709412e-05, | |
| "loss": 0.9248, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 7.276304570259208e-05, | |
| "loss": 0.9185, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.18515856564044952, | |
| "eval_runtime": 792.1602, | |
| "eval_samples_per_second": 20.081, | |
| "eval_steps_per_second": 2.511, | |
| "eval_wer": 0.20556243124312432, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.275025579809003e-05, | |
| "loss": 0.9147, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.2737465893588e-05, | |
| "loss": 0.924, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 7.272467598908595e-05, | |
| "loss": 0.9247, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 7.27118860845839e-05, | |
| "loss": 0.9331, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.269909618008185e-05, | |
| "loss": 0.9216, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.18740816414356232, | |
| "eval_runtime": 783.109, | |
| "eval_samples_per_second": 20.313, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.2095365786578658, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.26863062755798e-05, | |
| "loss": 0.93, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.267351637107776e-05, | |
| "loss": 0.9116, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.266072646657571e-05, | |
| "loss": 0.9348, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.264793656207366e-05, | |
| "loss": 0.9223, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 7.263514665757161e-05, | |
| "loss": 0.9176, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.18728592991828918, | |
| "eval_runtime": 790.4913, | |
| "eval_samples_per_second": 20.123, | |
| "eval_steps_per_second": 2.516, | |
| "eval_wer": 0.2078107810781078, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.262235675306957e-05, | |
| "loss": 0.9346, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 7.260956684856752e-05, | |
| "loss": 0.92, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 7.259677694406547e-05, | |
| "loss": 0.929, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.258398703956342e-05, | |
| "loss": 0.9235, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.257119713506139e-05, | |
| "loss": 0.9288, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.1864841878414154, | |
| "eval_runtime": 787.9985, | |
| "eval_samples_per_second": 20.187, | |
| "eval_steps_per_second": 2.524, | |
| "eval_wer": 0.2097428492849285, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.255840723055934e-05, | |
| "loss": 0.9205, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.25456173260573e-05, | |
| "loss": 0.9154, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.253282742155524e-05, | |
| "loss": 0.924, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.25200375170532e-05, | |
| "loss": 0.9245, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.250724761255115e-05, | |
| "loss": 0.9278, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.18693457543849945, | |
| "eval_runtime": 790.2361, | |
| "eval_samples_per_second": 20.129, | |
| "eval_steps_per_second": 2.517, | |
| "eval_wer": 0.20997662266226622, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.24944577080491e-05, | |
| "loss": 0.9339, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.248166780354707e-05, | |
| "loss": 0.9207, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.246887789904502e-05, | |
| "loss": 0.9267, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.245608799454297e-05, | |
| "loss": 0.9259, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.244329809004092e-05, | |
| "loss": 0.9295, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.18780598044395447, | |
| "eval_runtime": 781.1723, | |
| "eval_samples_per_second": 20.363, | |
| "eval_steps_per_second": 2.546, | |
| "eval_wer": 0.2095365786578658, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.243050818553888e-05, | |
| "loss": 0.9345, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.241771828103683e-05, | |
| "loss": 0.9321, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.240492837653478e-05, | |
| "loss": 0.9238, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.239213847203273e-05, | |
| "loss": 0.9232, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.237947646657571e-05, | |
| "loss": 0.9221, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.18524181842803955, | |
| "eval_runtime": 788.3977, | |
| "eval_samples_per_second": 20.176, | |
| "eval_steps_per_second": 2.523, | |
| "eval_wer": 0.21208058305830582, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 7.236668656207366e-05, | |
| "loss": 0.9282, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 7.235389665757161e-05, | |
| "loss": 0.9235, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.234110675306956e-05, | |
| "loss": 0.9362, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.232831684856753e-05, | |
| "loss": 0.9312, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.231552694406548e-05, | |
| "loss": 0.924, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.18553005158901215, | |
| "eval_runtime": 795.127, | |
| "eval_samples_per_second": 20.006, | |
| "eval_steps_per_second": 2.501, | |
| "eval_wer": 0.20418729372937294, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.230273703956344e-05, | |
| "loss": 0.923, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 7.228994713506138e-05, | |
| "loss": 0.9308, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 7.227715723055934e-05, | |
| "loss": 0.9188, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 7.226436732605729e-05, | |
| "loss": 0.9302, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7.225157742155524e-05, | |
| "loss": 0.9104, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.18578162789344788, | |
| "eval_runtime": 782.1788, | |
| "eval_samples_per_second": 20.337, | |
| "eval_steps_per_second": 2.543, | |
| "eval_wer": 0.21046479647964797, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.22387875170532e-05, | |
| "loss": 0.9344, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.222599761255116e-05, | |
| "loss": 0.9251, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 7.22132077080491e-05, | |
| "loss": 0.9193, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 7.220041780354706e-05, | |
| "loss": 0.9253, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 7.218762789904502e-05, | |
| "loss": 0.9284, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.18499909341335297, | |
| "eval_runtime": 795.2327, | |
| "eval_samples_per_second": 20.003, | |
| "eval_steps_per_second": 2.501, | |
| "eval_wer": 0.20799642464246423, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 7.217483799454297e-05, | |
| "loss": 0.9262, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 7.216204809004092e-05, | |
| "loss": 0.9169, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 7.214925818553887e-05, | |
| "loss": 0.9288, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 7.213646828103683e-05, | |
| "loss": 0.9054, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 7.212367837653478e-05, | |
| "loss": 0.9162, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.1839156299829483, | |
| "eval_runtime": 786.0752, | |
| "eval_samples_per_second": 20.236, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 0.20453795379537953, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.211101637107775e-05, | |
| "loss": 0.925, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 7.20982264665757e-05, | |
| "loss": 0.9107, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.208543656207367e-05, | |
| "loss": 0.9044, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 7.207264665757162e-05, | |
| "loss": 0.9215, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 7.205985675306957e-05, | |
| "loss": 0.9111, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.1838468611240387, | |
| "eval_runtime": 782.8069, | |
| "eval_samples_per_second": 20.32, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.2079689218921892, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 7.204706684856752e-05, | |
| "loss": 0.9254, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 7.203427694406548e-05, | |
| "loss": 0.9195, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 7.202148703956343e-05, | |
| "loss": 0.9224, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 7.20086971350614e-05, | |
| "loss": 0.9321, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 7.199590723055933e-05, | |
| "loss": 0.91, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.1888788938522339, | |
| "eval_runtime": 788.8222, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 2.521, | |
| "eval_wer": 0.21059543454345434, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.19831173260573e-05, | |
| "loss": 0.9046, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.197032742155524e-05, | |
| "loss": 0.903, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 7.19575375170532e-05, | |
| "loss": 0.9111, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.194474761255116e-05, | |
| "loss": 0.9197, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.193195770804911e-05, | |
| "loss": 0.9152, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.1855948269367218, | |
| "eval_runtime": 787.8992, | |
| "eval_samples_per_second": 20.189, | |
| "eval_steps_per_second": 2.524, | |
| "eval_wer": 0.20256463146314632, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.191929570259208e-05, | |
| "loss": 0.9145, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.190650579809004e-05, | |
| "loss": 0.9243, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.189371589358799e-05, | |
| "loss": 0.9118, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.188092598908594e-05, | |
| "loss": 0.8995, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.186813608458389e-05, | |
| "loss": 0.9209, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 0.1891188770532608, | |
| "eval_runtime": 785.3595, | |
| "eval_samples_per_second": 20.254, | |
| "eval_steps_per_second": 2.533, | |
| "eval_wer": 0.21331820682068206, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.185534618008184e-05, | |
| "loss": 0.9184, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.18425562755798e-05, | |
| "loss": 0.9132, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.182976637107776e-05, | |
| "loss": 0.9208, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.18169764665757e-05, | |
| "loss": 0.9125, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.180418656207366e-05, | |
| "loss": 0.9094, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.1856813281774521, | |
| "eval_runtime": 782.4289, | |
| "eval_samples_per_second": 20.33, | |
| "eval_steps_per_second": 2.542, | |
| "eval_wer": 0.20886963696369637, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.179139665757162e-05, | |
| "loss": 0.918, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.177860675306957e-05, | |
| "loss": 0.924, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.176581684856753e-05, | |
| "loss": 0.92, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.175302694406547e-05, | |
| "loss": 0.9133, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 7.174023703956343e-05, | |
| "loss": 0.9065, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.18404491245746613, | |
| "eval_runtime": 785.6812, | |
| "eval_samples_per_second": 20.246, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.20523239823982398, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.172744713506138e-05, | |
| "loss": 0.9062, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.171465723055935e-05, | |
| "loss": 0.9149, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 7.170186732605728e-05, | |
| "loss": 0.9039, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 7.168907742155525e-05, | |
| "loss": 0.9135, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 7.16762875170532e-05, | |
| "loss": 0.9156, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.1833326518535614, | |
| "eval_runtime": 782.8158, | |
| "eval_samples_per_second": 20.32, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.20625, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.166349761255115e-05, | |
| "loss": 0.9129, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.165070770804911e-05, | |
| "loss": 0.9133, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.163791780354706e-05, | |
| "loss": 0.9041, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.162512789904501e-05, | |
| "loss": 0.9181, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.161233799454296e-05, | |
| "loss": 0.8986, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.17894455790519714, | |
| "eval_runtime": 791.052, | |
| "eval_samples_per_second": 20.109, | |
| "eval_steps_per_second": 2.514, | |
| "eval_wer": 0.20006875687568756, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.159954809004093e-05, | |
| "loss": 0.9008, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.158675818553888e-05, | |
| "loss": 0.9029, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.157396828103683e-05, | |
| "loss": 0.9021, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.156117837653478e-05, | |
| "loss": 0.9028, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.154838847203274e-05, | |
| "loss": 0.9045, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 0.17688600718975067, | |
| "eval_runtime": 791.874, | |
| "eval_samples_per_second": 20.088, | |
| "eval_steps_per_second": 2.512, | |
| "eval_wer": 0.20222084708470847, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.153559856753069e-05, | |
| "loss": 0.9117, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.152280866302864e-05, | |
| "loss": 0.9241, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.151001875852659e-05, | |
| "loss": 0.9107, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.149722885402455e-05, | |
| "loss": 0.9083, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.14844389495225e-05, | |
| "loss": 0.9039, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 0.18187400698661804, | |
| "eval_runtime": 793.1992, | |
| "eval_samples_per_second": 20.054, | |
| "eval_steps_per_second": 2.508, | |
| "eval_wer": 0.20726760176017603, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.147164904502045e-05, | |
| "loss": 0.8957, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.145885914051842e-05, | |
| "loss": 0.9088, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.144606923601637e-05, | |
| "loss": 0.9208, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.143327933151432e-05, | |
| "loss": 0.8972, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.142048942701227e-05, | |
| "loss": 0.9145, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.182762011885643, | |
| "eval_runtime": 776.5063, | |
| "eval_samples_per_second": 20.485, | |
| "eval_steps_per_second": 2.561, | |
| "eval_wer": 0.20626375137513753, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.140769952251023e-05, | |
| "loss": 0.9034, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.139490961800818e-05, | |
| "loss": 0.9201, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.138211971350613e-05, | |
| "loss": 0.9018, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.136932980900408e-05, | |
| "loss": 0.897, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.135653990450205e-05, | |
| "loss": 0.9081, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.1811380684375763, | |
| "eval_runtime": 783.2545, | |
| "eval_samples_per_second": 20.309, | |
| "eval_steps_per_second": 2.539, | |
| "eval_wer": 0.20488861386138613, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.134375e-05, | |
| "loss": 0.9103, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.133096009549795e-05, | |
| "loss": 0.9189, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.131829809004092e-05, | |
| "loss": 0.9175, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.130550818553888e-05, | |
| "loss": 0.8983, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.129271828103683e-05, | |
| "loss": 0.9252, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.183289036154747, | |
| "eval_runtime": 775.833, | |
| "eval_samples_per_second": 20.503, | |
| "eval_steps_per_second": 2.564, | |
| "eval_wer": 0.20862211221122112, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.127992837653478e-05, | |
| "loss": 0.9191, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.126713847203273e-05, | |
| "loss": 0.9077, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.12543485675307e-05, | |
| "loss": 0.899, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.124155866302864e-05, | |
| "loss": 0.909, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.12287687585266e-05, | |
| "loss": 0.8957, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.17950163781642914, | |
| "eval_runtime": 779.0687, | |
| "eval_samples_per_second": 20.418, | |
| "eval_steps_per_second": 2.553, | |
| "eval_wer": 0.20833333333333334, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.121597885402454e-05, | |
| "loss": 0.91, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.120318894952251e-05, | |
| "loss": 0.9041, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.119039904502046e-05, | |
| "loss": 0.899, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.117760914051841e-05, | |
| "loss": 0.9172, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.116481923601637e-05, | |
| "loss": 0.891, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.18092180788516998, | |
| "eval_runtime": 776.2498, | |
| "eval_samples_per_second": 20.492, | |
| "eval_steps_per_second": 2.562, | |
| "eval_wer": 0.20578245324532454, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.115202933151432e-05, | |
| "loss": 0.8962, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.113923942701227e-05, | |
| "loss": 0.9036, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.112644952251022e-05, | |
| "loss": 0.9097, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 7.111365961800819e-05, | |
| "loss": 0.9188, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.110086971350614e-05, | |
| "loss": 0.9023, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.1811733990907669, | |
| "eval_runtime": 770.8233, | |
| "eval_samples_per_second": 20.636, | |
| "eval_steps_per_second": 2.58, | |
| "eval_wer": 0.20608498349834983, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.108807980900409e-05, | |
| "loss": 0.9044, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.107528990450204e-05, | |
| "loss": 0.904, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.10625e-05, | |
| "loss": 0.9041, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.104971009549795e-05, | |
| "loss": 0.8982, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.10369201909959e-05, | |
| "loss": 0.8918, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.17748048901557922, | |
| "eval_runtime": 774.9097, | |
| "eval_samples_per_second": 20.528, | |
| "eval_steps_per_second": 2.567, | |
| "eval_wer": 0.19973184818481848, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.102413028649385e-05, | |
| "loss": 0.9032, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.101134038199181e-05, | |
| "loss": 0.8998, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.099867837653478e-05, | |
| "loss": 0.912, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.098588847203273e-05, | |
| "loss": 0.9047, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.097309856753068e-05, | |
| "loss": 0.8852, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.17901700735092163, | |
| "eval_runtime": 786.841, | |
| "eval_samples_per_second": 20.216, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.19968371837183718, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.096030866302865e-05, | |
| "loss": 0.9092, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.09475187585266e-05, | |
| "loss": 0.9125, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.093472885402455e-05, | |
| "loss": 0.9014, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.09219389495225e-05, | |
| "loss": 0.903, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.090914904502046e-05, | |
| "loss": 0.8928, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.17667756974697113, | |
| "eval_runtime": 792.1628, | |
| "eval_samples_per_second": 20.08, | |
| "eval_steps_per_second": 2.511, | |
| "eval_wer": 0.20127887788778878, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 7.089635914051841e-05, | |
| "loss": 0.9067, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.088356923601636e-05, | |
| "loss": 0.8958, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.087077933151432e-05, | |
| "loss": 0.9184, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.085798942701227e-05, | |
| "loss": 0.9056, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.084519952251023e-05, | |
| "loss": 0.9079, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.17351186275482178, | |
| "eval_runtime": 788.8014, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 2.522, | |
| "eval_wer": 0.19860423542354236, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.083240961800818e-05, | |
| "loss": 0.9016, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.081961971350614e-05, | |
| "loss": 0.9004, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.080682980900409e-05, | |
| "loss": 0.8833, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.079403990450204e-05, | |
| "loss": 0.8837, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.078124999999999e-05, | |
| "loss": 0.9032, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 0.1792880892753601, | |
| "eval_runtime": 788.4702, | |
| "eval_samples_per_second": 20.175, | |
| "eval_steps_per_second": 2.523, | |
| "eval_wer": 0.2024064906490649, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.076846009549795e-05, | |
| "loss": 0.9036, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.07556701909959e-05, | |
| "loss": 0.9097, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.074300818553887e-05, | |
| "loss": 0.9154, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.073021828103682e-05, | |
| "loss": 0.8799, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.071742837653479e-05, | |
| "loss": 0.9018, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 0.17777115106582642, | |
| "eval_runtime": 788.8183, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 2.521, | |
| "eval_wer": 0.20272277227722774, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.070463847203274e-05, | |
| "loss": 0.8929, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.069184856753069e-05, | |
| "loss": 0.8852, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.067905866302864e-05, | |
| "loss": 0.8866, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.06662687585266e-05, | |
| "loss": 0.9074, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.065347885402455e-05, | |
| "loss": 0.8846, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_loss": 0.17755627632141113, | |
| "eval_runtime": 789.1834, | |
| "eval_samples_per_second": 20.156, | |
| "eval_steps_per_second": 2.52, | |
| "eval_wer": 0.20464108910891088, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.06406889495225e-05, | |
| "loss": 0.9049, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.062789904502046e-05, | |
| "loss": 0.8844, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.061510914051841e-05, | |
| "loss": 0.8892, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.060231923601636e-05, | |
| "loss": 0.8914, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.058952933151431e-05, | |
| "loss": 0.8848, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 0.18120767176151276, | |
| "eval_runtime": 784.2619, | |
| "eval_samples_per_second": 20.283, | |
| "eval_steps_per_second": 2.536, | |
| "eval_wer": 0.20635313531353136, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.05768673260573e-05, | |
| "loss": 0.8994, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.056407742155525e-05, | |
| "loss": 0.9003, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.05512875170532e-05, | |
| "loss": 0.8945, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.053849761255115e-05, | |
| "loss": 0.9029, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.052570770804911e-05, | |
| "loss": 0.9062, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 0.17995673418045044, | |
| "eval_runtime": 786.3908, | |
| "eval_samples_per_second": 20.228, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.20178080308030802, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.051291780354706e-05, | |
| "loss": 0.8966, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.050012789904501e-05, | |
| "loss": 0.9156, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.048733799454296e-05, | |
| "loss": 0.9032, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.047454809004093e-05, | |
| "loss": 0.8911, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 7.046175818553888e-05, | |
| "loss": 0.9011, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.1783064901828766, | |
| "eval_runtime": 785.3165, | |
| "eval_samples_per_second": 20.256, | |
| "eval_steps_per_second": 2.533, | |
| "eval_wer": 0.20491611661166118, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.044896828103683e-05, | |
| "loss": 0.8918, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.043617837653478e-05, | |
| "loss": 0.8972, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.042338847203274e-05, | |
| "loss": 0.8857, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 7.041059856753069e-05, | |
| "loss": 0.9027, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 7.039780866302864e-05, | |
| "loss": 0.8996, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.18099059164524078, | |
| "eval_runtime": 793.5734, | |
| "eval_samples_per_second": 20.045, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.20363036303630364, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.038501875852659e-05, | |
| "loss": 0.8978, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 7.037222885402455e-05, | |
| "loss": 0.8947, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 7.03594389495225e-05, | |
| "loss": 0.8957, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.034664904502045e-05, | |
| "loss": 0.8847, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 7.033385914051842e-05, | |
| "loss": 0.893, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_loss": 0.18052442371845245, | |
| "eval_runtime": 794.0582, | |
| "eval_samples_per_second": 20.033, | |
| "eval_steps_per_second": 2.505, | |
| "eval_wer": 0.20563806380638064, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 7.032106923601637e-05, | |
| "loss": 0.905, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 7.030827933151432e-05, | |
| "loss": 0.8916, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 7.029548942701227e-05, | |
| "loss": 0.908, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 7.028269952251023e-05, | |
| "loss": 0.8984, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 7.026990961800818e-05, | |
| "loss": 0.897, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "eval_loss": 0.17730969190597534, | |
| "eval_runtime": 791.0919, | |
| "eval_samples_per_second": 20.108, | |
| "eval_steps_per_second": 2.514, | |
| "eval_wer": 0.20351347634763475, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 7.025711971350613e-05, | |
| "loss": 0.8926, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.024432980900408e-05, | |
| "loss": 0.9031, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 7.023153990450205e-05, | |
| "loss": 0.8943, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 7.021875e-05, | |
| "loss": 0.8854, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 7.020596009549795e-05, | |
| "loss": 0.8992, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.18037009239196777, | |
| "eval_runtime": 798.2659, | |
| "eval_samples_per_second": 19.927, | |
| "eval_steps_per_second": 2.492, | |
| "eval_wer": 0.20536303630363037, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 7.01931701909959e-05, | |
| "loss": 0.9009, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 7.018038028649386e-05, | |
| "loss": 0.8927, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 7.016759038199181e-05, | |
| "loss": 0.8803, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 7.015480047748976e-05, | |
| "loss": 0.8784, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.014201057298772e-05, | |
| "loss": 0.8987, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 0.17680302262306213, | |
| "eval_runtime": 792.6165, | |
| "eval_samples_per_second": 20.069, | |
| "eval_steps_per_second": 2.509, | |
| "eval_wer": 0.20156765676567656, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "step": 40000, | |
| "total_flos": 2.0146212451775722e+20, | |
| "train_loss": 0.0, | |
| "train_runtime": 2.2028, | |
| "train_samples_per_second": 0.0, | |
| "train_steps_per_second": 0.0 | |
| } | |
| ], | |
| "max_steps": 0, | |
| "num_train_epochs": 0, | |
| "total_flos": 2.0146212451775722e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |