| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.999947081547335, | |
| "global_step": 141720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 20.7222, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 19.3811, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.475e-05, | |
| "loss": 16.0691, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9750000000000002e-05, | |
| "loss": 9.6857, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.4750000000000002e-05, | |
| "loss": 6.2179, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 4.130920886993408, | |
| "eval_runtime": 1871.6838, | |
| "eval_samples_per_second": 21.722, | |
| "eval_steps_per_second": 1.358, | |
| "eval_wer": 0.9997532611076562, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.975e-05, | |
| "loss": 3.3464, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.475e-05, | |
| "loss": 3.1108, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.9750000000000004e-05, | |
| "loss": 2.9857, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.4750000000000004e-05, | |
| "loss": 2.9706, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.975e-05, | |
| "loss": 2.9345, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.923755168914795, | |
| "eval_runtime": 1838.0646, | |
| "eval_samples_per_second": 22.119, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5.475e-05, | |
| "loss": 2.8508, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5.975000000000001e-05, | |
| "loss": 2.1876, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.475e-05, | |
| "loss": 1.2426, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 6.975e-05, | |
| "loss": 0.8594, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.475000000000001e-05, | |
| "loss": 0.7252, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.398578405380249, | |
| "eval_runtime": 1854.9996, | |
| "eval_samples_per_second": 21.918, | |
| "eval_steps_per_second": 1.37, | |
| "eval_wer": 0.3913857913646423, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.975e-05, | |
| "loss": 0.6558, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.475000000000001e-05, | |
| "loss": 0.5771, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.975e-05, | |
| "loss": 0.5528, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.475e-05, | |
| "loss": 0.54, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.975000000000001e-05, | |
| "loss": 0.5085, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.26914846897125244, | |
| "eval_runtime": 1837.1664, | |
| "eval_samples_per_second": 22.13, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.2844320347650064, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.993200687088463e-05, | |
| "loss": 0.4777, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.986043515602635e-05, | |
| "loss": 0.4541, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.978886344116805e-05, | |
| "loss": 0.4244, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.971729172630977e-05, | |
| "loss": 0.4365, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.964572001145149e-05, | |
| "loss": 0.397, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.22097741067409515, | |
| "eval_runtime": 1837.785, | |
| "eval_samples_per_second": 22.123, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.234683935032139, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.957414829659319e-05, | |
| "loss": 0.4083, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.950257658173491e-05, | |
| "loss": 0.3971, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.943100486687663e-05, | |
| "loss": 0.4026, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.935943315201832e-05, | |
| "loss": 0.3692, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.928786143716003e-05, | |
| "loss": 0.3632, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.1961178481578827, | |
| "eval_runtime": 1848.1771, | |
| "eval_samples_per_second": 21.998, | |
| "eval_steps_per_second": 1.375, | |
| "eval_wer": 0.20422678829047713, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.921628972230175e-05, | |
| "loss": 0.3853, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.914471800744346e-05, | |
| "loss": 0.3715, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.907314629258517e-05, | |
| "loss": 0.3551, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.900157457772689e-05, | |
| "loss": 0.3572, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.89300028628686e-05, | |
| "loss": 0.3393, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.179328054189682, | |
| "eval_runtime": 1838.2574, | |
| "eval_samples_per_second": 22.117, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.1848099481093003, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.885843114801031e-05, | |
| "loss": 0.3416, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.878685943315202e-05, | |
| "loss": 0.3352, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.871528771829374e-05, | |
| "loss": 0.3253, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.864371600343545e-05, | |
| "loss": 0.3485, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.857214428857716e-05, | |
| "loss": 0.32, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.16373108327388763, | |
| "eval_runtime": 1833.6704, | |
| "eval_samples_per_second": 22.172, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.1682431939090742, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.850057257371887e-05, | |
| "loss": 0.307, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.842900085886059e-05, | |
| "loss": 0.3086, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.83574291440023e-05, | |
| "loss": 0.3286, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.8285857429144e-05, | |
| "loss": 0.316, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.821428571428572e-05, | |
| "loss": 0.3074, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.15200646221637726, | |
| "eval_runtime": 1837.9323, | |
| "eval_samples_per_second": 22.121, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.15923470659472633, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.814271399942742e-05, | |
| "loss": 0.2964, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.807114228456914e-05, | |
| "loss": 0.2957, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.799957056971086e-05, | |
| "loss": 0.3022, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.792799885485256e-05, | |
| "loss": 0.2958, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.785642713999428e-05, | |
| "loss": 0.2941, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.14346471428871155, | |
| "eval_runtime": 1838.6876, | |
| "eval_samples_per_second": 22.112, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.15317701501330627, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.7784855425136e-05, | |
| "loss": 0.29, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.77132837102777e-05, | |
| "loss": 0.2799, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.764171199541942e-05, | |
| "loss": 0.2668, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.757014028056112e-05, | |
| "loss": 0.2791, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.749856856570284e-05, | |
| "loss": 0.2706, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.13907302916049957, | |
| "eval_runtime": 1834.6058, | |
| "eval_samples_per_second": 22.161, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.1468222296635539, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.742699685084456e-05, | |
| "loss": 0.2644, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.735542513598626e-05, | |
| "loss": 0.2713, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.728385342112798e-05, | |
| "loss": 0.2824, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.72122817062697e-05, | |
| "loss": 0.278, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.714070999141139e-05, | |
| "loss": 0.2704, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.1340305507183075, | |
| "eval_runtime": 1862.7031, | |
| "eval_samples_per_second": 21.827, | |
| "eval_steps_per_second": 1.365, | |
| "eval_wer": 0.13853885256344084, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.70691382765531e-05, | |
| "loss": 0.2611, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.699756656169482e-05, | |
| "loss": 0.2782, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.692599484683653e-05, | |
| "loss": 0.2643, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.685442313197824e-05, | |
| "loss": 0.2653, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.678285141711996e-05, | |
| "loss": 0.2526, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.1274126172065735, | |
| "eval_runtime": 1857.9682, | |
| "eval_samples_per_second": 21.883, | |
| "eval_steps_per_second": 1.368, | |
| "eval_wer": 0.13355623758437588, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.671127970226167e-05, | |
| "loss": 0.2553, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.663970798740338e-05, | |
| "loss": 0.2535, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.65681362725451e-05, | |
| "loss": 0.2453, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.64965645576868e-05, | |
| "loss": 0.2469, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.642499284282852e-05, | |
| "loss": 0.2508, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.1191219836473465, | |
| "eval_runtime": 1832.8794, | |
| "eval_samples_per_second": 22.182, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.12896890838182087, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.635342112797023e-05, | |
| "loss": 0.2551, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.628184941311195e-05, | |
| "loss": 0.2512, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.621027769825366e-05, | |
| "loss": 0.2456, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.613870598339537e-05, | |
| "loss": 0.2521, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.606713426853707e-05, | |
| "loss": 0.2372, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.12152421474456787, | |
| "eval_runtime": 1848.1442, | |
| "eval_samples_per_second": 21.999, | |
| "eval_steps_per_second": 1.375, | |
| "eval_wer": 0.12516711524468693, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.599556255367879e-05, | |
| "loss": 0.2433, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.592399083882049e-05, | |
| "loss": 0.2336, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.585241912396221e-05, | |
| "loss": 0.2385, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.578084740910393e-05, | |
| "loss": 0.2508, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.570927569424563e-05, | |
| "loss": 0.2416, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.11769524961709976, | |
| "eval_runtime": 1848.956, | |
| "eval_samples_per_second": 21.989, | |
| "eval_steps_per_second": 1.375, | |
| "eval_wer": 0.12456033898902516, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.563770397938735e-05, | |
| "loss": 0.2355, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.556613226452907e-05, | |
| "loss": 0.2244, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.549456054967077e-05, | |
| "loss": 0.2448, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.542298883481249e-05, | |
| "loss": 0.2161, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.535141711995421e-05, | |
| "loss": 0.2269, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.11093774437904358, | |
| "eval_runtime": 1839.5019, | |
| "eval_samples_per_second": 22.102, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.11907165750627548, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.527984540509591e-05, | |
| "loss": 0.2422, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.520827369023763e-05, | |
| "loss": 0.2282, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.513670197537933e-05, | |
| "loss": 0.2232, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.506513026052105e-05, | |
| "loss": 0.2306, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.499355854566277e-05, | |
| "loss": 0.2373, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.10600640624761581, | |
| "eval_runtime": 1834.0346, | |
| "eval_samples_per_second": 22.168, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.12017191154662483, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.492198683080447e-05, | |
| "loss": 0.2231, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.485041511594618e-05, | |
| "loss": 0.2246, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.47788434010879e-05, | |
| "loss": 0.2254, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.47072716862296e-05, | |
| "loss": 0.2219, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.463569997137132e-05, | |
| "loss": 0.2355, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.10465243458747864, | |
| "eval_runtime": 1852.5858, | |
| "eval_samples_per_second": 21.946, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.11860083941578273, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.456412825651303e-05, | |
| "loss": 0.2017, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.449255654165474e-05, | |
| "loss": 0.2042, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.442098482679645e-05, | |
| "loss": 0.2072, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.434941311193817e-05, | |
| "loss": 0.2192, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.427784139707988e-05, | |
| "loss": 0.2112, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.10814522206783295, | |
| "eval_runtime": 1831.3729, | |
| "eval_samples_per_second": 22.2, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.11226871376022518, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.42062696822216e-05, | |
| "loss": 0.2163, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.413469796736331e-05, | |
| "loss": 0.2007, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.40638419696536e-05, | |
| "loss": 0.291, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.399227025479531e-05, | |
| "loss": 0.1986, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.392069853993703e-05, | |
| "loss": 0.2099, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.10887959599494934, | |
| "eval_runtime": 1830.1738, | |
| "eval_samples_per_second": 22.215, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.11089150790193891, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.384912682507873e-05, | |
| "loss": 0.1992, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.377755511022045e-05, | |
| "loss": 0.1985, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 9.370598339536216e-05, | |
| "loss": 0.2215, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 9.363441168050386e-05, | |
| "loss": 0.2162, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.356283996564558e-05, | |
| "loss": 0.1878, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.10087338089942932, | |
| "eval_runtime": 1858.2211, | |
| "eval_samples_per_second": 21.88, | |
| "eval_steps_per_second": 1.368, | |
| "eval_wer": 0.11022934128268976, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.34912682507873e-05, | |
| "loss": 0.2084, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 9.3419696535929e-05, | |
| "loss": 0.1954, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.334812482107072e-05, | |
| "loss": 0.1952, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.327655310621242e-05, | |
| "loss": 0.1981, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.320498139135414e-05, | |
| "loss": 0.2194, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.09638988971710205, | |
| "eval_runtime": 1829.8997, | |
| "eval_samples_per_second": 22.218, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.11214282657025386, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 9.313340967649586e-05, | |
| "loss": 0.1932, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 9.306183796163756e-05, | |
| "loss": 0.1964, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.299026624677928e-05, | |
| "loss": 0.1976, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.2918694531921e-05, | |
| "loss": 0.1974, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.28471228170627e-05, | |
| "loss": 0.204, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.09526728093624115, | |
| "eval_runtime": 1821.2709, | |
| "eval_samples_per_second": 22.323, | |
| "eval_steps_per_second": 1.396, | |
| "eval_wer": 0.10509062618806035, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.277555110220442e-05, | |
| "loss": 0.1971, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 9.270397938734614e-05, | |
| "loss": 0.1933, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.263240767248784e-05, | |
| "loss": 0.2007, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 9.256083595762956e-05, | |
| "loss": 0.1852, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.248926424277126e-05, | |
| "loss": 0.184, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.09342432767152786, | |
| "eval_runtime": 1822.4754, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.10512839234505175, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.241769252791297e-05, | |
| "loss": 0.1968, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 9.234612081305468e-05, | |
| "loss": 0.199, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.22745490981964e-05, | |
| "loss": 0.1925, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.22029773833381e-05, | |
| "loss": 0.1885, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 9.213140566847982e-05, | |
| "loss": 0.1896, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.09680452197790146, | |
| "eval_runtime": 1836.4407, | |
| "eval_samples_per_second": 22.139, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.10365047673478842, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.205983395362153e-05, | |
| "loss": 0.1943, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.198826223876324e-05, | |
| "loss": 0.1973, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.191669052390496e-05, | |
| "loss": 0.1812, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.184511880904667e-05, | |
| "loss": 0.1905, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.177354709418838e-05, | |
| "loss": 0.1849, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.09168621897697449, | |
| "eval_runtime": 1825.9698, | |
| "eval_samples_per_second": 22.266, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.10383427203214655, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.17019753793301e-05, | |
| "loss": 0.1856, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.16304036644718e-05, | |
| "loss": 0.1903, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.155883194961352e-05, | |
| "loss": 0.1867, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.148726023475524e-05, | |
| "loss": 0.1895, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.141568851989693e-05, | |
| "loss": 0.1829, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.0906834751367569, | |
| "eval_runtime": 1832.098, | |
| "eval_samples_per_second": 22.191, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.10015836608498392, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9.134411680503865e-05, | |
| "loss": 0.1851, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.127254509018037e-05, | |
| "loss": 0.1844, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.120097337532207e-05, | |
| "loss": 0.1948, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.112940166046379e-05, | |
| "loss": 0.1849, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.10578299456055e-05, | |
| "loss": 0.1781, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.08980628848075867, | |
| "eval_runtime": 1869.4604, | |
| "eval_samples_per_second": 21.748, | |
| "eval_steps_per_second": 1.36, | |
| "eval_wer": 0.09970768994488659, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.098625823074721e-05, | |
| "loss": 0.1729, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.091468651588893e-05, | |
| "loss": 0.176, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.084311480103063e-05, | |
| "loss": 0.1723, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.077154308617235e-05, | |
| "loss": 0.1822, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 9.069997137131407e-05, | |
| "loss": 0.1838, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.08726300299167633, | |
| "eval_runtime": 1826.9498, | |
| "eval_samples_per_second": 22.254, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.10017095480398105, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.062839965645577e-05, | |
| "loss": 0.1856, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.055682794159749e-05, | |
| "loss": 0.1701, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.04852562267392e-05, | |
| "loss": 0.1702, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.041368451188091e-05, | |
| "loss": 0.1853, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 9.034211279702261e-05, | |
| "loss": 0.1868, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.08833219110965729, | |
| "eval_runtime": 1853.5163, | |
| "eval_samples_per_second": 21.935, | |
| "eval_steps_per_second": 1.371, | |
| "eval_wer": 0.09377840329723729, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.027054108216433e-05, | |
| "loss": 0.1733, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.019896936730604e-05, | |
| "loss": 0.1808, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 9.012739765244775e-05, | |
| "loss": 0.1803, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.005582593758947e-05, | |
| "loss": 0.1771, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.998496993987975e-05, | |
| "loss": 0.1888, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.08499713242053986, | |
| "eval_runtime": 1841.0851, | |
| "eval_samples_per_second": 22.083, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.09277382352126612, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.991339822502147e-05, | |
| "loss": 0.1792, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.984182651016319e-05, | |
| "loss": 0.1817, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.97702547953049e-05, | |
| "loss": 0.1721, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.969868308044661e-05, | |
| "loss": 0.1737, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.962711136558833e-05, | |
| "loss": 0.1767, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.08506972342729568, | |
| "eval_runtime": 1831.4551, | |
| "eval_samples_per_second": 22.199, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.09145704351416609, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.955625536787861e-05, | |
| "loss": 0.1746, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.948468365302033e-05, | |
| "loss": 0.1788, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.941311193816205e-05, | |
| "loss": 0.1702, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.934154022330375e-05, | |
| "loss": 0.1722, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.926996850844547e-05, | |
| "loss": 0.1759, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.0863996371626854, | |
| "eval_runtime": 1843.2484, | |
| "eval_samples_per_second": 22.057, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.09324464161175887, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.919839679358719e-05, | |
| "loss": 0.17, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.912682507872889e-05, | |
| "loss": 0.1683, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.905525336387061e-05, | |
| "loss": 0.1668, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.898368164901231e-05, | |
| "loss": 0.179, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.891210993415403e-05, | |
| "loss": 0.1778, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.08419219404459, | |
| "eval_runtime": 1830.5571, | |
| "eval_samples_per_second": 22.21, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.09128835467960451, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.884053821929575e-05, | |
| "loss": 0.1818, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.876896650443745e-05, | |
| "loss": 0.1713, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.869739478957916e-05, | |
| "loss": 0.1791, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 8.862582307472087e-05, | |
| "loss": 0.1677, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.855425135986258e-05, | |
| "loss": 0.1612, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.0830991342663765, | |
| "eval_runtime": 1842.2373, | |
| "eval_samples_per_second": 22.069, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.08729773075751358, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.84826796450043e-05, | |
| "loss": 0.1665, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.841110793014601e-05, | |
| "loss": 0.1753, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.833953621528772e-05, | |
| "loss": 0.1747, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.826796450042943e-05, | |
| "loss": 0.1614, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.819639278557115e-05, | |
| "loss": 0.163, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.0796523168683052, | |
| "eval_runtime": 1835.7459, | |
| "eval_samples_per_second": 22.147, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.09395968085079598, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.812482107071286e-05, | |
| "loss": 0.1609, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.805324935585457e-05, | |
| "loss": 0.1644, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.798167764099629e-05, | |
| "loss": 0.1716, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.7910105926138e-05, | |
| "loss": 0.1835, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.783853421127971e-05, | |
| "loss": 0.1618, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.07980114221572876, | |
| "eval_runtime": 1844.6868, | |
| "eval_samples_per_second": 22.04, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.09016040545746146, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.776696249642142e-05, | |
| "loss": 0.1673, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.769539078156313e-05, | |
| "loss": 0.1619, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.762381906670484e-05, | |
| "loss": 0.1582, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.755224735184656e-05, | |
| "loss": 0.1607, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.748067563698826e-05, | |
| "loss": 0.1576, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.08184105157852173, | |
| "eval_runtime": 1833.8868, | |
| "eval_samples_per_second": 22.17, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.08827965083928989, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.740910392212998e-05, | |
| "loss": 0.1562, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.733753220727168e-05, | |
| "loss": 0.1615, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.72659604924134e-05, | |
| "loss": 0.1565, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.719438877755512e-05, | |
| "loss": 0.1617, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.712281706269682e-05, | |
| "loss": 0.1585, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.08081966638565063, | |
| "eval_runtime": 1833.0686, | |
| "eval_samples_per_second": 22.18, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.08793975542636732, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.705124534783854e-05, | |
| "loss": 0.1584, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.697967363298026e-05, | |
| "loss": 0.158, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.690810191812196e-05, | |
| "loss": 0.1614, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.683653020326368e-05, | |
| "loss": 0.155, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.67649584884054e-05, | |
| "loss": 0.1519, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.08036702871322632, | |
| "eval_runtime": 1843.0044, | |
| "eval_samples_per_second": 22.06, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.08677152230343345, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.66933867735471e-05, | |
| "loss": 0.1633, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.662181505868882e-05, | |
| "loss": 0.1504, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.655024334383052e-05, | |
| "loss": 0.1615, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.647867162897223e-05, | |
| "loss": 0.1427, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.640709991411394e-05, | |
| "loss": 0.1504, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.07900594919919968, | |
| "eval_runtime": 1832.7229, | |
| "eval_samples_per_second": 22.184, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.08337760366180658, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.633624391640424e-05, | |
| "loss": 0.1581, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.626467220154594e-05, | |
| "loss": 0.1542, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.619310048668766e-05, | |
| "loss": 0.153, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.612152877182938e-05, | |
| "loss": 0.1498, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.604995705697108e-05, | |
| "loss": 0.1518, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.07715685665607452, | |
| "eval_runtime": 1824.649, | |
| "eval_samples_per_second": 22.282, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.08321395031484387, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.59783853421128e-05, | |
| "loss": 0.1454, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.59068136272545e-05, | |
| "loss": 0.1567, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.583524191239622e-05, | |
| "loss": 0.1534, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 8.576367019753794e-05, | |
| "loss": 0.1426, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.569209848267964e-05, | |
| "loss": 0.1521, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.07570967823266983, | |
| "eval_runtime": 1824.6871, | |
| "eval_samples_per_second": 22.282, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.08204571719190999, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.562052676782136e-05, | |
| "loss": 0.1585, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.554895505296308e-05, | |
| "loss": 0.1637, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.547738333810478e-05, | |
| "loss": 0.1441, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.54058116232465e-05, | |
| "loss": 0.1459, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.533423990838822e-05, | |
| "loss": 0.1459, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.07781235128641129, | |
| "eval_runtime": 1842.5856, | |
| "eval_samples_per_second": 22.065, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.08145152965524534, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.526266819352992e-05, | |
| "loss": 0.1523, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.519109647867163e-05, | |
| "loss": 0.1515, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 8.511952476381335e-05, | |
| "loss": 0.1514, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.504795304895505e-05, | |
| "loss": 0.1548, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.497638133409677e-05, | |
| "loss": 0.1436, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.07773680984973907, | |
| "eval_runtime": 1826.4234, | |
| "eval_samples_per_second": 22.26, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.0808095049863916, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.490480961923848e-05, | |
| "loss": 0.1491, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.483323790438019e-05, | |
| "loss": 0.1495, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.47616661895219e-05, | |
| "loss": 0.1467, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.469009447466361e-05, | |
| "loss": 0.1497, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.461852275980533e-05, | |
| "loss": 0.1475, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.07359211146831512, | |
| "eval_runtime": 1836.1706, | |
| "eval_samples_per_second": 22.142, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.079991238251578, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.454695104494705e-05, | |
| "loss": 0.1433, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.447537933008875e-05, | |
| "loss": 0.1645, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.440452333237905e-05, | |
| "loss": 0.1543, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.433295161752076e-05, | |
| "loss": 0.1443, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.426137990266247e-05, | |
| "loss": 0.1448, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.07584570348262787, | |
| "eval_runtime": 1843.0558, | |
| "eval_samples_per_second": 22.06, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.08089007278797324, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.418980818780419e-05, | |
| "loss": 0.1494, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.41182364729459e-05, | |
| "loss": 0.1487, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.404666475808761e-05, | |
| "loss": 0.1528, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 8.397509304322933e-05, | |
| "loss": 0.1502, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 8.390352132837103e-05, | |
| "loss": 0.1602, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.0721326395869255, | |
| "eval_runtime": 1827.4452, | |
| "eval_samples_per_second": 22.248, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.0802379771439218, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 8.383194961351273e-05, | |
| "loss": 0.1444, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.376037789865445e-05, | |
| "loss": 0.1497, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 8.368880618379617e-05, | |
| "loss": 0.1493, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 8.361723446893787e-05, | |
| "loss": 0.1542, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 8.354566275407959e-05, | |
| "loss": 0.1417, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.07162601500749588, | |
| "eval_runtime": 1849.9735, | |
| "eval_samples_per_second": 21.977, | |
| "eval_steps_per_second": 1.374, | |
| "eval_wer": 0.07949020723549213, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 8.347409103922131e-05, | |
| "loss": 0.1386, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 8.340251932436301e-05, | |
| "loss": 0.1409, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 8.333094760950473e-05, | |
| "loss": 0.1427, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 8.325937589464645e-05, | |
| "loss": 0.1483, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 8.318780417978815e-05, | |
| "loss": 0.145, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.07193588465452194, | |
| "eval_runtime": 1827.8965, | |
| "eval_samples_per_second": 22.243, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.07910247469038045, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 8.311623246492987e-05, | |
| "loss": 0.142, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 8.304466075007157e-05, | |
| "loss": 0.1499, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 8.297308903521329e-05, | |
| "loss": 0.1418, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 8.290151732035501e-05, | |
| "loss": 0.1393, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.282994560549671e-05, | |
| "loss": 0.1456, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 0.07210829854011536, | |
| "eval_runtime": 1824.5675, | |
| "eval_samples_per_second": 22.283, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.08134830215946885, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 8.275837389063842e-05, | |
| "loss": 0.1525, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 8.268680217578013e-05, | |
| "loss": 0.1495, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 8.261523046092184e-05, | |
| "loss": 0.1434, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 8.254365874606356e-05, | |
| "loss": 0.151, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 8.247208703120527e-05, | |
| "loss": 0.1391, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.06869999319314957, | |
| "eval_runtime": 1830.3685, | |
| "eval_samples_per_second": 22.212, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.07798711418723453, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 8.240123103349556e-05, | |
| "loss": 0.1403, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 8.232965931863727e-05, | |
| "loss": 0.1376, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 8.225808760377899e-05, | |
| "loss": 0.1373, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 8.21865158889207e-05, | |
| "loss": 0.1396, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 8.211494417406241e-05, | |
| "loss": 0.1431, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.0726616308093071, | |
| "eval_runtime": 1835.8433, | |
| "eval_samples_per_second": 22.146, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.07695735697326911, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 8.204337245920413e-05, | |
| "loss": 0.1426, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.197180074434584e-05, | |
| "loss": 0.1384, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 8.190022902948755e-05, | |
| "loss": 0.1416, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 8.182865731462927e-05, | |
| "loss": 0.1469, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.175780131691955e-05, | |
| "loss": 0.24, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.06985440850257874, | |
| "eval_runtime": 1831.656, | |
| "eval_samples_per_second": 22.197, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.07694728599807141, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.168622960206127e-05, | |
| "loss": 0.1502, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 8.161465788720299e-05, | |
| "loss": 0.1452, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.154308617234469e-05, | |
| "loss": 0.1457, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.147151445748641e-05, | |
| "loss": 0.1475, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 8.139994274262811e-05, | |
| "loss": 0.1333, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.07012754678726196, | |
| "eval_runtime": 1827.6224, | |
| "eval_samples_per_second": 22.246, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.07701022959305708, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 8.132837102776983e-05, | |
| "loss": 0.1453, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 8.125679931291155e-05, | |
| "loss": 0.1438, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.118522759805325e-05, | |
| "loss": 0.1467, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 8.111365588319496e-05, | |
| "loss": 0.1407, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 8.104208416833668e-05, | |
| "loss": 0.1305, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 0.07148761302232742, | |
| "eval_runtime": 1833.5641, | |
| "eval_samples_per_second": 22.174, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.07564813019756736, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.097051245347838e-05, | |
| "loss": 0.1346, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 8.08989407386201e-05, | |
| "loss": 0.1427, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 8.082736902376182e-05, | |
| "loss": 0.1326, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 8.075579730890352e-05, | |
| "loss": 0.1363, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 8.068422559404524e-05, | |
| "loss": 0.1366, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 0.0700342133641243, | |
| "eval_runtime": 1835.3068, | |
| "eval_samples_per_second": 22.153, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.07638331138699989, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.061265387918695e-05, | |
| "loss": 0.136, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 8.054108216432866e-05, | |
| "loss": 0.1242, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 8.046951044947038e-05, | |
| "loss": 0.1295, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 8.03979387346121e-05, | |
| "loss": 0.1428, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 8.03263670197538e-05, | |
| "loss": 0.1354, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.06739675253629684, | |
| "eval_runtime": 1831.4671, | |
| "eval_samples_per_second": 22.199, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.07430365500867363, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 8.025479530489552e-05, | |
| "loss": 0.1394, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 8.018322359003722e-05, | |
| "loss": 0.134, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 8.011165187517892e-05, | |
| "loss": 0.1355, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.004008016032064e-05, | |
| "loss": 0.14, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.996850844546236e-05, | |
| "loss": 0.1269, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 0.06894645094871521, | |
| "eval_runtime": 1841.6647, | |
| "eval_samples_per_second": 22.076, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.07649409211417464, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 7.989693673060406e-05, | |
| "loss": 0.1331, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.982536501574578e-05, | |
| "loss": 0.129, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.975379330088748e-05, | |
| "loss": 0.143, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 7.96822215860292e-05, | |
| "loss": 0.1214, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 7.961064987117092e-05, | |
| "loss": 0.1259, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.07028140127658844, | |
| "eval_runtime": 1826.7268, | |
| "eval_samples_per_second": 22.257, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.07727207494819742, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.953907815631262e-05, | |
| "loss": 0.1379, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 7.946750644145434e-05, | |
| "loss": 0.1325, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.939593472659606e-05, | |
| "loss": 0.1195, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 7.932436301173776e-05, | |
| "loss": 0.1348, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 7.925279129687948e-05, | |
| "loss": 0.1246, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 0.06716904789209366, | |
| "eval_runtime": 1820.0988, | |
| "eval_samples_per_second": 22.338, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.07396627733955048, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 7.91812195820212e-05, | |
| "loss": 0.137, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 7.91096478671629e-05, | |
| "loss": 0.124, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 7.903807615230461e-05, | |
| "loss": 0.1296, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 7.896650443744632e-05, | |
| "loss": 0.121, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.889493272258803e-05, | |
| "loss": 0.1281, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.06832349300384521, | |
| "eval_runtime": 1831.42, | |
| "eval_samples_per_second": 22.2, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.07315808157993459, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 7.882336100772975e-05, | |
| "loss": 0.1295, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 7.875178929287146e-05, | |
| "loss": 0.124, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 7.868021757801317e-05, | |
| "loss": 0.1229, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 7.860864586315489e-05, | |
| "loss": 0.1368, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 7.853707414829659e-05, | |
| "loss": 0.1356, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 0.06861495971679688, | |
| "eval_runtime": 1860.0665, | |
| "eval_samples_per_second": 21.858, | |
| "eval_steps_per_second": 1.367, | |
| "eval_wer": 0.07244556008469691, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.846550243343831e-05, | |
| "loss": 0.1391, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 7.839393071858003e-05, | |
| "loss": 0.1353, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 7.832235900372173e-05, | |
| "loss": 0.1195, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 7.825078728886345e-05, | |
| "loss": 0.1298, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 7.817921557400516e-05, | |
| "loss": 0.1258, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 0.06629330664873123, | |
| "eval_runtime": 1825.3938, | |
| "eval_samples_per_second": 22.273, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.07183123059763685, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 7.810764385914687e-05, | |
| "loss": 0.1258, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 7.803607214428859e-05, | |
| "loss": 0.1279, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 7.79645004294303e-05, | |
| "loss": 0.1271, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 7.7892928714572e-05, | |
| "loss": 0.1198, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 7.782135699971371e-05, | |
| "loss": 0.1305, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_loss": 0.06801504641771317, | |
| "eval_runtime": 1821.9107, | |
| "eval_samples_per_second": 22.316, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.07151399487890911, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 7.774978528485543e-05, | |
| "loss": 0.1219, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 7.767821356999713e-05, | |
| "loss": 0.1175, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 7.760664185513885e-05, | |
| "loss": 0.1304, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 7.753507014028057e-05, | |
| "loss": 0.1245, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 7.746349842542227e-05, | |
| "loss": 0.1274, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 0.06824016571044922, | |
| "eval_runtime": 1834.2676, | |
| "eval_samples_per_second": 22.165, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.07040618760716147, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 7.739264242771257e-05, | |
| "loss": 0.1333, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 7.732107071285429e-05, | |
| "loss": 0.1309, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 7.724949899799599e-05, | |
| "loss": 0.1416, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 7.717792728313771e-05, | |
| "loss": 0.1192, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 7.7107071285428e-05, | |
| "loss": 0.2169, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.06627916544675827, | |
| "eval_runtime": 1849.2194, | |
| "eval_samples_per_second": 21.986, | |
| "eval_steps_per_second": 1.375, | |
| "eval_wer": 0.07158449170529305, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 7.703549957056971e-05, | |
| "loss": 0.1297, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 7.696392785571143e-05, | |
| "loss": 0.1176, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 7.689235614085314e-05, | |
| "loss": 0.1317, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 7.682078442599485e-05, | |
| "loss": 0.1222, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 7.674921271113657e-05, | |
| "loss": 0.1301, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 0.06541716307401657, | |
| "eval_runtime": 1840.6854, | |
| "eval_samples_per_second": 22.088, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.07069824588789494, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 7.667764099627827e-05, | |
| "loss": 0.1323, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 7.660606928141999e-05, | |
| "loss": 0.1259, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 7.65344975665617e-05, | |
| "loss": 0.123, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 7.646292585170341e-05, | |
| "loss": 0.1292, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 7.639135413684513e-05, | |
| "loss": 0.1242, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 0.06527630984783173, | |
| "eval_runtime": 1823.971, | |
| "eval_samples_per_second": 22.29, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.0702475697477976, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 7.631978242198683e-05, | |
| "loss": 0.1217, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 7.624892642427713e-05, | |
| "loss": 0.1175, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.617735470941885e-05, | |
| "loss": 0.1225, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 7.610578299456055e-05, | |
| "loss": 0.1302, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 7.603421127970227e-05, | |
| "loss": 0.1284, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 0.06405790895223618, | |
| "eval_runtime": 1831.0943, | |
| "eval_samples_per_second": 22.204, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.0720351678453904, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 7.596263956484397e-05, | |
| "loss": 0.1215, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 7.589106784998569e-05, | |
| "loss": 0.1301, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 7.58194961351274e-05, | |
| "loss": 0.1175, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 7.574792442026911e-05, | |
| "loss": 0.1377, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 7.567635270541083e-05, | |
| "loss": 0.1204, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 0.06423558294773102, | |
| "eval_runtime": 1863.1858, | |
| "eval_samples_per_second": 21.821, | |
| "eval_steps_per_second": 1.364, | |
| "eval_wer": 0.07310017347254778, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 7.560478099055253e-05, | |
| "loss": 0.1235, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.553320927569425e-05, | |
| "loss": 0.1278, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 7.546163756083597e-05, | |
| "loss": 0.1265, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.539006584597767e-05, | |
| "loss": 0.1217, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 7.531849413111939e-05, | |
| "loss": 0.1256, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 0.06451215595006943, | |
| "eval_runtime": 1828.5015, | |
| "eval_samples_per_second": 22.235, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.07717640068381922, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 7.524692241626111e-05, | |
| "loss": 0.1182, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 7.517535070140281e-05, | |
| "loss": 0.1295, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 7.510377898654453e-05, | |
| "loss": 0.1261, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 7.503220727168623e-05, | |
| "loss": 0.1081, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 7.496063555682794e-05, | |
| "loss": 0.1147, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 0.06585133075714111, | |
| "eval_runtime": 1835.8326, | |
| "eval_samples_per_second": 22.146, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.07339474949708068, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 7.488906384196966e-05, | |
| "loss": 0.1319, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 7.481749212711137e-05, | |
| "loss": 0.1184, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 7.474592041225308e-05, | |
| "loss": 0.1237, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 7.46743486973948e-05, | |
| "loss": 0.1237, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 7.460349269968509e-05, | |
| "loss": 0.112, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 0.06693475693464279, | |
| "eval_runtime": 1835.6276, | |
| "eval_samples_per_second": 22.149, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.07278293775382004, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 7.45319209848268e-05, | |
| "loss": 0.1217, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 7.446034926996851e-05, | |
| "loss": 0.1224, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.438877755511022e-05, | |
| "loss": 0.1145, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.431720584025193e-05, | |
| "loss": 0.118, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.424563412539365e-05, | |
| "loss": 0.1153, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 0.06470324099063873, | |
| "eval_runtime": 1836.0618, | |
| "eval_samples_per_second": 22.144, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.07375730460419809, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.417406241053536e-05, | |
| "loss": 0.114, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.410249069567707e-05, | |
| "loss": 0.2068, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.403091898081879e-05, | |
| "loss": 0.1179, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.39593472659605e-05, | |
| "loss": 0.1168, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 7.388777555110221e-05, | |
| "loss": 0.1169, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "eval_loss": 0.06484906375408173, | |
| "eval_runtime": 1836.4586, | |
| "eval_samples_per_second": 22.139, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.06811252300588397, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 7.381620383624393e-05, | |
| "loss": 0.1144, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 7.374463212138563e-05, | |
| "loss": 0.1036, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 7.367306040652734e-05, | |
| "loss": 0.1198, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 7.360148869166906e-05, | |
| "loss": 0.1175, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 7.352991697681076e-05, | |
| "loss": 0.1145, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_loss": 0.06532098352909088, | |
| "eval_runtime": 1829.5036, | |
| "eval_samples_per_second": 22.223, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.06864376694756295, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 7.345834526195248e-05, | |
| "loss": 0.1169, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 7.33867735470942e-05, | |
| "loss": 0.1157, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 7.33152018322359e-05, | |
| "loss": 0.1128, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 7.324363011737762e-05, | |
| "loss": 0.1159, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 7.317205840251932e-05, | |
| "loss": 0.108, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 0.06431237608194351, | |
| "eval_runtime": 1829.3137, | |
| "eval_samples_per_second": 22.225, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.06877972511273198, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 7.310048668766104e-05, | |
| "loss": 0.1091, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 7.302891497280276e-05, | |
| "loss": 0.1136, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 7.295734325794446e-05, | |
| "loss": 0.1111, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 7.288577154308618e-05, | |
| "loss": 0.1138, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 7.28141998282279e-05, | |
| "loss": 0.1142, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_loss": 0.06367102265357971, | |
| "eval_runtime": 1829.8855, | |
| "eval_samples_per_second": 22.218, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.07031051334278327, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 7.27426281133696e-05, | |
| "loss": 0.127, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 7.267105639851132e-05, | |
| "loss": 0.1199, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 7.259948468365302e-05, | |
| "loss": 0.1182, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 7.252791296879473e-05, | |
| "loss": 0.1191, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 7.245634125393644e-05, | |
| "loss": 0.1126, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 0.06367914378643036, | |
| "eval_runtime": 1827.8803, | |
| "eval_samples_per_second": 22.243, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.0684297587246117, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 7.238476953907816e-05, | |
| "loss": 0.1098, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 7.231319782421987e-05, | |
| "loss": 0.1155, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.224162610936158e-05, | |
| "loss": 0.1152, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 7.21700543945033e-05, | |
| "loss": 0.111, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 7.2098482679645e-05, | |
| "loss": 0.118, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "eval_loss": 0.06473113596439362, | |
| "eval_runtime": 1830.0876, | |
| "eval_samples_per_second": 22.216, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.06685365110617074, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 7.202691096478672e-05, | |
| "loss": 0.1156, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 7.195533924992843e-05, | |
| "loss": 0.1139, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 7.188376753507014e-05, | |
| "loss": 0.1219, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 7.181219582021186e-05, | |
| "loss": 0.1097, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 7.174062410535357e-05, | |
| "loss": 0.1128, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 0.0639992505311966, | |
| "eval_runtime": 1833.2906, | |
| "eval_samples_per_second": 22.177, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.06799670679111035, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 7.166905239049528e-05, | |
| "loss": 0.1086, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 7.1597480675637e-05, | |
| "loss": 0.1108, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 7.15259089607787e-05, | |
| "loss": 0.1122, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 7.145433724592041e-05, | |
| "loss": 0.1107, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 7.138276553106213e-05, | |
| "loss": 0.1159, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "eval_loss": 0.061267126351594925, | |
| "eval_runtime": 1834.3808, | |
| "eval_samples_per_second": 22.164, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.0671734045686979, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 7.131119381620383e-05, | |
| "loss": 0.1188, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 7.123962210134555e-05, | |
| "loss": 0.1147, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 7.116805038648727e-05, | |
| "loss": 0.1133, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 7.109647867162897e-05, | |
| "loss": 0.1054, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 7.102562267391927e-05, | |
| "loss": 0.1149, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 0.06170805171132088, | |
| "eval_runtime": 1849.5649, | |
| "eval_samples_per_second": 21.982, | |
| "eval_steps_per_second": 1.374, | |
| "eval_wer": 0.06595985205737434, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.095405095906098e-05, | |
| "loss": 0.1085, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 7.088247924420269e-05, | |
| "loss": 0.113, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 7.08109075293444e-05, | |
| "loss": 0.1109, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 7.07400515316347e-05, | |
| "loss": 0.119, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 7.066847981677641e-05, | |
| "loss": 0.1111, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_loss": 0.06057364493608475, | |
| "eval_runtime": 1834.2021, | |
| "eval_samples_per_second": 22.166, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.06644325886686422, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 7.05976238190667e-05, | |
| "loss": 0.1116, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 7.052605210420842e-05, | |
| "loss": 0.1091, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 7.045448038935013e-05, | |
| "loss": 0.1172, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 7.038290867449184e-05, | |
| "loss": 0.1124, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 7.031133695963356e-05, | |
| "loss": 0.1162, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 0.06048477068543434, | |
| "eval_runtime": 1824.8362, | |
| "eval_samples_per_second": 22.28, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.06550917591727701, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 7.023976524477526e-05, | |
| "loss": 0.1128, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 7.016819352991698e-05, | |
| "loss": 0.1065, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 7.00966218150587e-05, | |
| "loss": 0.1165, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 7.00250501002004e-05, | |
| "loss": 0.1053, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 6.995347838534212e-05, | |
| "loss": 0.1087, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "eval_loss": 0.061376214027404785, | |
| "eval_runtime": 1852.9997, | |
| "eval_samples_per_second": 21.941, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.06715326261830248, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 6.988190667048383e-05, | |
| "loss": 0.1106, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 6.981033495562554e-05, | |
| "loss": 0.1112, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.973876324076726e-05, | |
| "loss": 0.1169, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 6.966719152590897e-05, | |
| "loss": 0.1203, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 6.959561981105067e-05, | |
| "loss": 0.1161, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "eval_loss": 0.061812758445739746, | |
| "eval_runtime": 1827.0699, | |
| "eval_samples_per_second": 22.253, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.06744783864283538, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 6.952404809619239e-05, | |
| "loss": 0.1153, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 6.945247638133409e-05, | |
| "loss": 0.1109, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 6.938090466647581e-05, | |
| "loss": 0.1127, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 6.930933295161753e-05, | |
| "loss": 0.1096, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6.923776123675923e-05, | |
| "loss": 0.1093, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_loss": 0.06167362630367279, | |
| "eval_runtime": 1837.6169, | |
| "eval_samples_per_second": 22.125, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.06762659845259467, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 6.916618952190095e-05, | |
| "loss": 0.1199, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 6.909461780704267e-05, | |
| "loss": 0.1124, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 6.902304609218437e-05, | |
| "loss": 0.1161, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 6.895147437732609e-05, | |
| "loss": 0.1062, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 6.88799026624678e-05, | |
| "loss": 0.1157, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "eval_loss": 0.06186460331082344, | |
| "eval_runtime": 1841.4816, | |
| "eval_samples_per_second": 22.078, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.06525740153733436, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.880833094760951e-05, | |
| "loss": 0.1074, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 6.873675923275123e-05, | |
| "loss": 0.1061, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 6.866518751789293e-05, | |
| "loss": 0.1043, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 6.859361580303464e-05, | |
| "loss": 0.1083, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 6.852204408817635e-05, | |
| "loss": 0.1077, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "eval_loss": 0.06055865064263344, | |
| "eval_runtime": 1830.9807, | |
| "eval_samples_per_second": 22.205, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.06538832421490454, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 6.845047237331807e-05, | |
| "loss": 0.1182, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 6.837890065845977e-05, | |
| "loss": 0.1134, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 6.830732894360149e-05, | |
| "loss": 0.1127, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 6.82357572287432e-05, | |
| "loss": 0.1073, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 6.816418551388491e-05, | |
| "loss": 0.1059, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 0.059741489589214325, | |
| "eval_runtime": 1828.9602, | |
| "eval_samples_per_second": 22.23, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.06325075972919147, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 6.809261379902663e-05, | |
| "loss": 0.115, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 6.802104208416834e-05, | |
| "loss": 0.1092, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 6.794947036931005e-05, | |
| "loss": 0.1034, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 6.787789865445177e-05, | |
| "loss": 0.1136, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 6.780632693959347e-05, | |
| "loss": 0.1031, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_loss": 0.06078292056918144, | |
| "eval_runtime": 1866.6566, | |
| "eval_samples_per_second": 21.781, | |
| "eval_steps_per_second": 1.362, | |
| "eval_wer": 0.06377193269567276, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 6.773475522473519e-05, | |
| "loss": 0.1193, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.766318350987691e-05, | |
| "loss": 0.1079, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 6.759161179501861e-05, | |
| "loss": 0.1023, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 6.752004008016032e-05, | |
| "loss": 0.1042, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 6.744846836530204e-05, | |
| "loss": 0.109, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 0.05950151011347771, | |
| "eval_runtime": 1834.7165, | |
| "eval_samples_per_second": 22.16, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.06319536936560409, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.737689665044374e-05, | |
| "loss": 0.1063, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 6.730532493558546e-05, | |
| "loss": 0.1107, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 6.723375322072718e-05, | |
| "loss": 0.1036, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 6.716218150586888e-05, | |
| "loss": 0.1077, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 6.70906097910106e-05, | |
| "loss": 0.1009, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 0.05973907560110092, | |
| "eval_runtime": 1827.5948, | |
| "eval_samples_per_second": 22.246, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.06582389389220532, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 6.70190380761523e-05, | |
| "loss": 0.0962, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 6.694746636129402e-05, | |
| "loss": 0.1076, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 6.687589464643574e-05, | |
| "loss": 0.1036, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 6.680432293157744e-05, | |
| "loss": 0.1038, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 6.673275121671916e-05, | |
| "loss": 0.1008, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_loss": 0.06024264171719551, | |
| "eval_runtime": 1837.0153, | |
| "eval_samples_per_second": 22.132, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.06741510797344284, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 6.666117950186088e-05, | |
| "loss": 0.11, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 6.658960778700258e-05, | |
| "loss": 0.1085, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 6.65180360721443e-05, | |
| "loss": 0.1, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 6.644646435728602e-05, | |
| "loss": 0.1018, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 6.63748926424277e-05, | |
| "loss": 0.0952, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 0.06037185713648796, | |
| "eval_runtime": 1831.1047, | |
| "eval_samples_per_second": 22.204, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.06767443558478377, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 6.630332092756942e-05, | |
| "loss": 0.1027, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 6.623174921271114e-05, | |
| "loss": 0.1049, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 6.616017749785285e-05, | |
| "loss": 0.1009, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 6.608860578299456e-05, | |
| "loss": 0.106, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 6.601703406813628e-05, | |
| "loss": 0.1084, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_loss": 0.06061859056353569, | |
| "eval_runtime": 1826.5979, | |
| "eval_samples_per_second": 22.258, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.06716081584970077, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 6.594546235327798e-05, | |
| "loss": 0.1148, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 6.58738906384197e-05, | |
| "loss": 0.1044, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 6.58023189235614e-05, | |
| "loss": 0.1055, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 6.57314629258517e-05, | |
| "loss": 0.1085, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 6.565989121099342e-05, | |
| "loss": 0.1061, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "eval_loss": 0.057925790548324585, | |
| "eval_runtime": 1834.2973, | |
| "eval_samples_per_second": 22.165, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.0653656645207097, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 6.558831949613512e-05, | |
| "loss": 0.0946, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 6.551674778127684e-05, | |
| "loss": 0.1019, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 6.544517606641856e-05, | |
| "loss": 0.1018, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 6.537360435156026e-05, | |
| "loss": 0.1043, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 6.530203263670198e-05, | |
| "loss": 0.0968, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_loss": 0.06070750579237938, | |
| "eval_runtime": 1826.5864, | |
| "eval_samples_per_second": 22.258, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.06663964288321948, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 6.52304609218437e-05, | |
| "loss": 0.1059, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 6.51588892069854e-05, | |
| "loss": 0.0938, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 6.508731749212711e-05, | |
| "loss": 0.1009, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 6.501574577726882e-05, | |
| "loss": 0.1062, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 6.494417406241053e-05, | |
| "loss": 0.1025, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "eval_loss": 0.059405963867902756, | |
| "eval_runtime": 1821.8333, | |
| "eval_samples_per_second": 22.317, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.06549406945448046, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 6.487260234755225e-05, | |
| "loss": 0.1015, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 6.480103063269396e-05, | |
| "loss": 0.1087, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 6.473017463498425e-05, | |
| "loss": 0.2055, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 6.465860292012596e-05, | |
| "loss": 0.1011, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 6.458703120526768e-05, | |
| "loss": 0.1086, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 0.05971784517168999, | |
| "eval_runtime": 1843.6536, | |
| "eval_samples_per_second": 22.052, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.06772730820457172, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 6.451545949040939e-05, | |
| "loss": 0.0976, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 6.44438877755511e-05, | |
| "loss": 0.1045, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 6.437231606069282e-05, | |
| "loss": 0.1013, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 6.430074434583453e-05, | |
| "loss": 0.1036, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 6.422917263097624e-05, | |
| "loss": 0.1007, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "eval_loss": 0.05899954214692116, | |
| "eval_runtime": 1841.1238, | |
| "eval_samples_per_second": 22.083, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.0632054403408018, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 6.415760091611796e-05, | |
| "loss": 0.0999, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 6.408602920125967e-05, | |
| "loss": 0.1078, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 6.401445748640138e-05, | |
| "loss": 0.1058, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 6.394288577154309e-05, | |
| "loss": 0.0997, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 6.38713140566848e-05, | |
| "loss": 0.0996, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_loss": 0.059191133826971054, | |
| "eval_runtime": 1826.6594, | |
| "eval_samples_per_second": 22.258, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.06325831296058976, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 6.379974234182652e-05, | |
| "loss": 0.1056, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 6.372817062696823e-05, | |
| "loss": 0.0999, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 6.365659891210993e-05, | |
| "loss": 0.1004, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 6.358502719725165e-05, | |
| "loss": 0.1077, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 6.351345548239335e-05, | |
| "loss": 0.1041, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_loss": 0.05928120017051697, | |
| "eval_runtime": 1867.3469, | |
| "eval_samples_per_second": 21.773, | |
| "eval_steps_per_second": 1.361, | |
| "eval_wer": 0.06371654233208537, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 6.344188376753507e-05, | |
| "loss": 0.1078, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 6.337031205267679e-05, | |
| "loss": 0.1053, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 6.329874033781849e-05, | |
| "loss": 0.1038, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 6.322716862296021e-05, | |
| "loss": 0.1004, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 6.315559690810193e-05, | |
| "loss": 0.1071, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "eval_loss": 0.057574424892663956, | |
| "eval_runtime": 1833.1263, | |
| "eval_samples_per_second": 22.179, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.06268930286191937, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 6.308402519324363e-05, | |
| "loss": 0.102, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 6.301245347838535e-05, | |
| "loss": 0.0972, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 6.294088176352707e-05, | |
| "loss": 0.0962, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 6.286931004866877e-05, | |
| "loss": 0.0984, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 6.279773833381049e-05, | |
| "loss": 0.1073, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "eval_loss": 0.05905884504318237, | |
| "eval_runtime": 1821.1212, | |
| "eval_samples_per_second": 22.325, | |
| "eval_steps_per_second": 1.396, | |
| "eval_wer": 0.06369640038168996, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 6.272616661895219e-05, | |
| "loss": 0.1021, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 6.265459490409391e-05, | |
| "loss": 0.1064, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 6.258302318923561e-05, | |
| "loss": 0.105, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 6.251145147437733e-05, | |
| "loss": 0.1034, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 6.243987975951904e-05, | |
| "loss": 0.1086, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 0.058083437383174896, | |
| "eval_runtime": 1830.553, | |
| "eval_samples_per_second": 22.21, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.061944050697289144, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 6.236830804466075e-05, | |
| "loss": 0.0998, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 6.229673632980246e-05, | |
| "loss": 0.0936, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 6.222516461494417e-05, | |
| "loss": 0.099, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 6.215359290008589e-05, | |
| "loss": 0.1016, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 6.208273690237618e-05, | |
| "loss": 0.1043, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_loss": 0.0582878552377224, | |
| "eval_runtime": 1836.9478, | |
| "eval_samples_per_second": 22.133, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.06125922438384515, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 6.201116518751789e-05, | |
| "loss": 0.0929, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 6.193959347265961e-05, | |
| "loss": 0.0963, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 6.186802175780131e-05, | |
| "loss": 0.1012, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 6.179645004294303e-05, | |
| "loss": 0.096, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 6.172487832808475e-05, | |
| "loss": 0.1037, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "eval_loss": 0.058865148574113846, | |
| "eval_runtime": 1833.3568, | |
| "eval_samples_per_second": 22.176, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.06140525352421188, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 6.165330661322645e-05, | |
| "loss": 0.1048, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 6.158173489836817e-05, | |
| "loss": 0.105, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 6.151016318350989e-05, | |
| "loss": 0.1032, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 6.14385914686516e-05, | |
| "loss": 0.1073, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 6.136701975379331e-05, | |
| "loss": 0.1008, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 0.057612381875514984, | |
| "eval_runtime": 1827.0037, | |
| "eval_samples_per_second": 22.253, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.060378014054045887, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 6.129544803893502e-05, | |
| "loss": 0.0985, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 6.122387632407672e-05, | |
| "loss": 0.1075, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 6.115230460921844e-05, | |
| "loss": 0.1002, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 6.108073289436015e-05, | |
| "loss": 0.1031, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 6.100916117950186e-05, | |
| "loss": 0.1074, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_loss": 0.05607431009411812, | |
| "eval_runtime": 1831.7935, | |
| "eval_samples_per_second": 22.195, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.06075315788016043, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 6.0937589464643576e-05, | |
| "loss": 0.097, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 6.086601774978529e-05, | |
| "loss": 0.1019, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 6.0794446034927e-05, | |
| "loss": 0.0895, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 6.072287432006871e-05, | |
| "loss": 0.093, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 6.0651302605210427e-05, | |
| "loss": 0.0978, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_loss": 0.05759399011731148, | |
| "eval_runtime": 1840.6032, | |
| "eval_samples_per_second": 22.089, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.0609973790287048, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 6.057973089035214e-05, | |
| "loss": 0.0985, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 6.050815917549385e-05, | |
| "loss": 0.0936, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 6.0436587460635566e-05, | |
| "loss": 0.0919, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 6.036501574577728e-05, | |
| "loss": 0.0984, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 6.029344403091899e-05, | |
| "loss": 0.094, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_loss": 0.058671869337558746, | |
| "eval_runtime": 1828.2656, | |
| "eval_samples_per_second": 22.238, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.05978634426118067, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 6.0222588033209284e-05, | |
| "loss": 0.1105, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 6.0151016318350995e-05, | |
| "loss": 0.0886, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 6.0079444603492706e-05, | |
| "loss": 0.0965, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 6.000787288863442e-05, | |
| "loss": 0.0904, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 5.993630117377612e-05, | |
| "loss": 0.0918, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_loss": 0.05874784663319588, | |
| "eval_runtime": 1828.0379, | |
| "eval_samples_per_second": 22.241, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.060330176921856785, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 5.986472945891783e-05, | |
| "loss": 0.0968, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 5.979315774405955e-05, | |
| "loss": 0.0975, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 5.972158602920126e-05, | |
| "loss": 0.0882, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 5.965001431434297e-05, | |
| "loss": 0.0992, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 5.957844259948468e-05, | |
| "loss": 0.0998, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "eval_loss": 0.05643482133746147, | |
| "eval_runtime": 1835.9551, | |
| "eval_samples_per_second": 22.145, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.059582407013427124, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 5.95068708846264e-05, | |
| "loss": 0.1058, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 5.943529916976811e-05, | |
| "loss": 0.0916, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 5.936372745490982e-05, | |
| "loss": 0.0936, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 5.929215574005154e-05, | |
| "loss": 0.0932, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 5.922058402519325e-05, | |
| "loss": 0.1049, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "eval_loss": 0.055979445576667786, | |
| "eval_runtime": 1822.9635, | |
| "eval_samples_per_second": 22.303, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.05902095014615503, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 5.914901231033496e-05, | |
| "loss": 0.0976, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 5.907744059547667e-05, | |
| "loss": 0.0864, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 5.900586888061839e-05, | |
| "loss": 0.0957, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 5.89342971657601e-05, | |
| "loss": 0.1044, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 5.8862725450901804e-05, | |
| "loss": 0.0986, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 0.05642736703157425, | |
| "eval_runtime": 1832.6164, | |
| "eval_samples_per_second": 22.185, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.060884080557730605, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 5.8791153736043515e-05, | |
| "loss": 0.099, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 5.8719582021185226e-05, | |
| "loss": 0.114, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 5.864801030632694e-05, | |
| "loss": 0.092, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 5.8576438591468654e-05, | |
| "loss": 0.1014, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 5.8504866876610365e-05, | |
| "loss": 0.092, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "eval_loss": 0.05650107562541962, | |
| "eval_runtime": 1838.5206, | |
| "eval_samples_per_second": 22.114, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.060101062236108976, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 5.8433295161752076e-05, | |
| "loss": 0.1008, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 5.836243916404237e-05, | |
| "loss": 0.0932, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 5.8290867449184083e-05, | |
| "loss": 0.0923, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 5.8219295734325794e-05, | |
| "loss": 0.0989, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 5.814772401946751e-05, | |
| "loss": 0.0944, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 0.0552012175321579, | |
| "eval_runtime": 1829.5735, | |
| "eval_samples_per_second": 22.222, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05957233603822942, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 5.807615230460922e-05, | |
| "loss": 0.094, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 5.8004580589750934e-05, | |
| "loss": 0.1026, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 5.7933008874892645e-05, | |
| "loss": 0.1, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 5.786143716003436e-05, | |
| "loss": 0.0926, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 5.778986544517607e-05, | |
| "loss": 0.0908, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "eval_loss": 0.05671604722738266, | |
| "eval_runtime": 1830.2361, | |
| "eval_samples_per_second": 22.214, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05925258257570226, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 5.7718293730317784e-05, | |
| "loss": 0.0955, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 5.7646722015459495e-05, | |
| "loss": 0.1024, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 5.757515030060121e-05, | |
| "loss": 0.0912, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 5.750357858574291e-05, | |
| "loss": 0.096, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 5.743200687088463e-05, | |
| "loss": 0.096, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_loss": 0.05623726546764374, | |
| "eval_runtime": 1833.6307, | |
| "eval_samples_per_second": 22.173, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.05880694192320378, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 5.736043515602634e-05, | |
| "loss": 0.0946, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 5.728886344116805e-05, | |
| "loss": 0.0919, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 5.721729172630976e-05, | |
| "loss": 0.0948, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 5.714572001145148e-05, | |
| "loss": 0.092, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 5.707414829659319e-05, | |
| "loss": 0.0977, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 0.0565749928355217, | |
| "eval_runtime": 1847.8714, | |
| "eval_samples_per_second": 22.002, | |
| "eval_steps_per_second": 1.376, | |
| "eval_wer": 0.06012623967410324, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 5.70025765817349e-05, | |
| "loss": 0.0911, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 5.693100486687662e-05, | |
| "loss": 0.0987, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 5.685943315201833e-05, | |
| "loss": 0.0924, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 5.678786143716004e-05, | |
| "loss": 0.1, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 5.671628972230175e-05, | |
| "loss": 0.0987, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "eval_loss": 0.055459294468164444, | |
| "eval_runtime": 1838.8522, | |
| "eval_samples_per_second": 22.11, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.05939105848467072, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 5.664471800744347e-05, | |
| "loss": 0.0887, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 5.657314629258518e-05, | |
| "loss": 0.0906, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 5.650157457772689e-05, | |
| "loss": 0.0978, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 5.643000286286859e-05, | |
| "loss": 0.0918, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 5.6358431148010304e-05, | |
| "loss": 0.0941, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 0.055653560906648636, | |
| "eval_runtime": 1827.0123, | |
| "eval_samples_per_second": 22.253, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.06033773015325507, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 5.6286859433152015e-05, | |
| "loss": 0.0979, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 5.621528771829373e-05, | |
| "loss": 0.0961, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 5.614371600343544e-05, | |
| "loss": 0.0879, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 5.6072144288577154e-05, | |
| "loss": 0.0948, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 5.6000572573718865e-05, | |
| "loss": 0.0992, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "eval_loss": 0.055055249482393265, | |
| "eval_runtime": 1830.7356, | |
| "eval_samples_per_second": 22.208, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.06034276564085392, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 5.592900085886058e-05, | |
| "loss": 0.0923, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 5.5857429144002293e-05, | |
| "loss": 0.0978, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 5.5785857429144004e-05, | |
| "loss": 0.0911, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 5.571428571428572e-05, | |
| "loss": 0.098, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 5.564271399942743e-05, | |
| "loss": 0.0888, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "eval_loss": 0.05645658075809479, | |
| "eval_runtime": 1828.6352, | |
| "eval_samples_per_second": 22.234, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.06233430098620025, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 5.5571142284569144e-05, | |
| "loss": 0.0956, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 5.5499570569710855e-05, | |
| "loss": 0.0936, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 5.542943028914973e-05, | |
| "loss": 0.1818, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 5.535785857429144e-05, | |
| "loss": 0.0941, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 5.528628685943316e-05, | |
| "loss": 0.1065, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "eval_loss": 0.05382963642477989, | |
| "eval_runtime": 1825.8481, | |
| "eval_samples_per_second": 22.267, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.05980145072397723, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 5.521471514457487e-05, | |
| "loss": 0.0921, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 5.514314342971658e-05, | |
| "loss": 0.0915, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 5.507157171485829e-05, | |
| "loss": 0.0853, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0999, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 5.492842828514172e-05, | |
| "loss": 0.0996, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_loss": 0.055864159017801285, | |
| "eval_runtime": 1830.8087, | |
| "eval_samples_per_second": 22.207, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.060058260591518725, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 5.4856856570283424e-05, | |
| "loss": 0.104, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 5.4785284855425135e-05, | |
| "loss": 0.0935, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 5.4713713140566845e-05, | |
| "loss": 0.098, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 5.4642141425708556e-05, | |
| "loss": 0.097, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 5.4570569710850274e-05, | |
| "loss": 0.0945, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_loss": 0.05432205647230148, | |
| "eval_runtime": 1829.1234, | |
| "eval_samples_per_second": 22.228, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.06077078208675642, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 5.4498997995991985e-05, | |
| "loss": 0.0904, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 5.4427426281133696e-05, | |
| "loss": 0.0979, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 5.435585456627541e-05, | |
| "loss": 0.0876, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 5.4284282851417124e-05, | |
| "loss": 0.0889, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 5.4212711136558835e-05, | |
| "loss": 0.0898, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_loss": 0.05514631047844887, | |
| "eval_runtime": 1837.8126, | |
| "eval_samples_per_second": 22.122, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.0599978347403325, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 5.4141139421700546e-05, | |
| "loss": 0.091, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.4069567706842264e-05, | |
| "loss": 0.0925, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 5.3997995991983974e-05, | |
| "loss": 0.0912, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.3926424277125685e-05, | |
| "loss": 0.0933, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 5.3854852562267396e-05, | |
| "loss": 0.0911, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 0.05679044872522354, | |
| "eval_runtime": 1879.77, | |
| "eval_samples_per_second": 21.629, | |
| "eval_steps_per_second": 1.352, | |
| "eval_wer": 0.059819074930573216, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 5.37832808474091e-05, | |
| "loss": 0.0865, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 5.371170913255081e-05, | |
| "loss": 0.0812, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 5.364013741769253e-05, | |
| "loss": 0.0948, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 5.356856570283424e-05, | |
| "loss": 0.0846, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 5.349699398797595e-05, | |
| "loss": 0.0871, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_loss": 0.055375006049871445, | |
| "eval_runtime": 1833.6646, | |
| "eval_samples_per_second": 22.173, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.0605315964258109, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 5.342542227311766e-05, | |
| "loss": 0.0924, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 5.335385055825938e-05, | |
| "loss": 0.088, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 5.328227884340109e-05, | |
| "loss": 0.0933, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 5.32107071285428e-05, | |
| "loss": 0.0955, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 5.313913541368452e-05, | |
| "loss": 0.0898, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "eval_loss": 0.05607745051383972, | |
| "eval_runtime": 1830.1933, | |
| "eval_samples_per_second": 22.215, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05999279925273364, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 5.306756369882623e-05, | |
| "loss": 0.0918, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 5.299599198396794e-05, | |
| "loss": 0.0888, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 5.292442026910965e-05, | |
| "loss": 0.0924, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 5.285284855425137e-05, | |
| "loss": 0.0891, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 5.278127683939308e-05, | |
| "loss": 0.0905, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_loss": 0.056004349142313004, | |
| "eval_runtime": 1829.5213, | |
| "eval_samples_per_second": 22.223, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.058177505973347164, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 5.270970512453479e-05, | |
| "loss": 0.092, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 5.2638133409676494e-05, | |
| "loss": 0.0935, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 5.2566561694818205e-05, | |
| "loss": 0.0863, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 5.2494989979959916e-05, | |
| "loss": 0.08, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 5.2423418265101634e-05, | |
| "loss": 0.0866, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "eval_loss": 0.0549277663230896, | |
| "eval_runtime": 1833.9128, | |
| "eval_samples_per_second": 22.17, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.06140273578041246, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 5.2351846550243345e-05, | |
| "loss": 0.0961, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 5.2280990552533634e-05, | |
| "loss": 0.1764, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 5.220941883767535e-05, | |
| "loss": 0.0884, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 5.213784712281706e-05, | |
| "loss": 0.0925, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 5.2066275407958774e-05, | |
| "loss": 0.0857, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "eval_loss": 0.05575016140937805, | |
| "eval_runtime": 1828.6323, | |
| "eval_samples_per_second": 22.234, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.059401129459868425, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 5.199470369310049e-05, | |
| "loss": 0.0859, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 5.19231319782422e-05, | |
| "loss": 0.083, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 5.185156026338391e-05, | |
| "loss": 0.0846, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 5.1779988548525624e-05, | |
| "loss": 0.088, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 5.170841683366734e-05, | |
| "loss": 0.0827, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "eval_loss": 0.05699002370238304, | |
| "eval_runtime": 1835.4908, | |
| "eval_samples_per_second": 22.15, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.06028737527726653, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 5.163684511880905e-05, | |
| "loss": 0.0896, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 5.156527340395076e-05, | |
| "loss": 0.0845, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 5.149441740624106e-05, | |
| "loss": 0.0887, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 5.142284569138277e-05, | |
| "loss": 0.0928, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 5.135127397652448e-05, | |
| "loss": 0.0913, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "eval_loss": 0.0544581301510334, | |
| "eval_runtime": 1830.2392, | |
| "eval_samples_per_second": 22.214, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.059192156724516026, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 5.12797022616662e-05, | |
| "loss": 0.0908, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 5.120813054680791e-05, | |
| "loss": 0.098, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 5.113655883194962e-05, | |
| "loss": 0.0834, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 5.1064987117091325e-05, | |
| "loss": 0.0912, | |
| "step": 70400 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 5.0993415402233036e-05, | |
| "loss": 0.0862, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "eval_loss": 0.05570187047123909, | |
| "eval_runtime": 1824.0904, | |
| "eval_samples_per_second": 22.289, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.05911914215433266, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 5.092184368737475e-05, | |
| "loss": 0.0891, | |
| "step": 70600 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 5.0850271972516464e-05, | |
| "loss": 0.0878, | |
| "step": 70700 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 5.0778700257658175e-05, | |
| "loss": 0.0834, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 5.0707128542799886e-05, | |
| "loss": 0.0944, | |
| "step": 70900 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 5.06355568279416e-05, | |
| "loss": 0.0904, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_loss": 0.053875070065259933, | |
| "eval_runtime": 1826.2531, | |
| "eval_samples_per_second": 22.263, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.057457431246711196, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 5.0563985113083315e-05, | |
| "loss": 0.0988, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 5.0492413398225025e-05, | |
| "loss": 0.0824, | |
| "step": 71200 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 5.0420841683366736e-05, | |
| "loss": 0.0925, | |
| "step": 71300 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 5.034926996850845e-05, | |
| "loss": 0.0959, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 5.0277698253650165e-05, | |
| "loss": 0.0876, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_loss": 0.0541791133582592, | |
| "eval_runtime": 1838.0123, | |
| "eval_samples_per_second": 22.12, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.05869867893982844, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 5.0206842255940455e-05, | |
| "loss": 0.0822, | |
| "step": 71600 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 5.013527054108217e-05, | |
| "loss": 0.0906, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 5.006369882622388e-05, | |
| "loss": 0.0827, | |
| "step": 71800 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 4.999212711136559e-05, | |
| "loss": 0.0924, | |
| "step": 71900 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 4.9920555396507305e-05, | |
| "loss": 0.0873, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "eval_loss": 0.05554695054888725, | |
| "eval_runtime": 1841.3162, | |
| "eval_samples_per_second": 22.08, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.05758080069288309, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 4.9848983681649016e-05, | |
| "loss": 0.0932, | |
| "step": 72100 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 4.9777411966790727e-05, | |
| "loss": 0.0844, | |
| "step": 72200 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 4.970584025193244e-05, | |
| "loss": 0.0872, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 4.9634268537074155e-05, | |
| "loss": 0.0881, | |
| "step": 72400 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 4.9562696822215866e-05, | |
| "loss": 0.0895, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_loss": 0.05411553010344505, | |
| "eval_runtime": 1842.1453, | |
| "eval_samples_per_second": 22.07, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.058595451444051955, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.949112510735757e-05, | |
| "loss": 0.0864, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.941955339249929e-05, | |
| "loss": 0.0901, | |
| "step": 72700 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 4.9347981677641e-05, | |
| "loss": 0.0899, | |
| "step": 72800 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 4.927640996278271e-05, | |
| "loss": 0.0846, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 4.920483824792442e-05, | |
| "loss": 0.0892, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "eval_loss": 0.05273270606994629, | |
| "eval_runtime": 1857.5901, | |
| "eval_samples_per_second": 21.887, | |
| "eval_steps_per_second": 1.368, | |
| "eval_wer": 0.057570729717685384, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 4.913326653306614e-05, | |
| "loss": 0.0916, | |
| "step": 73100 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 4.906169481820785e-05, | |
| "loss": 0.0881, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 4.899012310334956e-05, | |
| "loss": 0.0869, | |
| "step": 73300 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 4.891855138849127e-05, | |
| "loss": 0.0904, | |
| "step": 73400 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 4.884697967363298e-05, | |
| "loss": 0.0878, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_loss": 0.05417392775416374, | |
| "eval_runtime": 1835.7585, | |
| "eval_samples_per_second": 22.147, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.058809459667003204, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 4.877540795877469e-05, | |
| "loss": 0.0925, | |
| "step": 73600 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 4.870383624391641e-05, | |
| "loss": 0.089, | |
| "step": 73700 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 4.863226452905812e-05, | |
| "loss": 0.0811, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 4.856069281419983e-05, | |
| "loss": 0.0925, | |
| "step": 73900 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 4.848912109934154e-05, | |
| "loss": 0.0904, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "eval_loss": 0.052437931299209595, | |
| "eval_runtime": 1828.4976, | |
| "eval_samples_per_second": 22.235, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.05769409916385729, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.841754938448326e-05, | |
| "loss": 0.0856, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 4.8345977669624964e-05, | |
| "loss": 0.0931, | |
| "step": 74200 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 4.8274405954766675e-05, | |
| "loss": 0.0886, | |
| "step": 74300 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 4.820283423990839e-05, | |
| "loss": 0.0827, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 4.8131262525050103e-05, | |
| "loss": 0.0888, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_loss": 0.05222867429256439, | |
| "eval_runtime": 1827.4527, | |
| "eval_samples_per_second": 22.248, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.05819261243614372, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 4.8059690810191814e-05, | |
| "loss": 0.0866, | |
| "step": 74600 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 4.7988119095333525e-05, | |
| "loss": 0.0845, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 4.791654738047524e-05, | |
| "loss": 0.0891, | |
| "step": 74800 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 4.784497566561695e-05, | |
| "loss": 0.0868, | |
| "step": 74900 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 4.777340395075866e-05, | |
| "loss": 0.0848, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_loss": 0.05257893726229668, | |
| "eval_runtime": 1846.7443, | |
| "eval_samples_per_second": 22.016, | |
| "eval_steps_per_second": 1.376, | |
| "eval_wer": 0.0568582082224477, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 4.7701832235900375e-05, | |
| "loss": 0.0911, | |
| "step": 75100 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 4.7630260521042086e-05, | |
| "loss": 0.0837, | |
| "step": 75200 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 4.75586888061838e-05, | |
| "loss": 0.0842, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 4.7487117091325515e-05, | |
| "loss": 0.0862, | |
| "step": 75400 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 4.7416261093615805e-05, | |
| "loss": 0.0879, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 0.05244538560509682, | |
| "eval_runtime": 1843.8979, | |
| "eval_samples_per_second": 22.049, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.05835374803930701, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.7344689378757515e-05, | |
| "loss": 0.0906, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.727311766389923e-05, | |
| "loss": 0.0749, | |
| "step": 75700 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.7201545949040944e-05, | |
| "loss": 0.0885, | |
| "step": 75800 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 4.7129974234182655e-05, | |
| "loss": 0.0949, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 4.7058402519324366e-05, | |
| "loss": 0.0789, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_loss": 0.05331570655107498, | |
| "eval_runtime": 1831.1473, | |
| "eval_samples_per_second": 22.203, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.059567300550630566, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 4.6986830804466076e-05, | |
| "loss": 0.0833, | |
| "step": 76100 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 4.691525908960779e-05, | |
| "loss": 0.0836, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 4.68436873747495e-05, | |
| "loss": 0.0855, | |
| "step": 76300 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.6772115659891216e-05, | |
| "loss": 0.0856, | |
| "step": 76400 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 4.670054394503293e-05, | |
| "loss": 0.0798, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_loss": 0.0539526641368866, | |
| "eval_runtime": 1839.2143, | |
| "eval_samples_per_second": 22.106, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.05917201477412062, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 4.662897223017464e-05, | |
| "loss": 0.0772, | |
| "step": 76600 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 4.655740051531635e-05, | |
| "loss": 0.0782, | |
| "step": 76700 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 4.648582880045806e-05, | |
| "loss": 0.0893, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 4.641425708559977e-05, | |
| "loss": 0.0845, | |
| "step": 76900 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 4.634268537074148e-05, | |
| "loss": 0.0901, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "eval_loss": 0.051582325249910355, | |
| "eval_runtime": 1828.5987, | |
| "eval_samples_per_second": 22.234, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.059028503377553304, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 4.62711136558832e-05, | |
| "loss": 0.0851, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 4.619954194102491e-05, | |
| "loss": 0.0838, | |
| "step": 77200 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 4.612797022616662e-05, | |
| "loss": 0.0902, | |
| "step": 77300 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 4.605639851130834e-05, | |
| "loss": 0.0892, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 4.598482679645005e-05, | |
| "loss": 0.0798, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "eval_loss": 0.05253351107239723, | |
| "eval_runtime": 1831.9684, | |
| "eval_samples_per_second": 22.193, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.057117535833788625, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 4.591325508159175e-05, | |
| "loss": 0.0826, | |
| "step": 77600 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.584168336673347e-05, | |
| "loss": 0.0809, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 4.577011165187518e-05, | |
| "loss": 0.083, | |
| "step": 77800 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 4.569853993701689e-05, | |
| "loss": 0.0824, | |
| "step": 77900 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 4.56269682221586e-05, | |
| "loss": 0.0844, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_loss": 0.052411746233701706, | |
| "eval_runtime": 1824.2506, | |
| "eval_samples_per_second": 22.287, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.05672225005727867, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 4.555539650730032e-05, | |
| "loss": 0.0794, | |
| "step": 78100 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 4.548382479244203e-05, | |
| "loss": 0.0856, | |
| "step": 78200 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 4.5412253077583736e-05, | |
| "loss": 0.0836, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.5340681362725453e-05, | |
| "loss": 0.0797, | |
| "step": 78400 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 4.5269109647867164e-05, | |
| "loss": 0.0824, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "eval_loss": 0.053092110902071, | |
| "eval_runtime": 1833.5833, | |
| "eval_samples_per_second": 22.174, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.05597951563644787, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.5197537933008875e-05, | |
| "loss": 0.091, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 4.5125966218150586e-05, | |
| "loss": 0.0784, | |
| "step": 78700 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 4.5054394503292304e-05, | |
| "loss": 0.0789, | |
| "step": 78800 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 4.4982822788434015e-05, | |
| "loss": 0.0858, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 4.4911251073575725e-05, | |
| "loss": 0.0825, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_loss": 0.05265763774514198, | |
| "eval_runtime": 1823.3309, | |
| "eval_samples_per_second": 22.298, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.05582845100848228, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 4.4839679358717436e-05, | |
| "loss": 0.0794, | |
| "step": 79100 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 4.476810764385915e-05, | |
| "loss": 0.0804, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 4.469653592900086e-05, | |
| "loss": 0.0742, | |
| "step": 79300 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 4.4624964214142576e-05, | |
| "loss": 0.192, | |
| "step": 79400 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 4.4553392499284286e-05, | |
| "loss": 0.0873, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "eval_loss": 0.05249021574854851, | |
| "eval_runtime": 1829.0557, | |
| "eval_samples_per_second": 22.228, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.05644026275174291, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 4.4481820784426e-05, | |
| "loss": 0.0811, | |
| "step": 79600 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 4.441024906956771e-05, | |
| "loss": 0.0813, | |
| "step": 79700 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 4.4338677354709426e-05, | |
| "loss": 0.0771, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 4.426710563985113e-05, | |
| "loss": 0.0889, | |
| "step": 79900 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 4.419553392499284e-05, | |
| "loss": 0.0842, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "eval_loss": 0.052821435034275055, | |
| "eval_runtime": 1832.7861, | |
| "eval_samples_per_second": 22.183, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05571011704990923, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 4.412396221013456e-05, | |
| "loss": 0.0808, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 4.405239049527627e-05, | |
| "loss": 0.0775, | |
| "step": 80200 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 4.398081878041798e-05, | |
| "loss": 0.088, | |
| "step": 80300 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.390924706555969e-05, | |
| "loss": 0.0802, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 4.383767535070141e-05, | |
| "loss": 0.0802, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "eval_loss": 0.05230957642197609, | |
| "eval_runtime": 1821.9499, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.05587125265307253, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 4.376610363584311e-05, | |
| "loss": 0.084, | |
| "step": 80600 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 4.3694531920984824e-05, | |
| "loss": 0.09, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.362296020612654e-05, | |
| "loss": 0.0861, | |
| "step": 80800 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 4.355138849126825e-05, | |
| "loss": 0.0775, | |
| "step": 80900 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 4.347981677640996e-05, | |
| "loss": 0.0866, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "eval_loss": 0.052853163331747055, | |
| "eval_runtime": 1828.8793, | |
| "eval_samples_per_second": 22.231, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.05618093514040198, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 4.340824506155168e-05, | |
| "loss": 0.0808, | |
| "step": 81100 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 4.333667334669339e-05, | |
| "loss": 0.0848, | |
| "step": 81200 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 4.32651016318351e-05, | |
| "loss": 0.0833, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 4.319352991697681e-05, | |
| "loss": 0.0883, | |
| "step": 81400 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 4.3121958202118524e-05, | |
| "loss": 0.0848, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "eval_loss": 0.051813945174217224, | |
| "eval_runtime": 1833.404, | |
| "eval_samples_per_second": 22.176, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.05670714359448211, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.305110220440882e-05, | |
| "loss": 0.0765, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 4.297953048955053e-05, | |
| "loss": 0.074, | |
| "step": 81700 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 4.290795877469224e-05, | |
| "loss": 0.0863, | |
| "step": 81800 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 4.283638705983395e-05, | |
| "loss": 0.0848, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 4.2764815344975664e-05, | |
| "loss": 0.0819, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "eval_loss": 0.0514368936419487, | |
| "eval_runtime": 1836.8554, | |
| "eval_samples_per_second": 22.134, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.055992104355445, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 4.269324363011738e-05, | |
| "loss": 0.0831, | |
| "step": 82100 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 4.262167191525909e-05, | |
| "loss": 0.0787, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 4.2550100200400803e-05, | |
| "loss": 0.0793, | |
| "step": 82300 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 4.247852848554252e-05, | |
| "loss": 0.0798, | |
| "step": 82400 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 4.2406956770684225e-05, | |
| "loss": 0.0882, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "eval_loss": 0.051576580852270126, | |
| "eval_runtime": 1833.9028, | |
| "eval_samples_per_second": 22.17, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.056447815983141185, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 4.2335385055825936e-05, | |
| "loss": 0.0791, | |
| "step": 82600 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 4.2263813340967654e-05, | |
| "loss": 0.0808, | |
| "step": 82700 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 4.2192241626109365e-05, | |
| "loss": 0.0822, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 4.2120669911251075e-05, | |
| "loss": 0.0807, | |
| "step": 82900 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 4.2049098196392786e-05, | |
| "loss": 0.0854, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "eval_loss": 0.051234595477581024, | |
| "eval_runtime": 1836.5292, | |
| "eval_samples_per_second": 22.138, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.05545834266996659, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 4.1977526481534504e-05, | |
| "loss": 0.0841, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 4.1905954766676215e-05, | |
| "loss": 0.082, | |
| "step": 83200 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 4.183438305181792e-05, | |
| "loss": 0.0811, | |
| "step": 83300 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 4.1762811336959636e-05, | |
| "loss": 0.0767, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 4.169123962210135e-05, | |
| "loss": 0.0733, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_loss": 0.05319647490978241, | |
| "eval_runtime": 1838.5459, | |
| "eval_samples_per_second": 22.114, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.05582593326468285, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 4.161966790724306e-05, | |
| "loss": 0.081, | |
| "step": 83600 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 4.154809619238477e-05, | |
| "loss": 0.0849, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 4.147652447752649e-05, | |
| "loss": 0.0827, | |
| "step": 83800 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 4.14049527626682e-05, | |
| "loss": 0.0752, | |
| "step": 83900 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.13333810478099e-05, | |
| "loss": 0.0835, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_loss": 0.05085168033838272, | |
| "eval_runtime": 1870.9533, | |
| "eval_samples_per_second": 21.731, | |
| "eval_steps_per_second": 1.359, | |
| "eval_wer": 0.055226710240419356, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 4.126180933295162e-05, | |
| "loss": 0.086, | |
| "step": 84100 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 4.1190953335241916e-05, | |
| "loss": 0.0929, | |
| "step": 84200 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 4.111938162038363e-05, | |
| "loss": 0.0786, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 4.104780990552534e-05, | |
| "loss": 0.0758, | |
| "step": 84400 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 4.097623819066705e-05, | |
| "loss": 0.0787, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_loss": 0.05154638737440109, | |
| "eval_runtime": 1823.2917, | |
| "eval_samples_per_second": 22.299, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.05471560824913579, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 4.090466647580876e-05, | |
| "loss": 0.0937, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.083309476095048e-05, | |
| "loss": 0.0826, | |
| "step": 84700 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 4.076223876324077e-05, | |
| "loss": 0.0822, | |
| "step": 84800 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 4.069066704838248e-05, | |
| "loss": 0.0852, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.0619811050672774e-05, | |
| "loss": 0.0803, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.05102900415658951, | |
| "eval_runtime": 1828.7068, | |
| "eval_samples_per_second": 22.233, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.05625143196678593, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.0548239335814485e-05, | |
| "loss": 0.0846, | |
| "step": 85100 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.0476667620956196e-05, | |
| "loss": 0.081, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.0405095906097913e-05, | |
| "loss": 0.0757, | |
| "step": 85300 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.0333524191239624e-05, | |
| "loss": 0.0771, | |
| "step": 85400 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 4.0261952476381335e-05, | |
| "loss": 0.0798, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "eval_loss": 0.052222542464733124, | |
| "eval_runtime": 1820.8839, | |
| "eval_samples_per_second": 22.328, | |
| "eval_steps_per_second": 1.396, | |
| "eval_wer": 0.055800755826688586, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 4.019038076152305e-05, | |
| "loss": 0.0829, | |
| "step": 85600 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 4.0118809046664764e-05, | |
| "loss": 0.0789, | |
| "step": 85700 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 4.004723733180647e-05, | |
| "loss": 0.0811, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 3.9975665616948185e-05, | |
| "loss": 0.0809, | |
| "step": 85900 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 3.9904093902089896e-05, | |
| "loss": 0.0801, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 0.05197376757860184, | |
| "eval_runtime": 1835.5698, | |
| "eval_samples_per_second": 22.15, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.058618111138246796, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 3.983252218723161e-05, | |
| "loss": 0.0813, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.976095047237332e-05, | |
| "loss": 0.0757, | |
| "step": 86200 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 3.9689378757515036e-05, | |
| "loss": 0.0849, | |
| "step": 86300 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 3.9617807042656746e-05, | |
| "loss": 0.0747, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 3.954623532779845e-05, | |
| "loss": 0.075, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 0.051361363381147385, | |
| "eval_runtime": 1839.9407, | |
| "eval_samples_per_second": 22.097, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.05667944841268842, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 3.947466361294017e-05, | |
| "loss": 0.0864, | |
| "step": 86600 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.940309189808188e-05, | |
| "loss": 0.0862, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 3.933152018322359e-05, | |
| "loss": 0.0791, | |
| "step": 86800 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.92599484683653e-05, | |
| "loss": 0.0805, | |
| "step": 86900 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 3.918837675350702e-05, | |
| "loss": 0.0764, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "eval_loss": 0.05217781662940979, | |
| "eval_runtime": 1832.6184, | |
| "eval_samples_per_second": 22.185, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.057603460387077934, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 3.911680503864873e-05, | |
| "loss": 0.073, | |
| "step": 87100 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.904523332379044e-05, | |
| "loss": 0.0796, | |
| "step": 87200 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 3.897366160893215e-05, | |
| "loss": 0.083, | |
| "step": 87300 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.890208989407386e-05, | |
| "loss": 0.0753, | |
| "step": 87400 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 3.883051817921557e-05, | |
| "loss": 0.0774, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "eval_loss": 0.05101511627435684, | |
| "eval_runtime": 1821.9742, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.05584607521507826, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 3.875894646435729e-05, | |
| "loss": 0.0815, | |
| "step": 87600 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8687374749499e-05, | |
| "loss": 0.0802, | |
| "step": 87700 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 3.861580303464071e-05, | |
| "loss": 0.0769, | |
| "step": 87800 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 3.854423131978242e-05, | |
| "loss": 0.0762, | |
| "step": 87900 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 3.847265960492414e-05, | |
| "loss": 0.1719, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "eval_loss": 0.04807417467236519, | |
| "eval_runtime": 1834.6542, | |
| "eval_samples_per_second": 22.161, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.05941371817886555, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.8401087890065845e-05, | |
| "loss": 0.0779, | |
| "step": 88100 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 3.8329516175207556e-05, | |
| "loss": 0.0714, | |
| "step": 88200 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 3.825794446034927e-05, | |
| "loss": 0.0845, | |
| "step": 88300 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.8186372745490984e-05, | |
| "loss": 0.0765, | |
| "step": 88400 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.8114801030632695e-05, | |
| "loss": 0.0839, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "eval_loss": 0.05076945573091507, | |
| "eval_runtime": 1831.5351, | |
| "eval_samples_per_second": 22.198, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.05765381526306646, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 3.8043229315774406e-05, | |
| "loss": 0.0807, | |
| "step": 88600 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 3.7971657600916123e-05, | |
| "loss": 0.0754, | |
| "step": 88700 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.7900085886057834e-05, | |
| "loss": 0.0748, | |
| "step": 88800 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 3.782851417119954e-05, | |
| "loss": 0.076, | |
| "step": 88900 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 3.7756942456341256e-05, | |
| "loss": 0.0777, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "eval_loss": 0.051343463361263275, | |
| "eval_runtime": 1837.4795, | |
| "eval_samples_per_second": 22.127, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.057515339354098007, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 3.768537074148297e-05, | |
| "loss": 0.0769, | |
| "step": 89100 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.761379902662468e-05, | |
| "loss": 0.0759, | |
| "step": 89200 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 3.7542227311766395e-05, | |
| "loss": 0.0717, | |
| "step": 89300 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 3.7470655596908106e-05, | |
| "loss": 0.0773, | |
| "step": 89400 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 3.739908388204982e-05, | |
| "loss": 0.0772, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_loss": 0.05197189748287201, | |
| "eval_runtime": 1866.9473, | |
| "eval_samples_per_second": 21.777, | |
| "eval_steps_per_second": 1.362, | |
| "eval_wer": 0.05689093889184024, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 3.732751216719153e-05, | |
| "loss": 0.0735, | |
| "step": 89600 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 3.725594045233324e-05, | |
| "loss": 0.0696, | |
| "step": 89700 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 3.718436873747495e-05, | |
| "loss": 0.08, | |
| "step": 89800 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 3.711279702261666e-05, | |
| "loss": 0.076, | |
| "step": 89900 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 3.704122530775838e-05, | |
| "loss": 0.0796, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_loss": 0.05086323991417885, | |
| "eval_runtime": 1833.4414, | |
| "eval_samples_per_second": 22.175, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.05513858920743943, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 3.696965359290009e-05, | |
| "loss": 0.0794, | |
| "step": 90100 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 3.68980818780418e-05, | |
| "loss": 0.0747, | |
| "step": 90200 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 3.6827225880332096e-05, | |
| "loss": 0.0757, | |
| "step": 90300 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 3.675565416547381e-05, | |
| "loss": 0.075, | |
| "step": 90400 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 3.668408245061552e-05, | |
| "loss": 0.0808, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "eval_loss": 0.0507289282977581, | |
| "eval_runtime": 1833.2264, | |
| "eval_samples_per_second": 22.178, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05553135724014996, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 3.6612510735757236e-05, | |
| "loss": 0.0772, | |
| "step": 90600 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.654093902089894e-05, | |
| "loss": 0.0774, | |
| "step": 90700 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 3.646936730604065e-05, | |
| "loss": 0.0702, | |
| "step": 90800 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 3.639779559118237e-05, | |
| "loss": 0.0708, | |
| "step": 90900 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 3.632622387632408e-05, | |
| "loss": 0.08, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "eval_loss": 0.05005011335015297, | |
| "eval_runtime": 1837.8845, | |
| "eval_samples_per_second": 22.122, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.05590146557866565, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 3.625465216146579e-05, | |
| "loss": 0.0801, | |
| "step": 91100 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 3.61830804466075e-05, | |
| "loss": 0.0718, | |
| "step": 91200 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 3.611150873174922e-05, | |
| "loss": 0.0791, | |
| "step": 91300 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 3.603993701689093e-05, | |
| "loss": 0.0782, | |
| "step": 91400 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 3.5968365302032634e-05, | |
| "loss": 0.0757, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "eval_loss": 0.049759119749069214, | |
| "eval_runtime": 1832.5723, | |
| "eval_samples_per_second": 22.186, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05537273938078609, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 3.589679358717435e-05, | |
| "loss": 0.0823, | |
| "step": 91600 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 3.582522187231606e-05, | |
| "loss": 0.0817, | |
| "step": 91700 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 3.575365015745777e-05, | |
| "loss": 0.0739, | |
| "step": 91800 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 3.5682078442599484e-05, | |
| "loss": 0.0776, | |
| "step": 91900 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 3.56105067277412e-05, | |
| "loss": 0.0724, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "eval_loss": 0.05045848712325096, | |
| "eval_runtime": 1829.8809, | |
| "eval_samples_per_second": 22.218, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05398798029110154, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 3.553893501288291e-05, | |
| "loss": 0.0744, | |
| "step": 92100 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.546736329802462e-05, | |
| "loss": 0.0743, | |
| "step": 92200 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 3.5395791583166334e-05, | |
| "loss": 0.0764, | |
| "step": 92300 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 3.5324219868308045e-05, | |
| "loss": 0.0762, | |
| "step": 92400 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 3.5252648153449756e-05, | |
| "loss": 0.0782, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_loss": 0.050730880349874496, | |
| "eval_runtime": 1823.0657, | |
| "eval_samples_per_second": 22.301, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.05508319884385205, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 3.5181076438591473e-05, | |
| "loss": 0.0759, | |
| "step": 92600 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 3.5109504723733184e-05, | |
| "loss": 0.0763, | |
| "step": 92700 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.5037933008874895e-05, | |
| "loss": 0.0785, | |
| "step": 92800 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 3.4966361294016606e-05, | |
| "loss": 0.0766, | |
| "step": 92900 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 3.489478957915832e-05, | |
| "loss": 0.0839, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 0.052314843982458115, | |
| "eval_runtime": 1867.422, | |
| "eval_samples_per_second": 21.772, | |
| "eval_steps_per_second": 1.361, | |
| "eval_wer": 0.05569249284331325, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 3.482321786430003e-05, | |
| "loss": 0.0812, | |
| "step": 93100 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 3.475164614944174e-05, | |
| "loss": 0.0738, | |
| "step": 93200 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 3.4680074434583456e-05, | |
| "loss": 0.0752, | |
| "step": 93300 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 3.460850271972517e-05, | |
| "loss": 0.0771, | |
| "step": 93400 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 3.453693100486688e-05, | |
| "loss": 0.0779, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "eval_loss": 0.0499575100839138, | |
| "eval_runtime": 1842.7219, | |
| "eval_samples_per_second": 22.064, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.054697984042539796, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 3.446535929000859e-05, | |
| "loss": 0.076, | |
| "step": 93600 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.4393787575150306e-05, | |
| "loss": 0.0797, | |
| "step": 93700 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 3.432221586029201e-05, | |
| "loss": 0.0722, | |
| "step": 93800 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 3.425064414543372e-05, | |
| "loss": 0.0818, | |
| "step": 93900 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 3.417907243057544e-05, | |
| "loss": 0.0768, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_loss": 0.05089777335524559, | |
| "eval_runtime": 1829.9164, | |
| "eval_samples_per_second": 22.218, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.055795720339089735, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 3.410750071571715e-05, | |
| "loss": 0.0727, | |
| "step": 94100 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 3.403592900085886e-05, | |
| "loss": 0.0726, | |
| "step": 94200 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 3.396435728600058e-05, | |
| "loss": 0.0749, | |
| "step": 94300 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 3.389278557114229e-05, | |
| "loss": 0.0702, | |
| "step": 94400 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.382192957343258e-05, | |
| "loss": 0.0786, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.05064282566308975, | |
| "eval_runtime": 1830.9204, | |
| "eval_samples_per_second": 22.206, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.05376641883675201, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 3.37503578585743e-05, | |
| "loss": 0.0759, | |
| "step": 94600 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 3.367878614371601e-05, | |
| "loss": 0.0625, | |
| "step": 94700 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 3.360721442885772e-05, | |
| "loss": 0.0677, | |
| "step": 94800 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 3.353564271399943e-05, | |
| "loss": 0.0829, | |
| "step": 94900 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 3.346407099914114e-05, | |
| "loss": 0.0719, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "eval_loss": 0.04920099675655365, | |
| "eval_runtime": 1842.8564, | |
| "eval_samples_per_second": 22.062, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.05629423361137617, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 3.339249928428285e-05, | |
| "loss": 0.0718, | |
| "step": 95100 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.332092756942456e-05, | |
| "loss": 0.075, | |
| "step": 95200 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 3.324935585456628e-05, | |
| "loss": 0.0672, | |
| "step": 95300 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 3.317778413970799e-05, | |
| "loss": 0.0825, | |
| "step": 95400 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 3.31062124248497e-05, | |
| "loss": 0.0721, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 0.05013180524110794, | |
| "eval_runtime": 1831.2541, | |
| "eval_samples_per_second": 22.202, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.05319992648188106, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 3.303464070999142e-05, | |
| "loss": 0.0752, | |
| "step": 95600 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 3.296306899513312e-05, | |
| "loss": 0.0762, | |
| "step": 95700 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 3.2891497280274834e-05, | |
| "loss": 0.0778, | |
| "step": 95800 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 3.281992556541655e-05, | |
| "loss": 0.0723, | |
| "step": 95900 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 3.274835385055826e-05, | |
| "loss": 0.0725, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "eval_loss": 0.049954310059547424, | |
| "eval_runtime": 1823.6274, | |
| "eval_samples_per_second": 22.295, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.05411386748107286, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 3.267678213569997e-05, | |
| "loss": 0.0739, | |
| "step": 96100 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 3.2605210420841684e-05, | |
| "loss": 0.0741, | |
| "step": 96200 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 3.25336387059834e-05, | |
| "loss": 0.0729, | |
| "step": 96300 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 3.2462066991125106e-05, | |
| "loss": 0.0694, | |
| "step": 96400 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 3.2390495276266817e-05, | |
| "loss": 0.0724, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "eval_loss": 0.05058996006846428, | |
| "eval_runtime": 1829.1346, | |
| "eval_samples_per_second": 22.227, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.05259566797001871, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 3.2318923561408534e-05, | |
| "loss": 0.0747, | |
| "step": 96600 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 3.2247351846550245e-05, | |
| "loss": 0.0743, | |
| "step": 96700 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 3.2175780131691956e-05, | |
| "loss": 0.0739, | |
| "step": 96800 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 3.210420841683367e-05, | |
| "loss": 0.0784, | |
| "step": 96900 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 3.2032636701975384e-05, | |
| "loss": 0.0677, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "eval_loss": 0.050292182713747025, | |
| "eval_runtime": 1827.4014, | |
| "eval_samples_per_second": 22.249, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.05251761791223648, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 3.1961064987117095e-05, | |
| "loss": 0.0757, | |
| "step": 97100 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 3.18894932722588e-05, | |
| "loss": 0.0727, | |
| "step": 97200 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 3.181792155740052e-05, | |
| "loss": 0.0791, | |
| "step": 97300 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 3.174634984254223e-05, | |
| "loss": 0.0702, | |
| "step": 97400 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 3.167477812768394e-05, | |
| "loss": 0.0726, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "eval_loss": 0.049884457141160965, | |
| "eval_runtime": 1831.8777, | |
| "eval_samples_per_second": 22.194, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.052933045639141856, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 3.1603206412825656e-05, | |
| "loss": 0.0699, | |
| "step": 97600 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 3.153163469796737e-05, | |
| "loss": 0.0758, | |
| "step": 97700 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 3.146006298310908e-05, | |
| "loss": 0.0869, | |
| "step": 97800 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 3.138849126825079e-05, | |
| "loss": 0.071, | |
| "step": 97900 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 3.13169195533925e-05, | |
| "loss": 0.0779, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "eval_loss": 0.04999667778611183, | |
| "eval_runtime": 1832.4595, | |
| "eval_samples_per_second": 22.187, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05292297466394415, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 3.124534783853421e-05, | |
| "loss": 0.0801, | |
| "step": 98100 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 3.117377612367592e-05, | |
| "loss": 0.0704, | |
| "step": 98200 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.110220440881764e-05, | |
| "loss": 0.0733, | |
| "step": 98300 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 3.103063269395935e-05, | |
| "loss": 0.0804, | |
| "step": 98400 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 3.095977669624964e-05, | |
| "loss": 0.1584, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "eval_loss": 0.050933390855789185, | |
| "eval_runtime": 1834.9908, | |
| "eval_samples_per_second": 22.157, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.05440592576180633, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 3.088820498139136e-05, | |
| "loss": 0.0807, | |
| "step": 98600 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 3.081663326653307e-05, | |
| "loss": 0.0737, | |
| "step": 98700 | |
| }, | |
| { | |
| "epoch": 10.46, | |
| "learning_rate": 3.074506155167478e-05, | |
| "loss": 0.0775, | |
| "step": 98800 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 3.06734898368165e-05, | |
| "loss": 0.0631, | |
| "step": 98900 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 3.060191812195821e-05, | |
| "loss": 0.0781, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "eval_loss": 0.05024658143520355, | |
| "eval_runtime": 1835.9956, | |
| "eval_samples_per_second": 22.144, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.05301864892832235, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 3.053034640709991e-05, | |
| "loss": 0.0761, | |
| "step": 99100 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 3.0458774692241626e-05, | |
| "loss": 0.0817, | |
| "step": 99200 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 3.038720297738334e-05, | |
| "loss": 0.0809, | |
| "step": 99300 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 3.031563126252505e-05, | |
| "loss": 0.0684, | |
| "step": 99400 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 3.0244059547666765e-05, | |
| "loss": 0.0677, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "eval_loss": 0.050260279327631, | |
| "eval_runtime": 1821.331, | |
| "eval_samples_per_second": 22.323, | |
| "eval_steps_per_second": 1.396, | |
| "eval_wer": 0.053502055737812235, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 3.0172487832808476e-05, | |
| "loss": 0.0704, | |
| "step": 99600 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 3.010091611795019e-05, | |
| "loss": 0.0746, | |
| "step": 99700 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.0029344403091898e-05, | |
| "loss": 0.0686, | |
| "step": 99800 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 2.995777268823361e-05, | |
| "loss": 0.0792, | |
| "step": 99900 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 2.9886200973375323e-05, | |
| "loss": 0.0729, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "eval_loss": 0.049756139516830444, | |
| "eval_runtime": 1830.587, | |
| "eval_samples_per_second": 22.21, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05349702025021338, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 2.981534497566562e-05, | |
| "loss": 0.0699, | |
| "step": 100100 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 2.9743773260807327e-05, | |
| "loss": 0.0718, | |
| "step": 100200 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 2.967220154594904e-05, | |
| "loss": 0.0758, | |
| "step": 100300 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 2.9600629831090752e-05, | |
| "loss": 0.0743, | |
| "step": 100400 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 2.9529058116232467e-05, | |
| "loss": 0.0741, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "eval_loss": 0.04930509254336357, | |
| "eval_runtime": 1823.4334, | |
| "eval_samples_per_second": 22.297, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.0539653205969067, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 2.945748640137418e-05, | |
| "loss": 0.0773, | |
| "step": 100600 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 2.938591468651589e-05, | |
| "loss": 0.0807, | |
| "step": 100700 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 2.9314342971657606e-05, | |
| "loss": 0.0747, | |
| "step": 100800 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 2.9242771256799313e-05, | |
| "loss": 0.0741, | |
| "step": 100900 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 2.9171199541941024e-05, | |
| "loss": 0.0698, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "eval_loss": 0.05008922144770622, | |
| "eval_runtime": 1863.9853, | |
| "eval_samples_per_second": 21.812, | |
| "eval_steps_per_second": 1.364, | |
| "eval_wer": 0.053230139407474175, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 2.909962782708274e-05, | |
| "loss": 0.076, | |
| "step": 101100 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 2.902805611222445e-05, | |
| "loss": 0.0773, | |
| "step": 101200 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 2.8956484397366164e-05, | |
| "loss": 0.0674, | |
| "step": 101300 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 2.8884912682507874e-05, | |
| "loss": 0.0675, | |
| "step": 101400 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 2.881334096764959e-05, | |
| "loss": 0.0711, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "eval_loss": 0.04847079887986183, | |
| "eval_runtime": 1836.3141, | |
| "eval_samples_per_second": 22.141, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.053784043043347995, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 2.87417692527913e-05, | |
| "loss": 0.0689, | |
| "step": 101600 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 2.8670197537933007e-05, | |
| "loss": 0.0758, | |
| "step": 101700 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 2.859862582307472e-05, | |
| "loss": 0.0765, | |
| "step": 101800 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 2.8527054108216432e-05, | |
| "loss": 0.0746, | |
| "step": 101900 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 2.8455482393358146e-05, | |
| "loss": 0.0763, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "eval_loss": 0.05001853406429291, | |
| "eval_runtime": 1835.2154, | |
| "eval_samples_per_second": 22.154, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.05441347899320461, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 2.8383910678499857e-05, | |
| "loss": 0.0703, | |
| "step": 102100 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 2.831233896364157e-05, | |
| "loss": 0.0709, | |
| "step": 102200 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 2.8240767248783286e-05, | |
| "loss": 0.0725, | |
| "step": 102300 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 2.8169195533924997e-05, | |
| "loss": 0.0712, | |
| "step": 102400 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 2.8097623819066704e-05, | |
| "loss": 0.0745, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "eval_loss": 0.04908216744661331, | |
| "eval_runtime": 1865.7807, | |
| "eval_samples_per_second": 21.791, | |
| "eval_steps_per_second": 1.362, | |
| "eval_wer": 0.05375131237395545, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 2.802605210420842e-05, | |
| "loss": 0.0776, | |
| "step": 102600 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 2.795448038935013e-05, | |
| "loss": 0.0726, | |
| "step": 102700 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 2.7882908674491843e-05, | |
| "loss": 0.0697, | |
| "step": 102800 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 2.7812052676782137e-05, | |
| "loss": 0.0721, | |
| "step": 102900 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 2.7740480961923847e-05, | |
| "loss": 0.0749, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "eval_loss": 0.04884283244609833, | |
| "eval_runtime": 1833.3565, | |
| "eval_samples_per_second": 22.176, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05471057276153693, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 2.766962496421414e-05, | |
| "loss": 0.0755, | |
| "step": 103100 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 2.7598053249355855e-05, | |
| "loss": 0.0659, | |
| "step": 103200 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 2.7526481534497566e-05, | |
| "loss": 0.0734, | |
| "step": 103300 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 2.745490981963928e-05, | |
| "loss": 0.0737, | |
| "step": 103400 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 2.738333810478099e-05, | |
| "loss": 0.0746, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "eval_loss": 0.050001319497823715, | |
| "eval_runtime": 1844.698, | |
| "eval_samples_per_second": 22.04, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.053502055737812235, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 2.7311766389922705e-05, | |
| "loss": 0.0751, | |
| "step": 103600 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 2.724019467506442e-05, | |
| "loss": 0.0694, | |
| "step": 103700 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 2.716862296020613e-05, | |
| "loss": 0.0722, | |
| "step": 103800 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 2.7097051245347838e-05, | |
| "loss": 0.0747, | |
| "step": 103900 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.7025479530489552e-05, | |
| "loss": 0.081, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "eval_loss": 0.048980310559272766, | |
| "eval_runtime": 1829.5762, | |
| "eval_samples_per_second": 22.222, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.053527233175806495, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 2.6953907815631263e-05, | |
| "loss": 0.0715, | |
| "step": 104100 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 2.6882336100772977e-05, | |
| "loss": 0.073, | |
| "step": 104200 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.6810764385914688e-05, | |
| "loss": 0.0646, | |
| "step": 104300 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.6739192671056402e-05, | |
| "loss": 0.0773, | |
| "step": 104400 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 2.6667620956198113e-05, | |
| "loss": 0.068, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "eval_loss": 0.04967235028743744, | |
| "eval_runtime": 1838.501, | |
| "eval_samples_per_second": 22.114, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.05215002731752023, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 2.659604924133982e-05, | |
| "loss": 0.0658, | |
| "step": 104600 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 2.6524477526481535e-05, | |
| "loss": 0.0702, | |
| "step": 104700 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 2.6452905811623246e-05, | |
| "loss": 0.0708, | |
| "step": 104800 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 2.638133409676496e-05, | |
| "loss": 0.0685, | |
| "step": 104900 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 2.630976238190667e-05, | |
| "loss": 0.07, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "eval_loss": 0.049936745315790176, | |
| "eval_runtime": 1826.4928, | |
| "eval_samples_per_second": 22.26, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.05420702400165164, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 2.6238190667048385e-05, | |
| "loss": 0.0653, | |
| "step": 105100 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 2.6166618952190096e-05, | |
| "loss": 0.0712, | |
| "step": 105200 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 2.609504723733181e-05, | |
| "loss": 0.0721, | |
| "step": 105300 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 2.6023475522473518e-05, | |
| "loss": 0.0688, | |
| "step": 105400 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 2.595190380761523e-05, | |
| "loss": 0.0706, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "eval_loss": 0.04866202548146248, | |
| "eval_runtime": 1821.1823, | |
| "eval_samples_per_second": 22.325, | |
| "eval_steps_per_second": 1.396, | |
| "eval_wer": 0.053930072183714726, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 2.5880332092756943e-05, | |
| "loss": 0.0728, | |
| "step": 105600 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 2.5808760377898657e-05, | |
| "loss": 0.0694, | |
| "step": 105700 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 2.5737188663040368e-05, | |
| "loss": 0.0706, | |
| "step": 105800 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 2.5665616948182082e-05, | |
| "loss": 0.0713, | |
| "step": 105900 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 2.5594045233323793e-05, | |
| "loss": 0.071, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "eval_loss": 0.048879798501729965, | |
| "eval_runtime": 1840.9128, | |
| "eval_samples_per_second": 22.085, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.05346177183702141, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 2.5523189235614086e-05, | |
| "loss": 0.1535, | |
| "step": 106100 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 2.54516175207558e-05, | |
| "loss": 0.0668, | |
| "step": 106200 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 2.538004580589751e-05, | |
| "loss": 0.0683, | |
| "step": 106300 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 2.5308474091039225e-05, | |
| "loss": 0.0754, | |
| "step": 106400 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 2.5236902376180933e-05, | |
| "loss": 0.0761, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "eval_loss": 0.048972226679325104, | |
| "eval_runtime": 1843.6775, | |
| "eval_samples_per_second": 22.052, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.053074039291909736, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 2.5165330661322644e-05, | |
| "loss": 0.077, | |
| "step": 106600 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 2.5093758946464358e-05, | |
| "loss": 0.0755, | |
| "step": 106700 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 2.502218723160607e-05, | |
| "loss": 0.0725, | |
| "step": 106800 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 2.4950615516747783e-05, | |
| "loss": 0.0693, | |
| "step": 106900 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 2.4879043801889494e-05, | |
| "loss": 0.0756, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "eval_loss": 0.04921906813979149, | |
| "eval_runtime": 1832.6036, | |
| "eval_samples_per_second": 22.185, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05356751707659732, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 2.4807472087031205e-05, | |
| "loss": 0.0675, | |
| "step": 107100 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 2.473590037217292e-05, | |
| "loss": 0.0712, | |
| "step": 107200 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 2.466432865731463e-05, | |
| "loss": 0.0706, | |
| "step": 107300 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 2.4592756942456344e-05, | |
| "loss": 0.0675, | |
| "step": 107400 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 2.4521185227598055e-05, | |
| "loss": 0.0679, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "eval_loss": 0.04994984716176987, | |
| "eval_runtime": 1857.7914, | |
| "eval_samples_per_second": 21.885, | |
| "eval_steps_per_second": 1.368, | |
| "eval_wer": 0.053016131184522926, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 2.4449613512739766e-05, | |
| "loss": 0.0673, | |
| "step": 107600 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 2.437804179788148e-05, | |
| "loss": 0.0679, | |
| "step": 107700 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 2.430647008302319e-05, | |
| "loss": 0.0719, | |
| "step": 107800 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 2.4234898368164902e-05, | |
| "loss": 0.0691, | |
| "step": 107900 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 2.4163326653306613e-05, | |
| "loss": 0.0701, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "eval_loss": 0.04892342910170555, | |
| "eval_runtime": 1834.6912, | |
| "eval_samples_per_second": 22.16, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.05234389359007606, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 2.4091754938448327e-05, | |
| "loss": 0.0686, | |
| "step": 108100 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 2.4020183223590038e-05, | |
| "loss": 0.0741, | |
| "step": 108200 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 2.394861150873175e-05, | |
| "loss": 0.0739, | |
| "step": 108300 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 2.3877039793873463e-05, | |
| "loss": 0.0727, | |
| "step": 108400 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 2.3805468079015174e-05, | |
| "loss": 0.0746, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "eval_loss": 0.049333617091178894, | |
| "eval_runtime": 1824.4661, | |
| "eval_samples_per_second": 22.284, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.05256293730062616, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 2.3733896364156885e-05, | |
| "loss": 0.0622, | |
| "step": 108600 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 2.36623246492986e-05, | |
| "loss": 0.074, | |
| "step": 108700 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 2.359075293444031e-05, | |
| "loss": 0.0714, | |
| "step": 108800 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 2.3519896936730606e-05, | |
| "loss": 0.0745, | |
| "step": 108900 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 2.3448325221872317e-05, | |
| "loss": 0.0716, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "eval_loss": 0.04945548623800278, | |
| "eval_runtime": 1827.2039, | |
| "eval_samples_per_second": 22.251, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.052860031068958487, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 2.3376753507014028e-05, | |
| "loss": 0.0699, | |
| "step": 109100 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 2.3305181792155742e-05, | |
| "loss": 0.0688, | |
| "step": 109200 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 2.3233610077297453e-05, | |
| "loss": 0.0746, | |
| "step": 109300 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 2.3162038362439164e-05, | |
| "loss": 0.0711, | |
| "step": 109400 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 2.309046664758088e-05, | |
| "loss": 0.066, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "eval_loss": 0.04909636825323105, | |
| "eval_runtime": 1828.2358, | |
| "eval_samples_per_second": 22.238, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.052583079251021576, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 2.301889493272259e-05, | |
| "loss": 0.0685, | |
| "step": 109600 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 2.29473232178643e-05, | |
| "loss": 0.0705, | |
| "step": 109700 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 2.2875751503006014e-05, | |
| "loss": 0.072, | |
| "step": 109800 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 2.2804179788147725e-05, | |
| "loss": 0.0639, | |
| "step": 109900 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 2.273260807328944e-05, | |
| "loss": 0.0713, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "eval_loss": 0.04901296645402908, | |
| "eval_runtime": 1831.8124, | |
| "eval_samples_per_second": 22.195, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.051437505822282535, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 2.2661036358431147e-05, | |
| "loss": 0.0634, | |
| "step": 110100 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 2.258946464357286e-05, | |
| "loss": 0.0678, | |
| "step": 110200 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 2.2517892928714572e-05, | |
| "loss": 0.0723, | |
| "step": 110300 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 2.2446321213856286e-05, | |
| "loss": 0.0658, | |
| "step": 110400 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 2.2374749498997997e-05, | |
| "loss": 0.0659, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "eval_loss": 0.04921530932188034, | |
| "eval_runtime": 1824.0313, | |
| "eval_samples_per_second": 22.29, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.051646478557634934, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 2.2303177784139708e-05, | |
| "loss": 0.0657, | |
| "step": 110600 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 2.2231606069281422e-05, | |
| "loss": 0.075, | |
| "step": 110700 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 2.2160034354423133e-05, | |
| "loss": 0.0671, | |
| "step": 110800 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 2.2088462639564844e-05, | |
| "loss": 0.0685, | |
| "step": 110900 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 2.2016890924706558e-05, | |
| "loss": 0.0737, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "eval_loss": 0.048330530524253845, | |
| "eval_runtime": 1835.5696, | |
| "eval_samples_per_second": 22.15, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.050319627575337186, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 2.194531920984827e-05, | |
| "loss": 0.0692, | |
| "step": 111100 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 2.1873747494989983e-05, | |
| "loss": 0.0766, | |
| "step": 111200 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 2.180217578013169e-05, | |
| "loss": 0.0688, | |
| "step": 111300 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 2.1730604065273405e-05, | |
| "loss": 0.0766, | |
| "step": 111400 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 2.165903235041512e-05, | |
| "loss": 0.0737, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "eval_loss": 0.048398155719041824, | |
| "eval_runtime": 1833.2465, | |
| "eval_samples_per_second": 22.178, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.05055629549248328, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 2.1587460635556827e-05, | |
| "loss": 0.0664, | |
| "step": 111600 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 2.151588892069854e-05, | |
| "loss": 0.069, | |
| "step": 111700 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 2.1444317205840252e-05, | |
| "loss": 0.0679, | |
| "step": 111800 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 2.1372745490981966e-05, | |
| "loss": 0.0667, | |
| "step": 111900 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 2.1301173776123677e-05, | |
| "loss": 0.0658, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "eval_loss": 0.048916447907686234, | |
| "eval_runtime": 1824.2933, | |
| "eval_samples_per_second": 22.286, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.05138463320249458, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 2.1229602061265388e-05, | |
| "loss": 0.0697, | |
| "step": 112100 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 2.1158030346407102e-05, | |
| "loss": 0.067, | |
| "step": 112200 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 2.1086458631548813e-05, | |
| "loss": 0.0694, | |
| "step": 112300 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 2.1014886916690524e-05, | |
| "loss": 0.0693, | |
| "step": 112400 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 2.0943315201832238e-05, | |
| "loss": 0.0726, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "eval_loss": 0.0476616695523262, | |
| "eval_runtime": 1826.5028, | |
| "eval_samples_per_second": 22.259, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.050674629451056316, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 2.087174348697395e-05, | |
| "loss": 0.0712, | |
| "step": 112600 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 2.0800171772115663e-05, | |
| "loss": 0.0644, | |
| "step": 112700 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 2.072860005725737e-05, | |
| "loss": 0.0713, | |
| "step": 112800 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 2.0657028342399085e-05, | |
| "loss": 0.0664, | |
| "step": 112900 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 2.0585456627540796e-05, | |
| "loss": 0.0737, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "eval_loss": 0.048905979841947556, | |
| "eval_runtime": 1825.083, | |
| "eval_samples_per_second": 22.277, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.05078792792203051, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 2.051388491268251e-05, | |
| "loss": 0.0675, | |
| "step": 113100 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 2.044231319782422e-05, | |
| "loss": 0.072, | |
| "step": 113200 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 2.0370741482965932e-05, | |
| "loss": 0.0695, | |
| "step": 113300 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 2.0299169768107646e-05, | |
| "loss": 0.0698, | |
| "step": 113400 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.0227598053249357e-05, | |
| "loss": 0.0677, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "eval_loss": 0.04910281300544739, | |
| "eval_runtime": 1824.7593, | |
| "eval_samples_per_second": 22.281, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.05099438291358348, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 2.0156026338391068e-05, | |
| "loss": 0.0623, | |
| "step": 113600 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.0085170340681364e-05, | |
| "loss": 0.0683, | |
| "step": 113700 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 2.0013598625823075e-05, | |
| "loss": 0.0632, | |
| "step": 113800 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 1.9942026910964786e-05, | |
| "loss": 0.068, | |
| "step": 113900 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 1.98704551961065e-05, | |
| "loss": 0.0696, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "eval_loss": 0.048529524356126785, | |
| "eval_runtime": 1820.0724, | |
| "eval_samples_per_second": 22.338, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.05079296340962936, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 1.979888348124821e-05, | |
| "loss": 0.0719, | |
| "step": 114100 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 1.9727311766389925e-05, | |
| "loss": 0.0744, | |
| "step": 114200 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 1.9655740051531636e-05, | |
| "loss": 0.074, | |
| "step": 114300 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 1.9584168336673347e-05, | |
| "loss": 0.0718, | |
| "step": 114400 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 1.951259662181506e-05, | |
| "loss": 0.0611, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 0.05006314441561699, | |
| "eval_runtime": 1826.7292, | |
| "eval_samples_per_second": 22.257, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.04994448374922265, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 1.9441024906956772e-05, | |
| "loss": 0.0675, | |
| "step": 114600 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 1.9369453192098483e-05, | |
| "loss": 0.0679, | |
| "step": 114700 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 1.9297881477240194e-05, | |
| "loss": 0.0643, | |
| "step": 114800 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 1.9226309762381908e-05, | |
| "loss": 0.0672, | |
| "step": 114900 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "learning_rate": 1.915473804752362e-05, | |
| "loss": 0.0629, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 12.17, | |
| "eval_loss": 0.04922989010810852, | |
| "eval_runtime": 1829.6851, | |
| "eval_samples_per_second": 22.221, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05026423721174981, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 1.908316633266533e-05, | |
| "loss": 0.0713, | |
| "step": 115100 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 1.9011594617807044e-05, | |
| "loss": 0.0754, | |
| "step": 115200 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 1.8940022902948755e-05, | |
| "loss": 0.0697, | |
| "step": 115300 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 1.8868451188090466e-05, | |
| "loss": 0.0681, | |
| "step": 115400 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 1.879687947323218e-05, | |
| "loss": 0.0694, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "eval_loss": 0.049531176686286926, | |
| "eval_runtime": 1837.6219, | |
| "eval_samples_per_second": 22.125, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.04969019162548057, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 1.872530775837389e-05, | |
| "loss": 0.0659, | |
| "step": 115600 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 1.8653736043515605e-05, | |
| "loss": 0.0708, | |
| "step": 115700 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 1.8582164328657313e-05, | |
| "loss": 0.0688, | |
| "step": 115800 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 1.851130833094761e-05, | |
| "loss": 0.0685, | |
| "step": 115900 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 1.8440452333237906e-05, | |
| "loss": 0.1572, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "eval_loss": 0.049631938338279724, | |
| "eval_runtime": 1835.3359, | |
| "eval_samples_per_second": 22.152, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.04996714344341748, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 1.8368880618379617e-05, | |
| "loss": 0.0727, | |
| "step": 116100 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 1.8297308903521328e-05, | |
| "loss": 0.0696, | |
| "step": 116200 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.8225737188663042e-05, | |
| "loss": 0.0676, | |
| "step": 116300 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 1.8154165473804756e-05, | |
| "loss": 0.07, | |
| "step": 116400 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 1.8082593758946464e-05, | |
| "loss": 0.0662, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "eval_loss": 0.049057915806770325, | |
| "eval_runtime": 1830.7122, | |
| "eval_samples_per_second": 22.208, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.05012827904658078, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 1.8011022044088178e-05, | |
| "loss": 0.0711, | |
| "step": 116600 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 1.793945032922989e-05, | |
| "loss": 0.0664, | |
| "step": 116700 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 1.78678786143716e-05, | |
| "loss": 0.0645, | |
| "step": 116800 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 1.7797022616661896e-05, | |
| "loss": 0.065, | |
| "step": 116900 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 1.7725450901803607e-05, | |
| "loss": 0.0667, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "eval_loss": 0.04901137202978134, | |
| "eval_runtime": 1832.9392, | |
| "eval_samples_per_second": 22.181, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.04970529808827713, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 1.765387918694532e-05, | |
| "loss": 0.0643, | |
| "step": 117100 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 1.7582307472087032e-05, | |
| "loss": 0.071, | |
| "step": 117200 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 1.7510735757228743e-05, | |
| "loss": 0.0683, | |
| "step": 117300 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 1.7439164042370457e-05, | |
| "loss": 0.0647, | |
| "step": 117400 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 1.7367592327512168e-05, | |
| "loss": 0.0717, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "eval_loss": 0.048731982707977295, | |
| "eval_runtime": 1829.6207, | |
| "eval_samples_per_second": 22.222, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.04953660925371556, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 1.729602061265388e-05, | |
| "loss": 0.07, | |
| "step": 117600 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 1.7224448897795593e-05, | |
| "loss": 0.0697, | |
| "step": 117700 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 1.7152877182937304e-05, | |
| "loss": 0.0701, | |
| "step": 117800 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 1.7081305468079015e-05, | |
| "loss": 0.0672, | |
| "step": 117900 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 1.700973375322073e-05, | |
| "loss": 0.0632, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "eval_loss": 0.04887591302394867, | |
| "eval_runtime": 1827.6581, | |
| "eval_samples_per_second": 22.245, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.04944345273313678, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 1.693816203836244e-05, | |
| "loss": 0.0688, | |
| "step": 118100 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 1.6866590323504154e-05, | |
| "loss": 0.0623, | |
| "step": 118200 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 1.679501860864586e-05, | |
| "loss": 0.068, | |
| "step": 118300 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 1.6723446893787576e-05, | |
| "loss": 0.066, | |
| "step": 118400 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 1.6651875178929287e-05, | |
| "loss": 0.0664, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "eval_loss": 0.048927851021289825, | |
| "eval_runtime": 1844.5767, | |
| "eval_samples_per_second": 22.041, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.04969522711307943, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 1.6580303464071e-05, | |
| "loss": 0.0661, | |
| "step": 118600 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 1.6508731749212712e-05, | |
| "loss": 0.0682, | |
| "step": 118700 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 1.6437160034354423e-05, | |
| "loss": 0.0709, | |
| "step": 118800 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 1.6365588319496137e-05, | |
| "loss": 0.062, | |
| "step": 118900 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 1.6294016604637848e-05, | |
| "loss": 0.0671, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "eval_loss": 0.04836230352520943, | |
| "eval_runtime": 1819.41, | |
| "eval_samples_per_second": 22.346, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.049362884931555134, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 1.622244488977956e-05, | |
| "loss": 0.066, | |
| "step": 119100 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 1.6150873174921273e-05, | |
| "loss": 0.066, | |
| "step": 119200 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 1.6079301460062984e-05, | |
| "loss": 0.0682, | |
| "step": 119300 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 1.6007729745204698e-05, | |
| "loss": 0.0728, | |
| "step": 119400 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 1.5936158030346406e-05, | |
| "loss": 0.0612, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "eval_loss": 0.04909917339682579, | |
| "eval_runtime": 1834.4038, | |
| "eval_samples_per_second": 22.164, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.04954416248511384, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "learning_rate": 1.586458631548812e-05, | |
| "loss": 0.0637, | |
| "step": 119600 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 1.5793014600629834e-05, | |
| "loss": 0.0694, | |
| "step": 119700 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 1.5721442885771545e-05, | |
| "loss": 0.0684, | |
| "step": 119800 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 1.5649871170913256e-05, | |
| "loss": 0.067, | |
| "step": 119900 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 1.5578299456054967e-05, | |
| "loss": 0.0626, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "eval_loss": 0.04957260563969612, | |
| "eval_runtime": 1831.8282, | |
| "eval_samples_per_second": 22.195, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.049352813956357426, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 1.550672774119668e-05, | |
| "loss": 0.0644, | |
| "step": 120100 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 1.5435156026338392e-05, | |
| "loss": 0.0699, | |
| "step": 120200 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 1.5363584311480103e-05, | |
| "loss": 0.0653, | |
| "step": 120300 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 1.5292012596621817e-05, | |
| "loss": 0.0632, | |
| "step": 120400 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 1.5220440881763528e-05, | |
| "loss": 0.0602, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "eval_loss": 0.04886753484606743, | |
| "eval_runtime": 1822.8349, | |
| "eval_samples_per_second": 22.304, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.048944939460850344, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 1.5148869166905239e-05, | |
| "loss": 0.0631, | |
| "step": 120600 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 1.5077297452046951e-05, | |
| "loss": 0.0729, | |
| "step": 120700 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 1.5005725737188664e-05, | |
| "loss": 0.0713, | |
| "step": 120800 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 1.4934154022330376e-05, | |
| "loss": 0.0656, | |
| "step": 120900 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 1.4862582307472087e-05, | |
| "loss": 0.0722, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "eval_loss": 0.048054035753011703, | |
| "eval_runtime": 1825.4105, | |
| "eval_samples_per_second": 22.273, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.04933267200596202, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 1.47910105926138e-05, | |
| "loss": 0.0739, | |
| "step": 121100 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 1.4719438877755512e-05, | |
| "loss": 0.069, | |
| "step": 121200 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 1.4647867162897225e-05, | |
| "loss": 0.0631, | |
| "step": 121300 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 1.4576295448038934e-05, | |
| "loss": 0.0701, | |
| "step": 121400 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.4504723733180647e-05, | |
| "loss": 0.0677, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_loss": 0.048838987946510315, | |
| "eval_runtime": 1836.5499, | |
| "eval_samples_per_second": 22.138, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.04972795778247197, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 1.443315201832236e-05, | |
| "loss": 0.0693, | |
| "step": 121600 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 1.4361580303464073e-05, | |
| "loss": 0.066, | |
| "step": 121700 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 1.4290008588605783e-05, | |
| "loss": 0.0646, | |
| "step": 121800 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 1.4218436873747495e-05, | |
| "loss": 0.0708, | |
| "step": 121900 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 1.4146865158889208e-05, | |
| "loss": 0.0642, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "eval_loss": 0.04883807525038719, | |
| "eval_runtime": 1830.5672, | |
| "eval_samples_per_second": 22.21, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.04998224990621404, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "learning_rate": 1.407529344403092e-05, | |
| "loss": 0.0703, | |
| "step": 122100 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 1.4003721729172631e-05, | |
| "loss": 0.0663, | |
| "step": 122200 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 1.3932150014314344e-05, | |
| "loss": 0.0716, | |
| "step": 122300 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 1.3860578299456056e-05, | |
| "loss": 0.0619, | |
| "step": 122400 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 1.3789006584597769e-05, | |
| "loss": 0.0635, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "eval_loss": 0.04818987101316452, | |
| "eval_runtime": 1819.7529, | |
| "eval_samples_per_second": 22.342, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.04981104332785304, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 1.371743486973948e-05, | |
| "loss": 0.0644, | |
| "step": 122600 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 1.3645863154881192e-05, | |
| "loss": 0.059, | |
| "step": 122700 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.3574291440022905e-05, | |
| "loss": 0.0602, | |
| "step": 122800 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.3502719725164614e-05, | |
| "loss": 0.0654, | |
| "step": 122900 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.3431148010306326e-05, | |
| "loss": 0.0702, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_loss": 0.04797869920730591, | |
| "eval_runtime": 1833.1698, | |
| "eval_samples_per_second": 22.179, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.04974306424526853, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 1.3359576295448039e-05, | |
| "loss": 0.064, | |
| "step": 123100 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.3288004580589753e-05, | |
| "loss": 0.0601, | |
| "step": 123200 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.3216432865731462e-05, | |
| "loss": 0.0719, | |
| "step": 123300 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 1.3145576868021759e-05, | |
| "loss": 0.0652, | |
| "step": 123400 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 1.3074005153163471e-05, | |
| "loss": 0.0622, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "eval_loss": 0.048894256353378296, | |
| "eval_runtime": 1828.9612, | |
| "eval_samples_per_second": 22.23, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.04932260103076431, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 1.3002433438305184e-05, | |
| "loss": 0.0659, | |
| "step": 123600 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 1.2930861723446893e-05, | |
| "loss": 0.0649, | |
| "step": 123700 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 1.2859290008588606e-05, | |
| "loss": 0.0656, | |
| "step": 123800 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 1.2787718293730318e-05, | |
| "loss": 0.0612, | |
| "step": 123900 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 1.271614657887203e-05, | |
| "loss": 0.0654, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "eval_loss": 0.048558782786130905, | |
| "eval_runtime": 1821.9996, | |
| "eval_samples_per_second": 22.314, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.049521502790919, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 1.2644574864013742e-05, | |
| "loss": 0.0686, | |
| "step": 124100 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 1.2573003149155454e-05, | |
| "loss": 0.0695, | |
| "step": 124200 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 1.2501431434297167e-05, | |
| "loss": 0.0619, | |
| "step": 124300 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 1.2429859719438878e-05, | |
| "loss": 0.0699, | |
| "step": 124400 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 1.235828800458059e-05, | |
| "loss": 0.0682, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "eval_loss": 0.04828205704689026, | |
| "eval_runtime": 1835.7356, | |
| "eval_samples_per_second": 22.148, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.049191678353194136, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 1.2286716289722303e-05, | |
| "loss": 0.0633, | |
| "step": 124600 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 1.2215144574864014e-05, | |
| "loss": 0.0599, | |
| "step": 124700 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 1.2143572860005726e-05, | |
| "loss": 0.0641, | |
| "step": 124800 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 1.2072001145147437e-05, | |
| "loss": 0.0681, | |
| "step": 124900 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 1.2000429430289151e-05, | |
| "loss": 0.062, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "eval_loss": 0.04858024790883064, | |
| "eval_runtime": 1837.6255, | |
| "eval_samples_per_second": 22.125, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.04906830890702224, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 1.1928857715430862e-05, | |
| "loss": 0.0657, | |
| "step": 125100 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 1.1857286000572575e-05, | |
| "loss": 0.061, | |
| "step": 125200 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 1.1785714285714286e-05, | |
| "loss": 0.0698, | |
| "step": 125300 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 1.1714142570855998e-05, | |
| "loss": 0.0683, | |
| "step": 125400 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 1.164257085599771e-05, | |
| "loss": 0.0666, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "eval_loss": 0.04896119236946106, | |
| "eval_runtime": 1836.7021, | |
| "eval_samples_per_second": 22.136, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.04922944451018553, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 1.1570999141139423e-05, | |
| "loss": 0.0598, | |
| "step": 125600 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 1.1500143143429718e-05, | |
| "loss": 0.0674, | |
| "step": 125700 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.0653, | |
| "step": 125800 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 1.1356999713713142e-05, | |
| "loss": 0.0702, | |
| "step": 125900 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 1.1286143716003436e-05, | |
| "loss": 0.1656, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "eval_loss": 0.048706572502851486, | |
| "eval_runtime": 1826.5133, | |
| "eval_samples_per_second": 22.259, | |
| "eval_steps_per_second": 1.392, | |
| "eval_wer": 0.049619694799096635, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 1.1214572001145147e-05, | |
| "loss": 0.0678, | |
| "step": 126100 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 1.114300028628686e-05, | |
| "loss": 0.0643, | |
| "step": 126200 | |
| }, | |
| { | |
| "epoch": 13.37, | |
| "learning_rate": 1.107142857142857e-05, | |
| "loss": 0.0645, | |
| "step": 126300 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 1.0999856856570285e-05, | |
| "loss": 0.0644, | |
| "step": 126400 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 1.0928285141711996e-05, | |
| "loss": 0.0633, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "eval_loss": 0.048714131116867065, | |
| "eval_runtime": 1830.5984, | |
| "eval_samples_per_second": 22.21, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.04972040455107369, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 1.0856713426853708e-05, | |
| "loss": 0.0649, | |
| "step": 126600 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 1.078514171199542e-05, | |
| "loss": 0.0598, | |
| "step": 126700 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 1.0713569997137132e-05, | |
| "loss": 0.0625, | |
| "step": 126800 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 1.0641998282278844e-05, | |
| "loss": 0.0601, | |
| "step": 126900 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 1.0570426567420557e-05, | |
| "loss": 0.0578, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "eval_loss": 0.04878106340765953, | |
| "eval_runtime": 1833.6071, | |
| "eval_samples_per_second": 22.173, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.04906830890702224, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 1.0498854852562268e-05, | |
| "loss": 0.066, | |
| "step": 127100 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "learning_rate": 1.042728313770398e-05, | |
| "loss": 0.0665, | |
| "step": 127200 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 1.0355711422845691e-05, | |
| "loss": 0.0616, | |
| "step": 127300 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 1.0284139707987404e-05, | |
| "loss": 0.0654, | |
| "step": 127400 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 1.0212567993129116e-05, | |
| "loss": 0.0595, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "eval_loss": 0.04866622015833855, | |
| "eval_runtime": 1819.6226, | |
| "eval_samples_per_second": 22.344, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.04997217893101634, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 1.0140996278270829e-05, | |
| "loss": 0.0655, | |
| "step": 127600 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 1.006942456341254e-05, | |
| "loss": 0.0638, | |
| "step": 127700 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 9.997852848554252e-06, | |
| "loss": 0.0595, | |
| "step": 127800 | |
| }, | |
| { | |
| "epoch": 13.54, | |
| "learning_rate": 9.926281133695963e-06, | |
| "loss": 0.0652, | |
| "step": 127900 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 9.854709418837676e-06, | |
| "loss": 0.0645, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "eval_loss": 0.048221223056316376, | |
| "eval_runtime": 1838.9644, | |
| "eval_samples_per_second": 22.109, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.04932511877456374, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 9.783137703979388e-06, | |
| "loss": 0.0625, | |
| "step": 128100 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 9.711565989121099e-06, | |
| "loss": 0.0665, | |
| "step": 128200 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 9.639994274262812e-06, | |
| "loss": 0.0615, | |
| "step": 128300 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 9.568422559404523e-06, | |
| "loss": 0.0604, | |
| "step": 128400 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 9.496850844546235e-06, | |
| "loss": 0.0722, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 0.04833672195672989, | |
| "eval_runtime": 1826.932, | |
| "eval_samples_per_second": 22.254, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.05003008703840315, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 9.425279129687948e-06, | |
| "loss": 0.0631, | |
| "step": 128600 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 9.35370741482966e-06, | |
| "loss": 0.0638, | |
| "step": 128700 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 9.282135699971371e-06, | |
| "loss": 0.0658, | |
| "step": 128800 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 9.210563985113084e-06, | |
| "loss": 0.0683, | |
| "step": 128900 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "learning_rate": 9.139707987403378e-06, | |
| "loss": 0.0664, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "eval_loss": 0.04846007749438286, | |
| "eval_runtime": 1820.3909, | |
| "eval_samples_per_second": 22.334, | |
| "eval_steps_per_second": 1.396, | |
| "eval_wer": 0.04959955284870122, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 9.06813627254509e-06, | |
| "loss": 0.0623, | |
| "step": 129100 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 8.996564557686802e-06, | |
| "loss": 0.0625, | |
| "step": 129200 | |
| }, | |
| { | |
| "epoch": 13.69, | |
| "learning_rate": 8.924992842828514e-06, | |
| "loss": 0.0679, | |
| "step": 129300 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 8.853421127970227e-06, | |
| "loss": 0.0622, | |
| "step": 129400 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 8.781849413111938e-06, | |
| "loss": 0.0627, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "eval_loss": 0.04862232133746147, | |
| "eval_runtime": 1827.8151, | |
| "eval_samples_per_second": 22.243, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.049760688451864515, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 8.71027769825365e-06, | |
| "loss": 0.066, | |
| "step": 129600 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 8.638705983395361e-06, | |
| "loss": 0.0682, | |
| "step": 129700 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 8.567849985685658e-06, | |
| "loss": 0.0593, | |
| "step": 129800 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 8.496278270827369e-06, | |
| "loss": 0.0645, | |
| "step": 129900 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 8.424706555969081e-06, | |
| "loss": 0.0605, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "eval_loss": 0.04856153205037117, | |
| "eval_runtime": 1838.7377, | |
| "eval_samples_per_second": 22.111, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.04961717705529721, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 8.353134841110794e-06, | |
| "loss": 0.0668, | |
| "step": 130100 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 8.281563126252505e-06, | |
| "loss": 0.0622, | |
| "step": 130200 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 8.209991411394217e-06, | |
| "loss": 0.0703, | |
| "step": 130300 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 8.138419696535928e-06, | |
| "loss": 0.0621, | |
| "step": 130400 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 8.066847981677642e-06, | |
| "loss": 0.0678, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "eval_loss": 0.04805918410420418, | |
| "eval_runtime": 1838.7425, | |
| "eval_samples_per_second": 22.111, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.04979090137745763, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 7.995276266819353e-06, | |
| "loss": 0.0643, | |
| "step": 130600 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 7.923704551961066e-06, | |
| "loss": 0.0668, | |
| "step": 130700 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "learning_rate": 7.852132837102777e-06, | |
| "loss": 0.0674, | |
| "step": 130800 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 7.78056112224449e-06, | |
| "loss": 0.061, | |
| "step": 130900 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 7.708989407386202e-06, | |
| "loss": 0.0695, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "eval_loss": 0.04855675995349884, | |
| "eval_runtime": 1837.8543, | |
| "eval_samples_per_second": 22.122, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.049526538278517857, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 7.637417692527914e-06, | |
| "loss": 0.0655, | |
| "step": 131100 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 7.565845977669625e-06, | |
| "loss": 0.0586, | |
| "step": 131200 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 7.494274262811338e-06, | |
| "loss": 0.0657, | |
| "step": 131300 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 7.422702547953049e-06, | |
| "loss": 0.0682, | |
| "step": 131400 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 7.351130833094762e-06, | |
| "loss": 0.0609, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "eval_loss": 0.047664593905210495, | |
| "eval_runtime": 1840.439, | |
| "eval_samples_per_second": 22.091, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.049659978699887454, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 7.279559118236473e-06, | |
| "loss": 0.0694, | |
| "step": 131600 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 7.207987403378185e-06, | |
| "loss": 0.0716, | |
| "step": 131700 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 7.136415688519897e-06, | |
| "loss": 0.0704, | |
| "step": 131800 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 7.06484397366161e-06, | |
| "loss": 0.063, | |
| "step": 131900 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 6.993272258803321e-06, | |
| "loss": 0.064, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "eval_loss": 0.04809276759624481, | |
| "eval_runtime": 1827.0981, | |
| "eval_samples_per_second": 22.252, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.04962221254289606, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 6.921700543945034e-06, | |
| "loss": 0.0638, | |
| "step": 132100 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 6.850128829086745e-06, | |
| "loss": 0.0621, | |
| "step": 132200 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 6.778557114228458e-06, | |
| "loss": 0.0627, | |
| "step": 132300 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 6.706985399370169e-06, | |
| "loss": 0.0664, | |
| "step": 132400 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 6.635413684511881e-06, | |
| "loss": 0.0583, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_loss": 0.04831588640809059, | |
| "eval_runtime": 1845.025, | |
| "eval_samples_per_second": 22.036, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.04987146917903928, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 6.563841969653593e-06, | |
| "loss": 0.0666, | |
| "step": 132600 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 6.492270254795304e-06, | |
| "loss": 0.063, | |
| "step": 132700 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 6.420698539937018e-06, | |
| "loss": 0.0623, | |
| "step": 132800 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 6.3491268250787285e-06, | |
| "loss": 0.0659, | |
| "step": 132900 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 6.277555110220441e-06, | |
| "loss": 0.0639, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "eval_loss": 0.04831910505890846, | |
| "eval_runtime": 1836.6719, | |
| "eval_samples_per_second": 22.136, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.049858880460042145, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 6.2059833953621536e-06, | |
| "loss": 0.0667, | |
| "step": 133100 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 6.134411680503865e-06, | |
| "loss": 0.0616, | |
| "step": 133200 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 6.062839965645577e-06, | |
| "loss": 0.073, | |
| "step": 133300 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 5.9912682507872895e-06, | |
| "loss": 0.0593, | |
| "step": 133400 | |
| }, | |
| { | |
| "epoch": 14.13, | |
| "learning_rate": 5.919696535929001e-06, | |
| "loss": 0.0683, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 14.13, | |
| "eval_loss": 0.04767517372965813, | |
| "eval_runtime": 1835.1685, | |
| "eval_samples_per_second": 22.154, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.049461076939732763, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 5.848124821070714e-06, | |
| "loss": 0.0592, | |
| "step": 133600 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 5.776553106212425e-06, | |
| "loss": 0.066, | |
| "step": 133700 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 5.704981391354137e-06, | |
| "loss": 0.0624, | |
| "step": 133800 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 5.634125393644432e-06, | |
| "loss": 0.0665, | |
| "step": 133900 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 5.562553678786144e-06, | |
| "loss": 0.0623, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "eval_loss": 0.04846768081188202, | |
| "eval_runtime": 1833.4683, | |
| "eval_samples_per_second": 22.175, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.049211820303589546, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 5.490981963927856e-06, | |
| "loss": 0.0599, | |
| "step": 134100 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 5.419410249069568e-06, | |
| "loss": 0.0645, | |
| "step": 134200 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 5.347838534211281e-06, | |
| "loss": 0.0583, | |
| "step": 134300 | |
| }, | |
| { | |
| "epoch": 14.23, | |
| "learning_rate": 5.276266819352992e-06, | |
| "loss": 0.0621, | |
| "step": 134400 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 5.204695104494704e-06, | |
| "loss": 0.0669, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "eval_loss": 0.048293642699718475, | |
| "eval_runtime": 1841.2938, | |
| "eval_samples_per_second": 22.081, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.049169018658999294, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 5.133123389636416e-06, | |
| "loss": 0.068, | |
| "step": 134600 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 5.0615516747781274e-06, | |
| "loss": 0.0633, | |
| "step": 134700 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 4.98997995991984e-06, | |
| "loss": 0.0616, | |
| "step": 134800 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 4.918408245061552e-06, | |
| "loss": 0.0659, | |
| "step": 134900 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 4.846836530203263e-06, | |
| "loss": 0.0603, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "eval_loss": 0.048429086804389954, | |
| "eval_runtime": 1851.3356, | |
| "eval_samples_per_second": 21.961, | |
| "eval_steps_per_second": 1.373, | |
| "eval_wer": 0.04943841724553793, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 4.775264815344976e-06, | |
| "loss": 0.0677, | |
| "step": 135100 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 4.703693100486688e-06, | |
| "loss": 0.0689, | |
| "step": 135200 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 4.632121385628399e-06, | |
| "loss": 0.063, | |
| "step": 135300 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 4.560549670770112e-06, | |
| "loss": 0.0672, | |
| "step": 135400 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 4.488977955911824e-06, | |
| "loss": 0.0696, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "eval_loss": 0.047997210174798965, | |
| "eval_runtime": 1831.5813, | |
| "eval_samples_per_second": 22.198, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.04937547365055227, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 4.417406241053535e-06, | |
| "loss": 0.057, | |
| "step": 135600 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 4.345834526195248e-06, | |
| "loss": 0.0628, | |
| "step": 135700 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 4.27426281133696e-06, | |
| "loss": 0.0636, | |
| "step": 135800 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 4.202691096478672e-06, | |
| "loss": 0.0643, | |
| "step": 135900 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "learning_rate": 4.131835098768966e-06, | |
| "loss": 0.0631, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "eval_loss": 0.04820747300982475, | |
| "eval_runtime": 1831.5305, | |
| "eval_samples_per_second": 22.198, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.049357849443956284, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 4.060263383910679e-06, | |
| "loss": 0.0646, | |
| "step": 136100 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 3.989407386200974e-06, | |
| "loss": 0.062, | |
| "step": 136200 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 3.917835671342686e-06, | |
| "loss": 0.062, | |
| "step": 136300 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 3.846263956484398e-06, | |
| "loss": 0.0694, | |
| "step": 136400 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "learning_rate": 3.774692241626109e-06, | |
| "loss": 0.0587, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "eval_loss": 0.04808710515499115, | |
| "eval_runtime": 1829.4666, | |
| "eval_samples_per_second": 22.223, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.049304976824168324, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 3.7031205267678213e-06, | |
| "loss": 0.0698, | |
| "step": 136600 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 3.6315488119095334e-06, | |
| "loss": 0.0665, | |
| "step": 136700 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 3.559977097051245e-06, | |
| "loss": 0.0643, | |
| "step": 136800 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 3.4884053821929572e-06, | |
| "loss": 0.0584, | |
| "step": 136900 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 3.4168336673346694e-06, | |
| "loss": 0.0671, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "eval_loss": 0.048282139003276825, | |
| "eval_runtime": 1823.6394, | |
| "eval_samples_per_second": 22.294, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.04924706871678152, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 3.3452619524763815e-06, | |
| "loss": 0.0571, | |
| "step": 137100 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 3.2736902376180932e-06, | |
| "loss": 0.0654, | |
| "step": 137200 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 3.2021185227598054e-06, | |
| "loss": 0.1572, | |
| "step": 137300 | |
| }, | |
| { | |
| "epoch": 14.54, | |
| "learning_rate": 3.1305468079015175e-06, | |
| "loss": 0.0708, | |
| "step": 137400 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 3.058975093043229e-06, | |
| "loss": 0.0592, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_loss": 0.048343904316425323, | |
| "eval_runtime": 1833.9888, | |
| "eval_samples_per_second": 22.169, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.04931253005556661, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 2.9874033781849413e-06, | |
| "loss": 0.068, | |
| "step": 137600 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 2.9158316633266535e-06, | |
| "loss": 0.0626, | |
| "step": 137700 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 2.8442599484683656e-06, | |
| "loss": 0.0572, | |
| "step": 137800 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 2.7726882336100773e-06, | |
| "loss": 0.0541, | |
| "step": 137900 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 2.7011165187517894e-06, | |
| "loss": 0.0592, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "eval_loss": 0.048862360417842865, | |
| "eval_runtime": 1830.1496, | |
| "eval_samples_per_second": 22.215, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.04935533170015686, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 2.6295448038935016e-06, | |
| "loss": 0.0612, | |
| "step": 138100 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 2.5579730890352137e-06, | |
| "loss": 0.0652, | |
| "step": 138200 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 2.4864013741769254e-06, | |
| "loss": 0.0624, | |
| "step": 138300 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 2.414829659318637e-06, | |
| "loss": 0.0665, | |
| "step": 138400 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "learning_rate": 2.3432579444603493e-06, | |
| "loss": 0.0584, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "eval_loss": 0.048502907156944275, | |
| "eval_runtime": 1837.1278, | |
| "eval_samples_per_second": 22.131, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.049461076939732763, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 2.2716862296020614e-06, | |
| "loss": 0.0688, | |
| "step": 138600 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 2.200114514743773e-06, | |
| "loss": 0.0667, | |
| "step": 138700 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 2.1285427998854852e-06, | |
| "loss": 0.0614, | |
| "step": 138800 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 2.0569710850271974e-06, | |
| "loss": 0.064, | |
| "step": 138900 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 1.9853993701689095e-06, | |
| "loss": 0.0575, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "eval_loss": 0.048280179500579834, | |
| "eval_runtime": 1832.9473, | |
| "eval_samples_per_second": 22.181, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.049518985047119574, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 1.9138276553106212e-06, | |
| "loss": 0.0643, | |
| "step": 139100 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 1.8422559404523334e-06, | |
| "loss": 0.0632, | |
| "step": 139200 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 1.7706842255940455e-06, | |
| "loss": 0.0665, | |
| "step": 139300 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 1.6991125107357574e-06, | |
| "loss": 0.0637, | |
| "step": 139400 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 1.6275407958774695e-06, | |
| "loss": 0.0724, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "eval_loss": 0.048176757991313934, | |
| "eval_runtime": 1845.2433, | |
| "eval_samples_per_second": 22.033, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.04939058011334883, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 1.5559690810191813e-06, | |
| "loss": 0.0583, | |
| "step": 139600 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 1.4843973661608934e-06, | |
| "loss": 0.0568, | |
| "step": 139700 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 1.4128256513026053e-06, | |
| "loss": 0.0571, | |
| "step": 139800 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 1.3412539364443174e-06, | |
| "loss": 0.0597, | |
| "step": 139900 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 1.2696822215860291e-06, | |
| "loss": 0.0629, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "eval_loss": 0.04831665754318237, | |
| "eval_runtime": 1847.5741, | |
| "eval_samples_per_second": 22.006, | |
| "eval_steps_per_second": 1.376, | |
| "eval_wer": 0.049327636518363166, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 1.1981105067277413e-06, | |
| "loss": 0.0647, | |
| "step": 140100 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 1.1265387918694532e-06, | |
| "loss": 0.0612, | |
| "step": 140200 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 1.0549670770111653e-06, | |
| "loss": 0.0645, | |
| "step": 140300 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 9.833953621528773e-07, | |
| "loss": 0.0602, | |
| "step": 140400 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 9.118236472945893e-07, | |
| "loss": 0.0609, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "eval_loss": 0.048305436968803406, | |
| "eval_runtime": 1838.8119, | |
| "eval_samples_per_second": 22.11, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.04931253005556661, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 8.402519324363011e-07, | |
| "loss": 0.0603, | |
| "step": 140600 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 7.686802175780131e-07, | |
| "loss": 0.0596, | |
| "step": 140700 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 6.971085027197252e-07, | |
| "loss": 0.0576, | |
| "step": 140800 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 6.255367878614372e-07, | |
| "loss": 0.0671, | |
| "step": 140900 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "learning_rate": 5.539650730031492e-07, | |
| "loss": 0.0573, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_loss": 0.04814313352108002, | |
| "eval_runtime": 1824.1706, | |
| "eval_samples_per_second": 22.288, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.049350296212558, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 4.823933581448611e-07, | |
| "loss": 0.0622, | |
| "step": 141100 | |
| }, | |
| { | |
| "epoch": 14.94, | |
| "learning_rate": 4.115373604351561e-07, | |
| "loss": 0.0612, | |
| "step": 141200 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 3.3996564557686805e-07, | |
| "loss": 0.0626, | |
| "step": 141300 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 2.6839393071858003e-07, | |
| "loss": 0.0632, | |
| "step": 141400 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 1.9682221586029203e-07, | |
| "loss": 0.0649, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_loss": 0.0482223704457283, | |
| "eval_runtime": 1855.5531, | |
| "eval_samples_per_second": 21.911, | |
| "eval_steps_per_second": 1.37, | |
| "eval_wer": 0.04934526072495915, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 1.25250501002004e-07, | |
| "loss": 0.0626, | |
| "step": 141600 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5.3678786143716006e-08, | |
| "loss": 0.0637, | |
| "step": 141700 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 141720, | |
| "total_flos": 7.62508050215935e+20, | |
| "train_loss": 0.17642972585578237, | |
| "train_runtime": 792752.3013, | |
| "train_samples_per_second": 5.721, | |
| "train_steps_per_second": 0.179 | |
| } | |
| ], | |
| "max_steps": 141720, | |
| "num_train_epochs": 15, | |
| "total_flos": 7.62508050215935e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |