| { | |
| "best_metric": 80.47772163527792, | |
| "best_model_checkpoint": "./checkpoint-9000", | |
| "epoch": 30.67484662576687, | |
| "eval_steps": 500, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.2e-08, | |
| "loss": 1.4678, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7e-08, | |
| "loss": 1.4671, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.2e-08, | |
| "loss": 1.4626, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.7e-08, | |
| "loss": 1.4314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2199999999999998e-07, | |
| "loss": 1.3735, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.4699999999999998e-07, | |
| "loss": 1.3455, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.7199999999999998e-07, | |
| "loss": 1.3064, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.97e-07, | |
| "loss": 1.2316, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.22e-07, | |
| "loss": 1.1693, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.47e-07, | |
| "loss": 1.1127, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.72e-07, | |
| "loss": 1.0361, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.9699999999999997e-07, | |
| "loss": 0.9756, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.22e-07, | |
| "loss": 0.9191, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.4699999999999997e-07, | |
| "loss": 0.8692, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.72e-07, | |
| "loss": 0.8278, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.97e-07, | |
| "loss": 0.822, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.2199999999999994e-07, | |
| "loss": 0.767, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.4699999999999997e-07, | |
| "loss": 0.7674, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.7199999999999994e-07, | |
| "loss": 0.7284, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.97e-07, | |
| "loss": 0.7392, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.8622996807098389, | |
| "eval_runtime": 1140.8248, | |
| "eval_samples_per_second": 9.174, | |
| "eval_steps_per_second": 0.288, | |
| "eval_wer": 100.81331567996973, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.988421052631579e-07, | |
| "loss": 0.7281, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.975263157894737e-07, | |
| "loss": 0.6999, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.962105263157894e-07, | |
| "loss": 0.7069, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.948947368421052e-07, | |
| "loss": 0.6858, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.93578947368421e-07, | |
| "loss": 0.6881, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.922631578947368e-07, | |
| "loss": 0.6889, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.909473684210526e-07, | |
| "loss": 0.6509, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 4.896315789473684e-07, | |
| "loss": 0.6679, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.883157894736842e-07, | |
| "loss": 0.647, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.87e-07, | |
| "loss": 0.6257, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.856842105263157e-07, | |
| "loss": 0.6503, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.843684210526315e-07, | |
| "loss": 0.6444, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.830526315789473e-07, | |
| "loss": 0.6248, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.817368421052631e-07, | |
| "loss": 0.6189, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.804210526315789e-07, | |
| "loss": 0.6117, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.791052631578947e-07, | |
| "loss": 0.616, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 4.777894736842105e-07, | |
| "loss": 0.6149, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.764736842105263e-07, | |
| "loss": 0.6161, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 4.7515789473684207e-07, | |
| "loss": 0.5894, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 4.7384210526315786e-07, | |
| "loss": 0.5938, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_loss": 0.7397418022155762, | |
| "eval_runtime": 1026.1036, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 0.32, | |
| "eval_wer": 93.66505444621579, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.7252631578947365e-07, | |
| "loss": 0.5896, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 4.7121052631578944e-07, | |
| "loss": 0.5836, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 4.6989473684210524e-07, | |
| "loss": 0.5846, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 4.6857894736842103e-07, | |
| "loss": 0.5738, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.672631578947368e-07, | |
| "loss": 0.5675, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 4.659473684210526e-07, | |
| "loss": 0.5737, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 4.646315789473684e-07, | |
| "loss": 0.5742, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.633157894736842e-07, | |
| "loss": 0.5902, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 4.62e-07, | |
| "loss": 0.573, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 4.6068421052631577e-07, | |
| "loss": 0.5686, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.5936842105263156e-07, | |
| "loss": 0.5673, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.5805263157894735e-07, | |
| "loss": 0.5452, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 4.5673684210526314e-07, | |
| "loss": 0.5624, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 4.5542105263157894e-07, | |
| "loss": 0.5435, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.5410526315789473e-07, | |
| "loss": 0.5538, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.527894736842105e-07, | |
| "loss": 0.5677, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 4.514736842105263e-07, | |
| "loss": 0.5333, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.5015789473684205e-07, | |
| "loss": 0.5482, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.4884210526315784e-07, | |
| "loss": 0.5304, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.4752631578947363e-07, | |
| "loss": 0.5388, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 0.6952596306800842, | |
| "eval_runtime": 1013.9022, | |
| "eval_samples_per_second": 10.322, | |
| "eval_steps_per_second": 0.324, | |
| "eval_wer": 92.30052149477153, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 4.462105263157894e-07, | |
| "loss": 0.5207, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 4.4489473684210526e-07, | |
| "loss": 0.5255, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 4.4357894736842105e-07, | |
| "loss": 0.5491, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 4.4226315789473685e-07, | |
| "loss": 0.5275, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 4.4094736842105264e-07, | |
| "loss": 0.5493, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 4.3963157894736843e-07, | |
| "loss": 0.5299, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 4.383157894736842e-07, | |
| "loss": 0.5211, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 4.3699999999999996e-07, | |
| "loss": 0.5179, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 4.3568421052631575e-07, | |
| "loss": 0.5311, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 4.3436842105263154e-07, | |
| "loss": 0.5316, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.3305263157894733e-07, | |
| "loss": 0.5113, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 4.317368421052631e-07, | |
| "loss": 0.5066, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.304210526315789e-07, | |
| "loss": 0.5082, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 4.291052631578947e-07, | |
| "loss": 0.5041, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 4.2778947368421055e-07, | |
| "loss": 0.5305, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 4.2647368421052634e-07, | |
| "loss": 0.502, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 4.2515789473684213e-07, | |
| "loss": 0.5229, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 4.2384210526315787e-07, | |
| "loss": 0.5048, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 4.2252631578947366e-07, | |
| "loss": 0.5063, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 4.2121052631578945e-07, | |
| "loss": 0.4982, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 0.6682108640670776, | |
| "eval_runtime": 1000.5318, | |
| "eval_samples_per_second": 10.46, | |
| "eval_steps_per_second": 0.328, | |
| "eval_wer": 88.93917695695642, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 4.1989473684210524e-07, | |
| "loss": 0.4973, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 4.1857894736842103e-07, | |
| "loss": 0.4864, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 4.172631578947368e-07, | |
| "loss": 0.5065, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 4.159473684210526e-07, | |
| "loss": 0.5117, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 4.146315789473684e-07, | |
| "loss": 0.4927, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 4.133157894736842e-07, | |
| "loss": 0.4957, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.12e-07, | |
| "loss": 0.4933, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 4.106842105263157e-07, | |
| "loss": 0.4908, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 4.0936842105263157e-07, | |
| "loss": 0.4925, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 4.0805263157894736e-07, | |
| "loss": 0.4896, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 4.0673684210526315e-07, | |
| "loss": 0.4895, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 4.0542105263157894e-07, | |
| "loss": 0.4854, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 4.0410526315789473e-07, | |
| "loss": 0.4833, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 4.027894736842105e-07, | |
| "loss": 0.4865, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 4.014736842105263e-07, | |
| "loss": 0.479, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.001578947368421e-07, | |
| "loss": 0.4846, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 3.988421052631579e-07, | |
| "loss": 0.476, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 3.9752631578947363e-07, | |
| "loss": 0.4839, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 3.962105263157894e-07, | |
| "loss": 0.4812, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 3.948947368421052e-07, | |
| "loss": 0.4795, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_loss": 0.6512458324432373, | |
| "eval_runtime": 980.8976, | |
| "eval_samples_per_second": 10.67, | |
| "eval_steps_per_second": 0.334, | |
| "eval_wer": 90.15239536329001, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 3.93578947368421e-07, | |
| "loss": 0.4687, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 3.9226315789473685e-07, | |
| "loss": 0.478, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 3.9094736842105264e-07, | |
| "loss": 0.4621, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 3.8963157894736843e-07, | |
| "loss": 0.4774, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 3.883157894736842e-07, | |
| "loss": 0.4712, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 3.87e-07, | |
| "loss": 0.4589, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 3.856842105263158e-07, | |
| "loss": 0.4565, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 3.8436842105263154e-07, | |
| "loss": 0.4732, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.8305263157894733e-07, | |
| "loss": 0.4791, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 3.817368421052631e-07, | |
| "loss": 0.4719, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 3.804210526315789e-07, | |
| "loss": 0.4719, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 3.791052631578947e-07, | |
| "loss": 0.4805, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 3.777894736842105e-07, | |
| "loss": 0.4655, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 3.764736842105263e-07, | |
| "loss": 0.459, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 3.751578947368421e-07, | |
| "loss": 0.4437, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 3.738421052631579e-07, | |
| "loss": 0.4595, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 3.725263157894737e-07, | |
| "loss": 0.462, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 3.7121052631578945e-07, | |
| "loss": 0.4692, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 3.6989473684210524e-07, | |
| "loss": 0.463, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.6857894736842103e-07, | |
| "loss": 0.4483, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 0.6372915506362915, | |
| "eval_runtime": 968.9455, | |
| "eval_samples_per_second": 10.801, | |
| "eval_steps_per_second": 0.339, | |
| "eval_wer": 87.12340241562863, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.672631578947368e-07, | |
| "loss": 0.469, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.659473684210526e-07, | |
| "loss": 0.4572, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 3.646315789473684e-07, | |
| "loss": 0.4458, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 3.633157894736842e-07, | |
| "loss": 0.4532, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 3.62e-07, | |
| "loss": 0.4506, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 3.606842105263158e-07, | |
| "loss": 0.4504, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 3.5936842105263157e-07, | |
| "loss": 0.4412, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.580526315789473e-07, | |
| "loss": 0.4631, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 3.5673684210526315e-07, | |
| "loss": 0.4392, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 3.5542105263157894e-07, | |
| "loss": 0.4409, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 3.5410526315789473e-07, | |
| "loss": 0.4404, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 3.527894736842105e-07, | |
| "loss": 0.439, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 3.514736842105263e-07, | |
| "loss": 0.4375, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 3.501578947368421e-07, | |
| "loss": 0.4463, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 3.488421052631579e-07, | |
| "loss": 0.4294, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 3.475263157894737e-07, | |
| "loss": 0.4453, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 3.462105263157895e-07, | |
| "loss": 0.4483, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 3.448947368421052e-07, | |
| "loss": 0.4488, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 3.43578947368421e-07, | |
| "loss": 0.4323, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 3.422631578947368e-07, | |
| "loss": 0.4374, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "eval_loss": 0.626091480255127, | |
| "eval_runtime": 975.9202, | |
| "eval_samples_per_second": 10.724, | |
| "eval_steps_per_second": 0.336, | |
| "eval_wer": 85.31438298792186, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 3.409473684210526e-07, | |
| "loss": 0.4479, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 3.396315789473684e-07, | |
| "loss": 0.4382, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 3.383157894736842e-07, | |
| "loss": 0.4409, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.37e-07, | |
| "loss": 0.4321, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 3.356842105263158e-07, | |
| "loss": 0.4455, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.343684210526316e-07, | |
| "loss": 0.4302, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 3.330526315789474e-07, | |
| "loss": 0.4218, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 3.317368421052631e-07, | |
| "loss": 0.4362, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 3.304210526315789e-07, | |
| "loss": 0.4189, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 3.291052631578947e-07, | |
| "loss": 0.443, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 3.277894736842105e-07, | |
| "loss": 0.4242, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 3.264736842105263e-07, | |
| "loss": 0.4333, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 3.251578947368421e-07, | |
| "loss": 0.4339, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 3.2384210526315787e-07, | |
| "loss": 0.4275, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 3.2252631578947366e-07, | |
| "loss": 0.4339, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 3.2121052631578945e-07, | |
| "loss": 0.4351, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 3.198947368421053e-07, | |
| "loss": 0.4246, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 3.1857894736842103e-07, | |
| "loss": 0.4213, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 3.172631578947368e-07, | |
| "loss": 0.4255, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 3.159473684210526e-07, | |
| "loss": 0.4331, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "eval_loss": 0.6179295778274536, | |
| "eval_runtime": 987.422, | |
| "eval_samples_per_second": 10.599, | |
| "eval_steps_per_second": 0.332, | |
| "eval_wer": 86.42897673538869, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 3.146315789473684e-07, | |
| "loss": 0.4194, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 3.133157894736842e-07, | |
| "loss": 0.4362, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 3.12e-07, | |
| "loss": 0.4288, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 3.106842105263158e-07, | |
| "loss": 0.4327, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 3.0936842105263157e-07, | |
| "loss": 0.4155, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 3.0805263157894736e-07, | |
| "loss": 0.4278, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 3.0673684210526315e-07, | |
| "loss": 0.4111, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 3.054210526315789e-07, | |
| "loss": 0.4332, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.041052631578947e-07, | |
| "loss": 0.4109, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 3.027894736842105e-07, | |
| "loss": 0.4247, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 3.014736842105263e-07, | |
| "loss": 0.4092, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 3.001578947368421e-07, | |
| "loss": 0.4278, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 2.988421052631579e-07, | |
| "loss": 0.4198, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 2.975263157894737e-07, | |
| "loss": 0.4165, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 2.962105263157895e-07, | |
| "loss": 0.4175, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 2.9489473684210527e-07, | |
| "loss": 0.4178, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 2.9357894736842106e-07, | |
| "loss": 0.4227, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "learning_rate": 2.922631578947368e-07, | |
| "loss": 0.406, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 2.909473684210526e-07, | |
| "loss": 0.4042, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 2.896315789473684e-07, | |
| "loss": 0.4125, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "eval_loss": 0.610640287399292, | |
| "eval_runtime": 949.6342, | |
| "eval_samples_per_second": 11.021, | |
| "eval_steps_per_second": 0.345, | |
| "eval_wer": 83.28649787889432, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 2.8831578947368417e-07, | |
| "loss": 0.4217, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 2.8699999999999996e-07, | |
| "loss": 0.4099, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 2.8568421052631575e-07, | |
| "loss": 0.4176, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 2.843684210526316e-07, | |
| "loss": 0.4158, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 2.830526315789474e-07, | |
| "loss": 0.4181, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 2.817368421052632e-07, | |
| "loss": 0.396, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 2.8042105263157897e-07, | |
| "loss": 0.4011, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 2.791052631578947e-07, | |
| "loss": 0.4069, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 2.777894736842105e-07, | |
| "loss": 0.4109, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 2.764736842105263e-07, | |
| "loss": 0.4098, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 2.751578947368421e-07, | |
| "loss": 0.4093, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.7384210526315787e-07, | |
| "loss": 0.4101, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 2.7252631578947366e-07, | |
| "loss": 0.3947, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.7121052631578945e-07, | |
| "loss": 0.4141, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 2.6989473684210524e-07, | |
| "loss": 0.414, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 2.6857894736842104e-07, | |
| "loss": 0.4074, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 2.672631578947369e-07, | |
| "loss": 0.4, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 2.659473684210526e-07, | |
| "loss": 0.4125, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 2.646315789473684e-07, | |
| "loss": 0.3934, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "learning_rate": 2.633157894736842e-07, | |
| "loss": 0.3984, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "eval_loss": 0.6058948040008545, | |
| "eval_runtime": 971.4806, | |
| "eval_samples_per_second": 10.773, | |
| "eval_steps_per_second": 0.338, | |
| "eval_wer": 83.06763219757356, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 2.62e-07, | |
| "loss": 0.4097, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 2.606842105263158e-07, | |
| "loss": 0.3892, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 2.5936842105263157e-07, | |
| "loss": 0.4194, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 2.5805263157894736e-07, | |
| "loss": 0.3991, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 2.5673684210526315e-07, | |
| "loss": 0.3985, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.5542105263157894e-07, | |
| "loss": 0.4032, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 2.5410526315789474e-07, | |
| "loss": 0.4087, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 2.527894736842105e-07, | |
| "loss": 0.3981, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 2.5147368421052626e-07, | |
| "loss": 0.4071, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 2.5015789473684206e-07, | |
| "loss": 0.3962, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 2.488421052631579e-07, | |
| "loss": 0.3838, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 2.475263157894737e-07, | |
| "loss": 0.3985, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 2.4621052631578943e-07, | |
| "loss": 0.3964, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 2.4489473684210527e-07, | |
| "loss": 0.4088, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 16.49, | |
| "learning_rate": 2.4357894736842106e-07, | |
| "loss": 0.3902, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 2.4226315789473685e-07, | |
| "loss": 0.4131, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4094736842105265e-07, | |
| "loss": 0.4108, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 2.396315789473684e-07, | |
| "loss": 0.395, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 2.383157894736842e-07, | |
| "loss": 0.3945, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 2.3699999999999996e-07, | |
| "loss": 0.4035, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "eval_loss": 0.6007612347602844, | |
| "eval_runtime": 964.162, | |
| "eval_samples_per_second": 10.855, | |
| "eval_steps_per_second": 0.34, | |
| "eval_wer": 82.21648788132616, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 2.3568421052631578e-07, | |
| "loss": 0.3914, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 2.3436842105263157e-07, | |
| "loss": 0.3901, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 2.3305263157894736e-07, | |
| "loss": 0.3923, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "learning_rate": 2.3173684210526316e-07, | |
| "loss": 0.397, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 2.3042105263157892e-07, | |
| "loss": 0.392, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 2.291052631578947e-07, | |
| "loss": 0.3992, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 2.277894736842105e-07, | |
| "loss": 0.3902, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "learning_rate": 2.2647368421052632e-07, | |
| "loss": 0.4042, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 17.56, | |
| "learning_rate": 2.251578947368421e-07, | |
| "loss": 0.3865, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 2.238421052631579e-07, | |
| "loss": 0.3879, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 2.2252631578947367e-07, | |
| "loss": 0.3935, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 2.2121052631578946e-07, | |
| "loss": 0.3882, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 2.1989473684210525e-07, | |
| "loss": 0.3892, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "learning_rate": 2.1857894736842104e-07, | |
| "loss": 0.4042, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 2.1726315789473686e-07, | |
| "loss": 0.3914, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 2.1594736842105262e-07, | |
| "loss": 0.3809, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 18.17, | |
| "learning_rate": 2.146315789473684e-07, | |
| "loss": 0.3822, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 2.133157894736842e-07, | |
| "loss": 0.3781, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 2.12e-07, | |
| "loss": 0.3925, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.1068421052631576e-07, | |
| "loss": 0.3997, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "eval_loss": 0.5970112085342407, | |
| "eval_runtime": 953.0961, | |
| "eval_samples_per_second": 10.981, | |
| "eval_steps_per_second": 0.344, | |
| "eval_wer": 81.11945742927395, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 2.0936842105263157e-07, | |
| "loss": 0.3887, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0805263157894737e-07, | |
| "loss": 0.389, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 2.0673684210526316e-07, | |
| "loss": 0.3827, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 2.0542105263157895e-07, | |
| "loss": 0.3913, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 2.041052631578947e-07, | |
| "loss": 0.3842, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 2.027894736842105e-07, | |
| "loss": 0.3855, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 2.0152631578947368e-07, | |
| "loss": 0.3961, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 2.0021052631578947e-07, | |
| "loss": 0.3843, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 1.9889473684210526e-07, | |
| "loss": 0.3861, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 1.9757894736842105e-07, | |
| "loss": 0.3877, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 1.962631578947368e-07, | |
| "loss": 0.3944, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "learning_rate": 1.949473684210526e-07, | |
| "loss": 0.3927, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 1.9363157894736842e-07, | |
| "loss": 0.3829, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 1.923157894736842e-07, | |
| "loss": 0.3814, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 1.91e-07, | |
| "loss": 0.3812, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 1.8968421052631577e-07, | |
| "loss": 0.3874, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 1.8836842105263156e-07, | |
| "loss": 0.3792, | |
| "step": 6425 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.8705263157894735e-07, | |
| "loss": 0.379, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 1.8573684210526314e-07, | |
| "loss": 0.3804, | |
| "step": 6475 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 1.8442105263157896e-07, | |
| "loss": 0.3878, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "eval_loss": 0.5940667986869812, | |
| "eval_runtime": 960.8217, | |
| "eval_samples_per_second": 10.893, | |
| "eval_steps_per_second": 0.341, | |
| "eval_wer": 81.71525845064714, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 1.8310526315789472e-07, | |
| "loss": 0.3745, | |
| "step": 6525 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 1.817894736842105e-07, | |
| "loss": 0.4015, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 20.17, | |
| "learning_rate": 1.804736842105263e-07, | |
| "loss": 0.3813, | |
| "step": 6575 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 1.791578947368421e-07, | |
| "loss": 0.376, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7784210526315789e-07, | |
| "loss": 0.3937, | |
| "step": 6625 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 1.7652631578947368e-07, | |
| "loss": 0.3875, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7521052631578947e-07, | |
| "loss": 0.3912, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 1.7389473684210526e-07, | |
| "loss": 0.3649, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 20.63, | |
| "learning_rate": 1.7257894736842105e-07, | |
| "loss": 0.3753, | |
| "step": 6725 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 1.7126315789473684e-07, | |
| "loss": 0.3711, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 20.78, | |
| "learning_rate": 1.699473684210526e-07, | |
| "loss": 0.382, | |
| "step": 6775 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "learning_rate": 1.686315789473684e-07, | |
| "loss": 0.3727, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 20.94, | |
| "learning_rate": 1.673157894736842e-07, | |
| "loss": 0.3706, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 1.66e-07, | |
| "loss": 0.3888, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 1.646842105263158e-07, | |
| "loss": 0.3676, | |
| "step": 6875 | |
| }, | |
| { | |
| "epoch": 21.17, | |
| "learning_rate": 1.6336842105263156e-07, | |
| "loss": 0.3791, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 21.24, | |
| "learning_rate": 1.6205263157894735e-07, | |
| "loss": 0.3793, | |
| "step": 6925 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 1.6073684210526314e-07, | |
| "loss": 0.3671, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 21.4, | |
| "learning_rate": 1.5942105263157893e-07, | |
| "loss": 0.3875, | |
| "step": 6975 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "learning_rate": 1.5810526315789475e-07, | |
| "loss": 0.3827, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "eval_loss": 0.5906410217285156, | |
| "eval_runtime": 960.7164, | |
| "eval_samples_per_second": 10.894, | |
| "eval_steps_per_second": 0.341, | |
| "eval_wer": 81.25591072441838, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 21.55, | |
| "learning_rate": 1.5678947368421051e-07, | |
| "loss": 0.3674, | |
| "step": 7025 | |
| }, | |
| { | |
| "epoch": 21.63, | |
| "learning_rate": 1.554736842105263e-07, | |
| "loss": 0.3851, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "learning_rate": 1.541578947368421e-07, | |
| "loss": 0.3878, | |
| "step": 7075 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 1.528421052631579e-07, | |
| "loss": 0.3724, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 21.86, | |
| "learning_rate": 1.5152631578947368e-07, | |
| "loss": 0.363, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 21.93, | |
| "learning_rate": 1.5021052631578944e-07, | |
| "loss": 0.3789, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 1.4889473684210526e-07, | |
| "loss": 0.3889, | |
| "step": 7175 | |
| }, | |
| { | |
| "epoch": 22.09, | |
| "learning_rate": 1.4757894736842105e-07, | |
| "loss": 0.3689, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 22.16, | |
| "learning_rate": 1.4626315789473684e-07, | |
| "loss": 0.382, | |
| "step": 7225 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 1.4494736842105263e-07, | |
| "loss": 0.3682, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 1.436315789473684e-07, | |
| "loss": 0.3727, | |
| "step": 7275 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 1.423157894736842e-07, | |
| "loss": 0.3831, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "learning_rate": 1.4099999999999998e-07, | |
| "loss": 0.367, | |
| "step": 7325 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 1.396842105263158e-07, | |
| "loss": 0.3853, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 1.383684210526316e-07, | |
| "loss": 0.3572, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "learning_rate": 1.3705263157894735e-07, | |
| "loss": 0.3779, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 1.3573684210526314e-07, | |
| "loss": 0.3811, | |
| "step": 7425 | |
| }, | |
| { | |
| "epoch": 22.85, | |
| "learning_rate": 1.3442105263157893e-07, | |
| "loss": 0.3765, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "learning_rate": 1.3310526315789472e-07, | |
| "loss": 0.3663, | |
| "step": 7475 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 1.3178947368421054e-07, | |
| "loss": 0.3785, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "eval_loss": 0.5891919732093811, | |
| "eval_runtime": 940.1062, | |
| "eval_samples_per_second": 11.133, | |
| "eval_steps_per_second": 0.349, | |
| "eval_wer": 81.05055527033966, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 1.304736842105263e-07, | |
| "loss": 0.3617, | |
| "step": 7525 | |
| }, | |
| { | |
| "epoch": 23.16, | |
| "learning_rate": 1.291578947368421e-07, | |
| "loss": 0.3755, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 23.24, | |
| "learning_rate": 1.278421052631579e-07, | |
| "loss": 0.3732, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 23.31, | |
| "learning_rate": 1.2652631578947368e-07, | |
| "loss": 0.3634, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 1.2521052631578947e-07, | |
| "loss": 0.3765, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 1.2389473684210526e-07, | |
| "loss": 0.3699, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 23.54, | |
| "learning_rate": 1.2257894736842105e-07, | |
| "loss": 0.3794, | |
| "step": 7675 | |
| }, | |
| { | |
| "epoch": 23.62, | |
| "learning_rate": 1.2126315789473684e-07, | |
| "loss": 0.3754, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 23.7, | |
| "learning_rate": 1.1994736842105263e-07, | |
| "loss": 0.3637, | |
| "step": 7725 | |
| }, | |
| { | |
| "epoch": 23.77, | |
| "learning_rate": 1.1863157894736841e-07, | |
| "loss": 0.37, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 23.85, | |
| "learning_rate": 1.173157894736842e-07, | |
| "loss": 0.3711, | |
| "step": 7775 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 1.16e-07, | |
| "loss": 0.3832, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.1468421052631578e-07, | |
| "loss": 0.3668, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 24.08, | |
| "learning_rate": 1.1336842105263158e-07, | |
| "loss": 0.3636, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 1.1205263157894735e-07, | |
| "loss": 0.3587, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 24.23, | |
| "learning_rate": 1.1073684210526316e-07, | |
| "loss": 0.3716, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 24.31, | |
| "learning_rate": 1.0942105263157895e-07, | |
| "loss": 0.3652, | |
| "step": 7925 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 1.0810526315789473e-07, | |
| "loss": 0.3662, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 24.46, | |
| "learning_rate": 1.0678947368421053e-07, | |
| "loss": 0.3646, | |
| "step": 7975 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "learning_rate": 1.0547368421052631e-07, | |
| "loss": 0.372, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "eval_loss": 0.5882065296173096, | |
| "eval_runtime": 953.6514, | |
| "eval_samples_per_second": 10.975, | |
| "eval_steps_per_second": 0.344, | |
| "eval_wer": 81.42478856494367, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 1.041578947368421e-07, | |
| "loss": 0.3793, | |
| "step": 8025 | |
| }, | |
| { | |
| "epoch": 24.69, | |
| "learning_rate": 1.028421052631579e-07, | |
| "loss": 0.3814, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 24.77, | |
| "learning_rate": 1.0152631578947368e-07, | |
| "loss": 0.3741, | |
| "step": 8075 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "learning_rate": 1.0021052631578947e-07, | |
| "loss": 0.371, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "learning_rate": 9.889473684210525e-08, | |
| "loss": 0.3745, | |
| "step": 8125 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 9.757894736842105e-08, | |
| "loss": 0.3667, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 25.08, | |
| "learning_rate": 9.626315789473684e-08, | |
| "loss": 0.3656, | |
| "step": 8175 | |
| }, | |
| { | |
| "epoch": 25.15, | |
| "learning_rate": 9.494736842105262e-08, | |
| "loss": 0.3628, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 25.23, | |
| "learning_rate": 9.363157894736843e-08, | |
| "loss": 0.3729, | |
| "step": 8225 | |
| }, | |
| { | |
| "epoch": 25.31, | |
| "learning_rate": 9.23157894736842e-08, | |
| "loss": 0.3739, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 9.1e-08, | |
| "loss": 0.364, | |
| "step": 8275 | |
| }, | |
| { | |
| "epoch": 25.46, | |
| "learning_rate": 8.968421052631579e-08, | |
| "loss": 0.3618, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "learning_rate": 8.836842105263158e-08, | |
| "loss": 0.3719, | |
| "step": 8325 | |
| }, | |
| { | |
| "epoch": 25.61, | |
| "learning_rate": 8.705263157894737e-08, | |
| "loss": 0.3684, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 8.573684210526314e-08, | |
| "loss": 0.3676, | |
| "step": 8375 | |
| }, | |
| { | |
| "epoch": 25.77, | |
| "learning_rate": 8.442105263157895e-08, | |
| "loss": 0.3728, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 25.84, | |
| "learning_rate": 8.310526315789474e-08, | |
| "loss": 0.3789, | |
| "step": 8425 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 8.178947368421052e-08, | |
| "loss": 0.3666, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 8.047368421052632e-08, | |
| "loss": 0.3661, | |
| "step": 8475 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "learning_rate": 7.91578947368421e-08, | |
| "loss": 0.3655, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "eval_loss": 0.5864801406860352, | |
| "eval_runtime": 968.3356, | |
| "eval_samples_per_second": 10.808, | |
| "eval_steps_per_second": 0.339, | |
| "eval_wer": 81.04785322489124, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 7.784210526315789e-08, | |
| "loss": 0.3658, | |
| "step": 8525 | |
| }, | |
| { | |
| "epoch": 26.23, | |
| "learning_rate": 7.652631578947368e-08, | |
| "loss": 0.37, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 26.3, | |
| "learning_rate": 7.521052631578947e-08, | |
| "loss": 0.3783, | |
| "step": 8575 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 7.389473684210526e-08, | |
| "loss": 0.3623, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 26.46, | |
| "learning_rate": 7.257894736842104e-08, | |
| "loss": 0.3572, | |
| "step": 8625 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 7.13157894736842e-08, | |
| "loss": 0.3655, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 26.61, | |
| "learning_rate": 7e-08, | |
| "loss": 0.364, | |
| "step": 8675 | |
| }, | |
| { | |
| "epoch": 26.69, | |
| "learning_rate": 6.868421052631578e-08, | |
| "loss": 0.3736, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 6.736842105263157e-08, | |
| "loss": 0.3624, | |
| "step": 8725 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "learning_rate": 6.605263157894736e-08, | |
| "loss": 0.3618, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "learning_rate": 6.473684210526316e-08, | |
| "loss": 0.3719, | |
| "step": 8775 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "learning_rate": 6.342105263157895e-08, | |
| "loss": 0.3625, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 27.07, | |
| "learning_rate": 6.210526315789474e-08, | |
| "loss": 0.3668, | |
| "step": 8825 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 6.078947368421053e-08, | |
| "loss": 0.3632, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 5.947368421052631e-08, | |
| "loss": 0.3508, | |
| "step": 8875 | |
| }, | |
| { | |
| "epoch": 27.3, | |
| "learning_rate": 5.81578947368421e-08, | |
| "loss": 0.3612, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 27.38, | |
| "learning_rate": 5.6842105263157894e-08, | |
| "loss": 0.3604, | |
| "step": 8925 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 5.5526315789473685e-08, | |
| "loss": 0.375, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 27.53, | |
| "learning_rate": 5.421052631578947e-08, | |
| "loss": 0.364, | |
| "step": 8975 | |
| }, | |
| { | |
| "epoch": 27.61, | |
| "learning_rate": 5.289473684210526e-08, | |
| "loss": 0.3697, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 27.61, | |
| "eval_loss": 0.5856062173843384, | |
| "eval_runtime": 963.5096, | |
| "eval_samples_per_second": 10.862, | |
| "eval_steps_per_second": 0.34, | |
| "eval_wer": 80.47772163527792, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 5.157894736842105e-08, | |
| "loss": 0.3692, | |
| "step": 9025 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 5.026315789473684e-08, | |
| "loss": 0.3826, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 4.8947368421052627e-08, | |
| "loss": 0.3615, | |
| "step": 9075 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 4.763157894736842e-08, | |
| "loss": 0.3779, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 4.631578947368421e-08, | |
| "loss": 0.3581, | |
| "step": 9125 | |
| }, | |
| { | |
| "epoch": 28.07, | |
| "learning_rate": 4.5e-08, | |
| "loss": 0.37, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 28.14, | |
| "learning_rate": 4.368421052631579e-08, | |
| "loss": 0.3787, | |
| "step": 9175 | |
| }, | |
| { | |
| "epoch": 28.22, | |
| "learning_rate": 4.2368421052631575e-08, | |
| "loss": 0.3578, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 4.1052631578947365e-08, | |
| "loss": 0.3708, | |
| "step": 9225 | |
| }, | |
| { | |
| "epoch": 28.37, | |
| "learning_rate": 3.9736842105263156e-08, | |
| "loss": 0.3706, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 28.45, | |
| "learning_rate": 3.842105263157895e-08, | |
| "loss": 0.3737, | |
| "step": 9275 | |
| }, | |
| { | |
| "epoch": 28.53, | |
| "learning_rate": 3.710526315789474e-08, | |
| "loss": 0.3629, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 28.6, | |
| "learning_rate": 3.578947368421052e-08, | |
| "loss": 0.3522, | |
| "step": 9325 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "learning_rate": 3.4473684210526313e-08, | |
| "loss": 0.3641, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "learning_rate": 3.3157894736842104e-08, | |
| "loss": 0.366, | |
| "step": 9375 | |
| }, | |
| { | |
| "epoch": 28.83, | |
| "learning_rate": 3.1842105263157895e-08, | |
| "loss": 0.3646, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 28.91, | |
| "learning_rate": 3.052631578947368e-08, | |
| "loss": 0.3718, | |
| "step": 9425 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "learning_rate": 2.9210526315789474e-08, | |
| "loss": 0.3461, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 29.06, | |
| "learning_rate": 2.789473684210526e-08, | |
| "loss": 0.3729, | |
| "step": 9475 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 2.6578947368421052e-08, | |
| "loss": 0.3658, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "eval_loss": 0.5849200487136841, | |
| "eval_runtime": 977.9456, | |
| "eval_samples_per_second": 10.702, | |
| "eval_steps_per_second": 0.335, | |
| "eval_wer": 80.61282390769813, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "learning_rate": 2.526315789473684e-08, | |
| "loss": 0.3671, | |
| "step": 9525 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 2.394736842105263e-08, | |
| "loss": 0.3582, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 29.37, | |
| "learning_rate": 2.2631578947368422e-08, | |
| "loss": 0.354, | |
| "step": 9575 | |
| }, | |
| { | |
| "epoch": 29.45, | |
| "learning_rate": 2.131578947368421e-08, | |
| "loss": 0.3532, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "learning_rate": 2e-08, | |
| "loss": 0.3523, | |
| "step": 9625 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 1.8684210526315788e-08, | |
| "loss": 0.3627, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 1.736842105263158e-08, | |
| "loss": 0.3725, | |
| "step": 9675 | |
| }, | |
| { | |
| "epoch": 29.75, | |
| "learning_rate": 1.6052631578947367e-08, | |
| "loss": 0.3643, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "learning_rate": 1.4736842105263158e-08, | |
| "loss": 0.3669, | |
| "step": 9725 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "learning_rate": 1.3421052631578947e-08, | |
| "loss": 0.3732, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 29.98, | |
| "learning_rate": 1.2105263157894736e-08, | |
| "loss": 0.3679, | |
| "step": 9775 | |
| }, | |
| { | |
| "epoch": 30.06, | |
| "learning_rate": 1.0789473684210525e-08, | |
| "loss": 0.3789, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 9.473684210526316e-09, | |
| "loss": 0.375, | |
| "step": 9825 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 8.157894736842106e-09, | |
| "loss": 0.3638, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 30.29, | |
| "learning_rate": 6.842105263157895e-09, | |
| "loss": 0.3734, | |
| "step": 9875 | |
| }, | |
| { | |
| "epoch": 30.37, | |
| "learning_rate": 5.526315789473683e-09, | |
| "loss": 0.3662, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 30.44, | |
| "learning_rate": 4.210526315789473e-09, | |
| "loss": 0.3435, | |
| "step": 9925 | |
| }, | |
| { | |
| "epoch": 30.52, | |
| "learning_rate": 2.894736842105263e-09, | |
| "loss": 0.3724, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 30.6, | |
| "learning_rate": 1.5789473684210525e-09, | |
| "loss": 0.3587, | |
| "step": 9975 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "learning_rate": 2.631578947368421e-10, | |
| "loss": 0.3539, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "eval_loss": 0.5847803354263306, | |
| "eval_runtime": 974.3996, | |
| "eval_samples_per_second": 10.741, | |
| "eval_steps_per_second": 0.337, | |
| "eval_wer": 80.66956686211462, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "step": 10000, | |
| "total_flos": 4.14675899449344e+19, | |
| "train_loss": 0.462699613571167, | |
| "train_runtime": 47184.4648, | |
| "train_samples_per_second": 13.564, | |
| "train_steps_per_second": 0.212 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 10000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 31, | |
| "save_steps": 500, | |
| "total_flos": 4.14675899449344e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |