| { | |
| "best_metric": 19.110790879037044, | |
| "best_model_checkpoint": "all_lang_models/kannada_models/whisper-medium-kn_alldata_multigpu/checkpoint-6300", | |
| "epoch": 3.876923076923077, | |
| "global_step": 6300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.69927719732729e-06, | |
| "loss": 2.1955, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.138553161620956e-06, | |
| "loss": 0.8969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.1880423643986635e-06, | |
| "loss": 0.5546, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.866236219818474e-06, | |
| "loss": 0.3974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.368259639277637e-06, | |
| "loss": 0.3085, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.767018303886829e-06, | |
| "loss": 0.2425, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.09783159198187e-06, | |
| "loss": 0.1934, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.38051793885471e-06, | |
| "loss": 0.1781, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.627318328692328e-06, | |
| "loss": 0.1588, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.846326112594556e-06, | |
| "loss": 0.1533, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.146240234375, | |
| "eval_runtime": 275.0598, | |
| "eval_samples_per_second": 7.816, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 42.09120962956684, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.043172071622172e-06, | |
| "loss": 0.1438, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.221932103540115e-06, | |
| "loss": 0.1387, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.385651763182433e-06, | |
| "loss": 0.134, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.536666713041757e-06, | |
| "loss": 0.1283, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.676807531470036e-06, | |
| "loss": 0.1197, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.807535603571304e-06, | |
| "loss": 0.1194, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.930036177107644e-06, | |
| "loss": 0.1177, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.998217468805706e-06, | |
| "loss": 0.112, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.992275698158051e-06, | |
| "loss": 0.1105, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.9863339275104e-06, | |
| "loss": 0.1085, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.11724853515625, | |
| "eval_runtime": 268.1147, | |
| "eval_samples_per_second": 8.019, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 34.301093498347036, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.980392156862746e-06, | |
| "loss": 0.1065, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.974450386215093e-06, | |
| "loss": 0.1067, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.96850861556744e-06, | |
| "loss": 0.1016, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.962566844919787e-06, | |
| "loss": 0.1, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.956625074272134e-06, | |
| "loss": 0.0969, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.95068330362448e-06, | |
| "loss": 0.0934, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.944741532976829e-06, | |
| "loss": 0.0951, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.938799762329176e-06, | |
| "loss": 0.0939, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.932857991681521e-06, | |
| "loss": 0.0915, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.92691622103387e-06, | |
| "loss": 0.0893, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.10052490234375, | |
| "eval_runtime": 269.816, | |
| "eval_samples_per_second": 7.968, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 30.660337373908618, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.920974450386216e-06, | |
| "loss": 0.0919, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.915032679738563e-06, | |
| "loss": 0.0871, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.90909090909091e-06, | |
| "loss": 0.0845, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.903149138443257e-06, | |
| "loss": 0.0846, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.897207367795604e-06, | |
| "loss": 0.0838, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.89126559714795e-06, | |
| "loss": 0.0859, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.885323826500299e-06, | |
| "loss": 0.0852, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.879382055852646e-06, | |
| "loss": 0.0844, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.873440285204991e-06, | |
| "loss": 0.0829, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.86749851455734e-06, | |
| "loss": 0.0814, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.0921630859375, | |
| "eval_runtime": 275.7387, | |
| "eval_samples_per_second": 7.797, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 28.63016021022294, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.861556743909686e-06, | |
| "loss": 0.0801, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.855614973262033e-06, | |
| "loss": 0.0801, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.84967320261438e-06, | |
| "loss": 0.0791, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.843731431966727e-06, | |
| "loss": 0.0784, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.837789661319074e-06, | |
| "loss": 0.0792, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.83184789067142e-06, | |
| "loss": 0.0764, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.825906120023769e-06, | |
| "loss": 0.079, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.819964349376116e-06, | |
| "loss": 0.0731, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.814022578728461e-06, | |
| "loss": 0.0754, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.80808080808081e-06, | |
| "loss": 0.0782, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.08685302734375, | |
| "eval_runtime": 268.1182, | |
| "eval_samples_per_second": 8.019, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 27.333220310248368, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.802139037433156e-06, | |
| "loss": 0.0739, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.796197266785503e-06, | |
| "loss": 0.0739, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.79025549613785e-06, | |
| "loss": 0.073, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.784313725490197e-06, | |
| "loss": 0.0732, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.778371954842544e-06, | |
| "loss": 0.0737, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.77243018419489e-06, | |
| "loss": 0.0754, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.766488413547239e-06, | |
| "loss": 0.0712, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.760546642899586e-06, | |
| "loss": 0.0711, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.754604872251931e-06, | |
| "loss": 0.0722, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.74866310160428e-06, | |
| "loss": 0.0679, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.08306884765625, | |
| "eval_runtime": 295.0588, | |
| "eval_samples_per_second": 7.287, | |
| "eval_steps_per_second": 0.058, | |
| "eval_wer": 26.570314486733913, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.742721330956626e-06, | |
| "loss": 0.0718, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.736779560308973e-06, | |
| "loss": 0.0685, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.73083778966132e-06, | |
| "loss": 0.0689, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.724896019013667e-06, | |
| "loss": 0.0712, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.718954248366014e-06, | |
| "loss": 0.0697, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.71301247771836e-06, | |
| "loss": 0.0705, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.707070707070709e-06, | |
| "loss": 0.0703, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.701128936423054e-06, | |
| "loss": 0.0698, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.695187165775401e-06, | |
| "loss": 0.068, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.68924539512775e-06, | |
| "loss": 0.0669, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.08062744140625, | |
| "eval_runtime": 274.2864, | |
| "eval_samples_per_second": 7.839, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.671780961261337, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.683303624480096e-06, | |
| "loss": 0.0674, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.677361853832443e-06, | |
| "loss": 0.0667, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.67142008318479e-06, | |
| "loss": 0.067, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.665478312537137e-06, | |
| "loss": 0.0648, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.659536541889484e-06, | |
| "loss": 0.063, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.65359477124183e-06, | |
| "loss": 0.0657, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.647653000594179e-06, | |
| "loss": 0.065, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.641711229946524e-06, | |
| "loss": 0.0647, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.635769459298871e-06, | |
| "loss": 0.0657, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.62982768865122e-06, | |
| "loss": 0.0628, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.07818603515625, | |
| "eval_runtime": 282.4906, | |
| "eval_samples_per_second": 7.611, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 25.298804780876495, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.623885918003566e-06, | |
| "loss": 0.0626, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.617944147355913e-06, | |
| "loss": 0.0647, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.61200237670826e-06, | |
| "loss": 0.0614, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.606060606060607e-06, | |
| "loss": 0.0623, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.600118835412954e-06, | |
| "loss": 0.064, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.5941770647653e-06, | |
| "loss": 0.0618, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.588235294117649e-06, | |
| "loss": 0.0627, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.582293523469994e-06, | |
| "loss": 0.0609, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.576351752822341e-06, | |
| "loss": 0.0629, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.57040998217469e-06, | |
| "loss": 0.0614, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.07489013671875, | |
| "eval_runtime": 278.8977, | |
| "eval_samples_per_second": 7.709, | |
| "eval_steps_per_second": 0.061, | |
| "eval_wer": 24.752055607357804, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.564468211527036e-06, | |
| "loss": 0.0601, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.558526440879383e-06, | |
| "loss": 0.0627, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.55258467023173e-06, | |
| "loss": 0.0619, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.546642899584077e-06, | |
| "loss": 0.0628, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.540701128936424e-06, | |
| "loss": 0.0633, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.53475935828877e-06, | |
| "loss": 0.0624, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.528817587641119e-06, | |
| "loss": 0.0619, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.522875816993464e-06, | |
| "loss": 0.0597, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.516934046345811e-06, | |
| "loss": 0.0593, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.51099227569816e-06, | |
| "loss": 0.0593, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.07318115234375, | |
| "eval_runtime": 273.7867, | |
| "eval_samples_per_second": 7.853, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 23.81961515639569, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.505050505050506e-06, | |
| "loss": 0.0616, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.499108734402853e-06, | |
| "loss": 0.0611, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.4931669637552e-06, | |
| "loss": 0.0602, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.487225193107547e-06, | |
| "loss": 0.0596, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.481283422459894e-06, | |
| "loss": 0.0589, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.47534165181224e-06, | |
| "loss": 0.0596, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.469399881164589e-06, | |
| "loss": 0.0602, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.463458110516934e-06, | |
| "loss": 0.0605, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.457516339869281e-06, | |
| "loss": 0.0589, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.45157456922163e-06, | |
| "loss": 0.0597, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.07110595703125, | |
| "eval_runtime": 264.9557, | |
| "eval_samples_per_second": 8.115, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 23.344918199542256, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.445632798573976e-06, | |
| "loss": 0.0604, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.439691027926323e-06, | |
| "loss": 0.0581, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.43374925727867e-06, | |
| "loss": 0.057, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.427807486631017e-06, | |
| "loss": 0.0586, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.421865715983364e-06, | |
| "loss": 0.0601, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.41592394533571e-06, | |
| "loss": 0.0581, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.409982174688059e-06, | |
| "loss": 0.0566, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.404040404040404e-06, | |
| "loss": 0.0558, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.39809863339275e-06, | |
| "loss": 0.0577, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.3921568627451e-06, | |
| "loss": 0.0565, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.068603515625, | |
| "eval_runtime": 278.2161, | |
| "eval_samples_per_second": 7.728, | |
| "eval_steps_per_second": 0.061, | |
| "eval_wer": 22.891413071119775, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.386215092097446e-06, | |
| "loss": 0.0586, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.380273321449793e-06, | |
| "loss": 0.0559, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.37433155080214e-06, | |
| "loss": 0.0561, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.368389780154487e-06, | |
| "loss": 0.0566, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.362448009506834e-06, | |
| "loss": 0.0567, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.35650623885918e-06, | |
| "loss": 0.0562, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.350564468211529e-06, | |
| "loss": 0.056, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.344622697563874e-06, | |
| "loss": 0.0566, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.33868092691622e-06, | |
| "loss": 0.0535, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.33273915626857e-06, | |
| "loss": 0.0589, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.06744384765625, | |
| "eval_runtime": 274.5158, | |
| "eval_samples_per_second": 7.832, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 23.005848944646946, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.326797385620916e-06, | |
| "loss": 0.0545, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.320855614973263e-06, | |
| "loss": 0.0572, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.31491384432561e-06, | |
| "loss": 0.0561, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.308972073677957e-06, | |
| "loss": 0.0538, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.303030303030303e-06, | |
| "loss": 0.0539, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.29708853238265e-06, | |
| "loss": 0.0543, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.291146761734999e-06, | |
| "loss": 0.0555, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.285204991087344e-06, | |
| "loss": 0.0549, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.27926322043969e-06, | |
| "loss": 0.053, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.27332144979204e-06, | |
| "loss": 0.0533, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.06646728515625, | |
| "eval_runtime": 271.2182, | |
| "eval_samples_per_second": 7.927, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 23.183860303466982, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.267379679144386e-06, | |
| "loss": 0.057, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.261437908496733e-06, | |
| "loss": 0.0559, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.25549613784908e-06, | |
| "loss": 0.0564, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.249554367201427e-06, | |
| "loss": 0.0539, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.243612596553773e-06, | |
| "loss": 0.0546, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.23767082590612e-06, | |
| "loss": 0.0581, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.231729055258469e-06, | |
| "loss": 0.055, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.225787284610814e-06, | |
| "loss": 0.0538, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.21984551396316e-06, | |
| "loss": 0.055, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.21390374331551e-06, | |
| "loss": 0.0532, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.065185546875, | |
| "eval_runtime": 267.4935, | |
| "eval_samples_per_second": 8.038, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 22.522675256421124, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.207961972667856e-06, | |
| "loss": 0.0551, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.202020202020203e-06, | |
| "loss": 0.0568, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.19607843137255e-06, | |
| "loss": 0.0525, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.190136660724897e-06, | |
| "loss": 0.0555, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.184194890077243e-06, | |
| "loss": 0.054, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.17825311942959e-06, | |
| "loss": 0.0547, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.172311348781939e-06, | |
| "loss": 0.0529, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.166369578134284e-06, | |
| "loss": 0.0523, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.16042780748663e-06, | |
| "loss": 0.055, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.15448603683898e-06, | |
| "loss": 0.0511, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.0635986328125, | |
| "eval_runtime": 264.7815, | |
| "eval_samples_per_second": 8.12, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 22.136983978977707, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.148544266191326e-06, | |
| "loss": 0.0516, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.142602495543673e-06, | |
| "loss": 0.0528, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.13666072489602e-06, | |
| "loss": 0.0481, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.130718954248367e-06, | |
| "loss": 0.0452, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.124777183600713e-06, | |
| "loss": 0.0465, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.11883541295306e-06, | |
| "loss": 0.0479, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.112893642305409e-06, | |
| "loss": 0.0456, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.106951871657754e-06, | |
| "loss": 0.0473, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.1010101010101e-06, | |
| "loss": 0.0454, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.09506833036245e-06, | |
| "loss": 0.0464, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.06341552734375, | |
| "eval_runtime": 274.0276, | |
| "eval_samples_per_second": 7.846, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 22.29380350936679, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.089126559714796e-06, | |
| "loss": 0.0463, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.083184789067143e-06, | |
| "loss": 0.0469, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.07724301841949e-06, | |
| "loss": 0.0468, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.071301247771837e-06, | |
| "loss": 0.0467, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.065359477124183e-06, | |
| "loss": 0.0463, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.05941770647653e-06, | |
| "loss": 0.0485, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.053475935828879e-06, | |
| "loss": 0.0474, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.047534165181224e-06, | |
| "loss": 0.0451, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.04159239453357e-06, | |
| "loss": 0.046, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.03565062388592e-06, | |
| "loss": 0.0449, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.06365966796875, | |
| "eval_runtime": 272.4047, | |
| "eval_samples_per_second": 7.893, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 21.920827328981947, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.029708853238266e-06, | |
| "loss": 0.0465, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.023767082590613e-06, | |
| "loss": 0.0455, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.01782531194296e-06, | |
| "loss": 0.047, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.011883541295307e-06, | |
| "loss": 0.0466, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 9.005941770647653e-06, | |
| "loss": 0.0476, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0441, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 8.994058229352349e-06, | |
| "loss": 0.0464, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.988116458704694e-06, | |
| "loss": 0.0465, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.98217468805704e-06, | |
| "loss": 0.0461, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.97623291740939e-06, | |
| "loss": 0.0465, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.061981201171875, | |
| "eval_runtime": 270.322, | |
| "eval_samples_per_second": 7.953, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 22.20903619564296, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.970291146761736e-06, | |
| "loss": 0.0449, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.964349376114083e-06, | |
| "loss": 0.0451, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 8.95840760546643e-06, | |
| "loss": 0.0474, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 8.952465834818777e-06, | |
| "loss": 0.0468, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.946524064171123e-06, | |
| "loss": 0.0432, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 8.94058229352347e-06, | |
| "loss": 0.0478, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 8.934640522875819e-06, | |
| "loss": 0.0449, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.928698752228164e-06, | |
| "loss": 0.0458, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.92275698158051e-06, | |
| "loss": 0.047, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.91681521093286e-06, | |
| "loss": 0.0451, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.0614013671875, | |
| "eval_runtime": 274.6038, | |
| "eval_samples_per_second": 7.829, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 21.63685682800712, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.910873440285206e-06, | |
| "loss": 0.0469, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.904931669637553e-06, | |
| "loss": 0.0458, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.8989898989899e-06, | |
| "loss": 0.0477, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.893048128342247e-06, | |
| "loss": 0.0474, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.887106357694593e-06, | |
| "loss": 0.0466, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.88116458704694e-06, | |
| "loss": 0.0457, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.875222816399289e-06, | |
| "loss": 0.0456, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.869281045751634e-06, | |
| "loss": 0.044, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.86333927510398e-06, | |
| "loss": 0.0462, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.85739750445633e-06, | |
| "loss": 0.0455, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.061614990234375, | |
| "eval_runtime": 264.7511, | |
| "eval_samples_per_second": 8.121, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 21.46732220055946, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.851455733808676e-06, | |
| "loss": 0.0459, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.845513963161023e-06, | |
| "loss": 0.0461, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.83957219251337e-06, | |
| "loss": 0.046, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.833630421865717e-06, | |
| "loss": 0.0455, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.827688651218063e-06, | |
| "loss": 0.0435, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.82174688057041e-06, | |
| "loss": 0.0449, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.815805109922759e-06, | |
| "loss": 0.0452, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.809863339275104e-06, | |
| "loss": 0.0448, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.803921568627452e-06, | |
| "loss": 0.0448, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.7979797979798e-06, | |
| "loss": 0.0457, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.06134033203125, | |
| "eval_runtime": 272.3621, | |
| "eval_samples_per_second": 7.894, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 21.882682037806223, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.792038027332146e-06, | |
| "loss": 0.0461, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.786096256684493e-06, | |
| "loss": 0.0445, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.78015448603684e-06, | |
| "loss": 0.0449, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.774212715389186e-06, | |
| "loss": 0.0458, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.768270944741533e-06, | |
| "loss": 0.0439, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.76232917409388e-06, | |
| "loss": 0.0471, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.756387403446229e-06, | |
| "loss": 0.0461, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.750445632798574e-06, | |
| "loss": 0.0463, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.744503862150922e-06, | |
| "loss": 0.0457, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.73856209150327e-06, | |
| "loss": 0.0457, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.06072998046875, | |
| "eval_runtime": 273.0528, | |
| "eval_samples_per_second": 7.874, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 21.797914724082393, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.732620320855616e-06, | |
| "loss": 0.0457, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.726678550207963e-06, | |
| "loss": 0.0468, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.72073677956031e-06, | |
| "loss": 0.0429, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.714795008912656e-06, | |
| "loss": 0.0443, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.708853238265003e-06, | |
| "loss": 0.0442, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.70291146761735e-06, | |
| "loss": 0.0439, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.696969696969699e-06, | |
| "loss": 0.0446, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.691027926322044e-06, | |
| "loss": 0.0445, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.685086155674392e-06, | |
| "loss": 0.0436, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.679144385026739e-06, | |
| "loss": 0.0443, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.059722900390625, | |
| "eval_runtime": 270.0699, | |
| "eval_samples_per_second": 7.961, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 21.081630923116045, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.673202614379086e-06, | |
| "loss": 0.0454, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.667260843731433e-06, | |
| "loss": 0.0447, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 8.66131907308378e-06, | |
| "loss": 0.0448, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 8.655377302436126e-06, | |
| "loss": 0.0434, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.649435531788473e-06, | |
| "loss": 0.0446, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.64349376114082e-06, | |
| "loss": 0.0454, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 8.637551990493169e-06, | |
| "loss": 0.0449, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 8.631610219845514e-06, | |
| "loss": 0.0451, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 8.625668449197862e-06, | |
| "loss": 0.045, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.619726678550209e-06, | |
| "loss": 0.044, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.05938720703125, | |
| "eval_runtime": 279.6518, | |
| "eval_samples_per_second": 7.688, | |
| "eval_steps_per_second": 0.061, | |
| "eval_wer": 21.200305162329407, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.613784907902556e-06, | |
| "loss": 0.0438, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.607843137254903e-06, | |
| "loss": 0.0425, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.60190136660725e-06, | |
| "loss": 0.0433, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.595959595959596e-06, | |
| "loss": 0.0456, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.590017825311943e-06, | |
| "loss": 0.0459, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.58407605466429e-06, | |
| "loss": 0.0436, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.578134284016639e-06, | |
| "loss": 0.0434, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.572192513368984e-06, | |
| "loss": 0.0424, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.566250742721332e-06, | |
| "loss": 0.0446, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.560308972073679e-06, | |
| "loss": 0.0425, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.057830810546875, | |
| "eval_runtime": 265.7037, | |
| "eval_samples_per_second": 8.092, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 21.263880647622276, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.554367201426026e-06, | |
| "loss": 0.0417, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.548425430778373e-06, | |
| "loss": 0.0448, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 8.54248366013072e-06, | |
| "loss": 0.0425, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 8.536541889483066e-06, | |
| "loss": 0.0431, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 8.530600118835413e-06, | |
| "loss": 0.0452, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.524658348187762e-06, | |
| "loss": 0.0427, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.518716577540109e-06, | |
| "loss": 0.0456, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.512774806892454e-06, | |
| "loss": 0.0454, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.506833036244802e-06, | |
| "loss": 0.0429, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.500891265597149e-06, | |
| "loss": 0.0448, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.05841064453125, | |
| "eval_runtime": 276.4184, | |
| "eval_samples_per_second": 7.778, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 20.848520810375522, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.494949494949496e-06, | |
| "loss": 0.0447, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.489007724301843e-06, | |
| "loss": 0.0451, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.48306595365419e-06, | |
| "loss": 0.0433, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.477124183006536e-06, | |
| "loss": 0.0449, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.471182412358883e-06, | |
| "loss": 0.043, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.465240641711232e-06, | |
| "loss": 0.0445, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.459298871063579e-06, | |
| "loss": 0.0427, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.453357100415924e-06, | |
| "loss": 0.0438, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.447415329768272e-06, | |
| "loss": 0.0448, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.441473559120619e-06, | |
| "loss": 0.0432, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.0570068359375, | |
| "eval_runtime": 268.2611, | |
| "eval_samples_per_second": 8.015, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 20.289056539798253, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.435531788472966e-06, | |
| "loss": 0.0443, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.429590017825313e-06, | |
| "loss": 0.0436, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.42364824717766e-06, | |
| "loss": 0.0443, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.417706476530006e-06, | |
| "loss": 0.0431, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.411764705882353e-06, | |
| "loss": 0.0434, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.405822935234702e-06, | |
| "loss": 0.0452, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.399881164587049e-06, | |
| "loss": 0.0444, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.393939393939394e-06, | |
| "loss": 0.0425, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.387997623291742e-06, | |
| "loss": 0.0428, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.382055852644089e-06, | |
| "loss": 0.0432, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.05816650390625, | |
| "eval_runtime": 265.2446, | |
| "eval_samples_per_second": 8.106, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 21.18335169958464, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.376114081996436e-06, | |
| "loss": 0.0425, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.370172311348783e-06, | |
| "loss": 0.0429, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.36423054070113e-06, | |
| "loss": 0.0428, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.358288770053476e-06, | |
| "loss": 0.0437, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.352346999405823e-06, | |
| "loss": 0.0441, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.346405228758172e-06, | |
| "loss": 0.0439, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.340463458110519e-06, | |
| "loss": 0.0438, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.334521687462864e-06, | |
| "loss": 0.0419, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.328579916815212e-06, | |
| "loss": 0.0418, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.322638146167559e-06, | |
| "loss": 0.0441, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.056884765625, | |
| "eval_runtime": 260.1925, | |
| "eval_samples_per_second": 8.263, | |
| "eval_steps_per_second": 0.065, | |
| "eval_wer": 20.369585487835888, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.316696375519906e-06, | |
| "loss": 0.0431, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.310754604872253e-06, | |
| "loss": 0.0421, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.3048128342246e-06, | |
| "loss": 0.0424, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.298871063576946e-06, | |
| "loss": 0.043, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.292929292929293e-06, | |
| "loss": 0.0425, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.286987522281642e-06, | |
| "loss": 0.0429, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 8.281045751633987e-06, | |
| "loss": 0.043, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 8.275103980986334e-06, | |
| "loss": 0.0421, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 8.269162210338682e-06, | |
| "loss": 0.0411, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.263220439691029e-06, | |
| "loss": 0.0423, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.05633544921875, | |
| "eval_runtime": 272.288, | |
| "eval_samples_per_second": 7.896, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 20.479782995676867, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.257278669043376e-06, | |
| "loss": 0.0434, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.251336898395723e-06, | |
| "loss": 0.0423, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.24539512774807e-06, | |
| "loss": 0.0434, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.239453357100416e-06, | |
| "loss": 0.0426, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.233511586452763e-06, | |
| "loss": 0.0417, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.227569815805112e-06, | |
| "loss": 0.043, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.221628045157457e-06, | |
| "loss": 0.0424, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.215686274509804e-06, | |
| "loss": 0.0431, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.209744503862152e-06, | |
| "loss": 0.0412, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.203802733214499e-06, | |
| "loss": 0.0424, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.05596923828125, | |
| "eval_runtime": 273.3037, | |
| "eval_samples_per_second": 7.867, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 19.96694074764771, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.197860962566846e-06, | |
| "loss": 0.0412, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.191919191919193e-06, | |
| "loss": 0.0414, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.18597742127154e-06, | |
| "loss": 0.044, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.180035650623886e-06, | |
| "loss": 0.0431, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.174093879976233e-06, | |
| "loss": 0.044, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.168152109328582e-06, | |
| "loss": 0.0361, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.162210338680927e-06, | |
| "loss": 0.0353, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.156268568033274e-06, | |
| "loss": 0.0341, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.150326797385622e-06, | |
| "loss": 0.0362, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.144385026737969e-06, | |
| "loss": 0.0351, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.05633544921875, | |
| "eval_runtime": 279.325, | |
| "eval_samples_per_second": 7.697, | |
| "eval_steps_per_second": 0.061, | |
| "eval_wer": 20.136475375095365, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.138443256090316e-06, | |
| "loss": 0.035, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.132501485442663e-06, | |
| "loss": 0.0341, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.12655971479501e-06, | |
| "loss": 0.0372, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.120617944147356e-06, | |
| "loss": 0.0374, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.114676173499703e-06, | |
| "loss": 0.0341, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.108734402852052e-06, | |
| "loss": 0.035, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.102792632204397e-06, | |
| "loss": 0.0366, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.096850861556744e-06, | |
| "loss": 0.0358, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.090909090909092e-06, | |
| "loss": 0.0341, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.084967320261439e-06, | |
| "loss": 0.0356, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.056732177734375, | |
| "eval_runtime": 271.2326, | |
| "eval_samples_per_second": 7.927, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 19.509197253539035, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.079025549613786e-06, | |
| "loss": 0.035, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.073083778966133e-06, | |
| "loss": 0.0375, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.06714200831848e-06, | |
| "loss": 0.0371, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.061200237670826e-06, | |
| "loss": 0.0374, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.055258467023173e-06, | |
| "loss": 0.036, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.049316696375522e-06, | |
| "loss": 0.0366, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.043374925727867e-06, | |
| "loss": 0.0348, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.037433155080214e-06, | |
| "loss": 0.0368, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.031491384432562e-06, | |
| "loss": 0.0362, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.025549613784909e-06, | |
| "loss": 0.0362, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.056610107421875, | |
| "eval_runtime": 270.5291, | |
| "eval_samples_per_second": 7.947, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 19.780452657455285, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.019607843137256e-06, | |
| "loss": 0.035, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.013666072489603e-06, | |
| "loss": 0.0367, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.00772430184195e-06, | |
| "loss": 0.0359, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.001782531194296e-06, | |
| "loss": 0.0387, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.995840760546643e-06, | |
| "loss": 0.0368, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 7.989898989898992e-06, | |
| "loss": 0.0351, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.983957219251337e-06, | |
| "loss": 0.0372, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.978015448603684e-06, | |
| "loss": 0.0353, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.972073677956032e-06, | |
| "loss": 0.0358, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.966131907308379e-06, | |
| "loss": 0.0349, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.057464599609375, | |
| "eval_runtime": 266.5992, | |
| "eval_samples_per_second": 8.065, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 20.01356277019581, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.960190136660726e-06, | |
| "loss": 0.0364, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.954248366013073e-06, | |
| "loss": 0.0362, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.94830659536542e-06, | |
| "loss": 0.035, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.942364824717766e-06, | |
| "loss": 0.0365, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.936423054070113e-06, | |
| "loss": 0.0355, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.930481283422462e-06, | |
| "loss": 0.0358, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.924539512774807e-06, | |
| "loss": 0.036, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.918597742127154e-06, | |
| "loss": 0.0346, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.912655971479502e-06, | |
| "loss": 0.0361, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.906714200831849e-06, | |
| "loss": 0.0366, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.056549072265625, | |
| "eval_runtime": 275.4886, | |
| "eval_samples_per_second": 7.804, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 20.18733576332966, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.900772430184196e-06, | |
| "loss": 0.0362, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.894830659536543e-06, | |
| "loss": 0.0368, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.88888888888889e-06, | |
| "loss": 0.0354, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.882947118241236e-06, | |
| "loss": 0.0352, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.877005347593583e-06, | |
| "loss": 0.0359, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.871063576945932e-06, | |
| "loss": 0.0354, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.865121806298277e-06, | |
| "loss": 0.0365, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.859180035650624e-06, | |
| "loss": 0.0349, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.853238265002972e-06, | |
| "loss": 0.0363, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 7.847296494355319e-06, | |
| "loss": 0.0361, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.057403564453125, | |
| "eval_runtime": 266.321, | |
| "eval_samples_per_second": 8.073, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 19.835551411375775, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 7.841354723707666e-06, | |
| "loss": 0.0369, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.835412953060013e-06, | |
| "loss": 0.035, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 7.82947118241236e-06, | |
| "loss": 0.0362, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 7.823529411764706e-06, | |
| "loss": 0.0354, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 7.817587641117053e-06, | |
| "loss": 0.0365, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 7.811645870469402e-06, | |
| "loss": 0.0371, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 7.805704099821747e-06, | |
| "loss": 0.0365, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.799762329174094e-06, | |
| "loss": 0.036, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.793820558526442e-06, | |
| "loss": 0.035, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.787878787878789e-06, | |
| "loss": 0.0368, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.057220458984375, | |
| "eval_runtime": 236.6525, | |
| "eval_samples_per_second": 9.085, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 20.170382300584894, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.781937017231136e-06, | |
| "loss": 0.0356, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.775995246583483e-06, | |
| "loss": 0.0356, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.77005347593583e-06, | |
| "loss": 0.0348, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.764111705288176e-06, | |
| "loss": 0.0357, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.758169934640523e-06, | |
| "loss": 0.0349, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.752228163992872e-06, | |
| "loss": 0.0373, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.746286393345217e-06, | |
| "loss": 0.0346, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.740344622697564e-06, | |
| "loss": 0.0358, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.734402852049912e-06, | |
| "loss": 0.0358, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.728461081402259e-06, | |
| "loss": 0.0357, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 0.05609130859375, | |
| "eval_runtime": 238.1705, | |
| "eval_samples_per_second": 9.027, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 20.01356277019581, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.722519310754606e-06, | |
| "loss": 0.036, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.716577540106953e-06, | |
| "loss": 0.035, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.7106357694593e-06, | |
| "loss": 0.0352, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.704693998811646e-06, | |
| "loss": 0.0353, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.698752228163993e-06, | |
| "loss": 0.0348, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.692810457516342e-06, | |
| "loss": 0.0365, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.686868686868687e-06, | |
| "loss": 0.0359, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.680926916221033e-06, | |
| "loss": 0.0355, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.674985145573382e-06, | |
| "loss": 0.0375, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.669043374925729e-06, | |
| "loss": 0.038, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.055450439453125, | |
| "eval_runtime": 240.3662, | |
| "eval_samples_per_second": 8.945, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 20.161905569212514, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.663101604278076e-06, | |
| "loss": 0.0349, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.657159833630423e-06, | |
| "loss": 0.0377, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.65121806298277e-06, | |
| "loss": 0.0363, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.645276292335116e-06, | |
| "loss": 0.0345, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.639334521687463e-06, | |
| "loss": 0.0363, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.633392751039812e-06, | |
| "loss": 0.0372, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.627450980392157e-06, | |
| "loss": 0.0354, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.621509209744504e-06, | |
| "loss": 0.0352, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.615567439096851e-06, | |
| "loss": 0.0346, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.609625668449199e-06, | |
| "loss": 0.0359, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 0.055328369140625, | |
| "eval_runtime": 237.9056, | |
| "eval_samples_per_second": 9.037, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 19.810121217258626, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.603683897801546e-06, | |
| "loss": 0.0366, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.597742127153892e-06, | |
| "loss": 0.0365, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.591800356506239e-06, | |
| "loss": 0.0364, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.585858585858586e-06, | |
| "loss": 0.036, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.579916815210934e-06, | |
| "loss": 0.0362, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.573975044563281e-06, | |
| "loss": 0.035, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.568033273915627e-06, | |
| "loss": 0.035, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.562091503267974e-06, | |
| "loss": 0.0354, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.556149732620321e-06, | |
| "loss": 0.036, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.550207961972669e-06, | |
| "loss": 0.0349, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.055267333984375, | |
| "eval_runtime": 232.2496, | |
| "eval_samples_per_second": 9.257, | |
| "eval_steps_per_second": 0.073, | |
| "eval_wer": 19.839789777061963, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.544266191325016e-06, | |
| "loss": 0.0352, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.538324420677362e-06, | |
| "loss": 0.0354, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.532382650029709e-06, | |
| "loss": 0.0344, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.526440879382056e-06, | |
| "loss": 0.0385, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.520499108734404e-06, | |
| "loss": 0.0362, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.514557338086751e-06, | |
| "loss": 0.0359, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.508615567439097e-06, | |
| "loss": 0.0357, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.502673796791444e-06, | |
| "loss": 0.0349, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.496732026143791e-06, | |
| "loss": 0.0358, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.490790255496139e-06, | |
| "loss": 0.0363, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.05438232421875, | |
| "eval_runtime": 236.2463, | |
| "eval_samples_per_second": 9.101, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 20.026277867254386, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.484848484848486e-06, | |
| "loss": 0.036, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.4789067142008324e-06, | |
| "loss": 0.0369, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.472964943553179e-06, | |
| "loss": 0.0368, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.467023172905526e-06, | |
| "loss": 0.036, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.461081402257874e-06, | |
| "loss": 0.0351, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.455139631610221e-06, | |
| "loss": 0.0359, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 7.4491978609625674e-06, | |
| "loss": 0.0357, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.443256090314914e-06, | |
| "loss": 0.035, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.437314319667261e-06, | |
| "loss": 0.0352, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.431372549019609e-06, | |
| "loss": 0.0353, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.0548095703125, | |
| "eval_runtime": 234.9071, | |
| "eval_samples_per_second": 9.153, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 19.88641179961007, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.425430778371956e-06, | |
| "loss": 0.0352, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.4194890077243024e-06, | |
| "loss": 0.0345, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.413547237076649e-06, | |
| "loss": 0.0355, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.407605466428996e-06, | |
| "loss": 0.0365, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.401663695781344e-06, | |
| "loss": 0.0353, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.395721925133691e-06, | |
| "loss": 0.0353, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.389780154486037e-06, | |
| "loss": 0.0365, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.383838383838384e-06, | |
| "loss": 0.0364, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.377896613190731e-06, | |
| "loss": 0.0354, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.371954842543079e-06, | |
| "loss": 0.0372, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.053741455078125, | |
| "eval_runtime": 247.1644, | |
| "eval_samples_per_second": 8.699, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 19.687208612359075, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.366013071895426e-06, | |
| "loss": 0.0355, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.360071301247772e-06, | |
| "loss": 0.0355, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.354129530600119e-06, | |
| "loss": 0.0379, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.348187759952466e-06, | |
| "loss": 0.035, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.342245989304814e-06, | |
| "loss": 0.0376, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.3363042186571606e-06, | |
| "loss": 0.0345, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.330362448009507e-06, | |
| "loss": 0.0358, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.324420677361854e-06, | |
| "loss": 0.034, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.318478906714201e-06, | |
| "loss": 0.0351, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.312537136066549e-06, | |
| "loss": 0.0361, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.0540771484375, | |
| "eval_runtime": 240.5503, | |
| "eval_samples_per_second": 8.938, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 19.678731880986692, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 7.3065953654188956e-06, | |
| "loss": 0.0369, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 7.300653594771242e-06, | |
| "loss": 0.0365, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.294711824123589e-06, | |
| "loss": 0.0345, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.288770053475936e-06, | |
| "loss": 0.034, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.282828282828284e-06, | |
| "loss": 0.0352, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.2768865121806306e-06, | |
| "loss": 0.0355, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.270944741532977e-06, | |
| "loss": 0.035, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.265002970885324e-06, | |
| "loss": 0.0349, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.259061200237672e-06, | |
| "loss": 0.0365, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.253119429590019e-06, | |
| "loss": 0.0338, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.05499267578125, | |
| "eval_runtime": 246.5763, | |
| "eval_samples_per_second": 8.719, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 19.30575570060185, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.2471776589423655e-06, | |
| "loss": 0.0356, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.241235888294712e-06, | |
| "loss": 0.035, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.235294117647059e-06, | |
| "loss": 0.0372, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.229352346999407e-06, | |
| "loss": 0.035, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.223410576351754e-06, | |
| "loss": 0.0366, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.2174688057041005e-06, | |
| "loss": 0.0349, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.211527035056447e-06, | |
| "loss": 0.0354, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.205585264408794e-06, | |
| "loss": 0.0321, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.199643493761142e-06, | |
| "loss": 0.029, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.193701723113489e-06, | |
| "loss": 0.0292, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 0.05609130859375, | |
| "eval_runtime": 256.8453, | |
| "eval_samples_per_second": 8.371, | |
| "eval_steps_per_second": 0.066, | |
| "eval_wer": 19.860981605492924, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.1877599524658355e-06, | |
| "loss": 0.0294, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.181818181818182e-06, | |
| "loss": 0.0267, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.175876411170529e-06, | |
| "loss": 0.0284, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.169934640522877e-06, | |
| "loss": 0.0289, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.163992869875224e-06, | |
| "loss": 0.0304, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.1580510992275705e-06, | |
| "loss": 0.0289, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.152109328579917e-06, | |
| "loss": 0.0294, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.146167557932264e-06, | |
| "loss": 0.027, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.140225787284612e-06, | |
| "loss": 0.0294, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.134284016636959e-06, | |
| "loss": 0.0282, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.05615234375, | |
| "eval_runtime": 259.2509, | |
| "eval_samples_per_second": 8.293, | |
| "eval_steps_per_second": 0.066, | |
| "eval_wer": 20.280579808425873, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.1295306001188355e-06, | |
| "loss": 0.0292, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.123588829471183e-06, | |
| "loss": 0.0289, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.11764705882353e-06, | |
| "loss": 0.0313, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.111705288175878e-06, | |
| "loss": 0.0295, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.105763517528224e-06, | |
| "loss": 0.0287, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.0998217468805705e-06, | |
| "loss": 0.029, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.093879976232918e-06, | |
| "loss": 0.0285, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.087938205585265e-06, | |
| "loss": 0.0312, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.081996434937613e-06, | |
| "loss": 0.0286, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.076054664289959e-06, | |
| "loss": 0.0288, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 0.057220458984375, | |
| "eval_runtime": 252.907, | |
| "eval_samples_per_second": 8.501, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.74230736627956, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.0701128936423055e-06, | |
| "loss": 0.0274, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.064171122994653e-06, | |
| "loss": 0.0291, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.058229352347e-06, | |
| "loss": 0.0285, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.052287581699348e-06, | |
| "loss": 0.0307, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.046345811051694e-06, | |
| "loss": 0.0299, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.0404040404040404e-06, | |
| "loss": 0.0301, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.034462269756388e-06, | |
| "loss": 0.0296, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 7.028520499108735e-06, | |
| "loss": 0.0282, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 7.022578728461083e-06, | |
| "loss": 0.0301, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.016636957813429e-06, | |
| "loss": 0.0289, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.05841064453125, | |
| "eval_runtime": 248.6038, | |
| "eval_samples_per_second": 8.648, | |
| "eval_steps_per_second": 0.068, | |
| "eval_wer": 19.632109858438586, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.0106951871657754e-06, | |
| "loss": 0.0293, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.004753416518123e-06, | |
| "loss": 0.0284, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 6.99881164587047e-06, | |
| "loss": 0.0277, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 6.992869875222818e-06, | |
| "loss": 0.0298, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 6.986928104575164e-06, | |
| "loss": 0.0284, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 6.9809863339275104e-06, | |
| "loss": 0.0304, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 6.975044563279858e-06, | |
| "loss": 0.0292, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 6.969102792632205e-06, | |
| "loss": 0.0301, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 6.963161021984553e-06, | |
| "loss": 0.0289, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 6.957219251336899e-06, | |
| "loss": 0.0288, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 0.0565185546875, | |
| "eval_runtime": 247.4756, | |
| "eval_samples_per_second": 8.688, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 19.309994066288038, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 6.951277480689245e-06, | |
| "loss": 0.0303, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 6.945335710041593e-06, | |
| "loss": 0.0291, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 6.93939393939394e-06, | |
| "loss": 0.0296, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.933452168746288e-06, | |
| "loss": 0.0288, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.927510398098634e-06, | |
| "loss": 0.0276, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 6.92156862745098e-06, | |
| "loss": 0.031, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 6.915626856803328e-06, | |
| "loss": 0.0304, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 6.909685086155675e-06, | |
| "loss": 0.0298, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 6.903743315508023e-06, | |
| "loss": 0.0275, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 6.8978015448603686e-06, | |
| "loss": 0.0278, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 0.0572509765625, | |
| "eval_runtime": 253.3603, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.805882851572434, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 6.891859774212715e-06, | |
| "loss": 0.0286, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 6.885918003565063e-06, | |
| "loss": 0.0297, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 6.87997623291741e-06, | |
| "loss": 0.0298, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 6.874034462269758e-06, | |
| "loss": 0.0295, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 6.8680926916221036e-06, | |
| "loss": 0.0293, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 6.86215092097445e-06, | |
| "loss": 0.0288, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 6.856209150326798e-06, | |
| "loss": 0.03, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 6.850267379679145e-06, | |
| "loss": 0.0292, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 6.8443256090314926e-06, | |
| "loss": 0.0286, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 6.8383838383838386e-06, | |
| "loss": 0.0304, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 0.056854248046875, | |
| "eval_runtime": 252.8996, | |
| "eval_samples_per_second": 8.501, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.979655844706283, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.832442067736185e-06, | |
| "loss": 0.0288, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 6.826500297088533e-06, | |
| "loss": 0.0298, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 6.82055852644088e-06, | |
| "loss": 0.0298, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 6.8146167557932276e-06, | |
| "loss": 0.03, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 6.8086749851455735e-06, | |
| "loss": 0.0285, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 6.80273321449792e-06, | |
| "loss": 0.0303, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 6.796791443850268e-06, | |
| "loss": 0.03, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 6.790849673202615e-06, | |
| "loss": 0.0293, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 6.7849079025549626e-06, | |
| "loss": 0.0292, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.7789661319073085e-06, | |
| "loss": 0.0286, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 0.057830810546875, | |
| "eval_runtime": 247.1692, | |
| "eval_samples_per_second": 8.698, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 19.712638806476225, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.773024361259656e-06, | |
| "loss": 0.0299, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 6.767082590612003e-06, | |
| "loss": 0.0289, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 6.76114081996435e-06, | |
| "loss": 0.03, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.7551990493166975e-06, | |
| "loss": 0.0291, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 6.7492572786690435e-06, | |
| "loss": 0.0293, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 6.743315508021391e-06, | |
| "loss": 0.0294, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 6.737373737373738e-06, | |
| "loss": 0.0307, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.731431966726085e-06, | |
| "loss": 0.0291, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.7254901960784325e-06, | |
| "loss": 0.028, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 6.7195484254307785e-06, | |
| "loss": 0.0286, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 0.05731201171875, | |
| "eval_runtime": 254.7504, | |
| "eval_samples_per_second": 8.44, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.954225650589134, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 6.713606654783126e-06, | |
| "loss": 0.0313, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 6.707664884135473e-06, | |
| "loss": 0.0292, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 6.70172311348782e-06, | |
| "loss": 0.029, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 6.6957813428401675e-06, | |
| "loss": 0.0291, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 6.6898395721925135e-06, | |
| "loss": 0.0293, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 6.683897801544861e-06, | |
| "loss": 0.0279, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 6.677956030897208e-06, | |
| "loss": 0.0295, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 6.672014260249555e-06, | |
| "loss": 0.0296, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 6.6660724896019025e-06, | |
| "loss": 0.0295, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 6.6601307189542485e-06, | |
| "loss": 0.0302, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "eval_loss": 0.05621337890625, | |
| "eval_runtime": 254.0147, | |
| "eval_samples_per_second": 8.464, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.860981605492924, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 6.654188948306596e-06, | |
| "loss": 0.0282, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 6.648247177658943e-06, | |
| "loss": 0.0293, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 6.64230540701129e-06, | |
| "loss": 0.0285, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 6.6363636363636375e-06, | |
| "loss": 0.0293, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 6.6304218657159835e-06, | |
| "loss": 0.029, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 6.624480095068331e-06, | |
| "loss": 0.0287, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 6.618538324420678e-06, | |
| "loss": 0.0288, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 6.612596553773025e-06, | |
| "loss": 0.0293, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 6.6066547831253725e-06, | |
| "loss": 0.0294, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 6.6007130124777185e-06, | |
| "loss": 0.0303, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_loss": 0.056488037109375, | |
| "eval_runtime": 257.9715, | |
| "eval_samples_per_second": 8.334, | |
| "eval_steps_per_second": 0.066, | |
| "eval_wer": 19.835551411375775, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 6.594771241830066e-06, | |
| "loss": 0.0298, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 6.588829471182413e-06, | |
| "loss": 0.0294, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 6.58288770053476e-06, | |
| "loss": 0.0305, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 6.5769459298871075e-06, | |
| "loss": 0.0307, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 6.5710041592394535e-06, | |
| "loss": 0.0304, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 6.565062388591801e-06, | |
| "loss": 0.0275, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 6.559120617944148e-06, | |
| "loss": 0.0295, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 6.553178847296495e-06, | |
| "loss": 0.0289, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 6.547237076648842e-06, | |
| "loss": 0.029, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 6.5412953060011885e-06, | |
| "loss": 0.0299, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 0.05645751953125, | |
| "eval_runtime": 252.6224, | |
| "eval_samples_per_second": 8.511, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.568534373145717, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 6.536541889483067e-06, | |
| "loss": 0.0288, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 6.530600118835414e-06, | |
| "loss": 0.0292, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 6.52465834818776e-06, | |
| "loss": 0.0289, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 6.5187165775401074e-06, | |
| "loss": 0.0292, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 6.512774806892454e-06, | |
| "loss": 0.0301, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 6.506833036244802e-06, | |
| "loss": 0.0282, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 6.500891265597149e-06, | |
| "loss": 0.0293, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 6.494949494949495e-06, | |
| "loss": 0.0307, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 6.489007724301842e-06, | |
| "loss": 0.0294, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 6.483065953654189e-06, | |
| "loss": 0.0288, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.056915283203125, | |
| "eval_runtime": 248.0601, | |
| "eval_samples_per_second": 8.667, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 19.14045943884038, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 6.477124183006537e-06, | |
| "loss": 0.0299, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 6.471182412358884e-06, | |
| "loss": 0.0299, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 6.46524064171123e-06, | |
| "loss": 0.0288, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 6.459298871063577e-06, | |
| "loss": 0.03, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 6.453357100415924e-06, | |
| "loss": 0.0299, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 6.447415329768272e-06, | |
| "loss": 0.0306, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 6.441473559120619e-06, | |
| "loss": 0.0287, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 6.435531788472965e-06, | |
| "loss": 0.0286, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 6.429590017825312e-06, | |
| "loss": 0.0295, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 6.423648247177659e-06, | |
| "loss": 0.0296, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_loss": 0.056854248046875, | |
| "eval_runtime": 244.1093, | |
| "eval_samples_per_second": 8.808, | |
| "eval_steps_per_second": 0.07, | |
| "eval_wer": 19.40323811138425, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 6.417706476530007e-06, | |
| "loss": 0.03, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.411764705882354e-06, | |
| "loss": 0.029, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.4058229352347e-06, | |
| "loss": 0.0288, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 6.399881164587047e-06, | |
| "loss": 0.0293, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 6.393939393939394e-06, | |
| "loss": 0.0303, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 6.387997623291742e-06, | |
| "loss": 0.0319, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.382055852644089e-06, | |
| "loss": 0.0294, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.376114081996435e-06, | |
| "loss": 0.0293, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.370172311348782e-06, | |
| "loss": 0.0304, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.364230540701129e-06, | |
| "loss": 0.029, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.056976318359375, | |
| "eval_runtime": 252.6274, | |
| "eval_samples_per_second": 8.511, | |
| "eval_steps_per_second": 0.067, | |
| "eval_wer": 19.110790879037044, | |
| "step": 6300 | |
| } | |
| ], | |
| "max_steps": 17000, | |
| "num_train_epochs": 11, | |
| "total_flos": 1.6456274523451545e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |