| { | |
| "best_metric": 20.17910947438902, | |
| "best_model_checkpoint": "gujarati_models/whisper-medium-gu_alldata_multigpu/checkpoint-3800", | |
| "epoch": 3.544776119402985, | |
| "global_step": 3800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.2570200577939087e-06, | |
| "loss": 2.6172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5.269504270732932e-06, | |
| "loss": 1.4482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.44164771270531e-06, | |
| "loss": 0.8307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.1833237074248565e-06, | |
| "loss": 0.4404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.727115553011708e-06, | |
| "loss": 0.3196, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.156679637224794e-06, | |
| "loss": 0.2507, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.511772784687228e-06, | |
| "loss": 0.2069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.814440832045515e-06, | |
| "loss": 0.1823, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.078190720115011e-06, | |
| "loss": 0.1734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.311900181269438e-06, | |
| "loss": 0.1567, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.133056640625, | |
| "eval_runtime": 520.2248, | |
| "eval_samples_per_second": 6.034, | |
| "eval_steps_per_second": 0.048, | |
| "eval_wer": 42.65148978908604, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.521717895177596e-06, | |
| "loss": 0.1507, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.712078808748597e-06, | |
| "loss": 0.1441, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.886287204237489e-06, | |
| "loss": 0.1385, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.998445998446e-06, | |
| "loss": 0.1318, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.990675990675992e-06, | |
| "loss": 0.1308, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.982905982905984e-06, | |
| "loss": 0.1214, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.975135975135975e-06, | |
| "loss": 0.1211, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.967365967365968e-06, | |
| "loss": 0.118, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.95959595959596e-06, | |
| "loss": 0.1138, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.951825951825953e-06, | |
| "loss": 0.1091, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.0928955078125, | |
| "eval_runtime": 558.7731, | |
| "eval_samples_per_second": 5.618, | |
| "eval_steps_per_second": 0.045, | |
| "eval_wer": 32.88137484655731, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.944055944055945e-06, | |
| "loss": 0.1067, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.936285936285938e-06, | |
| "loss": 0.1062, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.928515928515929e-06, | |
| "loss": 0.1081, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.920745920745921e-06, | |
| "loss": 0.1036, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.912975912975914e-06, | |
| "loss": 0.1015, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.905205905205906e-06, | |
| "loss": 0.0987, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.897435897435899e-06, | |
| "loss": 0.0948, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.88966588966589e-06, | |
| "loss": 0.0953, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.881895881895884e-06, | |
| "loss": 0.0925, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.874125874125875e-06, | |
| "loss": 0.0919, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.07861328125, | |
| "eval_runtime": 583.7008, | |
| "eval_samples_per_second": 5.378, | |
| "eval_steps_per_second": 0.043, | |
| "eval_wer": 29.215489342707286, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.866355866355867e-06, | |
| "loss": 0.0933, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.85858585858586e-06, | |
| "loss": 0.0901, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.85081585081585e-06, | |
| "loss": 0.0909, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.843045843045845e-06, | |
| "loss": 0.0908, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.835275835275836e-06, | |
| "loss": 0.0842, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.827505827505828e-06, | |
| "loss": 0.0861, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.81973581973582e-06, | |
| "loss": 0.0854, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.811965811965812e-06, | |
| "loss": 0.0849, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.804195804195806e-06, | |
| "loss": 0.0834, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.796425796425797e-06, | |
| "loss": 0.0837, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.0682373046875, | |
| "eval_runtime": 577.1404, | |
| "eval_samples_per_second": 5.439, | |
| "eval_steps_per_second": 0.043, | |
| "eval_wer": 27.259792433880147, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.788655788655789e-06, | |
| "loss": 0.0833, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.780885780885782e-06, | |
| "loss": 0.0795, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.773115773115774e-06, | |
| "loss": 0.0808, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.765345765345767e-06, | |
| "loss": 0.0817, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.757575757575758e-06, | |
| "loss": 0.0791, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.74980574980575e-06, | |
| "loss": 0.0775, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.742035742035743e-06, | |
| "loss": 0.0796, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.734265734265735e-06, | |
| "loss": 0.0766, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.726495726495728e-06, | |
| "loss": 0.0756, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.71872571872572e-06, | |
| "loss": 0.0785, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.0635986328125, | |
| "eval_runtime": 599.8325, | |
| "eval_samples_per_second": 5.233, | |
| "eval_steps_per_second": 0.042, | |
| "eval_wer": 25.532864635643342, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.710955710955711e-06, | |
| "loss": 0.0777, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.703185703185704e-06, | |
| "loss": 0.0741, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.695415695415696e-06, | |
| "loss": 0.0763, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.687645687645689e-06, | |
| "loss": 0.0731, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.679875679875681e-06, | |
| "loss": 0.0747, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.672105672105672e-06, | |
| "loss": 0.0731, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.664335664335666e-06, | |
| "loss": 0.0724, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.656565656565657e-06, | |
| "loss": 0.0737, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.64879564879565e-06, | |
| "loss": 0.0726, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.641025641025642e-06, | |
| "loss": 0.072, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.0599365234375, | |
| "eval_runtime": 509.7652, | |
| "eval_samples_per_second": 6.158, | |
| "eval_steps_per_second": 0.049, | |
| "eval_wer": 24.7628612878027, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.633255633255633e-06, | |
| "loss": 0.0678, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.625485625485627e-06, | |
| "loss": 0.068, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.617715617715618e-06, | |
| "loss": 0.0685, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.60994560994561e-06, | |
| "loss": 0.0694, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.602175602175603e-06, | |
| "loss": 0.0687, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.594405594405596e-06, | |
| "loss": 0.0687, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.586635586635588e-06, | |
| "loss": 0.0673, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.578865578865579e-06, | |
| "loss": 0.0694, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.571095571095571e-06, | |
| "loss": 0.0691, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.563325563325564e-06, | |
| "loss": 0.0693, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.058197021484375, | |
| "eval_runtime": 506.7924, | |
| "eval_samples_per_second": 6.194, | |
| "eval_steps_per_second": 0.049, | |
| "eval_wer": 24.690324740542348, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.0712, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.547785547785549e-06, | |
| "loss": 0.0688, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.54001554001554e-06, | |
| "loss": 0.0664, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.532245532245532e-06, | |
| "loss": 0.0658, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.524475524475525e-06, | |
| "loss": 0.0637, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.516705516705517e-06, | |
| "loss": 0.0628, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.50893550893551e-06, | |
| "loss": 0.0682, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.501165501165502e-06, | |
| "loss": 0.0644, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.493395493395493e-06, | |
| "loss": 0.0645, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.485625485625486e-06, | |
| "loss": 0.0676, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.055938720703125, | |
| "eval_runtime": 400.9127, | |
| "eval_samples_per_second": 7.83, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 23.97611873674813, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.477855477855478e-06, | |
| "loss": 0.0654, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.470085470085471e-06, | |
| "loss": 0.0641, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.462315462315463e-06, | |
| "loss": 0.0675, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 0.0646, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.446775446775448e-06, | |
| "loss": 0.0647, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.43900543900544e-06, | |
| "loss": 0.066, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.431235431235432e-06, | |
| "loss": 0.0672, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.423465423465424e-06, | |
| "loss": 0.0632, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.415695415695417e-06, | |
| "loss": 0.0642, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.40792540792541e-06, | |
| "loss": 0.0626, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.054107666015625, | |
| "eval_runtime": 930.1378, | |
| "eval_samples_per_second": 3.375, | |
| "eval_steps_per_second": 0.027, | |
| "eval_wer": 23.409775694676934, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.4001554001554e-06, | |
| "loss": 0.066, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.392385392385393e-06, | |
| "loss": 0.0633, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.384615384615385e-06, | |
| "loss": 0.0658, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.376845376845378e-06, | |
| "loss": 0.0639, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.36907536907537e-06, | |
| "loss": 0.0626, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.361305361305361e-06, | |
| "loss": 0.0627, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.353535353535354e-06, | |
| "loss": 0.0625, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.345765345765346e-06, | |
| "loss": 0.0637, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.337995337995339e-06, | |
| "loss": 0.0628, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.330225330225331e-06, | |
| "loss": 0.0612, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.051910400390625, | |
| "eval_runtime": 735.505, | |
| "eval_samples_per_second": 4.268, | |
| "eval_steps_per_second": 0.034, | |
| "eval_wer": 22.888070527842874, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.322455322455322e-06, | |
| "loss": 0.0629, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.314685314685316e-06, | |
| "loss": 0.0605, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.306915306915307e-06, | |
| "loss": 0.0622, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.2991452991453e-06, | |
| "loss": 0.0618, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.291375291375292e-06, | |
| "loss": 0.06, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.283605283605285e-06, | |
| "loss": 0.0602, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.275835275835277e-06, | |
| "loss": 0.0613, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.268065268065268e-06, | |
| "loss": 0.0553, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.26029526029526e-06, | |
| "loss": 0.0556, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.252525252525253e-06, | |
| "loss": 0.0533, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.051300048828125, | |
| "eval_runtime": 650.4139, | |
| "eval_samples_per_second": 4.826, | |
| "eval_steps_per_second": 0.038, | |
| "eval_wer": 22.42495257225756, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.244755244755246e-06, | |
| "loss": 0.0546, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.236985236985238e-06, | |
| "loss": 0.0551, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.22921522921523e-06, | |
| "loss": 0.0535, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.221445221445222e-06, | |
| "loss": 0.0545, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.213675213675214e-06, | |
| "loss": 0.0549, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.205905205905207e-06, | |
| "loss": 0.0557, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.1981351981352e-06, | |
| "loss": 0.0514, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.190365190365192e-06, | |
| "loss": 0.0525, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.182595182595183e-06, | |
| "loss": 0.0536, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.174825174825177e-06, | |
| "loss": 0.0517, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.0499267578125, | |
| "eval_runtime": 620.6447, | |
| "eval_samples_per_second": 5.058, | |
| "eval_steps_per_second": 0.04, | |
| "eval_wer": 22.204553063274187, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.167055167055168e-06, | |
| "loss": 0.0539, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 9.15928515928516e-06, | |
| "loss": 0.0534, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 9.151515151515153e-06, | |
| "loss": 0.053, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.143745143745144e-06, | |
| "loss": 0.0542, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.135975135975138e-06, | |
| "loss": 0.0515, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.128205128205129e-06, | |
| "loss": 0.0537, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.120435120435121e-06, | |
| "loss": 0.0532, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 9.112665112665114e-06, | |
| "loss": 0.0528, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.104895104895104e-06, | |
| "loss": 0.0528, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.097125097125099e-06, | |
| "loss": 0.053, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.04913330078125, | |
| "eval_runtime": 661.9533, | |
| "eval_samples_per_second": 4.742, | |
| "eval_steps_per_second": 0.038, | |
| "eval_wer": 21.94788528066064, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.08935508935509e-06, | |
| "loss": 0.0544, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 9.081585081585082e-06, | |
| "loss": 0.0536, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 9.073815073815075e-06, | |
| "loss": 0.052, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.066045066045067e-06, | |
| "loss": 0.0519, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.05827505827506e-06, | |
| "loss": 0.0538, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.050505050505052e-06, | |
| "loss": 0.053, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.042735042735043e-06, | |
| "loss": 0.0521, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 9.034965034965036e-06, | |
| "loss": 0.0541, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.027195027195028e-06, | |
| "loss": 0.0517, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 9.01942501942502e-06, | |
| "loss": 0.053, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.0482177734375, | |
| "eval_runtime": 740.8226, | |
| "eval_samples_per_second": 4.237, | |
| "eval_steps_per_second": 0.034, | |
| "eval_wer": 21.713536435665663, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.011655011655013e-06, | |
| "loss": 0.0526, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.003885003885004e-06, | |
| "loss": 0.0536, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.996114996114998e-06, | |
| "loss": 0.0516, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.988344988344989e-06, | |
| "loss": 0.053, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.980574980574982e-06, | |
| "loss": 0.0526, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.972804972804974e-06, | |
| "loss": 0.0519, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.965034965034965e-06, | |
| "loss": 0.0519, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.957264957264959e-06, | |
| "loss": 0.0532, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.94949494949495e-06, | |
| "loss": 0.0522, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.941724941724942e-06, | |
| "loss": 0.0525, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.049072265625, | |
| "eval_runtime": 640.0145, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 0.039, | |
| "eval_wer": 21.917196741435106, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.933954933954935e-06, | |
| "loss": 0.0515, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.926184926184926e-06, | |
| "loss": 0.051, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.91841491841492e-06, | |
| "loss": 0.052, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.910644910644911e-06, | |
| "loss": 0.0515, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.902874902874903e-06, | |
| "loss": 0.0531, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.895104895104896e-06, | |
| "loss": 0.0511, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.887334887334888e-06, | |
| "loss": 0.0507, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.879564879564881e-06, | |
| "loss": 0.0493, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.871794871794872e-06, | |
| "loss": 0.051, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.864024864024864e-06, | |
| "loss": 0.0514, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.047882080078125, | |
| "eval_runtime": 622.3257, | |
| "eval_samples_per_second": 5.044, | |
| "eval_steps_per_second": 0.04, | |
| "eval_wer": 21.557303872335677, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 8.856254856254857e-06, | |
| "loss": 0.0497, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.84848484848485e-06, | |
| "loss": 0.0506, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 8.840714840714842e-06, | |
| "loss": 0.0506, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 8.832944832944835e-06, | |
| "loss": 0.0533, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.825174825174825e-06, | |
| "loss": 0.0518, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.817404817404818e-06, | |
| "loss": 0.0519, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.80963480963481e-06, | |
| "loss": 0.0526, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.801864801864803e-06, | |
| "loss": 0.0507, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.794094794094795e-06, | |
| "loss": 0.0509, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.786324786324786e-06, | |
| "loss": 0.0519, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.04705810546875, | |
| "eval_runtime": 680.4666, | |
| "eval_samples_per_second": 4.613, | |
| "eval_steps_per_second": 0.037, | |
| "eval_wer": 21.415020645017297, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.77855477855478e-06, | |
| "loss": 0.0502, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.770784770784771e-06, | |
| "loss": 0.0525, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.763014763014764e-06, | |
| "loss": 0.0516, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 8.755244755244756e-06, | |
| "loss": 0.0503, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 8.747474747474747e-06, | |
| "loss": 0.0517, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.739704739704741e-06, | |
| "loss": 0.0507, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.731934731934732e-06, | |
| "loss": 0.0486, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.724164724164725e-06, | |
| "loss": 0.0508, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.716394716394717e-06, | |
| "loss": 0.0493, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.708624708624708e-06, | |
| "loss": 0.0501, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.046722412109375, | |
| "eval_runtime": 595.6385, | |
| "eval_samples_per_second": 5.27, | |
| "eval_steps_per_second": 0.042, | |
| "eval_wer": 21.074656846334115, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.700854700854702e-06, | |
| "loss": 0.0506, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.693084693084693e-06, | |
| "loss": 0.0513, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.685314685314686e-06, | |
| "loss": 0.0524, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.677544677544678e-06, | |
| "loss": 0.0502, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.66977466977467e-06, | |
| "loss": 0.049, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.662004662004663e-06, | |
| "loss": 0.051, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.654234654234654e-06, | |
| "loss": 0.0516, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.646464646464647e-06, | |
| "loss": 0.0494, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.63869463869464e-06, | |
| "loss": 0.0497, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.630924630924632e-06, | |
| "loss": 0.0517, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.04644775390625, | |
| "eval_runtime": 767.331, | |
| "eval_samples_per_second": 4.091, | |
| "eval_steps_per_second": 0.033, | |
| "eval_wer": 21.236469144068742, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.623154623154624e-06, | |
| "loss": 0.0505, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.615384615384617e-06, | |
| "loss": 0.0485, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.607614607614608e-06, | |
| "loss": 0.0492, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.5998445998446e-06, | |
| "loss": 0.0478, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.592074592074593e-06, | |
| "loss": 0.049, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.584304584304585e-06, | |
| "loss": 0.0501, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.576534576534578e-06, | |
| "loss": 0.0488, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.568764568764569e-06, | |
| "loss": 0.0517, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.560994560994563e-06, | |
| "loss": 0.0519, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.553224553224554e-06, | |
| "loss": 0.0504, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.045989990234375, | |
| "eval_runtime": 531.824, | |
| "eval_samples_per_second": 5.902, | |
| "eval_steps_per_second": 0.047, | |
| "eval_wer": 20.96864189264591, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.545454545454546e-06, | |
| "loss": 0.0501, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.537684537684539e-06, | |
| "loss": 0.0504, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 8.52991452991453e-06, | |
| "loss": 0.0491, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 8.522144522144524e-06, | |
| "loss": 0.0498, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.514374514374515e-06, | |
| "loss": 0.0505, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.506604506604507e-06, | |
| "loss": 0.0489, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.4988344988345e-06, | |
| "loss": 0.0517, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.49106449106449e-06, | |
| "loss": 0.052, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.483294483294485e-06, | |
| "loss": 0.0492, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.475524475524476e-06, | |
| "loss": 0.0494, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.04583740234375, | |
| "eval_runtime": 667.8917, | |
| "eval_samples_per_second": 4.7, | |
| "eval_steps_per_second": 0.037, | |
| "eval_wer": 20.87099654056467, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.467754467754468e-06, | |
| "loss": 0.0504, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.45998445998446e-06, | |
| "loss": 0.0489, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.452214452214453e-06, | |
| "loss": 0.0488, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.0474, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.436674436674436e-06, | |
| "loss": 0.0455, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.428904428904429e-06, | |
| "loss": 0.0428, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.421134421134422e-06, | |
| "loss": 0.0439, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.413364413364414e-06, | |
| "loss": 0.0448, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.405594405594407e-06, | |
| "loss": 0.0422, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.397824397824399e-06, | |
| "loss": 0.0421, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.046478271484375, | |
| "eval_runtime": 626.9064, | |
| "eval_samples_per_second": 5.007, | |
| "eval_steps_per_second": 0.04, | |
| "eval_wer": 20.698024774020755, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.39005439005439e-06, | |
| "loss": 0.0441, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.382284382284382e-06, | |
| "loss": 0.043, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.374514374514375e-06, | |
| "loss": 0.0422, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.366744366744368e-06, | |
| "loss": 0.0407, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.35897435897436e-06, | |
| "loss": 0.0436, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.351204351204351e-06, | |
| "loss": 0.0437, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.343434343434345e-06, | |
| "loss": 0.0435, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.335664335664336e-06, | |
| "loss": 0.0414, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.327894327894329e-06, | |
| "loss": 0.0414, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.320124320124321e-06, | |
| "loss": 0.0415, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.046417236328125, | |
| "eval_runtime": 527.7226, | |
| "eval_samples_per_second": 5.948, | |
| "eval_steps_per_second": 0.047, | |
| "eval_wer": 20.70639437562772, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.312354312354312e-06, | |
| "loss": 0.044, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.304584304584306e-06, | |
| "loss": 0.042, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.296814296814297e-06, | |
| "loss": 0.0422, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.28904428904429e-06, | |
| "loss": 0.0433, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.281274281274282e-06, | |
| "loss": 0.0429, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.273504273504273e-06, | |
| "loss": 0.0422, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.265734265734267e-06, | |
| "loss": 0.042, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.257964257964258e-06, | |
| "loss": 0.0438, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.25019425019425e-06, | |
| "loss": 0.0436, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.242424242424243e-06, | |
| "loss": 0.0435, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.04595947265625, | |
| "eval_runtime": 653.0764, | |
| "eval_samples_per_second": 4.806, | |
| "eval_steps_per_second": 0.038, | |
| "eval_wer": 20.75103225086486, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.234654234654235e-06, | |
| "loss": 0.0432, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.226884226884228e-06, | |
| "loss": 0.0443, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.219114219114219e-06, | |
| "loss": 0.0426, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.211344211344211e-06, | |
| "loss": 0.0418, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.203574203574204e-06, | |
| "loss": 0.0433, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.195804195804196e-06, | |
| "loss": 0.0414, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.188034188034189e-06, | |
| "loss": 0.0427, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.180264180264181e-06, | |
| "loss": 0.0435, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 8.172494172494172e-06, | |
| "loss": 0.0427, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.164724164724165e-06, | |
| "loss": 0.0429, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.045684814453125, | |
| "eval_runtime": 746.9147, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.033, | |
| "eval_wer": 20.56690101551166, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 8.156954156954157e-06, | |
| "loss": 0.0428, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.14918414918415e-06, | |
| "loss": 0.0421, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.141414141414142e-06, | |
| "loss": 0.0436, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.133644133644133e-06, | |
| "loss": 0.0423, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.125874125874127e-06, | |
| "loss": 0.0435, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.118104118104118e-06, | |
| "loss": 0.0402, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.11033411033411e-06, | |
| "loss": 0.042, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 8.102564102564103e-06, | |
| "loss": 0.0436, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.094794094794096e-06, | |
| "loss": 0.044, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.087024087024088e-06, | |
| "loss": 0.043, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.04595947265625, | |
| "eval_runtime": 614.8064, | |
| "eval_samples_per_second": 5.106, | |
| "eval_steps_per_second": 0.041, | |
| "eval_wer": 20.502734069858274, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.07925407925408e-06, | |
| "loss": 0.0441, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.071484071484072e-06, | |
| "loss": 0.0438, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.063714063714064e-06, | |
| "loss": 0.0428, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.055944055944057e-06, | |
| "loss": 0.0434, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.04817404817405e-06, | |
| "loss": 0.0431, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.04040404040404e-06, | |
| "loss": 0.0425, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.032634032634033e-06, | |
| "loss": 0.0436, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.024864024864025e-06, | |
| "loss": 0.0446, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.017094017094018e-06, | |
| "loss": 0.0424, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.00932400932401e-06, | |
| "loss": 0.042, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.04595947265625, | |
| "eval_runtime": 594.6469, | |
| "eval_samples_per_second": 5.279, | |
| "eval_steps_per_second": 0.042, | |
| "eval_wer": 20.550161812297734, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.001554001554003e-06, | |
| "loss": 0.0425, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.993783993783994e-06, | |
| "loss": 0.0444, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.986013986013986e-06, | |
| "loss": 0.0414, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.978243978243979e-06, | |
| "loss": 0.0423, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.970473970473971e-06, | |
| "loss": 0.0425, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.962703962703964e-06, | |
| "loss": 0.0436, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.954933954933956e-06, | |
| "loss": 0.0419, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.947163947163949e-06, | |
| "loss": 0.0431, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.93939393939394e-06, | |
| "loss": 0.0416, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.931623931623932e-06, | |
| "loss": 0.0418, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.04583740234375, | |
| "eval_runtime": 460.6203, | |
| "eval_samples_per_second": 6.815, | |
| "eval_steps_per_second": 0.054, | |
| "eval_wer": 20.494364468251312, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.923853923853925e-06, | |
| "loss": 0.0406, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.916083916083917e-06, | |
| "loss": 0.044, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.90831390831391e-06, | |
| "loss": 0.0429, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.9005439005439e-06, | |
| "loss": 0.0429, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.892773892773893e-06, | |
| "loss": 0.0421, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.885003885003886e-06, | |
| "loss": 0.0399, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.877233877233878e-06, | |
| "loss": 0.0417, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.86946386946387e-06, | |
| "loss": 0.0416, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.861693861693862e-06, | |
| "loss": 0.0427, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.853923853923854e-06, | |
| "loss": 0.0437, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.0445556640625, | |
| "eval_runtime": 780.2352, | |
| "eval_samples_per_second": 4.023, | |
| "eval_steps_per_second": 0.032, | |
| "eval_wer": 20.391139381765427, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.846153846153847e-06, | |
| "loss": 0.0425, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.838383838383839e-06, | |
| "loss": 0.0425, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.830613830613832e-06, | |
| "loss": 0.0417, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.822843822843823e-06, | |
| "loss": 0.0424, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 7.815073815073817e-06, | |
| "loss": 0.044, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.807303807303808e-06, | |
| "loss": 0.0421, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.7995337995338e-06, | |
| "loss": 0.0417, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.791763791763793e-06, | |
| "loss": 0.0428, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.783993783993785e-06, | |
| "loss": 0.0411, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.776223776223778e-06, | |
| "loss": 0.0424, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.044952392578125, | |
| "eval_runtime": 825.8671, | |
| "eval_samples_per_second": 3.801, | |
| "eval_steps_per_second": 0.03, | |
| "eval_wer": 20.307443365695793, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.768453768453769e-06, | |
| "loss": 0.0429, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.760683760683761e-06, | |
| "loss": 0.0416, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.752913752913754e-06, | |
| "loss": 0.0408, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.745143745143746e-06, | |
| "loss": 0.043, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.737373737373739e-06, | |
| "loss": 0.0423, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.729603729603731e-06, | |
| "loss": 0.042, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.721833721833722e-06, | |
| "loss": 0.0429, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.714063714063715e-06, | |
| "loss": 0.0406, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.706293706293707e-06, | |
| "loss": 0.0407, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.6985236985237e-06, | |
| "loss": 0.0403, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.045135498046875, | |
| "eval_runtime": 771.5812, | |
| "eval_samples_per_second": 4.068, | |
| "eval_steps_per_second": 0.032, | |
| "eval_wer": 20.27117509206562, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 7.690753690753692e-06, | |
| "loss": 0.0423, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.682983682983683e-06, | |
| "loss": 0.0424, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.675213675213677e-06, | |
| "loss": 0.0413, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.667443667443668e-06, | |
| "loss": 0.0429, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.65967365967366e-06, | |
| "loss": 0.0429, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.651903651903653e-06, | |
| "loss": 0.042, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.644133644133644e-06, | |
| "loss": 0.0435, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.636363636363638e-06, | |
| "loss": 0.0436, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.628593628593629e-06, | |
| "loss": 0.0435, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.620823620823622e-06, | |
| "loss": 0.0422, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 0.045318603515625, | |
| "eval_runtime": 535.0728, | |
| "eval_samples_per_second": 5.866, | |
| "eval_steps_per_second": 0.047, | |
| "eval_wer": 20.27117509206562, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.613053613053614e-06, | |
| "loss": 0.0406, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.605283605283606e-06, | |
| "loss": 0.04, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.597513597513598e-06, | |
| "loss": 0.0351, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.58974358974359e-06, | |
| "loss": 0.0361, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.581973581973583e-06, | |
| "loss": 0.035, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.574203574203575e-06, | |
| "loss": 0.036, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.5664335664335675e-06, | |
| "loss": 0.0366, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.558663558663559e-06, | |
| "loss": 0.0352, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.550893550893551e-06, | |
| "loss": 0.0364, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.543123543123544e-06, | |
| "loss": 0.037, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.047210693359375, | |
| "eval_runtime": 783.6011, | |
| "eval_samples_per_second": 4.006, | |
| "eval_steps_per_second": 0.032, | |
| "eval_wer": 20.39671911617007, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.535353535353536e-06, | |
| "loss": 0.0352, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.527583527583528e-06, | |
| "loss": 0.0354, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.51981351981352e-06, | |
| "loss": 0.0366, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.5120435120435135e-06, | |
| "loss": 0.0366, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.504273504273505e-06, | |
| "loss": 0.0369, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.496503496503497e-06, | |
| "loss": 0.0351, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.488733488733489e-06, | |
| "loss": 0.0366, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.480963480963481e-06, | |
| "loss": 0.0373, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.473193473193474e-06, | |
| "loss": 0.0366, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.465423465423466e-06, | |
| "loss": 0.0365, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 0.047576904296875, | |
| "eval_runtime": 589.7846, | |
| "eval_samples_per_second": 5.322, | |
| "eval_steps_per_second": 0.042, | |
| "eval_wer": 20.313023100100438, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.457653457653459e-06, | |
| "loss": 0.0349, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 7.44988344988345e-06, | |
| "loss": 0.0355, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.442113442113442e-06, | |
| "loss": 0.0375, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.434343434343435e-06, | |
| "loss": 0.0378, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 7.426573426573427e-06, | |
| "loss": 0.0348, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 7.4188034188034196e-06, | |
| "loss": 0.0361, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 7.411033411033411e-06, | |
| "loss": 0.0351, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 7.403263403263405e-06, | |
| "loss": 0.0364, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.395493395493396e-06, | |
| "loss": 0.038, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.387723387723388e-06, | |
| "loss": 0.0372, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 0.047698974609375, | |
| "eval_runtime": 558.9053, | |
| "eval_samples_per_second": 5.616, | |
| "eval_steps_per_second": 0.045, | |
| "eval_wer": 20.46367592902578, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 7.3799533799533805e-06, | |
| "loss": 0.0363, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 7.372183372183372e-06, | |
| "loss": 0.0364, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 7.3644133644133656e-06, | |
| "loss": 0.0362, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 7.356643356643357e-06, | |
| "loss": 0.036, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 7.34887334887335e-06, | |
| "loss": 0.0362, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 7.3411033411033415e-06, | |
| "loss": 0.0347, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 0.0369, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 7.3255633255633265e-06, | |
| "loss": 0.0366, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 7.317793317793318e-06, | |
| "loss": 0.0375, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 7.310023310023311e-06, | |
| "loss": 0.0359, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.04803466796875, | |
| "eval_runtime": 762.734, | |
| "eval_samples_per_second": 4.115, | |
| "eval_steps_per_second": 0.033, | |
| "eval_wer": 20.32976230331436, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 7.302253302253302e-06, | |
| "loss": 0.0384, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 7.294483294483296e-06, | |
| "loss": 0.0349, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 7.2867132867132875e-06, | |
| "loss": 0.0357, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.278943278943279e-06, | |
| "loss": 0.0356, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.271173271173272e-06, | |
| "loss": 0.0369, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 7.263403263403263e-06, | |
| "loss": 0.0358, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 7.255633255633257e-06, | |
| "loss": 0.0355, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 7.247863247863248e-06, | |
| "loss": 0.0364, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 7.240093240093241e-06, | |
| "loss": 0.0362, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 7.232323232323233e-06, | |
| "loss": 0.0365, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 0.04779052734375, | |
| "eval_runtime": 760.0721, | |
| "eval_samples_per_second": 4.13, | |
| "eval_steps_per_second": 0.033, | |
| "eval_wer": 20.360450842539894, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 7.224553224553224e-06, | |
| "loss": 0.0362, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 7.216783216783218e-06, | |
| "loss": 0.0356, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 7.209013209013209e-06, | |
| "loss": 0.0375, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 7.201243201243202e-06, | |
| "loss": 0.0366, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 7.1934731934731936e-06, | |
| "loss": 0.0381, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 7.185703185703187e-06, | |
| "loss": 0.0359, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 7.177933177933179e-06, | |
| "loss": 0.0366, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 7.17016317016317e-06, | |
| "loss": 0.0368, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 7.162393162393163e-06, | |
| "loss": 0.036, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 7.1546231546231545e-06, | |
| "loss": 0.0372, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_loss": 0.04632568359375, | |
| "eval_runtime": 587.303, | |
| "eval_samples_per_second": 5.345, | |
| "eval_steps_per_second": 0.043, | |
| "eval_wer": 20.17910947438902, | |
| "step": 3800 | |
| } | |
| ], | |
| "max_steps": 13000, | |
| "num_train_epochs": 13, | |
| "total_flos": 9.926607557362167e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |