| { | |
| "best_metric": 25.09991015830726, | |
| "best_model_checkpoint": "all_lang_models/odia_models/whisper-medium-or_alldata_multigpu/checkpoint-5100", | |
| "epoch": 3.5075653370013757, | |
| "global_step": 5100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.192560871397968e-06, | |
| "loss": 3.5823, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.119010278963368e-06, | |
| "loss": 1.5595, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.257677982717129e-06, | |
| "loss": 1.1267, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.9781721403396e-06, | |
| "loss": 0.6488, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.506433605585243e-06, | |
| "loss": 0.4383, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.923729588202299e-06, | |
| "loss": 0.3338, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.268681480915506e-06, | |
| "loss": 0.2642, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.562705504037769e-06, | |
| "loss": 0.2227, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.818922847973121e-06, | |
| "loss": 0.2019, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.045957702197483e-06, | |
| "loss": 0.179, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.1595458984375, | |
| "eval_runtime": 342.1462, | |
| "eval_samples_per_second": 8.771, | |
| "eval_steps_per_second": 0.07, | |
| "eval_wer": 54.676415006660676, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.249783143647417e-06, | |
| "loss": 0.1662, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.43470745971544e-06, | |
| "loss": 0.1543, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.603940564268044e-06, | |
| "loss": 0.1431, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.759938293620717e-06, | |
| "loss": 0.134, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.904621547904999e-06, | |
| "loss": 0.1255, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.9986531986532e-06, | |
| "loss": 0.1215, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.991919191919192e-06, | |
| "loss": 0.1154, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.985185185185185e-06, | |
| "loss": 0.1117, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.978451178451179e-06, | |
| "loss": 0.1096, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.971717171717173e-06, | |
| "loss": 0.1049, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.10455322265625, | |
| "eval_runtime": 372.4886, | |
| "eval_samples_per_second": 8.057, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 42.1326559063168, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.964983164983167e-06, | |
| "loss": 0.1001, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.95824915824916e-06, | |
| "loss": 0.0962, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.951515151515152e-06, | |
| "loss": 0.0932, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.944781144781146e-06, | |
| "loss": 0.0913, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.938047138047138e-06, | |
| "loss": 0.0878, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.931313131313132e-06, | |
| "loss": 0.0845, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.924579124579126e-06, | |
| "loss": 0.0831, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.917845117845119e-06, | |
| "loss": 0.083, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.911111111111113e-06, | |
| "loss": 0.0816, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.904377104377105e-06, | |
| "loss": 0.0812, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.09039306640625, | |
| "eval_runtime": 340.7369, | |
| "eval_samples_per_second": 8.807, | |
| "eval_steps_per_second": 0.07, | |
| "eval_wer": 37.535239629480465, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.897643097643098e-06, | |
| "loss": 0.0773, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.890909090909092e-06, | |
| "loss": 0.0758, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.884175084175084e-06, | |
| "loss": 0.076, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.877441077441078e-06, | |
| "loss": 0.0741, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.870707070707072e-06, | |
| "loss": 0.0723, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.863973063973065e-06, | |
| "loss": 0.0717, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.857239057239057e-06, | |
| "loss": 0.0714, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.850505050505051e-06, | |
| "loss": 0.0697, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.843771043771044e-06, | |
| "loss": 0.067, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.837037037037038e-06, | |
| "loss": 0.0652, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.08392333984375, | |
| "eval_runtime": 333.3596, | |
| "eval_samples_per_second": 9.002, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 34.24207689209703, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.830303030303032e-06, | |
| "loss": 0.0668, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.823569023569024e-06, | |
| "loss": 0.0654, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.816835016835018e-06, | |
| "loss": 0.0625, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.81010101010101e-06, | |
| "loss": 0.0625, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.803367003367003e-06, | |
| "loss": 0.0653, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.796632996632997e-06, | |
| "loss": 0.0623, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.78989898989899e-06, | |
| "loss": 0.0626, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.783164983164984e-06, | |
| "loss": 0.0611, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.776430976430978e-06, | |
| "loss": 0.0596, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.76969696969697e-06, | |
| "loss": 0.0608, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.074951171875, | |
| "eval_runtime": 334.6599, | |
| "eval_samples_per_second": 8.967, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 32.52888875120047, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.762962962962964e-06, | |
| "loss": 0.0611, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.756228956228957e-06, | |
| "loss": 0.0596, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.749494949494949e-06, | |
| "loss": 0.058, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.742760942760943e-06, | |
| "loss": 0.0566, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.736026936026937e-06, | |
| "loss": 0.0562, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.729292929292931e-06, | |
| "loss": 0.0569, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.722558922558924e-06, | |
| "loss": 0.0545, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.715824915824916e-06, | |
| "loss": 0.0533, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.70909090909091e-06, | |
| "loss": 0.0557, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.702356902356903e-06, | |
| "loss": 0.0553, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.0740966796875, | |
| "eval_runtime": 340.3479, | |
| "eval_samples_per_second": 8.817, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 31.209145264723194, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.695622895622897e-06, | |
| "loss": 0.0535, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.688888888888889e-06, | |
| "loss": 0.0541, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.682154882154883e-06, | |
| "loss": 0.0531, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.675420875420877e-06, | |
| "loss": 0.0531, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.66868686868687e-06, | |
| "loss": 0.0518, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.661952861952862e-06, | |
| "loss": 0.0519, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.655218855218856e-06, | |
| "loss": 0.0536, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.648484848484849e-06, | |
| "loss": 0.0517, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.641750841750843e-06, | |
| "loss": 0.0516, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.635016835016837e-06, | |
| "loss": 0.0497, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.06781005859375, | |
| "eval_runtime": 332.0934, | |
| "eval_samples_per_second": 9.037, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 30.16202484587503, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.628282828282829e-06, | |
| "loss": 0.051, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.621548821548823e-06, | |
| "loss": 0.051, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.614814814814816e-06, | |
| "loss": 0.0504, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.608080808080808e-06, | |
| "loss": 0.0514, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.601346801346802e-06, | |
| "loss": 0.0499, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.594612794612796e-06, | |
| "loss": 0.05, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.587878787878789e-06, | |
| "loss": 0.05, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.581144781144783e-06, | |
| "loss": 0.0488, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.574410774410775e-06, | |
| "loss": 0.0498, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.56767676767677e-06, | |
| "loss": 0.048, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.06671142578125, | |
| "eval_runtime": 333.8217, | |
| "eval_samples_per_second": 8.99, | |
| "eval_steps_per_second": 0.072, | |
| "eval_wer": 30.038105269679978, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.560942760942762e-06, | |
| "loss": 0.0471, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.554208754208754e-06, | |
| "loss": 0.049, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.547474747474748e-06, | |
| "loss": 0.0484, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.540740740740742e-06, | |
| "loss": 0.0466, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.534006734006735e-06, | |
| "loss": 0.046, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.527272727272729e-06, | |
| "loss": 0.0478, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.520538720538721e-06, | |
| "loss": 0.0465, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.513804713804713e-06, | |
| "loss": 0.0491, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.507070707070707e-06, | |
| "loss": 0.0447, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.500336700336702e-06, | |
| "loss": 0.0456, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.06402587890625, | |
| "eval_runtime": 336.9235, | |
| "eval_samples_per_second": 8.907, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 28.80200749713436, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.493602693602694e-06, | |
| "loss": 0.0459, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.486868686868688e-06, | |
| "loss": 0.0472, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.48013468013468e-06, | |
| "loss": 0.0459, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.473400673400675e-06, | |
| "loss": 0.0457, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.466666666666667e-06, | |
| "loss": 0.0469, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.459932659932661e-06, | |
| "loss": 0.0456, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.453198653198653e-06, | |
| "loss": 0.0431, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.446464646464648e-06, | |
| "loss": 0.0435, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.439730639730642e-06, | |
| "loss": 0.0458, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.432996632996634e-06, | |
| "loss": 0.044, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.0638427734375, | |
| "eval_runtime": 345.0473, | |
| "eval_samples_per_second": 8.697, | |
| "eval_steps_per_second": 0.07, | |
| "eval_wer": 28.91973109451966, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.426262626262626e-06, | |
| "loss": 0.0453, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.41952861952862e-06, | |
| "loss": 0.043, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.412794612794613e-06, | |
| "loss": 0.044, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.406060606060607e-06, | |
| "loss": 0.0434, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.399326599326601e-06, | |
| "loss": 0.0438, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.392592592592593e-06, | |
| "loss": 0.0445, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.385858585858588e-06, | |
| "loss": 0.045, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.37912457912458e-06, | |
| "loss": 0.0415, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.372390572390572e-06, | |
| "loss": 0.0421, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.365656565656566e-06, | |
| "loss": 0.0426, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.0609130859375, | |
| "eval_runtime": 366.876, | |
| "eval_samples_per_second": 8.18, | |
| "eval_steps_per_second": 0.065, | |
| "eval_wer": 28.35589702283218, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.358922558922559e-06, | |
| "loss": 0.0438, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.352188552188553e-06, | |
| "loss": 0.0425, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.345454545454547e-06, | |
| "loss": 0.0439, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.33872053872054e-06, | |
| "loss": 0.0431, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.331986531986533e-06, | |
| "loss": 0.0434, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.325252525252526e-06, | |
| "loss": 0.0429, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.318518518518518e-06, | |
| "loss": 0.0423, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.311784511784512e-06, | |
| "loss": 0.0437, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.305050505050506e-06, | |
| "loss": 0.0422, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.298316498316499e-06, | |
| "loss": 0.0413, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.061065673828125, | |
| "eval_runtime": 478.7261, | |
| "eval_samples_per_second": 6.269, | |
| "eval_steps_per_second": 0.05, | |
| "eval_wer": 27.93766845317389, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.291582491582493e-06, | |
| "loss": 0.0422, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.284848484848485e-06, | |
| "loss": 0.0421, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.27811447811448e-06, | |
| "loss": 0.0439, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.271380471380472e-06, | |
| "loss": 0.041, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.264646464646466e-06, | |
| "loss": 0.0418, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.257912457912458e-06, | |
| "loss": 0.0413, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.251178451178452e-06, | |
| "loss": 0.0421, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.244444444444445e-06, | |
| "loss": 0.0416, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.237710437710439e-06, | |
| "loss": 0.0422, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.230976430976431e-06, | |
| "loss": 0.0416, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.060760498046875, | |
| "eval_runtime": 338.6372, | |
| "eval_samples_per_second": 8.862, | |
| "eval_steps_per_second": 0.071, | |
| "eval_wer": 28.266055330090772, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.224242424242424e-06, | |
| "loss": 0.0399, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.217508417508418e-06, | |
| "loss": 0.0408, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.210774410774412e-06, | |
| "loss": 0.0401, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 9.204040404040406e-06, | |
| "loss": 0.0399, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.197306397306398e-06, | |
| "loss": 0.0383, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.19057239057239e-06, | |
| "loss": 0.0394, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.183838383838385e-06, | |
| "loss": 0.0382, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.177104377104377e-06, | |
| "loss": 0.0397, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.170370370370371e-06, | |
| "loss": 0.0389, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.163636363636365e-06, | |
| "loss": 0.0401, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.060394287109375, | |
| "eval_runtime": 1283.2209, | |
| "eval_samples_per_second": 2.339, | |
| "eval_steps_per_second": 0.019, | |
| "eval_wer": 27.441990148393693, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.156902356902358e-06, | |
| "loss": 0.0406, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.150168350168352e-06, | |
| "loss": 0.0393, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.143434343434344e-06, | |
| "loss": 0.041, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.136700336700337e-06, | |
| "loss": 0.0403, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.12996632996633e-06, | |
| "loss": 0.0391, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.123232323232323e-06, | |
| "loss": 0.0361, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.116498316498317e-06, | |
| "loss": 0.0367, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.109764309764311e-06, | |
| "loss": 0.0334, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9.103030303030304e-06, | |
| "loss": 0.0337, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.096296296296298e-06, | |
| "loss": 0.0352, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.0601806640625, | |
| "eval_runtime": 383.1061, | |
| "eval_samples_per_second": 7.833, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 27.290188667554755, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.08956228956229e-06, | |
| "loss": 0.0359, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.082828282828283e-06, | |
| "loss": 0.0365, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.076094276094277e-06, | |
| "loss": 0.0351, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 9.06936026936027e-06, | |
| "loss": 0.0345, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.062626262626263e-06, | |
| "loss": 0.0348, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.055892255892257e-06, | |
| "loss": 0.0345, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.04915824915825e-06, | |
| "loss": 0.0367, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.042424242424244e-06, | |
| "loss": 0.0349, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.035690235690236e-06, | |
| "loss": 0.0344, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.028956228956229e-06, | |
| "loss": 0.0336, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.057952880859375, | |
| "eval_runtime": 392.8207, | |
| "eval_samples_per_second": 7.64, | |
| "eval_steps_per_second": 0.061, | |
| "eval_wer": 26.887450044920847, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.022222222222223e-06, | |
| "loss": 0.034, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.015488215488217e-06, | |
| "loss": 0.0341, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.008754208754209e-06, | |
| "loss": 0.0332, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.002020202020203e-06, | |
| "loss": 0.0346, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.995286195286196e-06, | |
| "loss": 0.0353, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 8.98855218855219e-06, | |
| "loss": 0.033, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 8.981818181818182e-06, | |
| "loss": 0.033, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.975084175084176e-06, | |
| "loss": 0.0349, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.96835016835017e-06, | |
| "loss": 0.0351, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.961616161616163e-06, | |
| "loss": 0.0349, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.05853271484375, | |
| "eval_runtime": 365.8153, | |
| "eval_samples_per_second": 8.204, | |
| "eval_steps_per_second": 0.066, | |
| "eval_wer": 26.70466867003315, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.954882154882155e-06, | |
| "loss": 0.0346, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.948148148148149e-06, | |
| "loss": 0.0338, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 8.941414141414142e-06, | |
| "loss": 0.0345, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.934680134680136e-06, | |
| "loss": 0.0354, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.927946127946128e-06, | |
| "loss": 0.0333, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 8.921212121212122e-06, | |
| "loss": 0.0341, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.914478114478116e-06, | |
| "loss": 0.0349, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.907744107744109e-06, | |
| "loss": 0.0345, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.901010101010101e-06, | |
| "loss": 0.035, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.894276094276095e-06, | |
| "loss": 0.0327, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.05743408203125, | |
| "eval_runtime": 374.9449, | |
| "eval_samples_per_second": 8.004, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 26.66439480776976, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.887542087542087e-06, | |
| "loss": 0.0325, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 8.880808080808082e-06, | |
| "loss": 0.0343, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.874074074074076e-06, | |
| "loss": 0.0324, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.867340067340068e-06, | |
| "loss": 0.0327, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.860606060606062e-06, | |
| "loss": 0.0341, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.853872053872055e-06, | |
| "loss": 0.034, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.847138047138047e-06, | |
| "loss": 0.034, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.840404040404041e-06, | |
| "loss": 0.0345, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.833670033670035e-06, | |
| "loss": 0.0341, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.826936026936027e-06, | |
| "loss": 0.0325, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.05572509765625, | |
| "eval_runtime": 348.8066, | |
| "eval_samples_per_second": 8.604, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 26.52498528455033, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.820202020202022e-06, | |
| "loss": 0.0346, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 8.813468013468014e-06, | |
| "loss": 0.0335, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.806734006734008e-06, | |
| "loss": 0.0319, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0335, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 8.793265993265993e-06, | |
| "loss": 0.0322, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.786531986531987e-06, | |
| "loss": 0.0342, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.779797979797981e-06, | |
| "loss": 0.0321, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.773063973063973e-06, | |
| "loss": 0.0339, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 8.766329966329968e-06, | |
| "loss": 0.034, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.75959595959596e-06, | |
| "loss": 0.0333, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.0565185546875, | |
| "eval_runtime": 425.1101, | |
| "eval_samples_per_second": 7.059, | |
| "eval_steps_per_second": 0.056, | |
| "eval_wer": 26.797608352179438, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.752861952861954e-06, | |
| "loss": 0.0328, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 8.746127946127946e-06, | |
| "loss": 0.0332, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.73939393939394e-06, | |
| "loss": 0.0336, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.732659932659935e-06, | |
| "loss": 0.0339, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 8.725925925925927e-06, | |
| "loss": 0.0335, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.71919191919192e-06, | |
| "loss": 0.0341, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.712457912457913e-06, | |
| "loss": 0.0335, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.705723905723906e-06, | |
| "loss": 0.0336, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.6989898989899e-06, | |
| "loss": 0.0324, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.692255892255892e-06, | |
| "loss": 0.0333, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.057342529296875, | |
| "eval_runtime": 379.4366, | |
| "eval_samples_per_second": 7.909, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 26.351497877877257, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 8.685521885521886e-06, | |
| "loss": 0.0326, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.67878787878788e-06, | |
| "loss": 0.0325, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.672053872053873e-06, | |
| "loss": 0.0341, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.665319865319865e-06, | |
| "loss": 0.0327, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.65858585858586e-06, | |
| "loss": 0.0336, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.651851851851852e-06, | |
| "loss": 0.0337, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.645117845117846e-06, | |
| "loss": 0.0329, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 8.63838383838384e-06, | |
| "loss": 0.0334, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.631649831649832e-06, | |
| "loss": 0.0335, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.624915824915826e-06, | |
| "loss": 0.0322, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.057952880859375, | |
| "eval_runtime": 363.6764, | |
| "eval_samples_per_second": 8.252, | |
| "eval_steps_per_second": 0.066, | |
| "eval_wer": 26.459927507047926, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 8.618181818181819e-06, | |
| "loss": 0.0338, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 8.611447811447811e-06, | |
| "loss": 0.0333, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 8.604713804713805e-06, | |
| "loss": 0.0329, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.597979797979798e-06, | |
| "loss": 0.0322, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.591245791245792e-06, | |
| "loss": 0.0321, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 8.584511784511786e-06, | |
| "loss": 0.032, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.577777777777778e-06, | |
| "loss": 0.0328, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.571043771043772e-06, | |
| "loss": 0.0327, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.564309764309765e-06, | |
| "loss": 0.0336, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.557575757575757e-06, | |
| "loss": 0.0311, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.054962158203125, | |
| "eval_runtime": 352.2221, | |
| "eval_samples_per_second": 8.52, | |
| "eval_steps_per_second": 0.068, | |
| "eval_wer": 26.190402428823695, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.550841750841751e-06, | |
| "loss": 0.032, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.544107744107745e-06, | |
| "loss": 0.0315, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.537373737373738e-06, | |
| "loss": 0.0317, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.530639730639732e-06, | |
| "loss": 0.0316, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 8.523905723905724e-06, | |
| "loss": 0.0321, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 8.517171717171718e-06, | |
| "loss": 0.0314, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 8.51043771043771e-06, | |
| "loss": 0.032, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.503703703703705e-06, | |
| "loss": 0.0318, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 8.496969696969697e-06, | |
| "loss": 0.0323, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.490235690235691e-06, | |
| "loss": 0.0321, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.0556640625, | |
| "eval_runtime": 402.6402, | |
| "eval_samples_per_second": 7.453, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 26.79141237336968, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.483501683501684e-06, | |
| "loss": 0.0329, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.476767676767678e-06, | |
| "loss": 0.0339, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.47003367003367e-06, | |
| "loss": 0.0315, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.463299663299664e-06, | |
| "loss": 0.0314, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.456565656565657e-06, | |
| "loss": 0.0328, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.44983164983165e-06, | |
| "loss": 0.0322, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.443097643097645e-06, | |
| "loss": 0.0308, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.436363636363637e-06, | |
| "loss": 0.0311, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.42962962962963e-06, | |
| "loss": 0.0322, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.422895622895624e-06, | |
| "loss": 0.0326, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.055755615234375, | |
| "eval_runtime": 372.9698, | |
| "eval_samples_per_second": 8.046, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 26.35769385668701, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.416161616161616e-06, | |
| "loss": 0.0302, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.40942760942761e-06, | |
| "loss": 0.0312, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.402693602693604e-06, | |
| "loss": 0.0315, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.395959595959597e-06, | |
| "loss": 0.0305, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.38922558922559e-06, | |
| "loss": 0.0317, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.382491582491583e-06, | |
| "loss": 0.0316, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.375757575757576e-06, | |
| "loss": 0.0314, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.36902356902357e-06, | |
| "loss": 0.0313, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.362289562289562e-06, | |
| "loss": 0.0327, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.355555555555556e-06, | |
| "loss": 0.0324, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.0538330078125, | |
| "eval_runtime": 403.0276, | |
| "eval_samples_per_second": 7.446, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 25.958053223457977, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.34882154882155e-06, | |
| "loss": 0.0318, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.342087542087543e-06, | |
| "loss": 0.0322, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.335353535353537e-06, | |
| "loss": 0.0316, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.328619528619529e-06, | |
| "loss": 0.0313, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.321885521885521e-06, | |
| "loss": 0.0321, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.315151515151516e-06, | |
| "loss": 0.0324, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.30841750841751e-06, | |
| "loss": 0.0325, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.301683501683502e-06, | |
| "loss": 0.0314, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.294949494949496e-06, | |
| "loss": 0.0317, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.288215488215489e-06, | |
| "loss": 0.0309, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.05511474609375, | |
| "eval_runtime": 350.0336, | |
| "eval_samples_per_second": 8.573, | |
| "eval_steps_per_second": 0.069, | |
| "eval_wer": 25.899191424765327, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.281481481481483e-06, | |
| "loss": 0.0313, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.274747474747475e-06, | |
| "loss": 0.0307, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.268013468013469e-06, | |
| "loss": 0.0297, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 8.261279461279462e-06, | |
| "loss": 0.0316, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 8.254545454545456e-06, | |
| "loss": 0.0312, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 8.247811447811448e-06, | |
| "loss": 0.0318, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.241077441077442e-06, | |
| "loss": 0.0322, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.234343434343434e-06, | |
| "loss": 0.0317, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.227609427609429e-06, | |
| "loss": 0.0307, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.220875420875421e-06, | |
| "loss": 0.0307, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.056976318359375, | |
| "eval_runtime": 411.91, | |
| "eval_samples_per_second": 7.286, | |
| "eval_steps_per_second": 0.058, | |
| "eval_wer": 25.700920102853246, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 8.214141414141415e-06, | |
| "loss": 0.0315, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.207407407407409e-06, | |
| "loss": 0.0307, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.200673400673402e-06, | |
| "loss": 0.0307, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.193939393939394e-06, | |
| "loss": 0.0315, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.187205387205388e-06, | |
| "loss": 0.03, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.18047138047138e-06, | |
| "loss": 0.0307, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 8.173737373737375e-06, | |
| "loss": 0.031, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.167003367003367e-06, | |
| "loss": 0.0317, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.160269360269361e-06, | |
| "loss": 0.0309, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.153535353535355e-06, | |
| "loss": 0.0306, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.05511474609375, | |
| "eval_runtime": 366.8057, | |
| "eval_samples_per_second": 8.181, | |
| "eval_steps_per_second": 0.065, | |
| "eval_wer": 25.691626134638618, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.146801346801347e-06, | |
| "loss": 0.0288, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.14006734006734e-06, | |
| "loss": 0.0275, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.133333333333334e-06, | |
| "loss": 0.0257, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.126599326599326e-06, | |
| "loss": 0.0273, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 8.11986531986532e-06, | |
| "loss": 0.0263, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.113131313131315e-06, | |
| "loss": 0.0262, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.106397306397307e-06, | |
| "loss": 0.027, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.099663299663301e-06, | |
| "loss": 0.0268, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.092929292929293e-06, | |
| "loss": 0.0279, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.086195286195286e-06, | |
| "loss": 0.0267, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.05584716796875, | |
| "eval_runtime": 377.5461, | |
| "eval_samples_per_second": 7.949, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 25.72570401809226, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.07946127946128e-06, | |
| "loss": 0.0262, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.072727272727274e-06, | |
| "loss": 0.0262, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.065993265993266e-06, | |
| "loss": 0.026, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.05925925925926e-06, | |
| "loss": 0.0279, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.052525252525253e-06, | |
| "loss": 0.0271, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.045791245791247e-06, | |
| "loss": 0.0261, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.03905723905724e-06, | |
| "loss": 0.0269, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.032323232323232e-06, | |
| "loss": 0.0257, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.025589225589226e-06, | |
| "loss": 0.0273, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.01885521885522e-06, | |
| "loss": 0.0262, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.054931640625, | |
| "eval_runtime": 389.5971, | |
| "eval_samples_per_second": 7.703, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.245515660336444, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.012121212121214e-06, | |
| "loss": 0.0259, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.005387205387206e-06, | |
| "loss": 0.0274, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 7.998653198653199e-06, | |
| "loss": 0.0267, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 7.991919191919193e-06, | |
| "loss": 0.0266, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 7.985185185185185e-06, | |
| "loss": 0.0268, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 7.97845117845118e-06, | |
| "loss": 0.0271, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.971717171717173e-06, | |
| "loss": 0.0273, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 7.964983164983166e-06, | |
| "loss": 0.027, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 7.95824915824916e-06, | |
| "loss": 0.027, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.951515151515152e-06, | |
| "loss": 0.0266, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.056793212890625, | |
| "eval_runtime": 388.5434, | |
| "eval_samples_per_second": 7.724, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.397317141175378, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.944781144781145e-06, | |
| "loss": 0.0269, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.938047138047139e-06, | |
| "loss": 0.0259, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.931313131313131e-06, | |
| "loss": 0.0262, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.924579124579125e-06, | |
| "loss": 0.0269, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.91784511784512e-06, | |
| "loss": 0.0268, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.911111111111112e-06, | |
| "loss": 0.0265, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.904377104377104e-06, | |
| "loss": 0.0263, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.897643097643098e-06, | |
| "loss": 0.0264, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.89090909090909e-06, | |
| "loss": 0.0266, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.884175084175085e-06, | |
| "loss": 0.0274, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.055633544921875, | |
| "eval_runtime": 386.9203, | |
| "eval_samples_per_second": 7.756, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.555314600824065, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.877441077441079e-06, | |
| "loss": 0.0272, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.870707070707071e-06, | |
| "loss": 0.0261, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.863973063973065e-06, | |
| "loss": 0.0262, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.857239057239058e-06, | |
| "loss": 0.0273, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.85050505050505e-06, | |
| "loss": 0.0267, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.843771043771044e-06, | |
| "loss": 0.0257, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.837037037037037e-06, | |
| "loss": 0.0253, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.83030303030303e-06, | |
| "loss": 0.0263, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.823569023569025e-06, | |
| "loss": 0.0274, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 7.816835016835017e-06, | |
| "loss": 0.0257, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.057891845703125, | |
| "eval_runtime": 384.8567, | |
| "eval_samples_per_second": 7.798, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.53672666439481, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.810101010101011e-06, | |
| "loss": 0.0262, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.803367003367004e-06, | |
| "loss": 0.0268, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 7.796632996632996e-06, | |
| "loss": 0.0269, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 7.78989898989899e-06, | |
| "loss": 0.0266, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 7.783164983164984e-06, | |
| "loss": 0.0281, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 7.776430976430978e-06, | |
| "loss": 0.0256, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.76969696969697e-06, | |
| "loss": 0.0265, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.762962962962963e-06, | |
| "loss": 0.0267, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.756228956228957e-06, | |
| "loss": 0.0265, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.74949494949495e-06, | |
| "loss": 0.0261, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.056182861328125, | |
| "eval_runtime": 400.7288, | |
| "eval_samples_per_second": 7.489, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 25.611078410111837, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 7.742760942760944e-06, | |
| "loss": 0.0271, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.736026936026936e-06, | |
| "loss": 0.0266, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.72929292929293e-06, | |
| "loss": 0.0261, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.722558922558924e-06, | |
| "loss": 0.0269, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.715824915824917e-06, | |
| "loss": 0.0259, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.709090909090909e-06, | |
| "loss": 0.0272, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.702356902356903e-06, | |
| "loss": 0.0277, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.695622895622896e-06, | |
| "loss": 0.0263, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.68888888888889e-06, | |
| "loss": 0.0277, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.682154882154884e-06, | |
| "loss": 0.0261, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.055633544921875, | |
| "eval_runtime": 381.8808, | |
| "eval_samples_per_second": 7.858, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 25.23931968152669, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.675420875420876e-06, | |
| "loss": 0.0275, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.66868686868687e-06, | |
| "loss": 0.0267, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.661952861952863e-06, | |
| "loss": 0.0264, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.655218855218855e-06, | |
| "loss": 0.0266, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 7.648484848484849e-06, | |
| "loss": 0.0263, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.641750841750843e-06, | |
| "loss": 0.0268, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.635016835016836e-06, | |
| "loss": 0.0269, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.628282828282829e-06, | |
| "loss": 0.0261, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.621548821548822e-06, | |
| "loss": 0.0271, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.614814814814816e-06, | |
| "loss": 0.0277, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.0546875, | |
| "eval_runtime": 370.152, | |
| "eval_samples_per_second": 8.107, | |
| "eval_steps_per_second": 0.065, | |
| "eval_wer": 25.62037237832647, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.6080808080808085e-06, | |
| "loss": 0.0266, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.601346801346802e-06, | |
| "loss": 0.026, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.594612794612796e-06, | |
| "loss": 0.0277, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.587878787878788e-06, | |
| "loss": 0.0274, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.5811447811447815e-06, | |
| "loss": 0.0263, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.574410774410776e-06, | |
| "loss": 0.0264, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.567676767676768e-06, | |
| "loss": 0.0276, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.560942760942761e-06, | |
| "loss": 0.0267, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.554208754208755e-06, | |
| "loss": 0.0262, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.547474747474748e-06, | |
| "loss": 0.0279, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.05615234375, | |
| "eval_runtime": 385.5195, | |
| "eval_samples_per_second": 7.784, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.524334706775303, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.540740740740742e-06, | |
| "loss": 0.0269, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.534006734006735e-06, | |
| "loss": 0.0269, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.5272727272727274e-06, | |
| "loss": 0.0271, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.5205387205387215e-06, | |
| "loss": 0.0267, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.513804713804714e-06, | |
| "loss": 0.0263, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.507070707070707e-06, | |
| "loss": 0.0285, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 7.500336700336701e-06, | |
| "loss": 0.0281, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.493602693602694e-06, | |
| "loss": 0.0272, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.486868686868688e-06, | |
| "loss": 0.0263, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.480134680134681e-06, | |
| "loss": 0.0274, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.056060791015625, | |
| "eval_runtime": 402.5369, | |
| "eval_samples_per_second": 7.455, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 25.50264878094117, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.473400673400673e-06, | |
| "loss": 0.0265, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.4666666666666675e-06, | |
| "loss": 0.0266, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 7.459932659932661e-06, | |
| "loss": 0.0264, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.453198653198653e-06, | |
| "loss": 0.0276, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.446464646464647e-06, | |
| "loss": 0.0261, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.4397306397306404e-06, | |
| "loss": 0.0259, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 7.4329966329966345e-06, | |
| "loss": 0.0262, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.426262626262627e-06, | |
| "loss": 0.0275, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.41952861952862e-06, | |
| "loss": 0.0269, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 7.412794612794613e-06, | |
| "loss": 0.0259, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 0.054962158203125, | |
| "eval_runtime": 389.7496, | |
| "eval_samples_per_second": 7.7, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.911583382384833, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.406060606060607e-06, | |
| "loss": 0.0268, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.3993265993266e-06, | |
| "loss": 0.0264, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.392592592592593e-06, | |
| "loss": 0.0274, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.385858585858586e-06, | |
| "loss": 0.0268, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.3791245791245805e-06, | |
| "loss": 0.0271, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.372390572390573e-06, | |
| "loss": 0.0261, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.365656565656566e-06, | |
| "loss": 0.0267, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.35892255892256e-06, | |
| "loss": 0.0266, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.3521885521885526e-06, | |
| "loss": 0.0264, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.345454545454546e-06, | |
| "loss": 0.0263, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.05572509765625, | |
| "eval_runtime": 389.9336, | |
| "eval_samples_per_second": 7.696, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.422101056414387, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.33872053872054e-06, | |
| "loss": 0.0264, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.331986531986532e-06, | |
| "loss": 0.0262, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.325252525252526e-06, | |
| "loss": 0.0257, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.31851851851852e-06, | |
| "loss": 0.0254, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.311784511784512e-06, | |
| "loss": 0.0277, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 7.305050505050506e-06, | |
| "loss": 0.0267, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.2983164983164985e-06, | |
| "loss": 0.0265, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.291582491582492e-06, | |
| "loss": 0.0258, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.284848484848486e-06, | |
| "loss": 0.0264, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.278114478114478e-06, | |
| "loss": 0.0268, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.055084228515625, | |
| "eval_runtime": 378.0135, | |
| "eval_samples_per_second": 7.939, | |
| "eval_steps_per_second": 0.063, | |
| "eval_wer": 25.23002571331206, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 7.2713804713804715e-06, | |
| "loss": 0.0282, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 7.2646464646464656e-06, | |
| "loss": 0.0271, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.257912457912458e-06, | |
| "loss": 0.026, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.251178451178452e-06, | |
| "loss": 0.0266, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.244444444444445e-06, | |
| "loss": 0.0265, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.237710437710438e-06, | |
| "loss": 0.0267, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.230976430976432e-06, | |
| "loss": 0.0265, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.224242424242425e-06, | |
| "loss": 0.0255, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.217508417508417e-06, | |
| "loss": 0.0257, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.2107744107744115e-06, | |
| "loss": 0.0265, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.05450439453125, | |
| "eval_runtime": 388.5783, | |
| "eval_samples_per_second": 7.723, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.34465132129248, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.204040404040405e-06, | |
| "loss": 0.0256, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.197306397306398e-06, | |
| "loss": 0.0271, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.190572390572391e-06, | |
| "loss": 0.0266, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 7.1838383838383845e-06, | |
| "loss": 0.026, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.177104377104378e-06, | |
| "loss": 0.0275, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.170370370370371e-06, | |
| "loss": 0.0272, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.163636363636363e-06, | |
| "loss": 0.0232, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.1569023569023574e-06, | |
| "loss": 0.0219, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.150168350168351e-06, | |
| "loss": 0.0221, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.143434343434345e-06, | |
| "loss": 0.0216, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 0.0604248046875, | |
| "eval_runtime": 624.2116, | |
| "eval_samples_per_second": 4.808, | |
| "eval_steps_per_second": 0.038, | |
| "eval_wer": 25.143282009975525, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 7.136700336700337e-06, | |
| "loss": 0.0223, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.12996632996633e-06, | |
| "loss": 0.0228, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.1232323232323245e-06, | |
| "loss": 0.0231, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.116498316498317e-06, | |
| "loss": 0.0224, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.10976430976431e-06, | |
| "loss": 0.0219, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.103030303030304e-06, | |
| "loss": 0.0223, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.096296296296297e-06, | |
| "loss": 0.0222, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 7.089562289562291e-06, | |
| "loss": 0.0223, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.082828282828283e-06, | |
| "loss": 0.0228, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.076094276094276e-06, | |
| "loss": 0.0224, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.059906005859375, | |
| "eval_runtime": 385.9412, | |
| "eval_samples_per_second": 7.776, | |
| "eval_steps_per_second": 0.062, | |
| "eval_wer": 25.406611109390003, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.0693602693602704e-06, | |
| "loss": 0.0227, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.062626262626263e-06, | |
| "loss": 0.023, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.055892255892256e-06, | |
| "loss": 0.0229, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.04915824915825e-06, | |
| "loss": 0.022, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.0424242424242426e-06, | |
| "loss": 0.0214, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.035690235690237e-06, | |
| "loss": 0.0225, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 7.02895622895623e-06, | |
| "loss": 0.022, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.022222222222222e-06, | |
| "loss": 0.0213, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.015488215488216e-06, | |
| "loss": 0.0233, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.00875420875421e-06, | |
| "loss": 0.0225, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_loss": 0.060638427734375, | |
| "eval_runtime": 398.8252, | |
| "eval_samples_per_second": 7.525, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 25.13089005235602, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 7.002020202020202e-06, | |
| "loss": 0.0223, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 6.995286195286196e-06, | |
| "loss": 0.0218, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 6.988552188552189e-06, | |
| "loss": 0.0218, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 6.981818181818183e-06, | |
| "loss": 0.0226, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 6.975084175084176e-06, | |
| "loss": 0.0227, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 6.968350168350169e-06, | |
| "loss": 0.0219, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 6.961616161616162e-06, | |
| "loss": 0.0223, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 6.9548821548821555e-06, | |
| "loss": 0.0222, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 6.948148148148148e-06, | |
| "loss": 0.0218, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 6.941414141414142e-06, | |
| "loss": 0.0227, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.057373046875, | |
| "eval_runtime": 512.6924, | |
| "eval_samples_per_second": 5.853, | |
| "eval_steps_per_second": 0.047, | |
| "eval_wer": 25.54292264320456, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 6.934680134680135e-06, | |
| "loss": 0.0224, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 6.927946127946128e-06, | |
| "loss": 0.022, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 6.921212121212122e-06, | |
| "loss": 0.0221, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 6.914478114478115e-06, | |
| "loss": 0.0215, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 6.907744107744109e-06, | |
| "loss": 0.0219, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 6.9010101010101015e-06, | |
| "loss": 0.0234, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 6.894276094276095e-06, | |
| "loss": 0.0233, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.887542087542089e-06, | |
| "loss": 0.0228, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.880808080808081e-06, | |
| "loss": 0.0226, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 6.8740740740740745e-06, | |
| "loss": 0.0224, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 0.060699462890625, | |
| "eval_runtime": 421.9795, | |
| "eval_samples_per_second": 7.112, | |
| "eval_steps_per_second": 0.057, | |
| "eval_wer": 25.357043278911984, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 6.867340067340068e-06, | |
| "loss": 0.0239, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 6.860606060606061e-06, | |
| "loss": 0.0216, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 6.853872053872055e-06, | |
| "loss": 0.0215, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 6.847138047138047e-06, | |
| "loss": 0.0226, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 6.840404040404041e-06, | |
| "loss": 0.0221, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 6.833670033670035e-06, | |
| "loss": 0.0231, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 6.826936026936027e-06, | |
| "loss": 0.0229, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 6.82020202020202e-06, | |
| "loss": 0.0225, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 6.8134680134680145e-06, | |
| "loss": 0.0223, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 6.806734006734007e-06, | |
| "loss": 0.023, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 0.061431884765625, | |
| "eval_runtime": 403.145, | |
| "eval_samples_per_second": 7.444, | |
| "eval_steps_per_second": 0.06, | |
| "eval_wer": 25.406611109390003, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.0219, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 6.793265993265994e-06, | |
| "loss": 0.0223, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.786531986531987e-06, | |
| "loss": 0.0223, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 6.779797979797981e-06, | |
| "loss": 0.0214, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 6.773063973063974e-06, | |
| "loss": 0.0226, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 6.766329966329966e-06, | |
| "loss": 0.0232, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 6.75959595959596e-06, | |
| "loss": 0.0222, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 6.752861952861953e-06, | |
| "loss": 0.0229, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 6.746127946127947e-06, | |
| "loss": 0.0225, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 6.73939393939394e-06, | |
| "loss": 0.0226, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 0.058746337890625, | |
| "eval_runtime": 412.3736, | |
| "eval_samples_per_second": 7.277, | |
| "eval_steps_per_second": 0.058, | |
| "eval_wer": 25.440688992843647, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.7326599326599325e-06, | |
| "loss": 0.0233, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.725925925925927e-06, | |
| "loss": 0.0231, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 6.71919191919192e-06, | |
| "loss": 0.0229, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.712457912457912e-06, | |
| "loss": 0.023, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.705723905723906e-06, | |
| "loss": 0.0226, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 6.6989898989899e-06, | |
| "loss": 0.0236, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 6.692255892255894e-06, | |
| "loss": 0.0224, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 6.685521885521886e-06, | |
| "loss": 0.0226, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.678787878787879e-06, | |
| "loss": 0.0234, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 6.672053872053873e-06, | |
| "loss": 0.0223, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 0.056854248046875, | |
| "eval_runtime": 415.0103, | |
| "eval_samples_per_second": 7.231, | |
| "eval_steps_per_second": 0.058, | |
| "eval_wer": 25.09991015830726, | |
| "step": 5100 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 11, | |
| "total_flos": 1.3322078469925015e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |