| { | |
| "best_metric": 0.45630136132240295, | |
| "best_model_checkpoint": "ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram/checkpoint-504", | |
| "epoch": 99.99653979238754, | |
| "global_step": 7200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5e-06, | |
| "loss": 0.48, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4916, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.45e-05, | |
| "loss": 0.4674, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 0.4695, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.45e-05, | |
| "loss": 0.4717, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.95e-05, | |
| "loss": 0.4723, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.45e-05, | |
| "loss": 0.504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.48100385069847107, | |
| "eval_runtime": 127.9947, | |
| "eval_samples_per_second": 4.156, | |
| "eval_steps_per_second": 0.523, | |
| "eval_wer": 0.23127852413704442, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.9500000000000005e-05, | |
| "loss": 0.4949, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.4500000000000004e-05, | |
| "loss": 0.4909, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 0.4735, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.993661971830986e-05, | |
| "loss": 0.5011, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.98661971830986e-05, | |
| "loss": 0.5118, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.9795774647887327e-05, | |
| "loss": 0.5348, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 4.972535211267606e-05, | |
| "loss": 0.5274, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4828048348426819, | |
| "eval_runtime": 129.7646, | |
| "eval_samples_per_second": 4.1, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.23879925435495275, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.965492957746479e-05, | |
| "loss": 0.5455, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.9584507042253526e-05, | |
| "loss": 0.518, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.951408450704226e-05, | |
| "loss": 0.5118, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.944366197183099e-05, | |
| "loss": 0.5116, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.9373239436619725e-05, | |
| "loss": 0.4943, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.930281690140845e-05, | |
| "loss": 0.5187, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.923239436619719e-05, | |
| "loss": 0.5021, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5007606744766235, | |
| "eval_runtime": 129.4059, | |
| "eval_samples_per_second": 4.111, | |
| "eval_steps_per_second": 0.518, | |
| "eval_wer": 0.2408562062094234, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.916901408450704e-05, | |
| "loss": 0.5289, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.909859154929578e-05, | |
| "loss": 0.4999, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 4.9028169014084506e-05, | |
| "loss": 0.535, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 4.895774647887324e-05, | |
| "loss": 0.5052, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 4.888732394366197e-05, | |
| "loss": 0.5107, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.8816901408450705e-05, | |
| "loss": 0.5191, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 4.874647887323944e-05, | |
| "loss": 0.4956, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.48966091871261597, | |
| "eval_runtime": 127.0197, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.24008484926399692, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.867605633802817e-05, | |
| "loss": 0.5342, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 4.8605633802816904e-05, | |
| "loss": 0.4984, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.853521126760563e-05, | |
| "loss": 0.4968, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.846478873239437e-05, | |
| "loss": 0.5207, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.83943661971831e-05, | |
| "loss": 0.5271, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 4.832394366197183e-05, | |
| "loss": 0.5277, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 4.8253521126760566e-05, | |
| "loss": 0.5238, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.8183098591549295e-05, | |
| "loss": 0.543, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.5795093774795532, | |
| "eval_runtime": 130.2268, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.24734846050009643, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 4.811267605633803e-05, | |
| "loss": 0.5184, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.8042253521126765e-05, | |
| "loss": 0.543, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 4.7971830985915494e-05, | |
| "loss": 0.5174, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 4.790140845070423e-05, | |
| "loss": 0.5021, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 4.783098591549296e-05, | |
| "loss": 0.5295, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 4.776056338028169e-05, | |
| "loss": 0.534, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 4.769014084507042e-05, | |
| "loss": 0.5239, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.5018669366836548, | |
| "eval_runtime": 126.6372, | |
| "eval_samples_per_second": 4.201, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.24901973388185383, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 4.761971830985916e-05, | |
| "loss": 0.5529, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 4.754929577464789e-05, | |
| "loss": 0.5127, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 4.747887323943662e-05, | |
| "loss": 0.5299, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 4.7408450704225356e-05, | |
| "loss": 0.5447, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 4.7338028169014084e-05, | |
| "loss": 0.5173, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 4.726760563380282e-05, | |
| "loss": 0.5003, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 4.7197183098591555e-05, | |
| "loss": 0.4928, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.45630136132240295, | |
| "eval_runtime": 126.0852, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.23121424439159222, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 4.7133802816901415e-05, | |
| "loss": 0.534, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 4.7063380281690144e-05, | |
| "loss": 0.5019, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.699295774647888e-05, | |
| "loss": 0.5234, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 4.692253521126761e-05, | |
| "loss": 0.5523, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 4.685211267605634e-05, | |
| "loss": 0.5048, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 4.678169014084508e-05, | |
| "loss": 0.5298, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 4.6711267605633806e-05, | |
| "loss": 0.5236, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.5311173796653748, | |
| "eval_runtime": 132.2426, | |
| "eval_samples_per_second": 4.023, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.2647682715176448, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 4.664084507042254e-05, | |
| "loss": 0.5346, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 4.657042253521127e-05, | |
| "loss": 0.5205, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 0.5074, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 4.6429577464788734e-05, | |
| "loss": 0.5188, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 4.635915492957747e-05, | |
| "loss": 0.5274, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 4.6288732394366204e-05, | |
| "loss": 0.5385, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.6218309859154926e-05, | |
| "loss": 0.5059, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.4728511869907379, | |
| "eval_runtime": 125.7839, | |
| "eval_samples_per_second": 4.229, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.22935013177347818, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.614788732394366e-05, | |
| "loss": 0.5293, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 4.60774647887324e-05, | |
| "loss": 0.5124, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 4.6007042253521125e-05, | |
| "loss": 0.5266, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 4.593661971830986e-05, | |
| "loss": 0.5256, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 4.586619718309859e-05, | |
| "loss": 0.517, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 4.5795774647887324e-05, | |
| "loss": 0.5001, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 4.572535211267606e-05, | |
| "loss": 0.4924, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.565492957746479e-05, | |
| "loss": 0.5064, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.5000531673431396, | |
| "eval_runtime": 126.1137, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2464485440637655, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 4.558450704225352e-05, | |
| "loss": 0.5004, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 4.551408450704225e-05, | |
| "loss": 0.522, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 4.544366197183099e-05, | |
| "loss": 0.5214, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 4.537323943661972e-05, | |
| "loss": 0.5257, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 4.530281690140845e-05, | |
| "loss": 0.5166, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 4.5232394366197186e-05, | |
| "loss": 0.516, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 4.5161971830985914e-05, | |
| "loss": 0.5032, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.4968065619468689, | |
| "eval_runtime": 127.6202, | |
| "eval_samples_per_second": 4.169, | |
| "eval_steps_per_second": 0.525, | |
| "eval_wer": 0.2335283152278717, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 4.509154929577465e-05, | |
| "loss": 0.5208, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 4.502112676056338e-05, | |
| "loss": 0.5148, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 4.4950704225352113e-05, | |
| "loss": 0.5035, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 4.488028169014085e-05, | |
| "loss": 0.5137, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 4.480985915492958e-05, | |
| "loss": 0.4974, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.473943661971831e-05, | |
| "loss": 0.513, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 4.466901408450704e-05, | |
| "loss": 0.5064, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.5237506031990051, | |
| "eval_runtime": 128.1921, | |
| "eval_samples_per_second": 4.15, | |
| "eval_steps_per_second": 0.523, | |
| "eval_wer": 0.23648518351867326, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 4.4598591549295776e-05, | |
| "loss": 0.5065, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 4.452816901408451e-05, | |
| "loss": 0.4883, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 4.445774647887324e-05, | |
| "loss": 0.5032, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.4387323943661975e-05, | |
| "loss": 0.4986, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 4.4316901408450704e-05, | |
| "loss": 0.4756, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 4.424647887323944e-05, | |
| "loss": 0.5002, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 4.4176056338028174e-05, | |
| "loss": 0.5001, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.477408230304718, | |
| "eval_runtime": 129.9607, | |
| "eval_samples_per_second": 4.094, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.23249983930063636, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 4.41056338028169e-05, | |
| "loss": 0.5252, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 4.403521126760564e-05, | |
| "loss": 0.4894, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 4.3964788732394366e-05, | |
| "loss": 0.5057, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 4.38943661971831e-05, | |
| "loss": 0.5051, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 4.382394366197183e-05, | |
| "loss": 0.4997, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 4.3753521126760566e-05, | |
| "loss": 0.5206, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 4.36830985915493e-05, | |
| "loss": 0.5003, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.4961102604866028, | |
| "eval_runtime": 125.9234, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.23391399370058494, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 4.361267605633803e-05, | |
| "loss": 0.5108, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 4.3542253521126765e-05, | |
| "loss": 0.4982, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 4.347183098591549e-05, | |
| "loss": 0.5178, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 4.340140845070423e-05, | |
| "loss": 0.5131, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 4.3330985915492964e-05, | |
| "loss": 0.523, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 4.326056338028169e-05, | |
| "loss": 0.5054, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 4.319014084507043e-05, | |
| "loss": 0.4994, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.3119718309859156e-05, | |
| "loss": 0.5085, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.46455711126327515, | |
| "eval_runtime": 125.665, | |
| "eval_samples_per_second": 4.233, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.2271003406826509, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 4.304929577464789e-05, | |
| "loss": 0.5079, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 4.2978873239436626e-05, | |
| "loss": 0.5114, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 4.2908450704225355e-05, | |
| "loss": 0.4859, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 4.283802816901409e-05, | |
| "loss": 0.4951, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 4.276760563380282e-05, | |
| "loss": 0.4861, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 4.2697183098591554e-05, | |
| "loss": 0.5128, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 4.263380281690141e-05, | |
| "loss": 0.4931, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.5006607174873352, | |
| "eval_runtime": 126.1174, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2320498810824709, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 4.256338028169014e-05, | |
| "loss": 0.5034, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 4.249295774647887e-05, | |
| "loss": 0.4863, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 4.2422535211267606e-05, | |
| "loss": 0.4821, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 4.2352112676056335e-05, | |
| "loss": 0.5075, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 4.228169014084507e-05, | |
| "loss": 0.5022, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.2211267605633805e-05, | |
| "loss": 0.4698, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 4.2140845070422534e-05, | |
| "loss": 0.4807, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.4817637503147125, | |
| "eval_runtime": 125.5305, | |
| "eval_samples_per_second": 4.238, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.22581474577360675, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 4.207042253521127e-05, | |
| "loss": 0.5367, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.4781, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 4.192957746478873e-05, | |
| "loss": 0.4866, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 4.185915492957747e-05, | |
| "loss": 0.5144, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 4.17887323943662e-05, | |
| "loss": 0.4789, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 4.171830985915493e-05, | |
| "loss": 0.5048, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 4.164788732394366e-05, | |
| "loss": 0.4894, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.49539196491241455, | |
| "eval_runtime": 126.545, | |
| "eval_samples_per_second": 4.204, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.2310856849006878, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 4.1577464788732396e-05, | |
| "loss": 0.5086, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 4.150704225352113e-05, | |
| "loss": 0.4923, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 4.143661971830986e-05, | |
| "loss": 0.509, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 4.1366197183098595e-05, | |
| "loss": 0.4926, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 4.129577464788732e-05, | |
| "loss": 0.5059, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 4.122535211267606e-05, | |
| "loss": 0.4753, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 4.115492957746479e-05, | |
| "loss": 0.4746, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.4951326847076416, | |
| "eval_runtime": 126.1102, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.22928585202802598, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 4.108450704225352e-05, | |
| "loss": 0.4928, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 4.101408450704226e-05, | |
| "loss": 0.4758, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 4.0943661971830986e-05, | |
| "loss": 0.4898, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 4.087323943661972e-05, | |
| "loss": 0.4933, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 4.080281690140845e-05, | |
| "loss": 0.5012, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 4.0732394366197185e-05, | |
| "loss": 0.4911, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 4.066197183098592e-05, | |
| "loss": 0.5053, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.059154929577465e-05, | |
| "loss": 0.4795, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.48727360367774963, | |
| "eval_runtime": 126.1522, | |
| "eval_samples_per_second": 4.217, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2304428874461657, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 4.0521126760563384e-05, | |
| "loss": 0.4929, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 20.28, | |
| "learning_rate": 4.045070422535211e-05, | |
| "loss": 0.481, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 4.038028169014085e-05, | |
| "loss": 0.4819, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 4.030985915492958e-05, | |
| "loss": 0.4814, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 4.023943661971831e-05, | |
| "loss": 0.4871, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 4.016901408450705e-05, | |
| "loss": 0.4934, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 20.97, | |
| "learning_rate": 4.0098591549295775e-05, | |
| "loss": 0.4964, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.49976399540901184, | |
| "eval_runtime": 126.0303, | |
| "eval_samples_per_second": 4.221, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.2431059973002507, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "learning_rate": 4.002816901408451e-05, | |
| "loss": 0.4966, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 3.9957746478873246e-05, | |
| "loss": 0.5021, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 3.9887323943661974e-05, | |
| "loss": 0.4965, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 3.981690140845071e-05, | |
| "loss": 0.4876, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 3.974647887323944e-05, | |
| "loss": 0.4755, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 3.967605633802817e-05, | |
| "loss": 0.479, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 3.96056338028169e-05, | |
| "loss": 0.4947, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.498555451631546, | |
| "eval_runtime": 126.1675, | |
| "eval_samples_per_second": 4.217, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.23237127980973196, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 3.953521126760564e-05, | |
| "loss": 0.5085, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 3.946478873239437e-05, | |
| "loss": 0.4862, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 3.93943661971831e-05, | |
| "loss": 0.4888, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 3.9323943661971836e-05, | |
| "loss": 0.4954, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 22.64, | |
| "learning_rate": 3.9253521126760565e-05, | |
| "loss": 0.4826, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 3.91830985915493e-05, | |
| "loss": 0.477, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 3.9112676056338035e-05, | |
| "loss": 0.4789, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.5379728078842163, | |
| "eval_runtime": 126.405, | |
| "eval_samples_per_second": 4.209, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.23809217715497846, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 3.9042253521126764e-05, | |
| "loss": 0.4964, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 3.89718309859155e-05, | |
| "loss": 0.4926, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 3.890140845070423e-05, | |
| "loss": 0.4901, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 3.883098591549296e-05, | |
| "loss": 0.4879, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 23.61, | |
| "learning_rate": 3.87605633802817e-05, | |
| "loss": 0.4833, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 3.869014084507042e-05, | |
| "loss": 0.4752, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 3.8619718309859155e-05, | |
| "loss": 0.4603, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.4818807542324066, | |
| "eval_runtime": 125.9972, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.23391399370058494, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 3.854929577464788e-05, | |
| "loss": 0.4808, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 3.847887323943662e-05, | |
| "loss": 0.4693, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 3.8408450704225354e-05, | |
| "loss": 0.4729, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 3.833802816901408e-05, | |
| "loss": 0.4722, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 24.58, | |
| "learning_rate": 3.826760563380282e-05, | |
| "loss": 0.4687, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 24.72, | |
| "learning_rate": 3.8197183098591546e-05, | |
| "loss": 0.4682, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 3.812676056338028e-05, | |
| "loss": 0.4694, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.8056338028169017e-05, | |
| "loss": 0.4591, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.4868641793727875, | |
| "eval_runtime": 126.1227, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.22022240791926465, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.14, | |
| "learning_rate": 3.7985915492957745e-05, | |
| "loss": 0.4893, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 3.791549295774648e-05, | |
| "loss": 0.4773, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 3.784507042253521e-05, | |
| "loss": 0.4635, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 25.55, | |
| "learning_rate": 3.7774647887323944e-05, | |
| "loss": 0.4789, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 3.770422535211268e-05, | |
| "loss": 0.4857, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 25.83, | |
| "learning_rate": 3.763380281690141e-05, | |
| "loss": 0.4734, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 3.756338028169014e-05, | |
| "loss": 0.4675, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.48727670311927795, | |
| "eval_runtime": 125.7599, | |
| "eval_samples_per_second": 4.23, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.2213794433374044, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 3.749295774647887e-05, | |
| "loss": 0.486, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 3.742253521126761e-05, | |
| "loss": 0.482, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 3.735211267605634e-05, | |
| "loss": 0.4778, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 3.728169014084507e-05, | |
| "loss": 0.4825, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 26.66, | |
| "learning_rate": 3.7211267605633806e-05, | |
| "loss": 0.4717, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "learning_rate": 3.7140845070422534e-05, | |
| "loss": 0.4944, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 3.707042253521127e-05, | |
| "loss": 0.4777, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.4872089922428131, | |
| "eval_runtime": 126.537, | |
| "eval_samples_per_second": 4.204, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.22909301279166935, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 27.08, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.4797, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 3.692957746478873e-05, | |
| "loss": 0.4747, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 3.685915492957747e-05, | |
| "loss": 0.4834, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 3.67887323943662e-05, | |
| "loss": 0.495, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 3.671830985915493e-05, | |
| "loss": 0.4811, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 3.664788732394366e-05, | |
| "loss": 0.5012, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 3.6577464788732396e-05, | |
| "loss": 0.475, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.4919745624065399, | |
| "eval_runtime": 126.8079, | |
| "eval_samples_per_second": 4.195, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.22851449508259947, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 3.650704225352113e-05, | |
| "loss": 0.4946, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 3.643661971830986e-05, | |
| "loss": 0.4748, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 28.33, | |
| "learning_rate": 3.6366197183098595e-05, | |
| "loss": 0.4808, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 3.6295774647887324e-05, | |
| "loss": 0.4753, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 28.61, | |
| "learning_rate": 3.622535211267606e-05, | |
| "loss": 0.4885, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 3.6154929577464794e-05, | |
| "loss": 0.4905, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 3.608450704225352e-05, | |
| "loss": 0.4921, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.48551997542381287, | |
| "eval_runtime": 125.816, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.2222793597737353, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 3.601408450704226e-05, | |
| "loss": 0.499, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 3.5943661971830986e-05, | |
| "loss": 0.4763, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 29.3, | |
| "learning_rate": 3.587323943661972e-05, | |
| "loss": 0.4753, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 3.580281690140846e-05, | |
| "loss": 0.4754, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 3.5732394366197185e-05, | |
| "loss": 0.4753, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "learning_rate": 3.566197183098592e-05, | |
| "loss": 0.4807, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 3.559154929577465e-05, | |
| "loss": 0.4899, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.5521126760563384e-05, | |
| "loss": 0.4875, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.4977600574493408, | |
| "eval_runtime": 126.131, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.22112232435559556, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 3.545070422535211e-05, | |
| "loss": 0.4823, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 3.538028169014085e-05, | |
| "loss": 0.4903, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 3.5309859154929583e-05, | |
| "loss": 0.4813, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 3.523943661971831e-05, | |
| "loss": 0.4825, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 3.516901408450705e-05, | |
| "loss": 0.4799, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 30.83, | |
| "learning_rate": 3.5098591549295776e-05, | |
| "loss": 0.4729, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "learning_rate": 3.502816901408451e-05, | |
| "loss": 0.4699, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.4961602985858917, | |
| "eval_runtime": 127.3244, | |
| "eval_samples_per_second": 4.178, | |
| "eval_steps_per_second": 0.526, | |
| "eval_wer": 0.2335925949733239, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 3.4957746478873246e-05, | |
| "loss": 0.486, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 3.4887323943661975e-05, | |
| "loss": 0.4742, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 31.39, | |
| "learning_rate": 3.481690140845071e-05, | |
| "loss": 0.4563, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 3.474647887323944e-05, | |
| "loss": 0.4764, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 31.66, | |
| "learning_rate": 3.4676056338028174e-05, | |
| "loss": 0.486, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 3.460563380281691e-05, | |
| "loss": 0.4868, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "learning_rate": 3.453521126760563e-05, | |
| "loss": 0.4787, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.5129938721656799, | |
| "eval_runtime": 127.1535, | |
| "eval_samples_per_second": 4.184, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.22755029890081635, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 32.08, | |
| "learning_rate": 3.4464788732394366e-05, | |
| "loss": 0.511, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 3.4394366197183094e-05, | |
| "loss": 0.4869, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 3.432394366197183e-05, | |
| "loss": 0.488, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 3.4253521126760565e-05, | |
| "loss": 0.4946, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 3.4183098591549293e-05, | |
| "loss": 0.4724, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 3.411267605633803e-05, | |
| "loss": 0.4761, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 3.404225352112676e-05, | |
| "loss": 0.4631, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.5091267228126526, | |
| "eval_runtime": 126.3003, | |
| "eval_samples_per_second": 4.212, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.22575046602815452, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 33.06, | |
| "learning_rate": 3.397887323943662e-05, | |
| "loss": 0.4953, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.390845070422535e-05, | |
| "loss": 0.4811, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 3.383802816901409e-05, | |
| "loss": 0.4829, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 33.47, | |
| "learning_rate": 3.376760563380282e-05, | |
| "loss": 0.4882, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 3.369718309859155e-05, | |
| "loss": 0.4766, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 3.362676056338028e-05, | |
| "loss": 0.4811, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 3.3556338028169016e-05, | |
| "loss": 0.4697, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.5217466354370117, | |
| "eval_runtime": 126.2747, | |
| "eval_samples_per_second": 4.213, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2479912579546185, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 34.03, | |
| "learning_rate": 3.348591549295775e-05, | |
| "loss": 0.5069, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 34.17, | |
| "learning_rate": 3.341549295774648e-05, | |
| "loss": 0.4806, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 3.3345070422535215e-05, | |
| "loss": 0.4772, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 3.327464788732394e-05, | |
| "loss": 0.5008, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 34.58, | |
| "learning_rate": 3.320422535211268e-05, | |
| "loss": 0.4682, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 34.72, | |
| "learning_rate": 3.3133802816901414e-05, | |
| "loss": 0.4793, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 3.306338028169014e-05, | |
| "loss": 0.4784, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.299295774647888e-05, | |
| "loss": 0.4677, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.485178142786026, | |
| "eval_runtime": 125.8332, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.2253647875554413, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 35.14, | |
| "learning_rate": 3.2922535211267606e-05, | |
| "loss": 0.4711, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 35.28, | |
| "learning_rate": 3.285211267605634e-05, | |
| "loss": 0.4639, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 35.42, | |
| "learning_rate": 3.278169014084507e-05, | |
| "loss": 0.4555, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 35.55, | |
| "learning_rate": 3.2711267605633805e-05, | |
| "loss": 0.4617, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 35.69, | |
| "learning_rate": 3.264084507042254e-05, | |
| "loss": 0.4641, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 35.83, | |
| "learning_rate": 3.257042253521127e-05, | |
| "loss": 0.4723, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.4644, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.5170550346374512, | |
| "eval_runtime": 126.7812, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.23333547599151508, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 36.11, | |
| "learning_rate": 3.242957746478873e-05, | |
| "loss": 0.481, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 3.235915492957747e-05, | |
| "loss": 0.4733, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 3.22887323943662e-05, | |
| "loss": 0.4548, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 36.53, | |
| "learning_rate": 3.221830985915493e-05, | |
| "loss": 0.4983, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 36.66, | |
| "learning_rate": 3.214788732394367e-05, | |
| "loss": 0.4708, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 3.2077464788732395e-05, | |
| "loss": 0.4757, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "learning_rate": 3.200704225352113e-05, | |
| "loss": 0.476, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.4745345115661621, | |
| "eval_runtime": 125.9959, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.22086520537378673, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 37.08, | |
| "learning_rate": 3.1936619718309866e-05, | |
| "loss": 0.4848, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 37.22, | |
| "learning_rate": 3.1866197183098594e-05, | |
| "loss": 0.4821, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "learning_rate": 3.179577464788733e-05, | |
| "loss": 0.4646, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 3.172535211267606e-05, | |
| "loss": 0.4606, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 37.64, | |
| "learning_rate": 3.165492957746479e-05, | |
| "loss": 0.4373, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 3.158450704225352e-05, | |
| "loss": 0.4681, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "learning_rate": 3.151408450704226e-05, | |
| "loss": 0.4491, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.4898006319999695, | |
| "eval_runtime": 126.7104, | |
| "eval_samples_per_second": 4.199, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.22819309635533844, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 38.06, | |
| "learning_rate": 3.144366197183099e-05, | |
| "loss": 0.4659, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 3.137323943661972e-05, | |
| "loss": 0.459, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 38.33, | |
| "learning_rate": 3.1302816901408456e-05, | |
| "loss": 0.4414, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 38.47, | |
| "learning_rate": 3.1232394366197184e-05, | |
| "loss": 0.4677, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 38.61, | |
| "learning_rate": 3.116197183098591e-05, | |
| "loss": 0.4553, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 3.109154929577465e-05, | |
| "loss": 0.4586, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 3.102112676056338e-05, | |
| "loss": 0.4432, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.4738123416900635, | |
| "eval_runtime": 126.1855, | |
| "eval_samples_per_second": 4.216, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.22369351417368388, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 39.03, | |
| "learning_rate": 3.095070422535211e-05, | |
| "loss": 0.4937, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "learning_rate": 3.088028169014085e-05, | |
| "loss": 0.4637, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 39.3, | |
| "learning_rate": 3.0809859154929576e-05, | |
| "loss": 0.4711, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 3.073943661971831e-05, | |
| "loss": 0.4621, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 39.58, | |
| "learning_rate": 3.066901408450704e-05, | |
| "loss": 0.4702, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 39.72, | |
| "learning_rate": 3.0598591549295775e-05, | |
| "loss": 0.4849, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 3.052816901408451e-05, | |
| "loss": 0.4627, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.045774647887324e-05, | |
| "loss": 0.4804, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.47442981600761414, | |
| "eval_runtime": 126.0003, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.22452915086456257, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 3.038732394366197e-05, | |
| "loss": 0.4869, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 40.28, | |
| "learning_rate": 3.0316901408450706e-05, | |
| "loss": 0.4599, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 40.42, | |
| "learning_rate": 3.0246478873239438e-05, | |
| "loss": 0.4565, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 3.017605633802817e-05, | |
| "loss": 0.4611, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 40.69, | |
| "learning_rate": 3.01056338028169e-05, | |
| "loss": 0.4487, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 40.83, | |
| "learning_rate": 3.0035211267605633e-05, | |
| "loss": 0.46, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 40.97, | |
| "learning_rate": 2.9964788732394365e-05, | |
| "loss": 0.4479, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.5006310939788818, | |
| "eval_runtime": 125.9565, | |
| "eval_samples_per_second": 4.224, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.22022240791926465, | |
| "step": 2952 | |
| }, | |
| { | |
| "epoch": 41.11, | |
| "learning_rate": 2.98943661971831e-05, | |
| "loss": 0.4604, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 41.25, | |
| "learning_rate": 2.9823943661971832e-05, | |
| "loss": 0.4544, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 41.39, | |
| "learning_rate": 2.9753521126760564e-05, | |
| "loss": 0.4427, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 2.9683098591549296e-05, | |
| "loss": 0.4401, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 41.66, | |
| "learning_rate": 2.9612676056338028e-05, | |
| "loss": 0.4672, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "learning_rate": 2.9542253521126763e-05, | |
| "loss": 0.4618, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 41.94, | |
| "learning_rate": 2.9471830985915495e-05, | |
| "loss": 0.4379, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.475214421749115, | |
| "eval_runtime": 126.1342, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2213794433374044, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 42.08, | |
| "learning_rate": 2.9401408450704227e-05, | |
| "loss": 0.4655, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 2.933098591549296e-05, | |
| "loss": 0.437, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 42.36, | |
| "learning_rate": 2.926056338028169e-05, | |
| "loss": 0.454, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 2.9190140845070422e-05, | |
| "loss": 0.46, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 2.9119718309859158e-05, | |
| "loss": 0.4389, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "learning_rate": 2.904929577464789e-05, | |
| "loss": 0.4554, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 2.897887323943662e-05, | |
| "loss": 0.4412, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.47216537594795227, | |
| "eval_runtime": 125.8233, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.22105804461014333, | |
| "step": 3096 | |
| }, | |
| { | |
| "epoch": 43.06, | |
| "learning_rate": 2.8908450704225353e-05, | |
| "loss": 0.4685, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 2.8838028169014085e-05, | |
| "loss": 0.4424, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 43.33, | |
| "learning_rate": 2.876760563380282e-05, | |
| "loss": 0.4495, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 43.47, | |
| "learning_rate": 2.8697183098591552e-05, | |
| "loss": 0.4576, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 43.61, | |
| "learning_rate": 2.8626760563380284e-05, | |
| "loss": 0.4564, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 2.8556338028169016e-05, | |
| "loss": 0.4458, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 43.89, | |
| "learning_rate": 2.8485915492957748e-05, | |
| "loss": 0.4459, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.4859280586242676, | |
| "eval_runtime": 126.1798, | |
| "eval_samples_per_second": 4.216, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.22028668766471685, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 44.03, | |
| "learning_rate": 2.841549295774648e-05, | |
| "loss": 0.4697, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 44.17, | |
| "learning_rate": 2.8345070422535215e-05, | |
| "loss": 0.4495, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 44.3, | |
| "learning_rate": 2.8274647887323947e-05, | |
| "loss": 0.4617, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 2.820422535211268e-05, | |
| "loss": 0.4659, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 2.813380281690141e-05, | |
| "loss": 0.4591, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 2.8063380281690143e-05, | |
| "loss": 0.4446, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 44.86, | |
| "learning_rate": 2.7992957746478874e-05, | |
| "loss": 0.4468, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.792253521126761e-05, | |
| "loss": 0.4541, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.48502814769744873, | |
| "eval_runtime": 126.9478, | |
| "eval_samples_per_second": 4.191, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.21893681301022047, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 45.14, | |
| "learning_rate": 2.785211267605634e-05, | |
| "loss": 0.4567, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 45.28, | |
| "learning_rate": 2.7781690140845073e-05, | |
| "loss": 0.4562, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 2.7711267605633805e-05, | |
| "loss": 0.4478, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 45.55, | |
| "learning_rate": 2.7640845070422537e-05, | |
| "loss": 0.4544, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 45.69, | |
| "learning_rate": 2.7570422535211272e-05, | |
| "loss": 0.452, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 45.83, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.4447, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 45.97, | |
| "learning_rate": 2.7429577464788736e-05, | |
| "loss": 0.4509, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.4837965965270996, | |
| "eval_runtime": 126.0838, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.21623706370122775, | |
| "step": 3312 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 2.7359154929577468e-05, | |
| "loss": 0.4564, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 46.25, | |
| "learning_rate": 2.72887323943662e-05, | |
| "loss": 0.4427, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 46.39, | |
| "learning_rate": 2.7218309859154932e-05, | |
| "loss": 0.4461, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 46.53, | |
| "learning_rate": 2.7147887323943667e-05, | |
| "loss": 0.4434, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 46.66, | |
| "learning_rate": 2.7077464788732392e-05, | |
| "loss": 0.4477, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "learning_rate": 2.7007042253521124e-05, | |
| "loss": 0.4417, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 46.94, | |
| "learning_rate": 2.693661971830986e-05, | |
| "loss": 0.4472, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.48925644159317017, | |
| "eval_runtime": 126.2561, | |
| "eval_samples_per_second": 4.214, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2310856849006878, | |
| "step": 3384 | |
| }, | |
| { | |
| "epoch": 47.08, | |
| "learning_rate": 2.686619718309859e-05, | |
| "loss": 0.4608, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 47.22, | |
| "learning_rate": 2.6795774647887323e-05, | |
| "loss": 0.4448, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 2.6725352112676055e-05, | |
| "loss": 0.4368, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 2.6654929577464787e-05, | |
| "loss": 0.4388, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 47.64, | |
| "learning_rate": 2.658450704225352e-05, | |
| "loss": 0.4271, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 47.78, | |
| "learning_rate": 2.6514084507042254e-05, | |
| "loss": 0.4443, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 2.6443661971830986e-05, | |
| "loss": 0.4341, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.4899713695049286, | |
| "eval_runtime": 127.6794, | |
| "eval_samples_per_second": 4.167, | |
| "eval_steps_per_second": 0.525, | |
| "eval_wer": 0.2198367294465514, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 48.06, | |
| "learning_rate": 2.6373239436619718e-05, | |
| "loss": 0.4632, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 2.630281690140845e-05, | |
| "loss": 0.4492, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 48.33, | |
| "learning_rate": 2.623239436619718e-05, | |
| "loss": 0.4472, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 48.47, | |
| "learning_rate": 2.6161971830985917e-05, | |
| "loss": 0.4323, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 48.61, | |
| "learning_rate": 2.609154929577465e-05, | |
| "loss": 0.4455, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "learning_rate": 2.602112676056338e-05, | |
| "loss": 0.4441, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "learning_rate": 2.5950704225352112e-05, | |
| "loss": 0.4306, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 0.5051801800727844, | |
| "eval_runtime": 126.7896, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.21662274217394098, | |
| "step": 3528 | |
| }, | |
| { | |
| "epoch": 49.03, | |
| "learning_rate": 2.5880281690140844e-05, | |
| "loss": 0.4485, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "learning_rate": 2.5809859154929576e-05, | |
| "loss": 0.4317, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 2.573943661971831e-05, | |
| "loss": 0.4475, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 49.44, | |
| "learning_rate": 2.5669014084507043e-05, | |
| "loss": 0.4293, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 49.58, | |
| "learning_rate": 2.5598591549295775e-05, | |
| "loss": 0.4437, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 49.72, | |
| "learning_rate": 2.5528169014084507e-05, | |
| "loss": 0.4452, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 49.86, | |
| "learning_rate": 2.545774647887324e-05, | |
| "loss": 0.4429, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.5387323943661974e-05, | |
| "loss": 0.44, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.508723795413971, | |
| "eval_runtime": 126.2458, | |
| "eval_samples_per_second": 4.214, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2229864369737096, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 50.14, | |
| "learning_rate": 2.5316901408450706e-05, | |
| "loss": 0.4377, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 50.28, | |
| "learning_rate": 2.5246478873239438e-05, | |
| "loss": 0.4285, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 50.42, | |
| "learning_rate": 2.517605633802817e-05, | |
| "loss": 0.4413, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 50.55, | |
| "learning_rate": 2.51056338028169e-05, | |
| "loss": 0.4518, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 50.69, | |
| "learning_rate": 2.5035211267605634e-05, | |
| "loss": 0.4334, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 50.83, | |
| "learning_rate": 2.496478873239437e-05, | |
| "loss": 0.4406, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "learning_rate": 2.48943661971831e-05, | |
| "loss": 0.4425, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 0.484998494386673, | |
| "eval_runtime": 125.9671, | |
| "eval_samples_per_second": 4.223, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.22002956868290802, | |
| "step": 3672 | |
| }, | |
| { | |
| "epoch": 51.11, | |
| "learning_rate": 2.4823943661971833e-05, | |
| "loss": 0.442, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 51.25, | |
| "learning_rate": 2.4753521126760564e-05, | |
| "loss": 0.435, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 51.39, | |
| "learning_rate": 2.4683098591549296e-05, | |
| "loss": 0.4345, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 51.53, | |
| "learning_rate": 2.4612676056338028e-05, | |
| "loss": 0.445, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 51.66, | |
| "learning_rate": 2.4542253521126763e-05, | |
| "loss": 0.4239, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "learning_rate": 2.4471830985915495e-05, | |
| "loss": 0.427, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 51.94, | |
| "learning_rate": 2.4401408450704227e-05, | |
| "loss": 0.4329, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 0.4712650775909424, | |
| "eval_runtime": 126.6273, | |
| "eval_samples_per_second": 4.201, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.21887253326476827, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 52.08, | |
| "learning_rate": 2.433098591549296e-05, | |
| "loss": 0.4487, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 52.22, | |
| "learning_rate": 2.426056338028169e-05, | |
| "loss": 0.4431, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 52.36, | |
| "learning_rate": 2.4190140845070426e-05, | |
| "loss": 0.438, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 52.5, | |
| "learning_rate": 2.4119718309859158e-05, | |
| "loss": 0.4351, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 52.64, | |
| "learning_rate": 2.404929577464789e-05, | |
| "loss": 0.4231, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 52.78, | |
| "learning_rate": 2.3978873239436622e-05, | |
| "loss": 0.4367, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 52.91, | |
| "learning_rate": 2.390845070422535e-05, | |
| "loss": 0.4335, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 0.4828576147556305, | |
| "eval_runtime": 126.5803, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.21379443337404383, | |
| "step": 3816 | |
| }, | |
| { | |
| "epoch": 53.06, | |
| "learning_rate": 2.3838028169014086e-05, | |
| "loss": 0.4454, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "learning_rate": 2.3767605633802817e-05, | |
| "loss": 0.4323, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 2.369718309859155e-05, | |
| "loss": 0.4371, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 53.47, | |
| "learning_rate": 2.362676056338028e-05, | |
| "loss": 0.4435, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 53.61, | |
| "learning_rate": 2.3556338028169013e-05, | |
| "loss": 0.4307, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 53.75, | |
| "learning_rate": 2.348591549295775e-05, | |
| "loss": 0.424, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "learning_rate": 2.341549295774648e-05, | |
| "loss": 0.4184, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 0.5033903121948242, | |
| "eval_runtime": 126.2852, | |
| "eval_samples_per_second": 4.213, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2127659574468085, | |
| "step": 3888 | |
| }, | |
| { | |
| "epoch": 54.03, | |
| "learning_rate": 2.3345070422535212e-05, | |
| "loss": 0.4599, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 54.17, | |
| "learning_rate": 2.3274647887323944e-05, | |
| "loss": 0.4255, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 54.3, | |
| "learning_rate": 2.3204225352112676e-05, | |
| "loss": 0.4408, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 54.44, | |
| "learning_rate": 2.3133802816901408e-05, | |
| "loss": 0.4261, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 54.58, | |
| "learning_rate": 2.3063380281690143e-05, | |
| "loss": 0.4391, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 54.72, | |
| "learning_rate": 2.2992957746478875e-05, | |
| "loss": 0.44, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 54.86, | |
| "learning_rate": 2.2922535211267607e-05, | |
| "loss": 0.4379, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 2.285211267605634e-05, | |
| "loss": 0.4303, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 0.4944688677787781, | |
| "eval_runtime": 127.0851, | |
| "eval_samples_per_second": 4.186, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.21662274217394098, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 55.14, | |
| "learning_rate": 2.278169014084507e-05, | |
| "loss": 0.4272, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 55.28, | |
| "learning_rate": 2.2711267605633806e-05, | |
| "loss": 0.4379, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 55.42, | |
| "learning_rate": 2.2640845070422538e-05, | |
| "loss": 0.4422, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "learning_rate": 2.257042253521127e-05, | |
| "loss": 0.4369, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 55.69, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.4451, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 55.83, | |
| "learning_rate": 2.2429577464788733e-05, | |
| "loss": 0.4423, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 2.2359154929577465e-05, | |
| "loss": 0.4519, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 0.5088710784912109, | |
| "eval_runtime": 127.0232, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.21058044610143345, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 56.11, | |
| "learning_rate": 2.22887323943662e-05, | |
| "loss": 0.4343, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 56.25, | |
| "learning_rate": 2.2218309859154932e-05, | |
| "loss": 0.4311, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 56.39, | |
| "learning_rate": 2.2147887323943664e-05, | |
| "loss": 0.4214, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 2.2077464788732396e-05, | |
| "loss": 0.4422, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 56.66, | |
| "learning_rate": 2.2007042253521128e-05, | |
| "loss": 0.4273, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 2.1936619718309863e-05, | |
| "loss": 0.4416, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 56.94, | |
| "learning_rate": 2.186619718309859e-05, | |
| "loss": 0.4336, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 0.5325378179550171, | |
| "eval_runtime": 133.5981, | |
| "eval_samples_per_second": 3.982, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 0.21463007006492255, | |
| "step": 4104 | |
| }, | |
| { | |
| "epoch": 57.08, | |
| "learning_rate": 2.1795774647887324e-05, | |
| "loss": 0.4356, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 57.22, | |
| "learning_rate": 2.1725352112676055e-05, | |
| "loss": 0.4303, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 57.36, | |
| "learning_rate": 2.1654929577464787e-05, | |
| "loss": 0.4352, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 57.5, | |
| "learning_rate": 2.1584507042253523e-05, | |
| "loss": 0.4417, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 57.64, | |
| "learning_rate": 2.1514084507042254e-05, | |
| "loss": 0.4322, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 57.78, | |
| "learning_rate": 2.1443661971830986e-05, | |
| "loss": 0.4461, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 57.91, | |
| "learning_rate": 2.1373239436619718e-05, | |
| "loss": 0.4274, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.5188899636268616, | |
| "eval_runtime": 126.4883, | |
| "eval_samples_per_second": 4.206, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.22202224079192645, | |
| "step": 4176 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "learning_rate": 2.130281690140845e-05, | |
| "loss": 0.4454, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 58.19, | |
| "learning_rate": 2.1232394366197182e-05, | |
| "loss": 0.4345, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "learning_rate": 2.1161971830985917e-05, | |
| "loss": 0.4421, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 58.47, | |
| "learning_rate": 2.109154929577465e-05, | |
| "loss": 0.4358, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 58.61, | |
| "learning_rate": 2.102112676056338e-05, | |
| "loss": 0.4267, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 58.75, | |
| "learning_rate": 2.0950704225352113e-05, | |
| "loss": 0.4531, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "learning_rate": 2.0880281690140845e-05, | |
| "loss": 0.4217, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 0.5071147084236145, | |
| "eval_runtime": 126.2477, | |
| "eval_samples_per_second": 4.214, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.2119303207559298, | |
| "step": 4248 | |
| }, | |
| { | |
| "epoch": 59.03, | |
| "learning_rate": 2.080985915492958e-05, | |
| "loss": 0.4357, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 59.17, | |
| "learning_rate": 2.0739436619718312e-05, | |
| "loss": 0.4185, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 59.3, | |
| "learning_rate": 2.0669014084507044e-05, | |
| "loss": 0.4357, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 59.44, | |
| "learning_rate": 2.0598591549295776e-05, | |
| "loss": 0.433, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 59.58, | |
| "learning_rate": 2.0528169014084507e-05, | |
| "loss": 0.4387, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 59.72, | |
| "learning_rate": 2.045774647887324e-05, | |
| "loss": 0.4357, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 59.86, | |
| "learning_rate": 2.0387323943661975e-05, | |
| "loss": 0.3986, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.0316901408450707e-05, | |
| "loss": 0.4173, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 0.5162719488143921, | |
| "eval_runtime": 126.1056, | |
| "eval_samples_per_second": 4.219, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.218486854792055, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 60.14, | |
| "learning_rate": 2.024647887323944e-05, | |
| "loss": 0.4373, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 60.28, | |
| "learning_rate": 2.017605633802817e-05, | |
| "loss": 0.4161, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 60.42, | |
| "learning_rate": 2.0105633802816902e-05, | |
| "loss": 0.4227, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 60.55, | |
| "learning_rate": 2.0035211267605637e-05, | |
| "loss": 0.417, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 60.69, | |
| "learning_rate": 1.996478873239437e-05, | |
| "loss": 0.4254, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 60.83, | |
| "learning_rate": 1.98943661971831e-05, | |
| "loss": 0.4221, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 60.97, | |
| "learning_rate": 1.9823943661971833e-05, | |
| "loss": 0.4221, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 0.48502665758132935, | |
| "eval_runtime": 125.8546, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.21893681301022047, | |
| "step": 4392 | |
| }, | |
| { | |
| "epoch": 61.11, | |
| "learning_rate": 1.975352112676056e-05, | |
| "loss": 0.4402, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 61.25, | |
| "learning_rate": 1.9683098591549297e-05, | |
| "loss": 0.4362, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 61.39, | |
| "learning_rate": 1.961267605633803e-05, | |
| "loss": 0.42, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 61.53, | |
| "learning_rate": 1.954225352112676e-05, | |
| "loss": 0.4152, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 61.66, | |
| "learning_rate": 1.9471830985915492e-05, | |
| "loss": 0.4042, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "learning_rate": 1.9401408450704224e-05, | |
| "loss": 0.4293, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "learning_rate": 1.933098591549296e-05, | |
| "loss": 0.4244, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 0.4899979829788208, | |
| "eval_runtime": 125.4884, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.21533714726489683, | |
| "step": 4464 | |
| }, | |
| { | |
| "epoch": 62.08, | |
| "learning_rate": 1.926056338028169e-05, | |
| "loss": 0.4405, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 1.9190140845070423e-05, | |
| "loss": 0.4257, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 62.36, | |
| "learning_rate": 1.9119718309859155e-05, | |
| "loss": 0.4237, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 1.9049295774647887e-05, | |
| "loss": 0.4236, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 62.64, | |
| "learning_rate": 1.897887323943662e-05, | |
| "loss": 0.414, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 62.78, | |
| "learning_rate": 1.8908450704225354e-05, | |
| "loss": 0.426, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "learning_rate": 1.8838028169014086e-05, | |
| "loss": 0.4147, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 0.4965975284576416, | |
| "eval_runtime": 126.8176, | |
| "eval_samples_per_second": 4.195, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.2077521373015363, | |
| "step": 4536 | |
| }, | |
| { | |
| "epoch": 63.06, | |
| "learning_rate": 1.8767605633802818e-05, | |
| "loss": 0.4279, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 63.19, | |
| "learning_rate": 1.869718309859155e-05, | |
| "loss": 0.4237, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 63.33, | |
| "learning_rate": 1.862676056338028e-05, | |
| "loss": 0.4317, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 63.47, | |
| "learning_rate": 1.8556338028169014e-05, | |
| "loss": 0.4234, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 63.61, | |
| "learning_rate": 1.848591549295775e-05, | |
| "loss": 0.424, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 63.75, | |
| "learning_rate": 1.841549295774648e-05, | |
| "loss": 0.4191, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "learning_rate": 1.8345070422535213e-05, | |
| "loss": 0.4135, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 0.5242801308631897, | |
| "eval_runtime": 126.406, | |
| "eval_samples_per_second": 4.209, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.21662274217394098, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 64.03, | |
| "learning_rate": 1.8274647887323944e-05, | |
| "loss": 0.4383, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 64.17, | |
| "learning_rate": 1.8204225352112676e-05, | |
| "loss": 0.4271, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 64.3, | |
| "learning_rate": 1.813380281690141e-05, | |
| "loss": 0.4191, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 64.44, | |
| "learning_rate": 1.8063380281690143e-05, | |
| "loss": 0.4142, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 64.58, | |
| "learning_rate": 1.7992957746478875e-05, | |
| "loss": 0.4244, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 64.72, | |
| "learning_rate": 1.7922535211267607e-05, | |
| "loss": 0.4209, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 64.86, | |
| "learning_rate": 1.785211267605634e-05, | |
| "loss": 0.4215, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 1.778169014084507e-05, | |
| "loss": 0.4127, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 0.4889000952243805, | |
| "eval_runtime": 125.6271, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.21642990293758438, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 65.14, | |
| "learning_rate": 1.7711267605633806e-05, | |
| "loss": 0.4334, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 65.28, | |
| "learning_rate": 1.7640845070422535e-05, | |
| "loss": 0.4268, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 1.7570422535211267e-05, | |
| "loss": 0.4253, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 65.55, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.4091, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 65.69, | |
| "learning_rate": 1.7429577464788734e-05, | |
| "loss": 0.4193, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 65.83, | |
| "learning_rate": 1.7359154929577466e-05, | |
| "loss": 0.4216, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 65.97, | |
| "learning_rate": 1.7288732394366197e-05, | |
| "loss": 0.3979, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 0.49280083179473877, | |
| "eval_runtime": 127.1568, | |
| "eval_samples_per_second": 4.184, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.21732981937391527, | |
| "step": 4752 | |
| }, | |
| { | |
| "epoch": 66.11, | |
| "learning_rate": 1.721830985915493e-05, | |
| "loss": 0.4282, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 66.25, | |
| "learning_rate": 1.714788732394366e-05, | |
| "loss": 0.4229, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 1.7077464788732393e-05, | |
| "loss": 0.4173, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 66.53, | |
| "learning_rate": 1.700704225352113e-05, | |
| "loss": 0.4271, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "learning_rate": 1.693661971830986e-05, | |
| "loss": 0.4215, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "learning_rate": 1.6866197183098592e-05, | |
| "loss": 0.4183, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 66.94, | |
| "learning_rate": 1.6795774647887324e-05, | |
| "loss": 0.4151, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 0.4978279173374176, | |
| "eval_runtime": 127.0381, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.21315163591952177, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 67.08, | |
| "learning_rate": 1.6725352112676056e-05, | |
| "loss": 0.4173, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 67.22, | |
| "learning_rate": 1.665492957746479e-05, | |
| "loss": 0.4197, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 67.36, | |
| "learning_rate": 1.6584507042253523e-05, | |
| "loss": 0.401, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 67.5, | |
| "learning_rate": 1.6514084507042255e-05, | |
| "loss": 0.4155, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 67.64, | |
| "learning_rate": 1.6443661971830987e-05, | |
| "loss": 0.4174, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 67.78, | |
| "learning_rate": 1.637323943661972e-05, | |
| "loss": 0.416, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 67.91, | |
| "learning_rate": 1.630281690140845e-05, | |
| "loss": 0.4157, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 0.5226835012435913, | |
| "eval_runtime": 126.8668, | |
| "eval_samples_per_second": 4.193, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.21687986115574984, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 68.06, | |
| "learning_rate": 1.6232394366197186e-05, | |
| "loss": 0.4272, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 68.19, | |
| "learning_rate": 1.6161971830985918e-05, | |
| "loss": 0.4193, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 68.33, | |
| "learning_rate": 1.609154929577465e-05, | |
| "loss": 0.4207, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 68.47, | |
| "learning_rate": 1.602112676056338e-05, | |
| "loss": 0.4255, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 68.61, | |
| "learning_rate": 1.5950704225352113e-05, | |
| "loss": 0.4123, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 68.75, | |
| "learning_rate": 1.588028169014085e-05, | |
| "loss": 0.4082, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "learning_rate": 1.580985915492958e-05, | |
| "loss": 0.4135, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 0.48659974336624146, | |
| "eval_runtime": 127.0425, | |
| "eval_samples_per_second": 4.188, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.21295879668316514, | |
| "step": 4968 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 1.5739436619718312e-05, | |
| "loss": 0.4276, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 69.17, | |
| "learning_rate": 1.5669014084507044e-05, | |
| "loss": 0.4104, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 69.3, | |
| "learning_rate": 1.5598591549295773e-05, | |
| "loss": 0.4186, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 69.44, | |
| "learning_rate": 1.5528169014084508e-05, | |
| "loss": 0.4111, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 69.58, | |
| "learning_rate": 1.545774647887324e-05, | |
| "loss": 0.4146, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 69.72, | |
| "learning_rate": 1.538732394366197e-05, | |
| "loss": 0.4143, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 69.86, | |
| "learning_rate": 1.5316901408450704e-05, | |
| "loss": 0.4029, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 1.5246478873239437e-05, | |
| "loss": 0.4109, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 0.484768807888031, | |
| "eval_runtime": 127.258, | |
| "eval_samples_per_second": 4.18, | |
| "eval_steps_per_second": 0.526, | |
| "eval_wer": 0.20935913093784148, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 70.14, | |
| "learning_rate": 1.5176056338028169e-05, | |
| "loss": 0.4176, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 70.28, | |
| "learning_rate": 1.5105633802816901e-05, | |
| "loss": 0.4091, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 70.42, | |
| "learning_rate": 1.5035211267605634e-05, | |
| "loss": 0.4115, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 70.55, | |
| "learning_rate": 1.4964788732394366e-05, | |
| "loss": 0.4036, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 70.69, | |
| "learning_rate": 1.4894366197183098e-05, | |
| "loss": 0.4078, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 70.83, | |
| "learning_rate": 1.4823943661971832e-05, | |
| "loss": 0.4158, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "learning_rate": 1.4753521126760564e-05, | |
| "loss": 0.4084, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 0.5011652112007141, | |
| "eval_runtime": 126.6418, | |
| "eval_samples_per_second": 4.201, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.2168155814102976, | |
| "step": 5112 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 1.4683098591549296e-05, | |
| "loss": 0.4189, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 71.25, | |
| "learning_rate": 1.4612676056338029e-05, | |
| "loss": 0.4007, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 71.39, | |
| "learning_rate": 1.4542253521126761e-05, | |
| "loss": 0.4055, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 71.53, | |
| "learning_rate": 1.4471830985915495e-05, | |
| "loss": 0.4133, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 71.66, | |
| "learning_rate": 1.4401408450704226e-05, | |
| "loss": 0.4116, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 1.4330985915492958e-05, | |
| "loss": 0.4091, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 71.94, | |
| "learning_rate": 1.4260563380281692e-05, | |
| "loss": 0.4078, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 0.4835646152496338, | |
| "eval_runtime": 126.9914, | |
| "eval_samples_per_second": 4.189, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.21855113453750724, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 72.08, | |
| "learning_rate": 1.4190140845070424e-05, | |
| "loss": 0.4281, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 72.22, | |
| "learning_rate": 1.4119718309859156e-05, | |
| "loss": 0.4153, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 72.36, | |
| "learning_rate": 1.404929577464789e-05, | |
| "loss": 0.3969, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 72.5, | |
| "learning_rate": 1.3978873239436621e-05, | |
| "loss": 0.4048, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 72.64, | |
| "learning_rate": 1.3908450704225353e-05, | |
| "loss": 0.4015, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 72.78, | |
| "learning_rate": 1.3838028169014086e-05, | |
| "loss": 0.4018, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 72.91, | |
| "learning_rate": 1.3767605633802818e-05, | |
| "loss": 0.4106, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 0.48354992270469666, | |
| "eval_runtime": 126.0348, | |
| "eval_samples_per_second": 4.221, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.21315163591952177, | |
| "step": 5256 | |
| }, | |
| { | |
| "epoch": 73.06, | |
| "learning_rate": 1.3697183098591552e-05, | |
| "loss": 0.4178, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 73.19, | |
| "learning_rate": 1.3626760563380284e-05, | |
| "loss": 0.4125, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 73.33, | |
| "learning_rate": 1.3556338028169016e-05, | |
| "loss": 0.4111, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 73.47, | |
| "learning_rate": 1.3485915492957746e-05, | |
| "loss": 0.4044, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 73.61, | |
| "learning_rate": 1.3415492957746478e-05, | |
| "loss": 0.4043, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 73.75, | |
| "learning_rate": 1.3345070422535211e-05, | |
| "loss": 0.4028, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "learning_rate": 1.3274647887323943e-05, | |
| "loss": 0.3977, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.5025292634963989, | |
| "eval_runtime": 127.807, | |
| "eval_samples_per_second": 4.163, | |
| "eval_steps_per_second": 0.524, | |
| "eval_wer": 0.215080028283088, | |
| "step": 5328 | |
| }, | |
| { | |
| "epoch": 74.03, | |
| "learning_rate": 1.3204225352112675e-05, | |
| "loss": 0.4266, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 74.17, | |
| "learning_rate": 1.3133802816901409e-05, | |
| "loss": 0.394, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 74.3, | |
| "learning_rate": 1.306338028169014e-05, | |
| "loss": 0.406, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 74.44, | |
| "learning_rate": 1.2992957746478872e-05, | |
| "loss": 0.4028, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 74.58, | |
| "learning_rate": 1.2922535211267606e-05, | |
| "loss": 0.4033, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 74.72, | |
| "learning_rate": 1.2852112676056338e-05, | |
| "loss": 0.4069, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 74.86, | |
| "learning_rate": 1.2781690140845071e-05, | |
| "loss": 0.4146, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.2711267605633803e-05, | |
| "loss": 0.4056, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 0.4893050789833069, | |
| "eval_runtime": 126.5689, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.2190653725011249, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 75.14, | |
| "learning_rate": 1.2640845070422535e-05, | |
| "loss": 0.4257, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 75.28, | |
| "learning_rate": 1.2570422535211269e-05, | |
| "loss": 0.4147, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 75.42, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.4026, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 75.55, | |
| "learning_rate": 1.2429577464788732e-05, | |
| "loss": 0.408, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 75.69, | |
| "learning_rate": 1.2359154929577466e-05, | |
| "loss": 0.3983, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 75.83, | |
| "learning_rate": 1.2288732394366198e-05, | |
| "loss": 0.4046, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 75.97, | |
| "learning_rate": 1.221830985915493e-05, | |
| "loss": 0.4019, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 0.48530757427215576, | |
| "eval_runtime": 127.0771, | |
| "eval_samples_per_second": 4.186, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.21083756508324228, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 76.11, | |
| "learning_rate": 1.2147887323943663e-05, | |
| "loss": 0.4, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 76.25, | |
| "learning_rate": 1.2077464788732395e-05, | |
| "loss": 0.412, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 76.39, | |
| "learning_rate": 1.2007042253521129e-05, | |
| "loss": 0.413, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 76.53, | |
| "learning_rate": 1.1936619718309859e-05, | |
| "loss": 0.4135, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 76.66, | |
| "learning_rate": 1.1866197183098591e-05, | |
| "loss": 0.4109, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 1.1795774647887324e-05, | |
| "loss": 0.4061, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 76.94, | |
| "learning_rate": 1.1725352112676056e-05, | |
| "loss": 0.4147, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 0.48485973477363586, | |
| "eval_runtime": 125.8319, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.21308735617406954, | |
| "step": 5544 | |
| }, | |
| { | |
| "epoch": 77.08, | |
| "learning_rate": 1.1654929577464788e-05, | |
| "loss": 0.4043, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 77.22, | |
| "learning_rate": 1.1584507042253522e-05, | |
| "loss": 0.4025, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 77.36, | |
| "learning_rate": 1.1514084507042254e-05, | |
| "loss": 0.4097, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 77.5, | |
| "learning_rate": 1.1443661971830987e-05, | |
| "loss": 0.4132, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 77.64, | |
| "learning_rate": 1.1373239436619719e-05, | |
| "loss": 0.3952, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "learning_rate": 1.1302816901408451e-05, | |
| "loss": 0.4721, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 77.91, | |
| "learning_rate": 1.1232394366197185e-05, | |
| "loss": 0.4075, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 0.5035993456840515, | |
| "eval_runtime": 127.1426, | |
| "eval_samples_per_second": 4.184, | |
| "eval_steps_per_second": 0.527, | |
| "eval_wer": 0.2117374815195732, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 78.06, | |
| "learning_rate": 1.1161971830985916e-05, | |
| "loss": 0.4084, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 78.19, | |
| "learning_rate": 1.1091549295774648e-05, | |
| "loss": 0.3951, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 78.33, | |
| "learning_rate": 1.1021126760563382e-05, | |
| "loss": 0.402, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 78.47, | |
| "learning_rate": 1.0950704225352114e-05, | |
| "loss": 0.3994, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 78.61, | |
| "learning_rate": 1.0880281690140846e-05, | |
| "loss": 0.398, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 78.75, | |
| "learning_rate": 1.0809859154929577e-05, | |
| "loss": 0.4013, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "learning_rate": 1.073943661971831e-05, | |
| "loss": 0.4064, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 0.47934702038764954, | |
| "eval_runtime": 126.7605, | |
| "eval_samples_per_second": 4.197, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.21328019541042617, | |
| "step": 5688 | |
| }, | |
| { | |
| "epoch": 79.03, | |
| "learning_rate": 1.0669014084507043e-05, | |
| "loss": 0.42, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 79.17, | |
| "learning_rate": 1.0598591549295775e-05, | |
| "loss": 0.402, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 79.3, | |
| "learning_rate": 1.0528169014084507e-05, | |
| "loss": 0.4035, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 79.44, | |
| "learning_rate": 1.045774647887324e-05, | |
| "loss": 0.3983, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 79.58, | |
| "learning_rate": 1.0387323943661972e-05, | |
| "loss": 0.4034, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 79.72, | |
| "learning_rate": 1.0316901408450706e-05, | |
| "loss": 0.409, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 79.86, | |
| "learning_rate": 1.0246478873239438e-05, | |
| "loss": 0.4005, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.017605633802817e-05, | |
| "loss": 0.4035, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 0.4917033612728119, | |
| "eval_runtime": 126.9746, | |
| "eval_samples_per_second": 4.19, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.20826637526515396, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 80.14, | |
| "learning_rate": 1.0105633802816903e-05, | |
| "loss": 0.4008, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 80.28, | |
| "learning_rate": 1.0035211267605635e-05, | |
| "loss": 0.4, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 80.42, | |
| "learning_rate": 9.964788732394367e-06, | |
| "loss": 0.3955, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 80.55, | |
| "learning_rate": 9.894366197183099e-06, | |
| "loss": 0.3864, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 80.69, | |
| "learning_rate": 9.82394366197183e-06, | |
| "loss": 0.398, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 80.83, | |
| "learning_rate": 9.753521126760564e-06, | |
| "loss": 0.4061, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 80.97, | |
| "learning_rate": 9.683098591549296e-06, | |
| "loss": 0.4083, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 0.4724813997745514, | |
| "eval_runtime": 126.4508, | |
| "eval_samples_per_second": 4.207, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.21160892202866877, | |
| "step": 5832 | |
| }, | |
| { | |
| "epoch": 81.11, | |
| "learning_rate": 9.612676056338028e-06, | |
| "loss": 0.4011, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 81.25, | |
| "learning_rate": 9.542253521126761e-06, | |
| "loss": 0.4006, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 81.39, | |
| "learning_rate": 9.471830985915493e-06, | |
| "loss": 0.3875, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 81.53, | |
| "learning_rate": 9.401408450704225e-06, | |
| "loss": 0.4037, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 81.66, | |
| "learning_rate": 9.330985915492959e-06, | |
| "loss": 0.4018, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 81.8, | |
| "learning_rate": 9.26056338028169e-06, | |
| "loss": 0.3989, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 81.94, | |
| "learning_rate": 9.190140845070422e-06, | |
| "loss": 0.3954, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 0.4957520365715027, | |
| "eval_runtime": 126.407, | |
| "eval_samples_per_second": 4.209, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.2119303207559298, | |
| "step": 5904 | |
| }, | |
| { | |
| "epoch": 82.08, | |
| "learning_rate": 9.119718309859156e-06, | |
| "loss": 0.4178, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 82.22, | |
| "learning_rate": 9.049295774647888e-06, | |
| "loss": 0.4004, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 82.36, | |
| "learning_rate": 8.978873239436621e-06, | |
| "loss": 0.3828, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 82.5, | |
| "learning_rate": 8.908450704225353e-06, | |
| "loss": 0.403, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 82.64, | |
| "learning_rate": 8.838028169014084e-06, | |
| "loss": 0.3932, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 82.78, | |
| "learning_rate": 8.767605633802817e-06, | |
| "loss": 0.3964, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 82.91, | |
| "learning_rate": 8.697183098591549e-06, | |
| "loss": 0.395, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 0.4897911846637726, | |
| "eval_runtime": 126.9226, | |
| "eval_samples_per_second": 4.192, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.2134730346467828, | |
| "step": 5976 | |
| }, | |
| { | |
| "epoch": 83.06, | |
| "learning_rate": 8.626760563380283e-06, | |
| "loss": 0.4032, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 83.19, | |
| "learning_rate": 8.556338028169014e-06, | |
| "loss": 0.409, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 8.485915492957746e-06, | |
| "loss": 0.3947, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 83.47, | |
| "learning_rate": 8.41549295774648e-06, | |
| "loss": 0.4052, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 83.61, | |
| "learning_rate": 8.345070422535212e-06, | |
| "loss": 0.3859, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 83.75, | |
| "learning_rate": 8.274647887323944e-06, | |
| "loss": 0.3938, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 83.89, | |
| "learning_rate": 8.204225352112677e-06, | |
| "loss": 0.391, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 0.4821723997592926, | |
| "eval_runtime": 126.3131, | |
| "eval_samples_per_second": 4.212, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.2151443080285402, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 84.03, | |
| "learning_rate": 8.133802816901409e-06, | |
| "loss": 0.4098, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 84.17, | |
| "learning_rate": 8.063380281690141e-06, | |
| "loss": 0.3925, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 84.3, | |
| "learning_rate": 7.992957746478875e-06, | |
| "loss": 0.3969, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 7.922535211267606e-06, | |
| "loss": 0.4094, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 84.58, | |
| "learning_rate": 7.852112676056338e-06, | |
| "loss": 0.392, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 84.72, | |
| "learning_rate": 7.78169014084507e-06, | |
| "loss": 0.3862, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 84.86, | |
| "learning_rate": 7.711267605633802e-06, | |
| "loss": 0.4002, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 7.640845070422536e-06, | |
| "loss": 0.3983, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 0.48090094327926636, | |
| "eval_runtime": 125.8708, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.21096612457414668, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 85.14, | |
| "learning_rate": 7.5704225352112675e-06, | |
| "loss": 0.3878, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 85.28, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.3909, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 85.42, | |
| "learning_rate": 7.429577464788733e-06, | |
| "loss": 0.4052, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 85.55, | |
| "learning_rate": 7.359154929577465e-06, | |
| "loss": 0.3954, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 85.69, | |
| "learning_rate": 7.2887323943661975e-06, | |
| "loss": 0.4011, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 85.83, | |
| "learning_rate": 7.21830985915493e-06, | |
| "loss": 0.3947, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 85.97, | |
| "learning_rate": 7.147887323943662e-06, | |
| "loss": 0.3883, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 0.4980515241622925, | |
| "eval_runtime": 126.7334, | |
| "eval_samples_per_second": 4.198, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.21077328533779005, | |
| "step": 6192 | |
| }, | |
| { | |
| "epoch": 86.11, | |
| "learning_rate": 7.077464788732395e-06, | |
| "loss": 0.4021, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 86.25, | |
| "learning_rate": 7.0070422535211276e-06, | |
| "loss": 0.398, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 86.39, | |
| "learning_rate": 6.93661971830986e-06, | |
| "loss": 0.3908, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 86.53, | |
| "learning_rate": 6.866197183098592e-06, | |
| "loss": 0.388, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 86.66, | |
| "learning_rate": 6.795774647887325e-06, | |
| "loss": 0.3938, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 86.8, | |
| "learning_rate": 6.725352112676056e-06, | |
| "loss": 0.3923, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 86.94, | |
| "learning_rate": 6.654929577464789e-06, | |
| "loss": 0.3955, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 0.4876667559146881, | |
| "eval_runtime": 126.7989, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.2110946840650511, | |
| "step": 6264 | |
| }, | |
| { | |
| "epoch": 87.08, | |
| "learning_rate": 6.584507042253521e-06, | |
| "loss": 0.4023, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 87.22, | |
| "learning_rate": 6.514084507042253e-06, | |
| "loss": 0.4015, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 87.36, | |
| "learning_rate": 6.443661971830986e-06, | |
| "loss": 0.3818, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 6.373239436619719e-06, | |
| "loss": 0.3921, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 87.64, | |
| "learning_rate": 6.3028169014084505e-06, | |
| "loss": 0.3817, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 87.78, | |
| "learning_rate": 6.232394366197183e-06, | |
| "loss": 0.384, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 87.91, | |
| "learning_rate": 6.161971830985916e-06, | |
| "loss": 0.3983, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 0.48789334297180176, | |
| "eval_runtime": 126.1213, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.213537314392235, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 88.06, | |
| "learning_rate": 6.091549295774649e-06, | |
| "loss": 0.4158, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 88.19, | |
| "learning_rate": 6.021126760563381e-06, | |
| "loss": 0.3983, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 88.33, | |
| "learning_rate": 5.9507042253521125e-06, | |
| "loss": 0.3945, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 88.47, | |
| "learning_rate": 5.880281690140845e-06, | |
| "loss": 0.3896, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 88.61, | |
| "learning_rate": 5.809859154929578e-06, | |
| "loss": 0.3819, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 88.75, | |
| "learning_rate": 5.73943661971831e-06, | |
| "loss": 0.3939, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 5.6690140845070425e-06, | |
| "loss": 0.3877, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 0.5021692514419556, | |
| "eval_runtime": 126.1298, | |
| "eval_samples_per_second": 4.218, | |
| "eval_steps_per_second": 0.531, | |
| "eval_wer": 0.21495146879218358, | |
| "step": 6408 | |
| }, | |
| { | |
| "epoch": 89.03, | |
| "learning_rate": 5.598591549295775e-06, | |
| "loss": 0.4044, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 89.17, | |
| "learning_rate": 5.528169014084508e-06, | |
| "loss": 0.3919, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 89.3, | |
| "learning_rate": 5.457746478873239e-06, | |
| "loss": 0.3851, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 89.44, | |
| "learning_rate": 5.387323943661972e-06, | |
| "loss": 0.3872, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 89.58, | |
| "learning_rate": 5.3169014084507044e-06, | |
| "loss": 0.3845, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 89.72, | |
| "learning_rate": 5.246478873239437e-06, | |
| "loss": 0.3998, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 89.86, | |
| "learning_rate": 5.176056338028169e-06, | |
| "loss": 0.3925, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 5.105633802816902e-06, | |
| "loss": 0.3992, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 0.5071265697479248, | |
| "eval_runtime": 126.7801, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.21167320177412097, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 90.14, | |
| "learning_rate": 5.0352112676056345e-06, | |
| "loss": 0.395, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 90.28, | |
| "learning_rate": 4.964788732394366e-06, | |
| "loss": 0.4013, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 90.42, | |
| "learning_rate": 4.894366197183098e-06, | |
| "loss": 0.3944, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 90.55, | |
| "learning_rate": 4.823943661971831e-06, | |
| "loss": 0.389, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 90.69, | |
| "learning_rate": 4.753521126760564e-06, | |
| "loss": 0.3898, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 90.83, | |
| "learning_rate": 4.683098591549296e-06, | |
| "loss": 0.3917, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 90.97, | |
| "learning_rate": 4.612676056338028e-06, | |
| "loss": 0.393, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 0.4833681583404541, | |
| "eval_runtime": 131.3542, | |
| "eval_samples_per_second": 4.05, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.21083756508324228, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 91.11, | |
| "learning_rate": 4.542253521126761e-06, | |
| "loss": 0.3948, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 91.25, | |
| "learning_rate": 4.471830985915494e-06, | |
| "loss": 0.3899, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 91.39, | |
| "learning_rate": 4.401408450704226e-06, | |
| "loss": 0.3798, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 91.53, | |
| "learning_rate": 4.3309859154929575e-06, | |
| "loss": 0.3839, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 91.66, | |
| "learning_rate": 4.26056338028169e-06, | |
| "loss": 0.3819, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 91.8, | |
| "learning_rate": 4.190140845070423e-06, | |
| "loss": 0.3805, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 91.94, | |
| "learning_rate": 4.119718309859155e-06, | |
| "loss": 0.3941, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 0.4961974024772644, | |
| "eval_runtime": 131.7625, | |
| "eval_samples_per_second": 4.038, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.2119303207559298, | |
| "step": 6624 | |
| }, | |
| { | |
| "epoch": 92.08, | |
| "learning_rate": 4.0492957746478875e-06, | |
| "loss": 0.408, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 92.22, | |
| "learning_rate": 3.97887323943662e-06, | |
| "loss": 0.3884, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 92.36, | |
| "learning_rate": 3.908450704225353e-06, | |
| "loss": 0.3812, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 92.5, | |
| "learning_rate": 3.838028169014085e-06, | |
| "loss": 0.3852, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 92.64, | |
| "learning_rate": 3.767605633802817e-06, | |
| "loss": 0.3827, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 92.78, | |
| "learning_rate": 3.6971830985915494e-06, | |
| "loss": 0.3944, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 92.91, | |
| "learning_rate": 3.6267605633802817e-06, | |
| "loss": 0.3877, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 0.4878864586353302, | |
| "eval_runtime": 127.8576, | |
| "eval_samples_per_second": 4.161, | |
| "eval_steps_per_second": 0.524, | |
| "eval_wer": 0.20762357781063187, | |
| "step": 6696 | |
| }, | |
| { | |
| "epoch": 93.06, | |
| "learning_rate": 3.5563380281690144e-06, | |
| "loss": 0.4055, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 93.19, | |
| "learning_rate": 3.4859154929577467e-06, | |
| "loss": 0.3828, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 93.33, | |
| "learning_rate": 3.4154929577464795e-06, | |
| "loss": 0.3835, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 93.47, | |
| "learning_rate": 3.3450704225352113e-06, | |
| "loss": 0.3891, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 93.61, | |
| "learning_rate": 3.2746478873239436e-06, | |
| "loss": 0.394, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 93.75, | |
| "learning_rate": 3.204225352112676e-06, | |
| "loss": 0.3938, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "learning_rate": 3.1338028169014087e-06, | |
| "loss": 0.3709, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 0.48774513602256775, | |
| "eval_runtime": 126.6111, | |
| "eval_samples_per_second": 4.202, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.20897345246512825, | |
| "step": 6768 | |
| }, | |
| { | |
| "epoch": 94.03, | |
| "learning_rate": 3.063380281690141e-06, | |
| "loss": 0.3925, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 94.17, | |
| "learning_rate": 2.9929577464788733e-06, | |
| "loss": 0.3871, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 94.3, | |
| "learning_rate": 2.9225352112676056e-06, | |
| "loss": 0.3915, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 94.44, | |
| "learning_rate": 2.8521126760563383e-06, | |
| "loss": 0.3777, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 94.58, | |
| "learning_rate": 2.7816901408450706e-06, | |
| "loss": 0.3821, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 94.72, | |
| "learning_rate": 2.711267605633803e-06, | |
| "loss": 0.3909, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 94.86, | |
| "learning_rate": 2.640845070422535e-06, | |
| "loss": 0.3907, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 2.570422535211268e-06, | |
| "loss": 0.3905, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 0.49698197841644287, | |
| "eval_runtime": 126.8507, | |
| "eval_samples_per_second": 4.194, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.21295879668316514, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 95.14, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.3814, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 95.28, | |
| "learning_rate": 2.4295774647887325e-06, | |
| "loss": 0.3908, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 95.42, | |
| "learning_rate": 2.359154929577465e-06, | |
| "loss": 0.387, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 95.55, | |
| "learning_rate": 2.2887323943661975e-06, | |
| "loss": 0.3889, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 95.69, | |
| "learning_rate": 2.21830985915493e-06, | |
| "loss": 0.3781, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 95.83, | |
| "learning_rate": 2.147887323943662e-06, | |
| "loss": 0.3948, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 95.97, | |
| "learning_rate": 2.0774647887323944e-06, | |
| "loss": 0.3918, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 0.48947659134864807, | |
| "eval_runtime": 127.7315, | |
| "eval_samples_per_second": 4.165, | |
| "eval_steps_per_second": 0.525, | |
| "eval_wer": 0.21064472584688565, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 96.11, | |
| "learning_rate": 2.007042253521127e-06, | |
| "loss": 0.3879, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 96.25, | |
| "learning_rate": 1.936619718309859e-06, | |
| "loss": 0.3809, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "learning_rate": 1.8661971830985915e-06, | |
| "loss": 0.3702, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 96.53, | |
| "learning_rate": 1.795774647887324e-06, | |
| "loss": 0.3975, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 96.66, | |
| "learning_rate": 1.7253521126760566e-06, | |
| "loss": 0.3847, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 96.8, | |
| "learning_rate": 1.6549295774647886e-06, | |
| "loss": 0.389, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 96.94, | |
| "learning_rate": 1.5845070422535212e-06, | |
| "loss": 0.3954, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 0.48836567997932434, | |
| "eval_runtime": 128.4968, | |
| "eval_samples_per_second": 4.14, | |
| "eval_steps_per_second": 0.521, | |
| "eval_wer": 0.2079449765378929, | |
| "step": 6984 | |
| }, | |
| { | |
| "epoch": 97.08, | |
| "learning_rate": 1.5140845070422537e-06, | |
| "loss": 0.3846, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 97.22, | |
| "learning_rate": 1.443661971830986e-06, | |
| "loss": 0.384, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 97.36, | |
| "learning_rate": 1.3732394366197185e-06, | |
| "loss": 0.3841, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 97.5, | |
| "learning_rate": 1.3028169014084508e-06, | |
| "loss": 0.3786, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 97.64, | |
| "learning_rate": 1.232394366197183e-06, | |
| "loss": 0.3702, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 97.78, | |
| "learning_rate": 1.1619718309859156e-06, | |
| "loss": 0.3828, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 97.91, | |
| "learning_rate": 1.0915492957746479e-06, | |
| "loss": 0.3979, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 0.48947107791900635, | |
| "eval_runtime": 130.633, | |
| "eval_samples_per_second": 4.072, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.20974480941055473, | |
| "step": 7056 | |
| }, | |
| { | |
| "epoch": 98.06, | |
| "learning_rate": 1.0211267605633804e-06, | |
| "loss": 0.3893, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 98.19, | |
| "learning_rate": 9.507042253521127e-07, | |
| "loss": 0.378, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 98.33, | |
| "learning_rate": 8.802816901408452e-07, | |
| "loss": 0.3816, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 98.47, | |
| "learning_rate": 8.098591549295775e-07, | |
| "loss": 0.3932, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 98.61, | |
| "learning_rate": 7.394366197183099e-07, | |
| "loss": 0.3814, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 98.75, | |
| "learning_rate": 6.690140845070423e-07, | |
| "loss": 0.3789, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "learning_rate": 5.985915492957746e-07, | |
| "loss": 0.373, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 0.4874747097492218, | |
| "eval_runtime": 126.7367, | |
| "eval_samples_per_second": 4.198, | |
| "eval_steps_per_second": 0.529, | |
| "eval_wer": 0.20762357781063187, | |
| "step": 7128 | |
| }, | |
| { | |
| "epoch": 99.03, | |
| "learning_rate": 5.28169014084507e-07, | |
| "loss": 0.4034, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 99.17, | |
| "learning_rate": 4.5774647887323947e-07, | |
| "loss": 0.3873, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 99.3, | |
| "learning_rate": 3.873239436619719e-07, | |
| "loss": 0.3784, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 99.44, | |
| "learning_rate": 3.1690140845070423e-07, | |
| "loss": 0.3909, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 99.58, | |
| "learning_rate": 2.4647887323943664e-07, | |
| "loss": 0.3863, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 99.72, | |
| "learning_rate": 1.7605633802816901e-07, | |
| "loss": 0.3796, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 99.86, | |
| "learning_rate": 1.056338028169014e-07, | |
| "loss": 0.3699, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 3.5211267605633804e-08, | |
| "loss": 0.3769, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 0.490430623292923, | |
| "eval_runtime": 126.8664, | |
| "eval_samples_per_second": 4.193, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.20871633348331942, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 7200, | |
| "total_flos": 2.7202925310621965e+20, | |
| "train_loss": 0.44683600352870095, | |
| "train_runtime": 190307.0487, | |
| "train_samples_per_second": 2.426, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "max_steps": 7200, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.7202925310621965e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |