| { | |
| "best_metric": 2.5726349353790283, | |
| "best_model_checkpoint": "ai-light-dance_singing3_ft_pretrain2_wav2vec2-large-xlsr-53/checkpoint-6624", | |
| "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": 3.5000000000000004e-06, | |
| "loss": 37.8998, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 20.6294, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 4.2282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.85e-05, | |
| "loss": 3.1117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.35e-05, | |
| "loss": 2.7247, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.8499999999999998e-05, | |
| "loss": 2.6035, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.35e-05, | |
| "loss": 2.1979, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.4874308109283447, | |
| "eval_runtime": 130.8827, | |
| "eval_samples_per_second": 4.065, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9922221508002829, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.85e-05, | |
| "loss": 2.2698, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.35e-05, | |
| "loss": 2.0742, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.85e-05, | |
| "loss": 2.3481, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.995070422535211e-05, | |
| "loss": 1.9461, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.988028169014085e-05, | |
| "loss": 2.0287, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.980985915492958e-05, | |
| "loss": 2.0229, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 4.973943661971831e-05, | |
| "loss": 1.9612, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 4.510500431060791, | |
| "eval_runtime": 131.7347, | |
| "eval_samples_per_second": 4.038, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.988879604036768, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 4.966901408450704e-05, | |
| "loss": 1.9514, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.9598591549295776e-05, | |
| "loss": 2.1498, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.952816901408451e-05, | |
| "loss": 2.1645, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.945774647887324e-05, | |
| "loss": 1.8589, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.9387323943661975e-05, | |
| "loss": 1.8882, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.93169014084507e-05, | |
| "loss": 1.856, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.924647887323944e-05, | |
| "loss": 1.8052, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 4.081934452056885, | |
| "eval_runtime": 130.8104, | |
| "eval_samples_per_second": 4.067, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9786591245098669, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.917605633802817e-05, | |
| "loss": 1.8272, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.91056338028169e-05, | |
| "loss": 1.7397, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 4.903521126760564e-05, | |
| "loss": 1.92, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 4.8964788732394366e-05, | |
| "loss": 1.8222, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 4.88943661971831e-05, | |
| "loss": 1.8094, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.882394366197183e-05, | |
| "loss": 1.6907, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 4.8753521126760565e-05, | |
| "loss": 1.827, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 4.405837059020996, | |
| "eval_runtime": 130.0974, | |
| "eval_samples_per_second": 4.089, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.9844443016005656, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.86830985915493e-05, | |
| "loss": 1.7429, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 4.861267605633803e-05, | |
| "loss": 1.778, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.8542253521126764e-05, | |
| "loss": 1.7108, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.847183098591549e-05, | |
| "loss": 1.7007, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.840140845070423e-05, | |
| "loss": 1.8591, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 4.833098591549296e-05, | |
| "loss": 1.6263, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 4.826056338028169e-05, | |
| "loss": 1.8142, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.819014084507043e-05, | |
| "loss": 1.6249, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 4.889533519744873, | |
| "eval_runtime": 130.9002, | |
| "eval_samples_per_second": 4.064, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9872083306550106, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 4.8119718309859155e-05, | |
| "loss": 1.7359, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.804929577464789e-05, | |
| "loss": 1.8771, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 4.7978873239436626e-05, | |
| "loss": 1.6211, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 4.7908450704225354e-05, | |
| "loss": 1.6833, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 4.783802816901409e-05, | |
| "loss": 1.6535, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 4.776760563380282e-05, | |
| "loss": 1.727, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 4.769718309859155e-05, | |
| "loss": 1.6285, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 4.753390312194824, | |
| "eval_runtime": 130.2251, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9837372244005914, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 4.762676056338028e-05, | |
| "loss": 1.7857, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 4.755633802816902e-05, | |
| "loss": 1.5781, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 4.748591549295775e-05, | |
| "loss": 1.7005, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 4.741549295774648e-05, | |
| "loss": 1.6211, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 4.7345070422535216e-05, | |
| "loss": 1.769, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 4.7274647887323945e-05, | |
| "loss": 1.7096, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 4.720422535211268e-05, | |
| "loss": 1.6713, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 4.558750629425049, | |
| "eval_runtime": 130.6897, | |
| "eval_samples_per_second": 4.071, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9818731117824774, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 4.7133802816901415e-05, | |
| "loss": 1.7235, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 4.7063380281690144e-05, | |
| "loss": 1.6237, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.699295774647888e-05, | |
| "loss": 1.6671, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 4.692253521126761e-05, | |
| "loss": 1.5521, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 4.685211267605634e-05, | |
| "loss": 1.6938, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 4.678169014084508e-05, | |
| "loss": 1.7133, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 4.6711267605633806e-05, | |
| "loss": 1.777, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 4.741362571716309, | |
| "eval_runtime": 131.3054, | |
| "eval_samples_per_second": 4.052, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9859870154914187, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 4.664084507042254e-05, | |
| "loss": 1.7278, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 4.657042253521127e-05, | |
| "loss": 1.6539, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 1.6884, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 4.6429577464788734e-05, | |
| "loss": 1.6151, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 4.635915492957747e-05, | |
| "loss": 1.7166, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 4.6288732394366204e-05, | |
| "loss": 1.4914, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.6218309859154926e-05, | |
| "loss": 1.6759, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 4.522234916687012, | |
| "eval_runtime": 130.413, | |
| "eval_samples_per_second": 4.079, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9874011698913673, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.614788732394366e-05, | |
| "loss": 1.6397, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 4.60774647887324e-05, | |
| "loss": 1.5902, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 4.6007042253521125e-05, | |
| "loss": 1.752, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 4.593661971830986e-05, | |
| "loss": 1.6492, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 4.586619718309859e-05, | |
| "loss": 1.6478, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 4.5795774647887324e-05, | |
| "loss": 1.593, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 4.572535211267606e-05, | |
| "loss": 1.6711, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.565492957746479e-05, | |
| "loss": 1.5533, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 3.6153128147125244, | |
| "eval_runtime": 129.7947, | |
| "eval_samples_per_second": 4.099, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.982387349746095, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 4.558450704225352e-05, | |
| "loss": 1.6175, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 4.551408450704225e-05, | |
| "loss": 1.6756, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 4.544366197183099e-05, | |
| "loss": 1.6021, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 4.537323943661972e-05, | |
| "loss": 1.5629, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 4.530281690140845e-05, | |
| "loss": 1.5889, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 4.5232394366197186e-05, | |
| "loss": 1.7345, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 4.5161971830985914e-05, | |
| "loss": 1.5053, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 5.648496150970459, | |
| "eval_runtime": 129.8957, | |
| "eval_samples_per_second": 4.096, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.9906794369094298, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 4.509154929577465e-05, | |
| "loss": 1.6899, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 4.502112676056338e-05, | |
| "loss": 1.5438, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 4.4950704225352113e-05, | |
| "loss": 1.6434, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 4.488028169014085e-05, | |
| "loss": 1.5148, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 4.480985915492958e-05, | |
| "loss": 1.5729, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.473943661971831e-05, | |
| "loss": 1.6381, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 4.466901408450704e-05, | |
| "loss": 1.6541, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 5.4656782150268555, | |
| "eval_runtime": 130.1688, | |
| "eval_samples_per_second": 4.087, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.9843157421096612, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 4.4598591549295776e-05, | |
| "loss": 1.6775, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 4.452816901408451e-05, | |
| "loss": 1.546, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 4.445774647887324e-05, | |
| "loss": 1.7313, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.4387323943661975e-05, | |
| "loss": 1.5004, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 4.4316901408450704e-05, | |
| "loss": 1.6062, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 4.424647887323944e-05, | |
| "loss": 1.5941, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 4.4176056338028174e-05, | |
| "loss": 1.5891, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 4.453381061553955, | |
| "eval_runtime": 130.587, | |
| "eval_samples_per_second": 4.074, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9877225686186283, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 4.41056338028169e-05, | |
| "loss": 1.6226, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 4.403521126760564e-05, | |
| "loss": 1.5122, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 4.3964788732394366e-05, | |
| "loss": 1.5418, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 4.38943661971831e-05, | |
| "loss": 1.5366, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 4.382394366197183e-05, | |
| "loss": 1.6477, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 4.3753521126760566e-05, | |
| "loss": 1.5524, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 4.36830985915493e-05, | |
| "loss": 1.6809, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 4.840369701385498, | |
| "eval_runtime": 129.3528, | |
| "eval_samples_per_second": 4.113, | |
| "eval_steps_per_second": 0.518, | |
| "eval_wer": 0.9890724432731246, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 4.361267605633803e-05, | |
| "loss": 1.5893, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 4.3542253521126765e-05, | |
| "loss": 1.5516, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 4.347183098591549e-05, | |
| "loss": 1.6468, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 4.340140845070423e-05, | |
| "loss": 1.5277, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 4.3330985915492964e-05, | |
| "loss": 1.5323, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 4.326056338028169e-05, | |
| "loss": 1.4823, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 4.319014084507043e-05, | |
| "loss": 1.6693, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.3119718309859156e-05, | |
| "loss": 1.5506, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 3.7248387336730957, | |
| "eval_runtime": 129.7977, | |
| "eval_samples_per_second": 4.099, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.9872726104004628, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 4.304929577464789e-05, | |
| "loss": 1.6658, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 4.2978873239436626e-05, | |
| "loss": 1.5241, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 4.2908450704225355e-05, | |
| "loss": 1.6534, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 4.283802816901409e-05, | |
| "loss": 1.5788, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 4.276760563380282e-05, | |
| "loss": 1.5388, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 4.2697183098591554e-05, | |
| "loss": 1.6622, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 4.262676056338029e-05, | |
| "loss": 1.4754, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 4.396983623504639, | |
| "eval_runtime": 130.0288, | |
| "eval_samples_per_second": 4.091, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.9864369737095842, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 4.255633802816902e-05, | |
| "loss": 1.6914, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 4.248591549295775e-05, | |
| "loss": 1.514, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 4.241549295774648e-05, | |
| "loss": 1.5457, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 4.2345070422535217e-05, | |
| "loss": 1.49, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 4.2274647887323945e-05, | |
| "loss": 1.672, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.220422535211268e-05, | |
| "loss": 1.5788, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 4.2133802816901416e-05, | |
| "loss": 1.4576, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 4.477088928222656, | |
| "eval_runtime": 130.6058, | |
| "eval_samples_per_second": 4.073, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9854727775278009, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 4.206338028169014e-05, | |
| "loss": 1.7007, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 4.199295774647887e-05, | |
| "loss": 1.6807, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 4.192253521126761e-05, | |
| "loss": 1.5547, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 4.1852112676056336e-05, | |
| "loss": 1.4415, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 4.178169014084507e-05, | |
| "loss": 1.5736, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 4.17112676056338e-05, | |
| "loss": 1.5291, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 4.1640845070422535e-05, | |
| "loss": 1.5614, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 3.5102336406707764, | |
| "eval_runtime": 129.8253, | |
| "eval_samples_per_second": 4.098, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.986115574982323, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 4.157042253521127e-05, | |
| "loss": 1.5626, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 4.15e-05, | |
| "loss": 1.4813, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 4.1429577464788734e-05, | |
| "loss": 1.5684, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 4.135915492957746e-05, | |
| "loss": 1.4684, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 4.12887323943662e-05, | |
| "loss": 1.5375, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 4.1218309859154927e-05, | |
| "loss": 1.4983, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 4.114788732394366e-05, | |
| "loss": 1.655, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 4.806183338165283, | |
| "eval_runtime": 129.9512, | |
| "eval_samples_per_second": 4.094, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.9863084142186797, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 4.10774647887324e-05, | |
| "loss": 1.6348, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 4.1007042253521126e-05, | |
| "loss": 1.558, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 4.093661971830986e-05, | |
| "loss": 1.5928, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 4.086619718309859e-05, | |
| "loss": 1.5327, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 4.0795774647887325e-05, | |
| "loss": 1.5945, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 4.072535211267606e-05, | |
| "loss": 1.4834, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 4.065492957746479e-05, | |
| "loss": 1.5911, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0584507042253524e-05, | |
| "loss": 1.455, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 5.0790300369262695, | |
| "eval_runtime": 129.7071, | |
| "eval_samples_per_second": 4.102, | |
| "eval_steps_per_second": 0.517, | |
| "eval_wer": 0.9879796876004371, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 4.051408450704225e-05, | |
| "loss": 1.6204, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 20.28, | |
| "learning_rate": 4.044366197183099e-05, | |
| "loss": 1.5141, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 4.037323943661972e-05, | |
| "loss": 1.5035, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 4.030281690140845e-05, | |
| "loss": 1.6486, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 4.0232394366197186e-05, | |
| "loss": 1.4833, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 4.0161971830985915e-05, | |
| "loss": 1.616, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 20.97, | |
| "learning_rate": 4.009154929577465e-05, | |
| "loss": 1.4701, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 4.231964111328125, | |
| "eval_runtime": 130.4172, | |
| "eval_samples_per_second": 4.079, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9850228193096355, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "learning_rate": 4.0021126760563385e-05, | |
| "loss": 1.6554, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 3.9950704225352114e-05, | |
| "loss": 1.5313, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 3.988028169014085e-05, | |
| "loss": 1.5128, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 3.980985915492958e-05, | |
| "loss": 1.5099, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 3.973943661971831e-05, | |
| "loss": 1.5616, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 3.966901408450704e-05, | |
| "loss": 1.5503, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 3.959859154929578e-05, | |
| "loss": 1.495, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 5.213191986083984, | |
| "eval_runtime": 130.3188, | |
| "eval_samples_per_second": 4.082, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.988879604036768, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 3.952816901408451e-05, | |
| "loss": 1.5799, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 3.945774647887324e-05, | |
| "loss": 1.4768, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 3.9387323943661976e-05, | |
| "loss": 1.5627, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 3.9316901408450704e-05, | |
| "loss": 1.502, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 22.64, | |
| "learning_rate": 3.924647887323944e-05, | |
| "loss": 1.5224, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 3.9176056338028175e-05, | |
| "loss": 1.4793, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 3.91056338028169e-05, | |
| "loss": 1.5676, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 4.159689426422119, | |
| "eval_runtime": 130.5889, | |
| "eval_samples_per_second": 4.074, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9805875168734332, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 3.903521126760564e-05, | |
| "loss": 1.5326, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 3.896478873239437e-05, | |
| "loss": 1.4812, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 3.88943661971831e-05, | |
| "loss": 1.5815, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 3.882394366197184e-05, | |
| "loss": 1.4233, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 23.61, | |
| "learning_rate": 3.8753521126760566e-05, | |
| "loss": 1.528, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 3.86830985915493e-05, | |
| "loss": 1.4451, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 3.861267605633803e-05, | |
| "loss": 1.5837, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 5.098143577575684, | |
| "eval_runtime": 130.0277, | |
| "eval_samples_per_second": 4.091, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.986694092691393, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 3.8542253521126765e-05, | |
| "loss": 1.5209, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 3.84718309859155e-05, | |
| "loss": 1.5073, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 3.840140845070423e-05, | |
| "loss": 1.5739, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 3.8330985915492964e-05, | |
| "loss": 1.4875, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 24.58, | |
| "learning_rate": 3.826056338028169e-05, | |
| "loss": 1.5407, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 24.72, | |
| "learning_rate": 3.819014084507043e-05, | |
| "loss": 1.4561, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 3.8119718309859156e-05, | |
| "loss": 1.5288, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.804929577464789e-05, | |
| "loss": 1.4437, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 3.6790771484375, | |
| "eval_runtime": 130.0598, | |
| "eval_samples_per_second": 4.09, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.9812945940734075, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.14, | |
| "learning_rate": 3.797887323943663e-05, | |
| "loss": 1.5601, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 3.790845070422535e-05, | |
| "loss": 1.6149, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 3.7838028169014084e-05, | |
| "loss": 1.4645, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 25.55, | |
| "learning_rate": 3.776760563380282e-05, | |
| "loss": 1.492, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 3.769718309859155e-05, | |
| "loss": 1.4875, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 25.83, | |
| "learning_rate": 3.762676056338028e-05, | |
| "loss": 1.5415, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 3.755633802816901e-05, | |
| "loss": 1.4684, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 4.066702842712402, | |
| "eval_runtime": 129.879, | |
| "eval_samples_per_second": 4.096, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.9868869319277496, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 3.7485915492957746e-05, | |
| "loss": 1.5748, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 3.741549295774648e-05, | |
| "loss": 1.4697, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 3.734507042253521e-05, | |
| "loss": 1.5225, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 3.7274647887323945e-05, | |
| "loss": 1.4683, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 26.66, | |
| "learning_rate": 3.7204225352112674e-05, | |
| "loss": 1.446, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "learning_rate": 3.713380281690141e-05, | |
| "loss": 1.5124, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 3.706338028169014e-05, | |
| "loss": 1.4617, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 5.2262139320373535, | |
| "eval_runtime": 130.3549, | |
| "eval_samples_per_second": 4.081, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9902294786912644, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 27.08, | |
| "learning_rate": 3.699295774647887e-05, | |
| "loss": 1.5184, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 3.692253521126761e-05, | |
| "loss": 1.5419, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 3.685211267605634e-05, | |
| "loss": 1.5046, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 3.678169014084507e-05, | |
| "loss": 1.4151, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 3.67112676056338e-05, | |
| "loss": 1.5072, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 3.6640845070422536e-05, | |
| "loss": 1.4767, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 3.657042253521127e-05, | |
| "loss": 1.5259, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 4.5762858390808105, | |
| "eval_runtime": 130.307, | |
| "eval_samples_per_second": 4.083, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9875940091277239, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 3.65e-05, | |
| "loss": 1.5078, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 3.6429577464788735e-05, | |
| "loss": 1.4085, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 28.33, | |
| "learning_rate": 3.635915492957746e-05, | |
| "loss": 1.4948, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 3.62887323943662e-05, | |
| "loss": 1.4401, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 28.61, | |
| "learning_rate": 3.6218309859154934e-05, | |
| "loss": 1.5285, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 3.614788732394366e-05, | |
| "loss": 1.4384, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 3.60774647887324e-05, | |
| "loss": 1.5127, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 3.5296952724456787, | |
| "eval_runtime": 130.1354, | |
| "eval_samples_per_second": 4.088, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.9830944269460693, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 3.6007042253521126e-05, | |
| "loss": 1.5654, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 3.593661971830986e-05, | |
| "loss": 1.4627, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 29.3, | |
| "learning_rate": 3.5866197183098597e-05, | |
| "loss": 1.4326, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 3.5795774647887325e-05, | |
| "loss": 1.4128, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 3.572535211267606e-05, | |
| "loss": 1.5034, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "learning_rate": 3.565492957746479e-05, | |
| "loss": 1.4244, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 3.5584507042253524e-05, | |
| "loss": 1.4928, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.551408450704225e-05, | |
| "loss": 1.4726, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 3.237917900085449, | |
| "eval_runtime": 130.2259, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9776306485826316, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 3.544366197183099e-05, | |
| "loss": 1.5197, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 3.537323943661972e-05, | |
| "loss": 1.4335, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 3.530281690140845e-05, | |
| "loss": 1.4897, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 3.523239436619719e-05, | |
| "loss": 1.4403, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 3.5161971830985915e-05, | |
| "loss": 1.4808, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 30.83, | |
| "learning_rate": 3.509154929577465e-05, | |
| "loss": 1.5281, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "learning_rate": 3.5021126760563386e-05, | |
| "loss": 1.446, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 3.9459383487701416, | |
| "eval_runtime": 129.8148, | |
| "eval_samples_per_second": 4.098, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.9834801054187825, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 3.4950704225352114e-05, | |
| "loss": 1.595, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 3.488028169014085e-05, | |
| "loss": 1.3812, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 31.39, | |
| "learning_rate": 3.480985915492958e-05, | |
| "loss": 1.5127, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 3.473943661971831e-05, | |
| "loss": 1.4908, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 31.66, | |
| "learning_rate": 3.466901408450705e-05, | |
| "loss": 1.4987, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 3.459859154929578e-05, | |
| "loss": 1.4607, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "learning_rate": 3.452816901408451e-05, | |
| "loss": 1.4116, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 3.535161256790161, | |
| "eval_runtime": 130.6285, | |
| "eval_samples_per_second": 4.073, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9814874333097641, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 32.08, | |
| "learning_rate": 3.445774647887324e-05, | |
| "loss": 1.5251, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 3.4387323943661976e-05, | |
| "loss": 1.3876, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 3.4316901408450705e-05, | |
| "loss": 1.5109, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 3.424647887323944e-05, | |
| "loss": 1.4014, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 3.4176056338028175e-05, | |
| "loss": 1.5301, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 3.4105633802816904e-05, | |
| "loss": 1.4588, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 3.403521126760564e-05, | |
| "loss": 1.462, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 3.3658456802368164, | |
| "eval_runtime": 130.4437, | |
| "eval_samples_per_second": 4.078, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9760879346917786, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 33.06, | |
| "learning_rate": 3.396478873239437e-05, | |
| "loss": 1.4869, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 3.38943661971831e-05, | |
| "loss": 1.4332, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 3.382394366197184e-05, | |
| "loss": 1.4464, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 33.47, | |
| "learning_rate": 3.3753521126760566e-05, | |
| "loss": 1.3993, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 3.3683098591549295e-05, | |
| "loss": 1.4726, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 3.361267605633803e-05, | |
| "loss": 1.4268, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 3.354225352112676e-05, | |
| "loss": 1.498, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 3.862046718597412, | |
| "eval_runtime": 131.0934, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9794947612007456, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 34.03, | |
| "learning_rate": 3.3471830985915494e-05, | |
| "loss": 1.4754, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 34.17, | |
| "learning_rate": 3.340140845070422e-05, | |
| "loss": 1.3934, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 3.333098591549296e-05, | |
| "loss": 1.4224, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 3.326056338028169e-05, | |
| "loss": 1.4338, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 34.58, | |
| "learning_rate": 3.319014084507042e-05, | |
| "loss": 1.5069, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 34.72, | |
| "learning_rate": 3.311971830985916e-05, | |
| "loss": 1.4498, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 3.3049295774647885e-05, | |
| "loss": 1.5188, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.297887323943662e-05, | |
| "loss": 1.382, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 3.473414182662964, | |
| "eval_runtime": 130.3567, | |
| "eval_samples_per_second": 4.081, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9797518801825544, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 35.14, | |
| "learning_rate": 3.290845070422535e-05, | |
| "loss": 1.5214, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 35.28, | |
| "learning_rate": 3.2838028169014084e-05, | |
| "loss": 1.4588, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 35.42, | |
| "learning_rate": 3.276760563380282e-05, | |
| "loss": 1.4542, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 35.55, | |
| "learning_rate": 3.269718309859155e-05, | |
| "loss": 1.449, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 35.69, | |
| "learning_rate": 3.262676056338028e-05, | |
| "loss": 1.4157, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 35.83, | |
| "learning_rate": 3.255633802816901e-05, | |
| "loss": 1.4518, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 3.248591549295775e-05, | |
| "loss": 1.3969, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 3.7284700870513916, | |
| "eval_runtime": 130.4462, | |
| "eval_samples_per_second": 4.078, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9780163270553449, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 36.11, | |
| "learning_rate": 3.241549295774648e-05, | |
| "loss": 1.4896, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 3.234507042253521e-05, | |
| "loss": 1.3764, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 3.2274647887323946e-05, | |
| "loss": 1.4335, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 36.53, | |
| "learning_rate": 3.2204225352112674e-05, | |
| "loss": 1.4429, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 36.66, | |
| "learning_rate": 3.213380281690141e-05, | |
| "loss": 1.4849, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 3.2063380281690145e-05, | |
| "loss": 1.4526, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "learning_rate": 3.1992957746478873e-05, | |
| "loss": 1.3945, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 3.725541353225708, | |
| "eval_runtime": 130.2241, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9820016712733818, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 37.08, | |
| "learning_rate": 3.192253521126761e-05, | |
| "loss": 1.4576, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 37.22, | |
| "learning_rate": 3.185211267605634e-05, | |
| "loss": 1.3657, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "learning_rate": 3.178169014084507e-05, | |
| "loss": 1.4399, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 3.17112676056338e-05, | |
| "loss": 1.3822, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 37.64, | |
| "learning_rate": 3.1640845070422536e-05, | |
| "loss": 1.4901, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 3.157042253521127e-05, | |
| "loss": 1.4733, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "learning_rate": 3.15e-05, | |
| "loss": 1.4616, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 3.878848075866699, | |
| "eval_runtime": 130.4377, | |
| "eval_samples_per_second": 4.079, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9812303143279553, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 38.06, | |
| "learning_rate": 3.1429577464788735e-05, | |
| "loss": 1.4583, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 3.1359154929577464e-05, | |
| "loss": 1.3932, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 38.33, | |
| "learning_rate": 3.12887323943662e-05, | |
| "loss": 1.4282, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 38.47, | |
| "learning_rate": 3.1218309859154934e-05, | |
| "loss": 1.3665, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 38.61, | |
| "learning_rate": 3.114788732394366e-05, | |
| "loss": 1.5116, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 3.10774647887324e-05, | |
| "loss": 1.4327, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 3.1007042253521126e-05, | |
| "loss": 1.4791, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 3.189089298248291, | |
| "eval_runtime": 130.1914, | |
| "eval_samples_per_second": 4.086, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.9780806068007971, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 39.03, | |
| "learning_rate": 3.093661971830986e-05, | |
| "loss": 1.4395, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "learning_rate": 3.08661971830986e-05, | |
| "loss": 1.3824, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 39.3, | |
| "learning_rate": 3.0795774647887325e-05, | |
| "loss": 1.4604, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 3.072535211267606e-05, | |
| "loss": 1.4136, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 39.58, | |
| "learning_rate": 3.065492957746479e-05, | |
| "loss": 1.42, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 39.72, | |
| "learning_rate": 3.0584507042253524e-05, | |
| "loss": 1.3876, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 3.0514084507042256e-05, | |
| "loss": 1.4762, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.0443661971830988e-05, | |
| "loss": 1.3875, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 3.6854491233825684, | |
| "eval_runtime": 130.6968, | |
| "eval_samples_per_second": 4.07, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9800732789098155, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 3.037323943661972e-05, | |
| "loss": 1.4414, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 40.28, | |
| "learning_rate": 3.0302816901408455e-05, | |
| "loss": 1.3793, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 40.42, | |
| "learning_rate": 3.0232394366197187e-05, | |
| "loss": 1.4228, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 3.016197183098592e-05, | |
| "loss": 1.403, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 40.69, | |
| "learning_rate": 3.009154929577465e-05, | |
| "loss": 1.3963, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 40.83, | |
| "learning_rate": 3.0021126760563383e-05, | |
| "loss": 1.4233, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 40.97, | |
| "learning_rate": 2.9950704225352115e-05, | |
| "loss": 1.3914, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 3.4011056423187256, | |
| "eval_runtime": 130.7999, | |
| "eval_samples_per_second": 4.067, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9742238220736645, | |
| "step": 2952 | |
| }, | |
| { | |
| "epoch": 41.11, | |
| "learning_rate": 2.988028169014085e-05, | |
| "loss": 1.4879, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 41.25, | |
| "learning_rate": 2.9809859154929582e-05, | |
| "loss": 1.3831, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 41.39, | |
| "learning_rate": 2.9739436619718314e-05, | |
| "loss": 1.4669, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 2.9669014084507046e-05, | |
| "loss": 1.3642, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 41.66, | |
| "learning_rate": 2.9598591549295778e-05, | |
| "loss": 1.4006, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "learning_rate": 2.9528169014084506e-05, | |
| "loss": 1.4594, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 41.94, | |
| "learning_rate": 2.9457746478873238e-05, | |
| "loss": 1.3744, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 3.5792057514190674, | |
| "eval_runtime": 130.4782, | |
| "eval_samples_per_second": 4.077, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9808446358552421, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 42.08, | |
| "learning_rate": 2.938732394366197e-05, | |
| "loss": 1.4386, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 2.93169014084507e-05, | |
| "loss": 1.3701, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 42.36, | |
| "learning_rate": 2.9246478873239437e-05, | |
| "loss": 1.4619, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 2.917605633802817e-05, | |
| "loss": 1.3623, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 2.91056338028169e-05, | |
| "loss": 1.3855, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "learning_rate": 2.9035211267605633e-05, | |
| "loss": 1.3731, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 2.8964788732394364e-05, | |
| "loss": 1.4085, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 2.9806365966796875, | |
| "eval_runtime": 130.7636, | |
| "eval_samples_per_second": 4.068, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9742881018191168, | |
| "step": 3096 | |
| }, | |
| { | |
| "epoch": 43.06, | |
| "learning_rate": 2.88943661971831e-05, | |
| "loss": 1.3944, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 2.882394366197183e-05, | |
| "loss": 1.3556, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 43.33, | |
| "learning_rate": 2.8753521126760563e-05, | |
| "loss": 1.415, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 43.47, | |
| "learning_rate": 2.8683098591549295e-05, | |
| "loss": 1.3848, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 43.61, | |
| "learning_rate": 2.8612676056338027e-05, | |
| "loss": 1.468, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 2.854225352112676e-05, | |
| "loss": 1.3518, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 43.89, | |
| "learning_rate": 2.8471830985915494e-05, | |
| "loss": 1.407, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 3.3188397884368896, | |
| "eval_runtime": 130.8549, | |
| "eval_samples_per_second": 4.066, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9821302307642862, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 44.03, | |
| "learning_rate": 2.8401408450704226e-05, | |
| "loss": 1.4181, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 44.17, | |
| "learning_rate": 2.8330985915492958e-05, | |
| "loss": 1.3522, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 44.3, | |
| "learning_rate": 2.826056338028169e-05, | |
| "loss": 1.3983, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 2.8190140845070422e-05, | |
| "loss": 1.4091, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 2.8119718309859157e-05, | |
| "loss": 1.4292, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 2.804929577464789e-05, | |
| "loss": 1.348, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 44.86, | |
| "learning_rate": 2.797887323943662e-05, | |
| "loss": 1.3977, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.7908450704225353e-05, | |
| "loss": 1.3678, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 3.6300089359283447, | |
| "eval_runtime": 130.6888, | |
| "eval_samples_per_second": 4.071, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9816802725461207, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 45.14, | |
| "learning_rate": 2.7838028169014085e-05, | |
| "loss": 1.43, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 45.28, | |
| "learning_rate": 2.7767605633802816e-05, | |
| "loss": 1.3639, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 2.7697183098591552e-05, | |
| "loss": 1.3611, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 45.55, | |
| "learning_rate": 2.7626760563380284e-05, | |
| "loss": 1.4093, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 45.69, | |
| "learning_rate": 2.7556338028169015e-05, | |
| "loss": 1.3651, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 45.83, | |
| "learning_rate": 2.7485915492957747e-05, | |
| "loss": 1.4214, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 45.97, | |
| "learning_rate": 2.741549295774648e-05, | |
| "loss": 1.3762, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 3.098646640777588, | |
| "eval_runtime": 130.2199, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.977437809346275, | |
| "step": 3312 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 2.734507042253521e-05, | |
| "loss": 1.421, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 46.25, | |
| "learning_rate": 2.7274647887323946e-05, | |
| "loss": 1.3568, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 46.39, | |
| "learning_rate": 2.7204225352112678e-05, | |
| "loss": 1.3897, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 46.53, | |
| "learning_rate": 2.713380281690141e-05, | |
| "loss": 1.3806, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 46.66, | |
| "learning_rate": 2.7063380281690142e-05, | |
| "loss": 1.3745, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "learning_rate": 2.6992957746478874e-05, | |
| "loss": 1.3942, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 46.94, | |
| "learning_rate": 2.692253521126761e-05, | |
| "loss": 1.3507, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 2.8956308364868164, | |
| "eval_runtime": 131.1936, | |
| "eval_samples_per_second": 4.055, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9732596258918814, | |
| "step": 3384 | |
| }, | |
| { | |
| "epoch": 47.08, | |
| "learning_rate": 2.685211267605634e-05, | |
| "loss": 1.4291, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 47.22, | |
| "learning_rate": 2.6781690140845073e-05, | |
| "loss": 1.3325, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 2.6711267605633805e-05, | |
| "loss": 1.419, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 2.6640845070422537e-05, | |
| "loss": 1.362, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 47.64, | |
| "learning_rate": 2.657042253521127e-05, | |
| "loss": 1.3878, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 47.78, | |
| "learning_rate": 2.6500000000000004e-05, | |
| "loss": 1.3695, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 2.6429577464788736e-05, | |
| "loss": 1.3646, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 2.836045503616333, | |
| "eval_runtime": 130.9286, | |
| "eval_samples_per_second": 4.063, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9730667866555248, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 48.06, | |
| "learning_rate": 2.6359154929577468e-05, | |
| "loss": 1.404, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 2.62887323943662e-05, | |
| "loss": 1.3409, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 48.33, | |
| "learning_rate": 2.621830985915493e-05, | |
| "loss": 1.3885, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 48.47, | |
| "learning_rate": 2.6147887323943667e-05, | |
| "loss": 1.3468, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 48.61, | |
| "learning_rate": 2.60774647887324e-05, | |
| "loss": 1.3811, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "learning_rate": 2.600704225352113e-05, | |
| "loss": 1.3525, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "learning_rate": 2.5936619718309862e-05, | |
| "loss": 1.4027, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 3.518127918243408, | |
| "eval_runtime": 130.7441, | |
| "eval_samples_per_second": 4.069, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9744166613100212, | |
| "step": 3528 | |
| }, | |
| { | |
| "epoch": 49.03, | |
| "learning_rate": 2.5866197183098594e-05, | |
| "loss": 1.4143, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "learning_rate": 2.5795774647887326e-05, | |
| "loss": 1.3482, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 2.572535211267606e-05, | |
| "loss": 1.379, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 49.44, | |
| "learning_rate": 2.5654929577464793e-05, | |
| "loss": 1.4315, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 49.58, | |
| "learning_rate": 2.5584507042253525e-05, | |
| "loss": 1.389, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 49.72, | |
| "learning_rate": 2.5514084507042257e-05, | |
| "loss": 1.3345, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 49.86, | |
| "learning_rate": 2.544366197183099e-05, | |
| "loss": 1.3777, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.5373239436619717e-05, | |
| "loss": 1.3383, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 3.27095627784729, | |
| "eval_runtime": 131.6783, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9768592916372051, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 50.14, | |
| "learning_rate": 2.530281690140845e-05, | |
| "loss": 1.4179, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 50.28, | |
| "learning_rate": 2.523239436619718e-05, | |
| "loss": 1.4183, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 50.42, | |
| "learning_rate": 2.5161971830985913e-05, | |
| "loss": 1.3428, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 50.55, | |
| "learning_rate": 2.5091549295774648e-05, | |
| "loss": 1.3861, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 50.69, | |
| "learning_rate": 2.502112676056338e-05, | |
| "loss": 1.3596, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 50.83, | |
| "learning_rate": 2.4950704225352115e-05, | |
| "loss": 1.3923, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "learning_rate": 2.4880281690140847e-05, | |
| "loss": 1.3517, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 2.997406244277954, | |
| "eval_runtime": 129.9638, | |
| "eval_samples_per_second": 4.093, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.975573696728161, | |
| "step": 3672 | |
| }, | |
| { | |
| "epoch": 51.11, | |
| "learning_rate": 2.480985915492958e-05, | |
| "loss": 1.4026, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 51.25, | |
| "learning_rate": 2.473943661971831e-05, | |
| "loss": 1.3317, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 51.39, | |
| "learning_rate": 2.4669014084507046e-05, | |
| "loss": 1.3968, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 51.53, | |
| "learning_rate": 2.4598591549295778e-05, | |
| "loss": 1.3303, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 51.66, | |
| "learning_rate": 2.452816901408451e-05, | |
| "loss": 1.3477, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "learning_rate": 2.4457746478873242e-05, | |
| "loss": 1.3425, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 51.94, | |
| "learning_rate": 2.4387323943661974e-05, | |
| "loss": 1.3551, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 3.3179967403411865, | |
| "eval_runtime": 131.3646, | |
| "eval_samples_per_second": 4.05, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9751237385099955, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 52.08, | |
| "learning_rate": 2.4316901408450705e-05, | |
| "loss": 1.3972, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 52.22, | |
| "learning_rate": 2.4246478873239437e-05, | |
| "loss": 1.3394, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 52.36, | |
| "learning_rate": 2.417605633802817e-05, | |
| "loss": 1.3707, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 52.5, | |
| "learning_rate": 2.41056338028169e-05, | |
| "loss": 1.3463, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 52.64, | |
| "learning_rate": 2.4035211267605633e-05, | |
| "loss": 1.3658, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 52.78, | |
| "learning_rate": 2.3964788732394365e-05, | |
| "loss": 1.358, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 52.91, | |
| "learning_rate": 2.38943661971831e-05, | |
| "loss": 1.3493, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 2.6087403297424316, | |
| "eval_runtime": 130.8988, | |
| "eval_samples_per_second": 4.064, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9994214822909301, | |
| "step": 3816 | |
| }, | |
| { | |
| "epoch": 53.06, | |
| "learning_rate": 2.3823943661971832e-05, | |
| "loss": 1.4151, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "learning_rate": 2.3753521126760564e-05, | |
| "loss": 1.3187, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 2.3683098591549296e-05, | |
| "loss": 1.3759, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 53.47, | |
| "learning_rate": 2.3612676056338028e-05, | |
| "loss": 1.3332, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 53.61, | |
| "learning_rate": 2.3542253521126763e-05, | |
| "loss": 1.3438, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 53.75, | |
| "learning_rate": 2.3471830985915495e-05, | |
| "loss": 1.3296, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "learning_rate": 2.3401408450704227e-05, | |
| "loss": 1.3977, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 2.6875009536743164, | |
| "eval_runtime": 132.1432, | |
| "eval_samples_per_second": 4.026, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.9778234878189882, | |
| "step": 3888 | |
| }, | |
| { | |
| "epoch": 54.03, | |
| "learning_rate": 2.333098591549296e-05, | |
| "loss": 1.3677, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 54.17, | |
| "learning_rate": 2.326056338028169e-05, | |
| "loss": 1.3172, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 54.3, | |
| "learning_rate": 2.3190140845070422e-05, | |
| "loss": 1.362, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 54.44, | |
| "learning_rate": 2.3119718309859158e-05, | |
| "loss": 1.3375, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 54.58, | |
| "learning_rate": 2.304929577464789e-05, | |
| "loss": 1.3644, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 54.72, | |
| "learning_rate": 2.297887323943662e-05, | |
| "loss": 1.3165, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 54.86, | |
| "learning_rate": 2.2908450704225353e-05, | |
| "loss": 1.3723, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 2.2838028169014085e-05, | |
| "loss": 1.3254, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 3.3662502765655518, | |
| "eval_runtime": 130.7472, | |
| "eval_samples_per_second": 4.069, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9787234042553191, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 55.14, | |
| "learning_rate": 2.276760563380282e-05, | |
| "loss": 1.3937, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 55.28, | |
| "learning_rate": 2.2697183098591552e-05, | |
| "loss": 1.3371, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 55.42, | |
| "learning_rate": 2.2626760563380284e-05, | |
| "loss": 1.3096, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "learning_rate": 2.2556338028169016e-05, | |
| "loss": 1.3341, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 55.69, | |
| "learning_rate": 2.2485915492957748e-05, | |
| "loss": 1.3173, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 55.83, | |
| "learning_rate": 2.241549295774648e-05, | |
| "loss": 1.3174, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 2.2345070422535215e-05, | |
| "loss": 1.303, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 2.6154274940490723, | |
| "eval_runtime": 131.383, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9692100019283924, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 56.11, | |
| "learning_rate": 2.2274647887323943e-05, | |
| "loss": 1.337, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 56.25, | |
| "learning_rate": 2.2204225352112675e-05, | |
| "loss": 1.2723, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 56.39, | |
| "learning_rate": 2.2133802816901407e-05, | |
| "loss": 1.3505, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 2.2063380281690142e-05, | |
| "loss": 1.3265, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 56.66, | |
| "learning_rate": 2.1992957746478874e-05, | |
| "loss": 1.2951, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 2.1922535211267606e-05, | |
| "loss": 1.3154, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 56.94, | |
| "learning_rate": 2.1852112676056338e-05, | |
| "loss": 1.2612, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 3.2773284912109375, | |
| "eval_runtime": 131.5337, | |
| "eval_samples_per_second": 4.045, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9760879346917786, | |
| "step": 4104 | |
| }, | |
| { | |
| "epoch": 57.08, | |
| "learning_rate": 2.178169014084507e-05, | |
| "loss": 1.3172, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 57.22, | |
| "learning_rate": 2.1711267605633802e-05, | |
| "loss": 1.2591, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 57.36, | |
| "learning_rate": 2.1640845070422537e-05, | |
| "loss": 1.3305, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 57.5, | |
| "learning_rate": 2.157042253521127e-05, | |
| "loss": 1.2637, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 57.64, | |
| "learning_rate": 2.15e-05, | |
| "loss": 1.3198, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 57.78, | |
| "learning_rate": 2.1429577464788733e-05, | |
| "loss": 1.2798, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 57.91, | |
| "learning_rate": 2.1359154929577465e-05, | |
| "loss": 1.3161, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 2.902003765106201, | |
| "eval_runtime": 131.0979, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9717169120010285, | |
| "step": 4176 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "learning_rate": 2.12887323943662e-05, | |
| "loss": 1.3129, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 58.19, | |
| "learning_rate": 2.1218309859154932e-05, | |
| "loss": 1.2534, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "learning_rate": 2.1147887323943664e-05, | |
| "loss": 1.3106, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 58.47, | |
| "learning_rate": 2.1077464788732395e-05, | |
| "loss": 1.2513, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 58.61, | |
| "learning_rate": 2.1007042253521127e-05, | |
| "loss": 1.2999, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 58.75, | |
| "learning_rate": 2.093661971830986e-05, | |
| "loss": 1.2241, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "learning_rate": 2.0866197183098594e-05, | |
| "loss": 1.3026, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 3.151747703552246, | |
| "eval_runtime": 131.6083, | |
| "eval_samples_per_second": 4.042, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9708812753101498, | |
| "step": 4248 | |
| }, | |
| { | |
| "epoch": 59.03, | |
| "learning_rate": 2.0795774647887326e-05, | |
| "loss": 1.3299, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 59.17, | |
| "learning_rate": 2.0725352112676058e-05, | |
| "loss": 1.2785, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 59.3, | |
| "learning_rate": 2.065492957746479e-05, | |
| "loss": 1.2908, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 59.44, | |
| "learning_rate": 2.0584507042253522e-05, | |
| "loss": 1.2814, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 59.58, | |
| "learning_rate": 2.0514084507042254e-05, | |
| "loss": 1.2841, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 59.72, | |
| "learning_rate": 2.044366197183099e-05, | |
| "loss": 1.2436, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 59.86, | |
| "learning_rate": 2.037323943661972e-05, | |
| "loss": 1.3191, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.0302816901408453e-05, | |
| "loss": 1.262, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 3.129873752593994, | |
| "eval_runtime": 130.7498, | |
| "eval_samples_per_second": 4.069, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9674744488011827, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 60.14, | |
| "learning_rate": 2.0232394366197185e-05, | |
| "loss": 1.3176, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 60.28, | |
| "learning_rate": 2.0161971830985917e-05, | |
| "loss": 1.271, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 60.42, | |
| "learning_rate": 2.009154929577465e-05, | |
| "loss": 1.2509, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 60.55, | |
| "learning_rate": 2.002112676056338e-05, | |
| "loss": 1.2607, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 60.69, | |
| "learning_rate": 1.9950704225352112e-05, | |
| "loss": 1.2664, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 60.83, | |
| "learning_rate": 1.9880281690140844e-05, | |
| "loss": 1.318, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 60.97, | |
| "learning_rate": 1.9809859154929576e-05, | |
| "loss": 1.2885, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 3.1023097038269043, | |
| "eval_runtime": 130.9774, | |
| "eval_samples_per_second": 4.062, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9723597094555505, | |
| "step": 4392 | |
| }, | |
| { | |
| "epoch": 61.11, | |
| "learning_rate": 1.973943661971831e-05, | |
| "loss": 1.3469, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 61.25, | |
| "learning_rate": 1.9669014084507043e-05, | |
| "loss": 1.2218, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 61.39, | |
| "learning_rate": 1.9598591549295775e-05, | |
| "loss": 1.2931, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 61.53, | |
| "learning_rate": 1.9528169014084507e-05, | |
| "loss": 1.2769, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 61.66, | |
| "learning_rate": 1.945774647887324e-05, | |
| "loss": 1.2587, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "learning_rate": 1.9387323943661974e-05, | |
| "loss": 1.3005, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "learning_rate": 1.9316901408450706e-05, | |
| "loss": 1.2538, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 2.7857325077056885, | |
| "eval_runtime": 131.3498, | |
| "eval_samples_per_second": 4.05, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9877225686186283, | |
| "step": 4464 | |
| }, | |
| { | |
| "epoch": 62.08, | |
| "learning_rate": 1.9246478873239438e-05, | |
| "loss": 1.3198, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 1.917605633802817e-05, | |
| "loss": 1.2637, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 62.36, | |
| "learning_rate": 1.91056338028169e-05, | |
| "loss": 1.3048, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 1.9035211267605633e-05, | |
| "loss": 1.2401, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 62.64, | |
| "learning_rate": 1.896478873239437e-05, | |
| "loss": 1.2781, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 62.78, | |
| "learning_rate": 1.88943661971831e-05, | |
| "loss": 1.2786, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "learning_rate": 1.8823943661971832e-05, | |
| "loss": 1.2536, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 3.014954090118408, | |
| "eval_runtime": 130.7805, | |
| "eval_samples_per_second": 4.068, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9703670373465321, | |
| "step": 4536 | |
| }, | |
| { | |
| "epoch": 63.06, | |
| "learning_rate": 1.8753521126760564e-05, | |
| "loss": 1.321, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 63.19, | |
| "learning_rate": 1.8683098591549296e-05, | |
| "loss": 1.2476, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 63.33, | |
| "learning_rate": 1.861267605633803e-05, | |
| "loss": 1.2828, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 63.47, | |
| "learning_rate": 1.8542253521126763e-05, | |
| "loss": 1.2221, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 63.61, | |
| "learning_rate": 1.8471830985915495e-05, | |
| "loss": 1.3011, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 63.75, | |
| "learning_rate": 1.8401408450704227e-05, | |
| "loss": 1.2338, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "learning_rate": 1.833098591549296e-05, | |
| "loss": 1.3339, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 2.930506706237793, | |
| "eval_runtime": 130.9798, | |
| "eval_samples_per_second": 4.062, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9722311499646461, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 64.03, | |
| "learning_rate": 1.826056338028169e-05, | |
| "loss": 1.2729, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 64.17, | |
| "learning_rate": 1.8190140845070426e-05, | |
| "loss": 1.2463, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 64.3, | |
| "learning_rate": 1.8119718309859155e-05, | |
| "loss": 1.2679, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 64.44, | |
| "learning_rate": 1.8049295774647886e-05, | |
| "loss": 1.231, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 64.58, | |
| "learning_rate": 1.797887323943662e-05, | |
| "loss": 1.2748, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 64.72, | |
| "learning_rate": 1.790845070422535e-05, | |
| "loss": 1.2311, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 64.86, | |
| "learning_rate": 1.7838028169014085e-05, | |
| "loss": 1.2795, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 1.7767605633802817e-05, | |
| "loss": 1.2392, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 2.769491195678711, | |
| "eval_runtime": 130.6674, | |
| "eval_samples_per_second": 4.071, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9749308992736389, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 65.14, | |
| "learning_rate": 1.769718309859155e-05, | |
| "loss": 1.2914, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 65.28, | |
| "learning_rate": 1.762676056338028e-05, | |
| "loss": 1.2715, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 1.7556338028169013e-05, | |
| "loss": 1.2494, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 65.55, | |
| "learning_rate": 1.7485915492957748e-05, | |
| "loss": 1.2789, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 65.69, | |
| "learning_rate": 1.741549295774648e-05, | |
| "loss": 1.2381, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 65.83, | |
| "learning_rate": 1.7345070422535212e-05, | |
| "loss": 1.3185, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 65.97, | |
| "learning_rate": 1.7274647887323944e-05, | |
| "loss": 1.2572, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 2.867743730545044, | |
| "eval_runtime": 130.6545, | |
| "eval_samples_per_second": 4.072, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9688886032011313, | |
| "step": 4752 | |
| }, | |
| { | |
| "epoch": 66.11, | |
| "learning_rate": 1.7204225352112676e-05, | |
| "loss": 1.3039, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 66.25, | |
| "learning_rate": 1.7133802816901408e-05, | |
| "loss": 1.2112, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 1.7063380281690143e-05, | |
| "loss": 1.28, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 66.53, | |
| "learning_rate": 1.6992957746478875e-05, | |
| "loss": 1.2529, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "learning_rate": 1.6922535211267607e-05, | |
| "loss": 1.2379, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "learning_rate": 1.685211267605634e-05, | |
| "loss": 1.2651, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 66.94, | |
| "learning_rate": 1.678169014084507e-05, | |
| "loss": 1.2538, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 2.8597300052642822, | |
| "eval_runtime": 131.086, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.980523237127981, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 67.08, | |
| "learning_rate": 1.6711267605633806e-05, | |
| "loss": 1.295, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 67.22, | |
| "learning_rate": 1.6640845070422538e-05, | |
| "loss": 1.2451, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 67.36, | |
| "learning_rate": 1.657042253521127e-05, | |
| "loss": 1.2734, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 67.5, | |
| "learning_rate": 1.65e-05, | |
| "loss": 1.2301, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 67.64, | |
| "learning_rate": 1.6429577464788733e-05, | |
| "loss": 1.2834, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 67.78, | |
| "learning_rate": 1.6359154929577465e-05, | |
| "loss": 1.255, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 67.91, | |
| "learning_rate": 1.62887323943662e-05, | |
| "loss": 1.2355, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 2.8299758434295654, | |
| "eval_runtime": 131.2445, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9787876840007713, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 68.06, | |
| "learning_rate": 1.6218309859154932e-05, | |
| "loss": 1.2631, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 68.19, | |
| "learning_rate": 1.6147887323943664e-05, | |
| "loss": 1.2278, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 68.33, | |
| "learning_rate": 1.6077464788732396e-05, | |
| "loss": 1.2391, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 68.47, | |
| "learning_rate": 1.6007042253521128e-05, | |
| "loss": 1.2209, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 68.61, | |
| "learning_rate": 1.593661971830986e-05, | |
| "loss": 1.2971, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 68.75, | |
| "learning_rate": 1.586619718309859e-05, | |
| "loss": 1.2235, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "learning_rate": 1.5795774647887323e-05, | |
| "loss": 1.2682, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 2.701061248779297, | |
| "eval_runtime": 131.5603, | |
| "eval_samples_per_second": 4.044, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9741595423282123, | |
| "step": 4968 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 1.5725352112676055e-05, | |
| "loss": 1.2781, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 69.17, | |
| "learning_rate": 1.5654929577464787e-05, | |
| "loss": 1.2314, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 69.3, | |
| "learning_rate": 1.5584507042253522e-05, | |
| "loss": 1.2574, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 69.44, | |
| "learning_rate": 1.5514084507042254e-05, | |
| "loss": 1.247, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 69.58, | |
| "learning_rate": 1.5443661971830986e-05, | |
| "loss": 1.2494, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 69.72, | |
| "learning_rate": 1.5373239436619718e-05, | |
| "loss": 1.1997, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 69.86, | |
| "learning_rate": 1.530281690140845e-05, | |
| "loss": 1.2613, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 1.5232394366197183e-05, | |
| "loss": 1.2252, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 2.8321807384490967, | |
| "eval_runtime": 131.0272, | |
| "eval_samples_per_second": 4.06, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9722311499646461, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 70.14, | |
| "learning_rate": 1.5161971830985915e-05, | |
| "loss": 1.2647, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 70.28, | |
| "learning_rate": 1.5091549295774649e-05, | |
| "loss": 1.2388, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 70.42, | |
| "learning_rate": 1.502112676056338e-05, | |
| "loss": 1.2413, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 70.55, | |
| "learning_rate": 1.4950704225352113e-05, | |
| "loss": 1.2658, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 70.69, | |
| "learning_rate": 1.4880281690140846e-05, | |
| "loss": 1.1942, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 70.83, | |
| "learning_rate": 1.4809859154929578e-05, | |
| "loss": 1.2409, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "learning_rate": 1.4739436619718312e-05, | |
| "loss": 1.2085, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 2.740072727203369, | |
| "eval_runtime": 130.8975, | |
| "eval_samples_per_second": 4.064, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9710741145465064, | |
| "step": 5112 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 1.4669014084507044e-05, | |
| "loss": 1.2891, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 71.25, | |
| "learning_rate": 1.4598591549295775e-05, | |
| "loss": 1.2077, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 71.39, | |
| "learning_rate": 1.4528169014084509e-05, | |
| "loss": 1.2418, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 71.53, | |
| "learning_rate": 1.4457746478873241e-05, | |
| "loss": 1.2247, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 71.66, | |
| "learning_rate": 1.4387323943661973e-05, | |
| "loss": 1.2343, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 1.4316901408450706e-05, | |
| "loss": 1.2643, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 71.94, | |
| "learning_rate": 1.4246478873239438e-05, | |
| "loss": 1.2412, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 2.6227338314056396, | |
| "eval_runtime": 130.7815, | |
| "eval_samples_per_second": 4.068, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9762807739281353, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 72.08, | |
| "learning_rate": 1.417605633802817e-05, | |
| "loss": 1.2857, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 72.22, | |
| "learning_rate": 1.4105633802816904e-05, | |
| "loss": 1.2068, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 72.36, | |
| "learning_rate": 1.4035211267605636e-05, | |
| "loss": 1.2536, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 72.5, | |
| "learning_rate": 1.3964788732394367e-05, | |
| "loss": 1.2114, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 72.64, | |
| "learning_rate": 1.3894366197183098e-05, | |
| "loss": 1.2595, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 72.78, | |
| "learning_rate": 1.3823943661971831e-05, | |
| "loss": 1.209, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 72.91, | |
| "learning_rate": 1.3753521126760563e-05, | |
| "loss": 1.2148, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 2.714576244354248, | |
| "eval_runtime": 131.252, | |
| "eval_samples_per_second": 4.053, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9689528829465835, | |
| "step": 5256 | |
| }, | |
| { | |
| "epoch": 73.06, | |
| "learning_rate": 1.3683098591549295e-05, | |
| "loss": 1.2858, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 73.19, | |
| "learning_rate": 1.3612676056338028e-05, | |
| "loss": 1.2126, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 73.33, | |
| "learning_rate": 1.354225352112676e-05, | |
| "loss": 1.257, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 73.47, | |
| "learning_rate": 1.3471830985915492e-05, | |
| "loss": 1.2102, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 73.61, | |
| "learning_rate": 1.3401408450704226e-05, | |
| "loss": 1.2511, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 73.75, | |
| "learning_rate": 1.3330985915492958e-05, | |
| "loss": 1.2035, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "learning_rate": 1.326056338028169e-05, | |
| "loss": 1.2411, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 2.996312141418457, | |
| "eval_runtime": 131.4356, | |
| "eval_samples_per_second": 4.048, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.966317413383043, | |
| "step": 5328 | |
| }, | |
| { | |
| "epoch": 74.03, | |
| "learning_rate": 1.3190140845070423e-05, | |
| "loss": 1.2552, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 74.17, | |
| "learning_rate": 1.3119718309859155e-05, | |
| "loss": 1.2058, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 74.3, | |
| "learning_rate": 1.3049295774647889e-05, | |
| "loss": 1.2041, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 74.44, | |
| "learning_rate": 1.297887323943662e-05, | |
| "loss": 1.2125, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 74.58, | |
| "learning_rate": 1.2908450704225352e-05, | |
| "loss": 1.2323, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 74.72, | |
| "learning_rate": 1.2838028169014086e-05, | |
| "loss": 1.2222, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 74.86, | |
| "learning_rate": 1.2767605633802818e-05, | |
| "loss": 1.2527, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.269718309859155e-05, | |
| "loss": 1.2012, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 2.7940216064453125, | |
| "eval_runtime": 130.9397, | |
| "eval_samples_per_second": 4.063, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9655460564376165, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 75.14, | |
| "learning_rate": 1.2626760563380283e-05, | |
| "loss": 1.2865, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 75.28, | |
| "learning_rate": 1.2556338028169015e-05, | |
| "loss": 1.2463, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 75.42, | |
| "learning_rate": 1.2485915492957747e-05, | |
| "loss": 1.2363, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 75.55, | |
| "learning_rate": 1.241549295774648e-05, | |
| "loss": 1.2467, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 75.69, | |
| "learning_rate": 1.234507042253521e-05, | |
| "loss": 1.2138, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 75.83, | |
| "learning_rate": 1.2274647887323944e-05, | |
| "loss": 1.2144, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 75.97, | |
| "learning_rate": 1.2204225352112676e-05, | |
| "loss": 1.1969, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 2.621224880218506, | |
| "eval_runtime": 131.068, | |
| "eval_samples_per_second": 4.059, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9790448029825802, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 76.11, | |
| "learning_rate": 1.2133802816901408e-05, | |
| "loss": 1.276, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 76.25, | |
| "learning_rate": 1.2063380281690142e-05, | |
| "loss": 1.2038, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 76.39, | |
| "learning_rate": 1.1992957746478873e-05, | |
| "loss": 1.2469, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 76.53, | |
| "learning_rate": 1.1922535211267605e-05, | |
| "loss": 1.2184, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 76.66, | |
| "learning_rate": 1.1852112676056339e-05, | |
| "loss": 1.216, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 1.178169014084507e-05, | |
| "loss": 1.2265, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 76.94, | |
| "learning_rate": 1.1711267605633804e-05, | |
| "loss": 1.2004, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 2.8644309043884277, | |
| "eval_runtime": 131.1358, | |
| "eval_samples_per_second": 4.057, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9710741145465064, | |
| "step": 5544 | |
| }, | |
| { | |
| "epoch": 77.08, | |
| "learning_rate": 1.1640845070422536e-05, | |
| "loss": 1.2794, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 77.22, | |
| "learning_rate": 1.1570422535211268e-05, | |
| "loss": 1.1772, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 77.36, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 1.2421, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 77.5, | |
| "learning_rate": 1.1429577464788734e-05, | |
| "loss": 1.1951, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 77.64, | |
| "learning_rate": 1.1359154929577465e-05, | |
| "loss": 1.2643, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "learning_rate": 1.1288732394366197e-05, | |
| "loss": 1.232, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 77.91, | |
| "learning_rate": 1.121830985915493e-05, | |
| "loss": 1.2247, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 2.612703561782837, | |
| "eval_runtime": 131.1043, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9620749501831972, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 78.06, | |
| "learning_rate": 1.1147887323943663e-05, | |
| "loss": 1.2683, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 78.19, | |
| "learning_rate": 1.1077464788732395e-05, | |
| "loss": 1.198, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 78.33, | |
| "learning_rate": 1.1007042253521127e-05, | |
| "loss": 1.2199, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 78.47, | |
| "learning_rate": 1.093661971830986e-05, | |
| "loss": 1.1778, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 78.61, | |
| "learning_rate": 1.0866197183098592e-05, | |
| "loss": 1.2063, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 78.75, | |
| "learning_rate": 1.0795774647887324e-05, | |
| "loss": 1.1895, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "learning_rate": 1.0725352112676057e-05, | |
| "loss": 1.2791, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 2.653787136077881, | |
| "eval_runtime": 131.0838, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9719097512373851, | |
| "step": 5688 | |
| }, | |
| { | |
| "epoch": 79.03, | |
| "learning_rate": 1.065492957746479e-05, | |
| "loss": 1.2484, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 79.17, | |
| "learning_rate": 1.0584507042253521e-05, | |
| "loss": 1.2304, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 79.3, | |
| "learning_rate": 1.0514084507042255e-05, | |
| "loss": 1.2353, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 79.44, | |
| "learning_rate": 1.0443661971830987e-05, | |
| "loss": 1.1799, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 79.58, | |
| "learning_rate": 1.037323943661972e-05, | |
| "loss": 1.2419, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 79.72, | |
| "learning_rate": 1.030281690140845e-05, | |
| "loss": 1.2154, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 79.86, | |
| "learning_rate": 1.0232394366197182e-05, | |
| "loss": 1.2384, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.0161971830985916e-05, | |
| "loss": 1.1867, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 2.7778642177581787, | |
| "eval_runtime": 129.0244, | |
| "eval_samples_per_second": 4.123, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.9586681236742303, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 80.14, | |
| "learning_rate": 1.0091549295774648e-05, | |
| "loss": 1.259, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 80.28, | |
| "learning_rate": 1.0021126760563381e-05, | |
| "loss": 1.2021, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 80.42, | |
| "learning_rate": 9.950704225352113e-06, | |
| "loss": 1.2074, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 80.55, | |
| "learning_rate": 9.880281690140845e-06, | |
| "loss": 1.2142, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 80.69, | |
| "learning_rate": 9.809859154929579e-06, | |
| "loss": 1.1929, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 80.83, | |
| "learning_rate": 9.73943661971831e-06, | |
| "loss": 1.2238, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 80.97, | |
| "learning_rate": 9.669014084507042e-06, | |
| "loss": 1.1992, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 2.829700231552124, | |
| "eval_runtime": 128.7334, | |
| "eval_samples_per_second": 4.133, | |
| "eval_steps_per_second": 0.52, | |
| "eval_wer": 0.9643247412740246, | |
| "step": 5832 | |
| }, | |
| { | |
| "epoch": 81.11, | |
| "learning_rate": 9.598591549295776e-06, | |
| "loss": 1.2484, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 81.25, | |
| "learning_rate": 9.528169014084508e-06, | |
| "loss": 1.2018, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 81.39, | |
| "learning_rate": 9.45774647887324e-06, | |
| "loss": 1.2252, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 81.53, | |
| "learning_rate": 9.387323943661973e-06, | |
| "loss": 1.1984, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 81.66, | |
| "learning_rate": 9.316901408450705e-06, | |
| "loss": 1.198, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 81.8, | |
| "learning_rate": 9.246478873239437e-06, | |
| "loss": 1.2184, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 81.94, | |
| "learning_rate": 9.176056338028169e-06, | |
| "loss": 1.1833, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 2.850757122039795, | |
| "eval_runtime": 128.577, | |
| "eval_samples_per_second": 4.138, | |
| "eval_steps_per_second": 0.521, | |
| "eval_wer": 0.9722954297100983, | |
| "step": 5904 | |
| }, | |
| { | |
| "epoch": 82.08, | |
| "learning_rate": 9.1056338028169e-06, | |
| "loss": 1.2571, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 82.22, | |
| "learning_rate": 9.035211267605634e-06, | |
| "loss": 1.1955, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 82.36, | |
| "learning_rate": 8.964788732394366e-06, | |
| "loss": 1.2139, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 82.5, | |
| "learning_rate": 8.894366197183098e-06, | |
| "loss": 1.1704, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 82.64, | |
| "learning_rate": 8.823943661971832e-06, | |
| "loss": 1.2177, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 82.78, | |
| "learning_rate": 8.753521126760563e-06, | |
| "loss": 1.2016, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 82.91, | |
| "learning_rate": 8.683098591549297e-06, | |
| "loss": 1.2092, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 2.8260996341705322, | |
| "eval_runtime": 128.9666, | |
| "eval_samples_per_second": 4.125, | |
| "eval_steps_per_second": 0.52, | |
| "eval_wer": 0.9690171626920357, | |
| "step": 5976 | |
| }, | |
| { | |
| "epoch": 83.06, | |
| "learning_rate": 8.612676056338029e-06, | |
| "loss": 1.2366, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 83.19, | |
| "learning_rate": 8.54225352112676e-06, | |
| "loss": 1.1923, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 8.471830985915494e-06, | |
| "loss": 1.205, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 83.47, | |
| "learning_rate": 8.401408450704226e-06, | |
| "loss": 1.1998, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 83.61, | |
| "learning_rate": 8.330985915492958e-06, | |
| "loss": 1.2067, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 83.75, | |
| "learning_rate": 8.260563380281692e-06, | |
| "loss": 1.1848, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 83.89, | |
| "learning_rate": 8.190140845070422e-06, | |
| "loss": 1.2215, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 2.599538564682007, | |
| "eval_runtime": 128.5443, | |
| "eval_samples_per_second": 4.139, | |
| "eval_steps_per_second": 0.521, | |
| "eval_wer": 0.9717169120010285, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 84.03, | |
| "learning_rate": 8.119718309859155e-06, | |
| "loss": 1.229, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 84.17, | |
| "learning_rate": 8.049295774647887e-06, | |
| "loss": 1.1939, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 84.3, | |
| "learning_rate": 7.97887323943662e-06, | |
| "loss": 1.2002, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 7.908450704225353e-06, | |
| "loss": 1.1931, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 84.58, | |
| "learning_rate": 7.838028169014085e-06, | |
| "loss": 1.1964, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 84.72, | |
| "learning_rate": 7.767605633802817e-06, | |
| "loss": 1.169, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 84.86, | |
| "learning_rate": 7.69718309859155e-06, | |
| "loss": 1.208, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 7.626760563380282e-06, | |
| "loss": 1.1966, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 2.7658963203430176, | |
| "eval_runtime": 128.9084, | |
| "eval_samples_per_second": 4.127, | |
| "eval_steps_per_second": 0.52, | |
| "eval_wer": 0.9677315677829916, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 85.14, | |
| "learning_rate": 7.556338028169015e-06, | |
| "loss": 1.242, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 85.28, | |
| "learning_rate": 7.485915492957747e-06, | |
| "loss": 1.2057, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 85.42, | |
| "learning_rate": 7.415492957746479e-06, | |
| "loss": 1.2159, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 85.55, | |
| "learning_rate": 7.345070422535212e-06, | |
| "loss": 1.2113, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 85.69, | |
| "learning_rate": 7.274647887323945e-06, | |
| "loss": 1.1814, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 85.83, | |
| "learning_rate": 7.2042253521126775e-06, | |
| "loss": 1.2145, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 85.97, | |
| "learning_rate": 7.1338028169014085e-06, | |
| "loss": 1.1774, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 2.628901243209839, | |
| "eval_runtime": 131.7057, | |
| "eval_samples_per_second": 4.039, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9703027576010799, | |
| "step": 6192 | |
| }, | |
| { | |
| "epoch": 86.11, | |
| "learning_rate": 7.06338028169014e-06, | |
| "loss": 1.2575, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 86.25, | |
| "learning_rate": 6.992957746478873e-06, | |
| "loss": 1.1787, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 86.39, | |
| "learning_rate": 6.922535211267606e-06, | |
| "loss": 1.2204, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 86.53, | |
| "learning_rate": 6.8521126760563385e-06, | |
| "loss": 1.1907, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 86.66, | |
| "learning_rate": 6.78169014084507e-06, | |
| "loss": 1.2021, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 86.8, | |
| "learning_rate": 6.711267605633803e-06, | |
| "loss": 1.1983, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 86.94, | |
| "learning_rate": 6.640845070422536e-06, | |
| "loss": 1.2002, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 2.719727039337158, | |
| "eval_runtime": 128.6644, | |
| "eval_samples_per_second": 4.135, | |
| "eval_steps_per_second": 0.521, | |
| "eval_wer": 0.9775020890917272, | |
| "step": 6264 | |
| }, | |
| { | |
| "epoch": 87.08, | |
| "learning_rate": 6.570422535211268e-06, | |
| "loss": 1.2199, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 87.22, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 1.1853, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 87.36, | |
| "learning_rate": 6.429577464788733e-06, | |
| "loss": 1.2159, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 6.359154929577466e-06, | |
| "loss": 1.1772, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 87.64, | |
| "learning_rate": 6.288732394366198e-06, | |
| "loss": 1.2092, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 87.78, | |
| "learning_rate": 6.21830985915493e-06, | |
| "loss": 1.1923, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 87.91, | |
| "learning_rate": 6.147887323943662e-06, | |
| "loss": 1.2035, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 2.6153945922851562, | |
| "eval_runtime": 128.668, | |
| "eval_samples_per_second": 4.135, | |
| "eval_steps_per_second": 0.521, | |
| "eval_wer": 0.9778234878189882, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 88.06, | |
| "learning_rate": 6.077464788732395e-06, | |
| "loss": 1.2339, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 88.19, | |
| "learning_rate": 6.007042253521127e-06, | |
| "loss": 1.1986, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 88.33, | |
| "learning_rate": 5.93661971830986e-06, | |
| "loss": 1.1895, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 88.47, | |
| "learning_rate": 5.8661971830985916e-06, | |
| "loss": 1.1787, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 88.61, | |
| "learning_rate": 5.795774647887324e-06, | |
| "loss": 1.202, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 88.75, | |
| "learning_rate": 5.725352112676056e-06, | |
| "loss": 1.1641, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 5.654929577464789e-06, | |
| "loss": 1.2219, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 2.6426045894622803, | |
| "eval_runtime": 130.6768, | |
| "eval_samples_per_second": 4.071, | |
| "eval_steps_per_second": 0.513, | |
| "eval_wer": 0.9760879346917786, | |
| "step": 6408 | |
| }, | |
| { | |
| "epoch": 89.03, | |
| "learning_rate": 5.584507042253522e-06, | |
| "loss": 1.2101, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 89.17, | |
| "learning_rate": 5.514084507042254e-06, | |
| "loss": 1.1915, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 89.3, | |
| "learning_rate": 5.443661971830986e-06, | |
| "loss": 1.1973, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 89.44, | |
| "learning_rate": 5.373239436619719e-06, | |
| "loss": 1.1821, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 89.58, | |
| "learning_rate": 5.302816901408451e-06, | |
| "loss": 1.1799, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 89.72, | |
| "learning_rate": 5.2323943661971835e-06, | |
| "loss": 1.181, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 89.86, | |
| "learning_rate": 5.161971830985915e-06, | |
| "loss": 1.2013, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 5.091549295774648e-06, | |
| "loss": 1.1724, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 2.599557399749756, | |
| "eval_runtime": 132.1227, | |
| "eval_samples_per_second": 4.027, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.9801375586552677, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 90.14, | |
| "learning_rate": 5.021126760563381e-06, | |
| "loss": 1.2122, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 90.28, | |
| "learning_rate": 4.950704225352113e-06, | |
| "loss": 1.1918, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 90.42, | |
| "learning_rate": 4.8802816901408454e-06, | |
| "loss": 1.1766, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 90.55, | |
| "learning_rate": 4.809859154929577e-06, | |
| "loss": 1.1855, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 90.69, | |
| "learning_rate": 4.73943661971831e-06, | |
| "loss": 1.1743, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 90.83, | |
| "learning_rate": 4.669014084507043e-06, | |
| "loss": 1.2096, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 90.97, | |
| "learning_rate": 4.598591549295775e-06, | |
| "loss": 1.1832, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 2.731451988220215, | |
| "eval_runtime": 131.0173, | |
| "eval_samples_per_second": 4.061, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9742881018191168, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 91.11, | |
| "learning_rate": 4.528169014084507e-06, | |
| "loss": 1.2037, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 91.25, | |
| "learning_rate": 4.45774647887324e-06, | |
| "loss": 1.1731, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 91.39, | |
| "learning_rate": 4.387323943661972e-06, | |
| "loss": 1.2071, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 91.53, | |
| "learning_rate": 4.316901408450704e-06, | |
| "loss": 1.1664, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 91.66, | |
| "learning_rate": 4.2464788732394366e-06, | |
| "loss": 1.1692, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 91.8, | |
| "learning_rate": 4.176056338028169e-06, | |
| "loss": 1.191, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 91.94, | |
| "learning_rate": 4.105633802816901e-06, | |
| "loss": 1.1759, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 2.5726349353790283, | |
| "eval_runtime": 131.726, | |
| "eval_samples_per_second": 4.039, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9965288937455807, | |
| "step": 6624 | |
| }, | |
| { | |
| "epoch": 92.08, | |
| "learning_rate": 4.035211267605634e-06, | |
| "loss": 1.2287, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 92.22, | |
| "learning_rate": 3.964788732394367e-06, | |
| "loss": 1.1849, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 92.36, | |
| "learning_rate": 3.894366197183099e-06, | |
| "loss": 1.2151, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 92.5, | |
| "learning_rate": 3.823943661971831e-06, | |
| "loss": 1.1783, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 92.64, | |
| "learning_rate": 3.753521126760563e-06, | |
| "loss": 1.1818, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 92.78, | |
| "learning_rate": 3.683098591549296e-06, | |
| "loss": 1.1783, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 92.91, | |
| "learning_rate": 3.612676056338028e-06, | |
| "loss": 1.1638, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 2.6569957733154297, | |
| "eval_runtime": 131.2307, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9865012534550364, | |
| "step": 6696 | |
| }, | |
| { | |
| "epoch": 93.06, | |
| "learning_rate": 3.542253521126761e-06, | |
| "loss": 1.2044, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 93.19, | |
| "learning_rate": 3.471830985915493e-06, | |
| "loss": 1.1595, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 93.33, | |
| "learning_rate": 3.401408450704226e-06, | |
| "loss": 1.188, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 93.47, | |
| "learning_rate": 3.330985915492958e-06, | |
| "loss": 1.1614, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 93.61, | |
| "learning_rate": 3.26056338028169e-06, | |
| "loss": 1.1906, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 93.75, | |
| "learning_rate": 3.1901408450704223e-06, | |
| "loss": 1.1665, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "learning_rate": 3.119718309859155e-06, | |
| "loss": 1.1872, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 2.6414103507995605, | |
| "eval_runtime": 131.1073, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9947933406183711, | |
| "step": 6768 | |
| }, | |
| { | |
| "epoch": 94.03, | |
| "learning_rate": 3.0492957746478873e-06, | |
| "loss": 1.2089, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 94.17, | |
| "learning_rate": 2.97887323943662e-06, | |
| "loss": 1.1699, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 94.3, | |
| "learning_rate": 2.9084507042253524e-06, | |
| "loss": 1.1739, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 94.44, | |
| "learning_rate": 2.8380281690140847e-06, | |
| "loss": 1.1663, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 94.58, | |
| "learning_rate": 2.767605633802817e-06, | |
| "loss": 1.1771, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 94.72, | |
| "learning_rate": 2.6971830985915497e-06, | |
| "loss": 1.1685, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 94.86, | |
| "learning_rate": 2.6267605633802816e-06, | |
| "loss": 1.2045, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 2.5563380281690143e-06, | |
| "loss": 1.144, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 2.6263763904571533, | |
| "eval_runtime": 131.0288, | |
| "eval_samples_per_second": 4.06, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9863084142186797, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 95.14, | |
| "learning_rate": 2.4859154929577466e-06, | |
| "loss": 1.2542, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 95.28, | |
| "learning_rate": 2.4154929577464793e-06, | |
| "loss": 1.1588, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 95.42, | |
| "learning_rate": 2.345070422535211e-06, | |
| "loss": 1.1804, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 95.55, | |
| "learning_rate": 2.274647887323944e-06, | |
| "loss": 1.1847, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 95.69, | |
| "learning_rate": 2.204225352112676e-06, | |
| "loss": 1.1723, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 95.83, | |
| "learning_rate": 2.1338028169014085e-06, | |
| "loss": 1.1867, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 95.97, | |
| "learning_rate": 2.063380281690141e-06, | |
| "loss": 1.1636, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 2.5819830894470215, | |
| "eval_runtime": 130.9251, | |
| "eval_samples_per_second": 4.063, | |
| "eval_steps_per_second": 0.512, | |
| "eval_wer": 0.9917721925821174, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 96.11, | |
| "learning_rate": 1.9929577464788735e-06, | |
| "loss": 1.2053, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 96.25, | |
| "learning_rate": 1.922535211267606e-06, | |
| "loss": 1.1621, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "learning_rate": 1.8521126760563383e-06, | |
| "loss": 1.1944, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 96.53, | |
| "learning_rate": 1.7816901408450704e-06, | |
| "loss": 1.1547, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 96.66, | |
| "learning_rate": 1.711267605633803e-06, | |
| "loss": 1.1609, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 96.8, | |
| "learning_rate": 1.6408450704225354e-06, | |
| "loss": 1.1928, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 96.94, | |
| "learning_rate": 1.5704225352112675e-06, | |
| "loss": 1.1714, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 2.596989870071411, | |
| "eval_runtime": 130.9899, | |
| "eval_samples_per_second": 4.061, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.991322234363952, | |
| "step": 6984 | |
| }, | |
| { | |
| "epoch": 97.08, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.211, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 97.22, | |
| "learning_rate": 1.4295774647887325e-06, | |
| "loss": 1.1678, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 97.36, | |
| "learning_rate": 1.3591549295774648e-06, | |
| "loss": 1.185, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 97.5, | |
| "learning_rate": 1.2887323943661974e-06, | |
| "loss": 1.1638, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 97.64, | |
| "learning_rate": 1.2183098591549297e-06, | |
| "loss": 1.1858, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 97.78, | |
| "learning_rate": 1.1478873239436622e-06, | |
| "loss": 1.1571, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 97.91, | |
| "learning_rate": 1.0774647887323945e-06, | |
| "loss": 1.1943, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 2.6308441162109375, | |
| "eval_runtime": 131.2345, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.9894581217458379, | |
| "step": 7056 | |
| }, | |
| { | |
| "epoch": 98.06, | |
| "learning_rate": 1.007042253521127e-06, | |
| "loss": 1.194, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 98.19, | |
| "learning_rate": 9.366197183098592e-07, | |
| "loss": 1.1703, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 98.33, | |
| "learning_rate": 8.661971830985915e-07, | |
| "loss": 1.1724, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 98.47, | |
| "learning_rate": 7.95774647887324e-07, | |
| "loss": 1.1557, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 98.61, | |
| "learning_rate": 7.253521126760564e-07, | |
| "loss": 1.1746, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 98.75, | |
| "learning_rate": 6.549295774647888e-07, | |
| "loss": 1.1476, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "learning_rate": 5.845070422535212e-07, | |
| "loss": 1.185, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 2.637880325317383, | |
| "eval_runtime": 131.2546, | |
| "eval_samples_per_second": 4.053, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.9898438002185511, | |
| "step": 7128 | |
| }, | |
| { | |
| "epoch": 99.03, | |
| "learning_rate": 5.140845070422535e-07, | |
| "loss": 1.2175, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 99.17, | |
| "learning_rate": 4.436619718309859e-07, | |
| "loss": 1.1628, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 99.3, | |
| "learning_rate": 3.7323943661971836e-07, | |
| "loss": 1.1645, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 99.44, | |
| "learning_rate": 3.0281690140845076e-07, | |
| "loss": 1.1748, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 99.58, | |
| "learning_rate": 2.323943661971831e-07, | |
| "loss": 1.164, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 99.72, | |
| "learning_rate": 1.619718309859155e-07, | |
| "loss": 1.1703, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 99.86, | |
| "learning_rate": 9.154929577464789e-08, | |
| "loss": 1.183, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 2.1126760563380285e-08, | |
| "loss": 1.1569, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 2.6330785751342773, | |
| "eval_runtime": 131.615, | |
| "eval_samples_per_second": 4.042, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.9906151571639776, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 7200, | |
| "total_flos": 2.7202925310621965e+20, | |
| "train_loss": 1.475777028269238, | |
| "train_runtime": 191216.7272, | |
| "train_samples_per_second": 2.415, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "max_steps": 7200, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.7202925310621965e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |