| { | |
| "best_metric": 0.3336529726456041, | |
| "best_model_checkpoint": "/workspace/data2/el/wav2vec2-large-xlsr-greek/checkpoint-9280", | |
| "epoch": 39.99784946236559, | |
| "global_step": 9280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00015, | |
| "loss": 18.1246, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0003, | |
| "loss": 16.1703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002946428571428571, | |
| "loss": 6.2477, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00028928571428571425, | |
| "loss": 3.5827, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00028392857142857137, | |
| "loss": 3.2333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00027857142857142854, | |
| "loss": 3.1704, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002732142857142857, | |
| "loss": 3.1395, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00026785714285714287, | |
| "loss": 3.1397, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002625, | |
| "loss": 3.1298, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002571428571428571, | |
| "loss": 3.1082, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00025178571428571426, | |
| "loss": 3.0917, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.068535089492798, | |
| "eval_runtime": 645.4744, | |
| "eval_samples_per_second": 2.358, | |
| "eval_wer": 1.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002464285714285714, | |
| "loss": 3.2085, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00024107142857142857, | |
| "loss": 3.0118, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00023571428571428569, | |
| "loss": 3.0139, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00023035714285714285, | |
| "loss": 3.0176, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.000225, | |
| "loss": 2.9979, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0002196428571428571, | |
| "loss": 2.9721, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00021428571428571427, | |
| "loss": 2.9585, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002089285714285714, | |
| "loss": 2.9578, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00020357142857142856, | |
| "loss": 2.9347, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0001982142857142857, | |
| "loss": 2.9348, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00019285714285714286, | |
| "loss": 2.9156, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00018749999999999998, | |
| "loss": 2.8911, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.9123377799987793, | |
| "eval_runtime": 651.1025, | |
| "eval_samples_per_second": 2.338, | |
| "eval_wer": 1.0, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00018214285714285712, | |
| "loss": 3.002, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00017678571428571428, | |
| "loss": 2.7696, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0001714285714285714, | |
| "loss": 2.6308, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00016607142857142857, | |
| "loss": 2.3949, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0001607142857142857, | |
| "loss": 2.0719, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00015535714285714285, | |
| "loss": 1.7915, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.00015, | |
| "loss": 1.5479, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00014464285714285713, | |
| "loss": 1.4167, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00013928571428571427, | |
| "loss": 1.2183, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00013392857142857144, | |
| "loss": 1.1713, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.00012857142857142855, | |
| "loss": 1.0325, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.8776374459266663, | |
| "eval_runtime": 651.452, | |
| "eval_samples_per_second": 2.336, | |
| "eval_wer": 0.8105380034319168, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0001232142857142857, | |
| "loss": 0.9978, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00011785714285714284, | |
| "loss": 0.8941, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.875, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00010714285714285714, | |
| "loss": 0.801, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00010178571428571428, | |
| "loss": 0.7847, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.642857142857143e-05, | |
| "loss": 0.6949, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 9.107142857142856e-05, | |
| "loss": 0.7307, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 8.57142857142857e-05, | |
| "loss": 0.6729, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 8.035714285714285e-05, | |
| "loss": 0.6699, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.6768, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.964285714285713e-05, | |
| "loss": 0.6459, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.428571428571427e-05, | |
| "loss": 0.6589, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.6442593336105347, | |
| "eval_runtime": 653.4327, | |
| "eval_samples_per_second": 2.329, | |
| "eval_wer": 0.7133340062582013, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 5.892857142857142e-05, | |
| "loss": 0.6647, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.357142857142857e-05, | |
| "loss": 0.6859, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.8214285714285716e-05, | |
| "loss": 0.6298, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.285714285714285e-05, | |
| "loss": 0.6076, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.5485, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.214285714285714e-05, | |
| "loss": 0.5852, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2.6785714285714284e-05, | |
| "loss": 0.5452, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.1428571428571425e-05, | |
| "loss": 0.5593, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.607142857142857e-05, | |
| "loss": 0.5316, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.0714285714285712e-05, | |
| "loss": 0.5742, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 5.357142857142856e-06, | |
| "loss": 0.5978, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5398, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.6011346578598022, | |
| "eval_runtime": 660.5778, | |
| "eval_samples_per_second": 2.304, | |
| "eval_wer": 0.687998384980317, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.0002005813953488372, | |
| "loss": 0.5457, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.00019883720930232555, | |
| "loss": 0.5124, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.00019709302325581393, | |
| "loss": 0.5249, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 0.00019534883720930232, | |
| "loss": 0.5133, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00019360465116279068, | |
| "loss": 0.5288, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 0.00019186046511627906, | |
| "loss": 0.544, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00019011627906976742, | |
| "loss": 0.5013, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.0001883720930232558, | |
| "loss": 0.4729, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.00018662790697674417, | |
| "loss": 0.5257, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.00018488372093023253, | |
| "loss": 0.5418, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 0.00018313953488372092, | |
| "loss": 0.4751, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.5606071352958679, | |
| "eval_runtime": 650.6852, | |
| "eval_samples_per_second": 2.339, | |
| "eval_wer": 0.630766124962148, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00018139534883720928, | |
| "loss": 0.5154, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00017965116279069763, | |
| "loss": 0.4327, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.00017790697674418605, | |
| "loss": 0.4265, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.0001761627906976744, | |
| "loss": 0.4695, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 0.0001744186046511628, | |
| "loss": 0.4606, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.00017267441860465115, | |
| "loss": 0.4286, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.0001709302325581395, | |
| "loss": 0.4215, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 0.0001691860465116279, | |
| "loss": 0.4614, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00016744186046511626, | |
| "loss": 0.4296, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00016569767441860464, | |
| "loss": 0.4462, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.000163953488372093, | |
| "loss": 0.4255, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.00016220930232558136, | |
| "loss": 0.4463, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.5151863694190979, | |
| "eval_runtime": 657.3854, | |
| "eval_samples_per_second": 2.315, | |
| "eval_wer": 0.5907943878066014, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 0.00016046511627906975, | |
| "loss": 0.4279, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.00015872093023255814, | |
| "loss": 0.3671, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 0.00015697674418604652, | |
| "loss": 0.3694, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.00015523255813953488, | |
| "loss": 0.3549, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 0.00015348837209302324, | |
| "loss": 0.3853, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 0.00015174418604651163, | |
| "loss": 0.3637, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.00015, | |
| "loss": 0.3457, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.00014825581395348835, | |
| "loss": 0.3741, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.00014651162790697673, | |
| "loss": 0.3726, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.00014476744186046512, | |
| "loss": 0.3297, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.00014302325581395348, | |
| "loss": 0.3659, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.4685789942741394, | |
| "eval_runtime": 658.0802, | |
| "eval_samples_per_second": 2.313, | |
| "eval_wer": 0.5541536287473504, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 0.00014127906976744184, | |
| "loss": 0.37, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 0.00013953488372093022, | |
| "loss": 0.3217, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.00013779069767441858, | |
| "loss": 0.3995, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 0.00013604651162790697, | |
| "loss": 0.351, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 0.00013430232558139533, | |
| "loss": 0.298, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00013255813953488372, | |
| "loss": 0.2876, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.00013081395348837207, | |
| "loss": 0.3023, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 0.00012906976744186046, | |
| "loss": 0.2861, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 0.00012732558139534882, | |
| "loss": 0.3058, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 0.0001255813953488372, | |
| "loss": 0.3048, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 0.00012383720930232557, | |
| "loss": 0.3093, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 0.00012209302325581395, | |
| "loss": 0.2921, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.4716265797615051, | |
| "eval_runtime": 661.023, | |
| "eval_samples_per_second": 2.302, | |
| "eval_wer": 0.5510245281114363, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 0.00012034883720930231, | |
| "loss": 0.2875, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00011860465116279069, | |
| "loss": 0.2854, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 0.00011686046511627907, | |
| "loss": 0.2508, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 0.00011511627906976743, | |
| "loss": 0.2777, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 0.0001133720930232558, | |
| "loss": 0.3192, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 0.00011162790697674418, | |
| "loss": 0.2474, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00010988372093023255, | |
| "loss": 0.2736, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 0.00010813953488372091, | |
| "loss": 0.2469, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.0001063953488372093, | |
| "loss": 0.2496, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 0.00010465116279069767, | |
| "loss": 0.2333, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 0.00010290697674418604, | |
| "loss": 0.262, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0001011627906976744, | |
| "loss": 0.2861, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.4394018054008484, | |
| "eval_runtime": 663.2479, | |
| "eval_samples_per_second": 2.295, | |
| "eval_wer": 0.5216513576259211, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 9.941860465116277e-05, | |
| "loss": 0.2817, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 9.767441860465116e-05, | |
| "loss": 0.257, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 9.593023255813953e-05, | |
| "loss": 0.2181, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 9.41860465116279e-05, | |
| "loss": 0.2173, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 9.244186046511626e-05, | |
| "loss": 0.261, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 9.069767441860464e-05, | |
| "loss": 0.1942, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 8.895348837209302e-05, | |
| "loss": 0.2252, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 8.72093023255814e-05, | |
| "loss": 0.2256, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 8.546511627906976e-05, | |
| "loss": 0.2071, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 8.372093023255813e-05, | |
| "loss": 0.2457, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 8.19767441860465e-05, | |
| "loss": 0.221, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.42013201117515564, | |
| "eval_runtime": 666.5166, | |
| "eval_samples_per_second": 2.284, | |
| "eval_wer": 0.508731200161502, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 8.023255813953487e-05, | |
| "loss": 0.2529, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 7.848837209302326e-05, | |
| "loss": 0.1994, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 7.674418604651162e-05, | |
| "loss": 0.2158, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.1888, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 7.325581395348837e-05, | |
| "loss": 0.2134, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 7.151162790697674e-05, | |
| "loss": 0.2182, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 6.976744186046511e-05, | |
| "loss": 0.2357, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 6.802325581395348e-05, | |
| "loss": 0.2091, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 6.627906976744186e-05, | |
| "loss": 0.1894, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 6.453488372093023e-05, | |
| "loss": 0.205, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 6.27906976744186e-05, | |
| "loss": 0.1775, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 6.104651162790698e-05, | |
| "loss": 0.1736, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.43105581402778625, | |
| "eval_runtime": 661.3357, | |
| "eval_samples_per_second": 2.301, | |
| "eval_wer": 0.49934389825375997, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 5.930232558139534e-05, | |
| "loss": 0.1956, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 5.7558139534883715e-05, | |
| "loss": 0.1675, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 5.581395348837209e-05, | |
| "loss": 0.2014, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 5.4069767441860454e-05, | |
| "loss": 0.1966, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 5.2325581395348834e-05, | |
| "loss": 0.1837, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 5.05813953488372e-05, | |
| "loss": 0.1972, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 4.883720930232558e-05, | |
| "loss": 0.1936, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 4.709302325581395e-05, | |
| "loss": 0.172, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 4.534883720930232e-05, | |
| "loss": 0.2008, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 4.36046511627907e-05, | |
| "loss": 0.1668, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 4.1860465116279065e-05, | |
| "loss": 0.1796, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.4192411005496979, | |
| "eval_runtime": 664.4607, | |
| "eval_samples_per_second": 2.291, | |
| "eval_wer": 0.48299182396285456, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 4.011627906976744e-05, | |
| "loss": 0.185, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 3.837209302325581e-05, | |
| "loss": 0.1469, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 3.662790697674418e-05, | |
| "loss": 0.2046, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 3.4883720930232556e-05, | |
| "loss": 0.1514, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 3.313953488372093e-05, | |
| "loss": 0.1649, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 3.13953488372093e-05, | |
| "loss": 0.1787, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 2.965116279069767e-05, | |
| "loss": 0.1808, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 2.7906976744186044e-05, | |
| "loss": 0.1292, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 2.6162790697674417e-05, | |
| "loss": 0.1767, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 2.441860465116279e-05, | |
| "loss": 0.1596, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 2.267441860465116e-05, | |
| "loss": 0.2036, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 2.0930232558139532e-05, | |
| "loss": 0.1593, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.42025962471961975, | |
| "eval_runtime": 664.1839, | |
| "eval_samples_per_second": 2.292, | |
| "eval_wer": 0.4830927626930453, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 1.9186046511627905e-05, | |
| "loss": 0.1429, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 1.7441860465116278e-05, | |
| "loss": 0.1558, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 1.569767441860465e-05, | |
| "loss": 0.1598, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 1.3953488372093022e-05, | |
| "loss": 0.1598, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "learning_rate": 1.2209302325581395e-05, | |
| "loss": 0.1742, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 1.0465116279069766e-05, | |
| "loss": 0.1402, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 8.720930232558139e-06, | |
| "loss": 0.163, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 6.976744186046511e-06, | |
| "loss": 0.2057, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 5.232558139534883e-06, | |
| "loss": 0.157, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 3.4883720930232555e-06, | |
| "loss": 0.1471, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 1.7441860465116278e-06, | |
| "loss": 0.2013, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.167, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.417759507894516, | |
| "eval_runtime": 663.3111, | |
| "eval_samples_per_second": 2.295, | |
| "eval_wer": 0.47945896840617747, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 0.00018766233766233763, | |
| "loss": 0.7294, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.00018701298701298698, | |
| "loss": 0.521, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.00018636363636363634, | |
| "loss": 0.4495, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 0.4751, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 0.00018506493506493507, | |
| "loss": 0.3635, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.0001844155844155844, | |
| "loss": 0.3542, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.00018376623376623375, | |
| "loss": 0.3538, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.0001831168831168831, | |
| "loss": 0.3165, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.00018246753246753245, | |
| "loss": 0.3112, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.0001818181818181818, | |
| "loss": 0.2908, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 0.00018116883116883116, | |
| "loss": 0.2654, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.5642479062080383, | |
| "eval_runtime": 162.5947, | |
| "eval_samples_per_second": 9.361, | |
| "eval_wer": 0.543151307156556, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 0.0001805194805194805, | |
| "loss": 0.2839, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.00017987012987012984, | |
| "loss": 0.2609, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 0.0001792207792207792, | |
| "loss": 0.2634, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 0.00017857142857142854, | |
| "loss": 0.2854, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.0001779220779220779, | |
| "loss": 0.2951, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.00017727272727272728, | |
| "loss": 0.319, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.00017662337662337663, | |
| "loss": 0.2618, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 0.00017597402597402596, | |
| "loss": 0.2858, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 0.0001753246753246753, | |
| "loss": 0.2259, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 0.00017467532467532466, | |
| "loss": 0.2892, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 0.00017402597402597401, | |
| "loss": 0.2668, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 0.00017337662337662337, | |
| "loss": 0.2553, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.00017272727272727272, | |
| "loss": 0.2421, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.00017207792207792205, | |
| "loss": 0.2892, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 0.0001714285714285714, | |
| "loss": 0.242, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00017077922077922075, | |
| "loss": 0.2353, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0001701298701298701, | |
| "loss": 0.2486, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 0.00016948051948051948, | |
| "loss": 0.2952, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 0.00016883116883116884, | |
| "loss": 0.2422, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 0.00016818181818181816, | |
| "loss": 0.2354, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 0.00016753246753246751, | |
| "loss": 0.2395, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 0.00016688311688311687, | |
| "loss": 0.2699, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 0.00016623376623376622, | |
| "loss": 0.2858, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.5172072052955627, | |
| "eval_runtime": 166.1449, | |
| "eval_samples_per_second": 9.161, | |
| "eval_wer": 0.5154940950842838, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 0.00016558441558441557, | |
| "loss": 0.268, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 0.00016493506493506493, | |
| "loss": 0.1977, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.00016428571428571428, | |
| "loss": 0.2355, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.0001636363636363636, | |
| "loss": 0.2398, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 0.00016298701298701296, | |
| "loss": 0.2471, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 0.0001623376623376623, | |
| "loss": 0.1975, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 0.0001616883116883117, | |
| "loss": 0.239, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 0.00016103896103896104, | |
| "loss": 0.2285, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.0001603896103896104, | |
| "loss": 0.2506, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 0.00015974025974025972, | |
| "loss": 0.2347, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 0.00015909090909090907, | |
| "loss": 0.2491, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 0.00015844155844155843, | |
| "loss": 0.1968, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.00015779220779220778, | |
| "loss": 0.2403, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00015714285714285713, | |
| "loss": 0.2518, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 0.00015649350649350649, | |
| "loss": 0.2112, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 0.0001558441558441558, | |
| "loss": 0.2068, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 0.00015519480519480516, | |
| "loss": 0.2092, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 0.00015454545454545452, | |
| "loss": 0.1868, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0001538961038961039, | |
| "loss": 0.2085, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 0.00015324675324675325, | |
| "loss": 0.2356, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 0.0001525974025974026, | |
| "loss": 0.2055, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 0.00015194805194805193, | |
| "loss": 0.18, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00015129870129870128, | |
| "loss": 0.221, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00015064935064935063, | |
| "loss": 0.203, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.5122302770614624, | |
| "eval_runtime": 165.9, | |
| "eval_samples_per_second": 9.174, | |
| "eval_wer": 0.4932875744423135, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1914, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 0.00014935064935064934, | |
| "loss": 0.1825, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 0.0001487012987012987, | |
| "loss": 0.1756, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 0.00014805194805194805, | |
| "loss": 0.2172, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0001474025974025974, | |
| "loss": 0.1853, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 0.00014675324675324672, | |
| "loss": 0.1908, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 0.00014610389610389608, | |
| "loss": 0.1766, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 0.1714, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 0.00014480519480519478, | |
| "loss": 0.1723, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.00014415584415584414, | |
| "loss": 0.205, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 0.0001435064935064935, | |
| "loss": 0.1578, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 0.00014285714285714284, | |
| "loss": 0.1727, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 0.0001422077922077922, | |
| "loss": 0.1761, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 0.00014155844155844155, | |
| "loss": 0.1958, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0001409090909090909, | |
| "loss": 0.1804, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 0.00014025974025974025, | |
| "loss": 0.2003, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 0.0001396103896103896, | |
| "loss": 0.2051, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 0.00013896103896103896, | |
| "loss": 0.1825, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 0.00013831168831168828, | |
| "loss": 0.192, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.00013766233766233766, | |
| "loss": 0.1578, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 0.00013701298701298702, | |
| "loss": 0.1688, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.00013636363636363634, | |
| "loss": 0.1489, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 0.0001357142857142857, | |
| "loss": 0.1646, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.5022615790367126, | |
| "eval_runtime": 166.6997, | |
| "eval_samples_per_second": 9.13, | |
| "eval_wer": 0.4882406379327748, | |
| "step": 2552 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 0.00013506493506493505, | |
| "loss": 0.2222, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.0001344155844155844, | |
| "loss": 0.148, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 0.00013376623376623375, | |
| "loss": 0.1729, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 0.0001331168831168831, | |
| "loss": 0.1621, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 0.00013246753246753246, | |
| "loss": 0.1835, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 0.0001318181818181818, | |
| "loss": 0.1588, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.00013116883116883116, | |
| "loss": 0.167, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 0.0001305194805194805, | |
| "loss": 0.143, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 0.00012987012987012987, | |
| "loss": 0.1527, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 0.00012922077922077922, | |
| "loss": 0.1446, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 0.00012857142857142855, | |
| "loss": 0.1462, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.0001279220779220779, | |
| "loss": 0.1539, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 0.00012727272727272725, | |
| "loss": 0.1925, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 0.0001266233766233766, | |
| "loss": 0.1926, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 0.00012597402597402596, | |
| "loss": 0.1805, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 0.0001253246753246753, | |
| "loss": 0.1829, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.00012467532467532467, | |
| "loss": 0.1378, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 0.00012402597402597402, | |
| "loss": 0.1783, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 0.00012337662337662337, | |
| "loss": 0.1356, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 0.00012272727272727272, | |
| "loss": 0.1687, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 0.00012207792207792208, | |
| "loss": 0.1537, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00012142857142857142, | |
| "loss": 0.1416, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 0.00012077922077922077, | |
| "loss": 0.1853, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.48231056332588196, | |
| "eval_runtime": 168.3536, | |
| "eval_samples_per_second": 9.04, | |
| "eval_wer": 0.4799636620571313, | |
| "step": 2784 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 0.00012012987012987012, | |
| "loss": 0.1258, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 0.00011948051948051947, | |
| "loss": 0.1321, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 0.00011883116883116883, | |
| "loss": 0.1744, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 0.00011818181818181817, | |
| "loss": 0.1272, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 0.00011753246753246752, | |
| "loss": 0.1375, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 0.00011688311688311687, | |
| "loss": 0.1372, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 0.00011623376623376621, | |
| "loss": 0.1467, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 0.00011558441558441558, | |
| "loss": 0.1322, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.00011493506493506493, | |
| "loss": 0.1502, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 0.00011428571428571427, | |
| "loss": 0.1538, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 0.00011363636363636362, | |
| "loss": 0.1297, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 0.00011298701298701298, | |
| "loss": 0.1433, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 0.00011233766233766231, | |
| "loss": 0.2079, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 0.00011168831168831168, | |
| "loss": 0.1315, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.00011103896103896103, | |
| "loss": 0.134, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 0.00011038961038961037, | |
| "loss": 0.1684, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 0.00010974025974025973, | |
| "loss": 0.1354, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 0.00010909090909090908, | |
| "loss": 0.1471, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.00010844155844155842, | |
| "loss": 0.1138, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 0.00010779220779220778, | |
| "loss": 0.11, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 0.00010714285714285714, | |
| "loss": 0.1385, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 0.00010649350649350649, | |
| "loss": 0.1339, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 0.00010584415584415583, | |
| "loss": 0.142, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.49411994218826294, | |
| "eval_runtime": 170.3026, | |
| "eval_samples_per_second": 8.937, | |
| "eval_wer": 0.4742101544362572, | |
| "step": 3016 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 0.00010519480519480518, | |
| "loss": 0.1411, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 0.00010454545454545455, | |
| "loss": 0.133, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 0.00010389610389610389, | |
| "loss": 0.1171, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 13.15, | |
| "learning_rate": 0.00010324675324675324, | |
| "loss": 0.1575, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 0.0001025974025974026, | |
| "loss": 0.1194, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.00010194805194805193, | |
| "loss": 0.1312, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00010129870129870129, | |
| "loss": 0.1214, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 0.00010064935064935065, | |
| "loss": 0.1174, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 0.142, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 9.935064935064934e-05, | |
| "loss": 0.1143, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 9.87012987012987e-05, | |
| "loss": 0.1363, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 9.805194805194804e-05, | |
| "loss": 0.1297, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 9.740259740259739e-05, | |
| "loss": 0.1373, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 9.675324675324676e-05, | |
| "loss": 0.092, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 9.61038961038961e-05, | |
| "loss": 0.1177, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 9.545454545454545e-05, | |
| "loss": 0.1292, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 9.48051948051948e-05, | |
| "loss": 0.098, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 9.415584415584414e-05, | |
| "loss": 0.114, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 9.350649350649349e-05, | |
| "loss": 0.101, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 9.285714285714286e-05, | |
| "loss": 0.1173, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 9.22077922077922e-05, | |
| "loss": 0.0998, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 9.155844155844155e-05, | |
| "loss": 0.1186, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 9.09090909090909e-05, | |
| "loss": 0.1155, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.4869328737258911, | |
| "eval_runtime": 173.2877, | |
| "eval_samples_per_second": 8.783, | |
| "eval_wer": 0.46189562935298273, | |
| "step": 3248 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 9.025974025974026e-05, | |
| "loss": 0.1039, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 8.96103896103896e-05, | |
| "loss": 0.1142, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 8.896103896103895e-05, | |
| "loss": 0.106, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 8.831168831168831e-05, | |
| "loss": 0.1123, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 8.766233766233765e-05, | |
| "loss": 0.121, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 8.701298701298701e-05, | |
| "loss": 0.1108, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 8.636363636363636e-05, | |
| "loss": 0.1195, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 8.57142857142857e-05, | |
| "loss": 0.1116, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 8.506493506493505e-05, | |
| "loss": 0.1008, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 8.441558441558442e-05, | |
| "loss": 0.1013, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 8.376623376623376e-05, | |
| "loss": 0.1282, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 8.311688311688311e-05, | |
| "loss": 0.1175, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 8.246753246753246e-05, | |
| "loss": 0.1254, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 8.18181818181818e-05, | |
| "loss": 0.1169, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 8.116883116883116e-05, | |
| "loss": 0.101, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 8.051948051948052e-05, | |
| "loss": 0.134, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 7.987012987012986e-05, | |
| "loss": 0.1124, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 7.922077922077921e-05, | |
| "loss": 0.0964, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 7.857142857142857e-05, | |
| "loss": 0.0959, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 7.79220779220779e-05, | |
| "loss": 0.0944, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 7.727272727272726e-05, | |
| "loss": 0.1302, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 7.662337662337662e-05, | |
| "loss": 0.1181, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 7.597402597402596e-05, | |
| "loss": 0.0713, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 7.532467532467532e-05, | |
| "loss": 0.0849, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.4888065457344055, | |
| "eval_runtime": 168.5146, | |
| "eval_samples_per_second": 9.032, | |
| "eval_wer": 0.4614918744322196, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 7.467532467532467e-05, | |
| "loss": 0.1545, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 7.402597402597402e-05, | |
| "loss": 0.0952, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 7.337662337662336e-05, | |
| "loss": 0.1229, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.086, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 7.207792207792207e-05, | |
| "loss": 0.093, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 7.142857142857142e-05, | |
| "loss": 0.1197, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 7.077922077922077e-05, | |
| "loss": 0.1104, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 15.34, | |
| "learning_rate": 7.012987012987013e-05, | |
| "loss": 0.1101, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 6.948051948051948e-05, | |
| "loss": 0.1005, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 6.883116883116883e-05, | |
| "loss": 0.0979, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 6.818181818181817e-05, | |
| "loss": 0.0979, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 6.753246753246752e-05, | |
| "loss": 0.0762, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 6.688311688311688e-05, | |
| "loss": 0.1136, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 6.623376623376623e-05, | |
| "loss": 0.1039, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 6.558441558441558e-05, | |
| "loss": 0.0897, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 6.493506493506494e-05, | |
| "loss": 0.0883, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 6.428571428571427e-05, | |
| "loss": 0.0931, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 15.77, | |
| "learning_rate": 6.363636363636363e-05, | |
| "loss": 0.0881, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 6.298701298701298e-05, | |
| "loss": 0.1156, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 6.233766233766233e-05, | |
| "loss": 0.0939, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 6.168831168831169e-05, | |
| "loss": 0.1109, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 6.103896103896104e-05, | |
| "loss": 0.0996, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 6.0389610389610384e-05, | |
| "loss": 0.0927, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.47719869017601013, | |
| "eval_runtime": 172.1905, | |
| "eval_samples_per_second": 8.839, | |
| "eval_wer": 0.448369839507419, | |
| "step": 3712 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 5.974025974025974e-05, | |
| "loss": 0.096, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 5.909090909090908e-05, | |
| "loss": 0.1205, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 16.12, | |
| "learning_rate": 5.8441558441558436e-05, | |
| "loss": 0.0864, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 5.779220779220779e-05, | |
| "loss": 0.1027, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 5.7142857142857135e-05, | |
| "loss": 0.0853, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 5.649350649350649e-05, | |
| "loss": 0.0866, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 5.584415584415584e-05, | |
| "loss": 0.0815, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 5.519480519480519e-05, | |
| "loss": 0.0971, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 5.454545454545454e-05, | |
| "loss": 0.0737, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 5.389610389610389e-05, | |
| "loss": 0.1072, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 5.3246753246753245e-05, | |
| "loss": 0.1073, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 5.259740259740259e-05, | |
| "loss": 0.0915, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 5.1948051948051944e-05, | |
| "loss": 0.1018, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 5.12987012987013e-05, | |
| "loss": 0.0941, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 5.064935064935064e-05, | |
| "loss": 0.0725, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 16.68, | |
| "learning_rate": 4.9999999999999996e-05, | |
| "loss": 0.0905, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 4.935064935064935e-05, | |
| "loss": 0.095, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 4.8701298701298694e-05, | |
| "loss": 0.0855, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 4.805194805194805e-05, | |
| "loss": 0.0754, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 16.85, | |
| "learning_rate": 4.74025974025974e-05, | |
| "loss": 0.0687, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 4.6753246753246746e-05, | |
| "loss": 0.0884, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 4.61038961038961e-05, | |
| "loss": 0.0887, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "learning_rate": 4.545454545454545e-05, | |
| "loss": 0.1013, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.48812878131866455, | |
| "eval_runtime": 172.0812, | |
| "eval_samples_per_second": 8.845, | |
| "eval_wer": 0.44079943474311095, | |
| "step": 3944 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 4.48051948051948e-05, | |
| "loss": 0.1091, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "learning_rate": 4.415584415584416e-05, | |
| "loss": 0.0671, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 4.3506493506493503e-05, | |
| "loss": 0.1076, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 4.285714285714285e-05, | |
| "loss": 0.0881, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 4.220779220779221e-05, | |
| "loss": 0.0764, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 4.1558441558441555e-05, | |
| "loss": 0.0892, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.09090909090909e-05, | |
| "loss": 0.1031, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 4.025974025974026e-05, | |
| "loss": 0.102, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 3.961038961038961e-05, | |
| "loss": 0.0653, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 3.896103896103895e-05, | |
| "loss": 0.0822, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 17.46, | |
| "learning_rate": 3.831168831168831e-05, | |
| "loss": 0.0911, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 3.766233766233766e-05, | |
| "loss": 0.0743, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 3.701298701298701e-05, | |
| "loss": 0.0768, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.0888, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 3.571428571428571e-05, | |
| "loss": 0.0753, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 17.67, | |
| "learning_rate": 3.506493506493506e-05, | |
| "loss": 0.0513, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 3.4415584415584416e-05, | |
| "loss": 0.0764, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 3.376623376623376e-05, | |
| "loss": 0.0788, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 3.3116883116883115e-05, | |
| "loss": 0.0754, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 3.246753246753247e-05, | |
| "loss": 0.1319, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "learning_rate": 3.1818181818181814e-05, | |
| "loss": 0.0941, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 3.1168831168831166e-05, | |
| "loss": 0.0838, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 3.051948051948052e-05, | |
| "loss": 0.0669, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.47913026809692383, | |
| "eval_runtime": 175.3638, | |
| "eval_samples_per_second": 8.679, | |
| "eval_wer": 0.4378722115675785, | |
| "step": 4176 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 2.987012987012987e-05, | |
| "loss": 0.0772, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 2.9220779220779218e-05, | |
| "loss": 0.0737, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 2.8571428571428567e-05, | |
| "loss": 0.098, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "learning_rate": 2.792207792207792e-05, | |
| "loss": 0.0967, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 2.727272727272727e-05, | |
| "loss": 0.0766, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 2.6623376623376623e-05, | |
| "loss": 0.0758, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 2.5974025974025972e-05, | |
| "loss": 0.0734, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 2.532467532467532e-05, | |
| "loss": 0.0573, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 2.4675324675324674e-05, | |
| "loss": 0.0711, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.4025974025974024e-05, | |
| "loss": 0.0686, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 2.3376623376623373e-05, | |
| "loss": 0.0851, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 2.2727272727272726e-05, | |
| "loss": 0.075, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 2.207792207792208e-05, | |
| "loss": 0.0806, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 18.58, | |
| "learning_rate": 2.1428571428571425e-05, | |
| "loss": 0.0751, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 2.0779220779220778e-05, | |
| "loss": 0.0741, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 2.012987012987013e-05, | |
| "loss": 0.0683, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 1.9480519480519476e-05, | |
| "loss": 0.0853, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 1.883116883116883e-05, | |
| "loss": 0.0759, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.0749, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 1.753246753246753e-05, | |
| "loss": 0.0884, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 1.688311688311688e-05, | |
| "loss": 0.0657, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "learning_rate": 1.6233766233766234e-05, | |
| "loss": 0.0698, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "learning_rate": 1.5584415584415583e-05, | |
| "loss": 0.0723, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.4765560030937195, | |
| "eval_runtime": 176.1902, | |
| "eval_samples_per_second": 8.638, | |
| "eval_wer": 0.43716564045624307, | |
| "step": 4408 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 1.4935064935064934e-05, | |
| "loss": 0.0774, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 1.4285714285714284e-05, | |
| "loss": 0.0721, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 1.3636363636363635e-05, | |
| "loss": 0.0752, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 1.2987012987012986e-05, | |
| "loss": 0.0556, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "learning_rate": 1.2337662337662337e-05, | |
| "loss": 0.0749, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 1.1688311688311687e-05, | |
| "loss": 0.0645, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 1.103896103896104e-05, | |
| "loss": 0.0757, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 1.0389610389610389e-05, | |
| "loss": 0.0726, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 9.740259740259738e-06, | |
| "loss": 0.073, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.0711, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 8.44155844155844e-06, | |
| "loss": 0.0813, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 19.48, | |
| "learning_rate": 7.792207792207792e-06, | |
| "loss": 0.0847, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 7.142857142857142e-06, | |
| "loss": 0.1081, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 6.493506493506493e-06, | |
| "loss": 0.0694, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "learning_rate": 5.844155844155843e-06, | |
| "loss": 0.0687, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 19.65, | |
| "learning_rate": 5.194805194805194e-06, | |
| "loss": 0.1179, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 0.0648, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 3.896103896103896e-06, | |
| "loss": 0.0782, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 3.2467532467532465e-06, | |
| "loss": 0.063, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "learning_rate": 2.597402597402597e-06, | |
| "loss": 0.0658, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 19.87, | |
| "learning_rate": 1.948051948051948e-06, | |
| "loss": 0.0613, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 1.2987012987012986e-06, | |
| "loss": 0.0873, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 6.493506493506493e-07, | |
| "loss": 0.1031, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0675, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.4751843214035034, | |
| "eval_runtime": 177.6725, | |
| "eval_samples_per_second": 8.566, | |
| "eval_wer": 0.4374684566468154, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 20.04, | |
| "learning_rate": 5.9688581314878885e-05, | |
| "loss": 0.0605, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 5.9169550173010376e-05, | |
| "loss": 0.0568, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 20.13, | |
| "learning_rate": 5.865051903114186e-05, | |
| "loss": 0.0844, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 20.17, | |
| "learning_rate": 5.813148788927335e-05, | |
| "loss": 0.0892, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 5.761245674740484e-05, | |
| "loss": 0.0686, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 20.26, | |
| "learning_rate": 5.7093425605536325e-05, | |
| "loss": 0.0704, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "learning_rate": 5.6574394463667816e-05, | |
| "loss": 0.0687, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 20.34, | |
| "learning_rate": 5.605536332179931e-05, | |
| "loss": 0.1011, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 20.39, | |
| "learning_rate": 5.553633217993079e-05, | |
| "loss": 0.0844, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 5.501730103806228e-05, | |
| "loss": 0.0722, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 20.47, | |
| "learning_rate": 5.449826989619377e-05, | |
| "loss": 0.057, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 20.52, | |
| "learning_rate": 5.3979238754325256e-05, | |
| "loss": 0.0596, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "learning_rate": 5.346020761245675e-05, | |
| "loss": 0.0786, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "learning_rate": 5.294117647058824e-05, | |
| "loss": 0.0835, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "learning_rate": 5.242214532871972e-05, | |
| "loss": 0.066, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 5.1903114186851205e-05, | |
| "loss": 0.0721, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 5.138408304498269e-05, | |
| "loss": 0.0978, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "learning_rate": 5.086505190311418e-05, | |
| "loss": 0.0893, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "learning_rate": 5.0346020761245664e-05, | |
| "loss": 0.0723, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "learning_rate": 4.9826989619377155e-05, | |
| "loss": 0.0697, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "learning_rate": 4.9307958477508645e-05, | |
| "loss": 0.0928, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 4.878892733564013e-05, | |
| "loss": 0.0894, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "learning_rate": 4.826989619377162e-05, | |
| "loss": 0.0782, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.46749043464660645, | |
| "eval_runtime": 156.5519, | |
| "eval_samples_per_second": 9.722, | |
| "eval_wer": 0.4334309074391844, | |
| "step": 4872 | |
| }, | |
| { | |
| "epoch": 21.03, | |
| "learning_rate": 4.775086505190311e-05, | |
| "loss": 0.1052, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 21.08, | |
| "learning_rate": 4.7231833910034595e-05, | |
| "loss": 0.0648, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 4.6712802768166085e-05, | |
| "loss": 0.0676, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 4.6193771626297576e-05, | |
| "loss": 0.0642, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "learning_rate": 4.567474048442906e-05, | |
| "loss": 0.0926, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 4.515570934256055e-05, | |
| "loss": 0.0781, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "learning_rate": 4.463667820069204e-05, | |
| "loss": 0.0668, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 21.34, | |
| "learning_rate": 4.4117647058823526e-05, | |
| "loss": 0.0725, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 21.38, | |
| "learning_rate": 4.3598615916955016e-05, | |
| "loss": 0.0785, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 21.42, | |
| "learning_rate": 4.307958477508651e-05, | |
| "loss": 0.057, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 4.256055363321799e-05, | |
| "loss": 0.0659, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "learning_rate": 4.204152249134948e-05, | |
| "loss": 0.0864, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 21.55, | |
| "learning_rate": 4.1522491349480966e-05, | |
| "loss": 0.0731, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 21.59, | |
| "learning_rate": 4.1003460207612456e-05, | |
| "loss": 0.0744, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 4.048442906574395e-05, | |
| "loss": 0.0769, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "learning_rate": 3.9965397923875424e-05, | |
| "loss": 0.079, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 3.9446366782006915e-05, | |
| "loss": 0.0875, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 21.77, | |
| "learning_rate": 3.89273356401384e-05, | |
| "loss": 0.0705, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 21.81, | |
| "learning_rate": 3.840830449826989e-05, | |
| "loss": 0.0723, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 3.788927335640138e-05, | |
| "loss": 0.0833, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "learning_rate": 3.7370242214532864e-05, | |
| "loss": 0.0914, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 3.6851211072664355e-05, | |
| "loss": 0.0754, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "learning_rate": 3.6332179930795846e-05, | |
| "loss": 0.0848, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.4894248843193054, | |
| "eval_runtime": 156.3927, | |
| "eval_samples_per_second": 9.732, | |
| "eval_wer": 0.4378722115675785, | |
| "step": 5104 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 3.581314878892733e-05, | |
| "loss": 0.0783, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 22.07, | |
| "learning_rate": 3.529411764705882e-05, | |
| "loss": 0.0698, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 22.11, | |
| "learning_rate": 3.477508650519031e-05, | |
| "loss": 0.0885, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 22.15, | |
| "learning_rate": 3.4256055363321795e-05, | |
| "loss": 0.0613, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 3.3737024221453286e-05, | |
| "loss": 0.0567, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 3.3217993079584777e-05, | |
| "loss": 0.0905, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 3.269896193771626e-05, | |
| "loss": 0.0865, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 3.217993079584775e-05, | |
| "loss": 0.0881, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 22.37, | |
| "learning_rate": 3.1660899653979235e-05, | |
| "loss": 0.0702, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 22.41, | |
| "learning_rate": 3.114186851211072e-05, | |
| "loss": 0.0688, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 22.46, | |
| "learning_rate": 3.062283737024221e-05, | |
| "loss": 0.0713, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 3.0103806228373697e-05, | |
| "loss": 0.0615, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 2.9584775086505188e-05, | |
| "loss": 0.0761, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 22.58, | |
| "learning_rate": 2.9065743944636675e-05, | |
| "loss": 0.0751, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 22.63, | |
| "learning_rate": 2.8546712802768163e-05, | |
| "loss": 0.0767, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "learning_rate": 2.8027681660899653e-05, | |
| "loss": 0.0765, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 22.71, | |
| "learning_rate": 2.750865051903114e-05, | |
| "loss": 0.0652, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "learning_rate": 2.6989619377162628e-05, | |
| "loss": 0.077, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 0.0643, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 22.84, | |
| "learning_rate": 2.5951557093425603e-05, | |
| "loss": 0.0646, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 2.543252595155709e-05, | |
| "loss": 0.084, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "learning_rate": 2.4913494809688577e-05, | |
| "loss": 0.0615, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "learning_rate": 2.4394463667820065e-05, | |
| "loss": 0.0859, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.4741663634777069, | |
| "eval_runtime": 158.2043, | |
| "eval_samples_per_second": 9.62, | |
| "eval_wer": 0.43252245886746743, | |
| "step": 5336 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.3875432525951555e-05, | |
| "loss": 0.085, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 2.3356401384083043e-05, | |
| "loss": 0.0685, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 2.283737024221453e-05, | |
| "loss": 0.0572, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 23.15, | |
| "learning_rate": 2.231833910034602e-05, | |
| "loss": 0.0752, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 2.1799307958477508e-05, | |
| "loss": 0.084, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 2.1280276816608995e-05, | |
| "loss": 0.0603, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "learning_rate": 2.0761245674740483e-05, | |
| "loss": 0.0702, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 23.32, | |
| "learning_rate": 2.0242214532871974e-05, | |
| "loss": 0.063, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.9723183391003457e-05, | |
| "loss": 0.0558, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 1.9204152249134945e-05, | |
| "loss": 0.0848, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 1.8685121107266432e-05, | |
| "loss": 0.0613, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 23.49, | |
| "learning_rate": 1.8166089965397923e-05, | |
| "loss": 0.0639, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 23.53, | |
| "learning_rate": 1.764705882352941e-05, | |
| "loss": 0.0778, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 23.58, | |
| "learning_rate": 1.7128027681660898e-05, | |
| "loss": 0.0645, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 23.62, | |
| "learning_rate": 1.6608996539792388e-05, | |
| "loss": 0.0766, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 23.66, | |
| "learning_rate": 1.6089965397923876e-05, | |
| "loss": 0.054, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 23.71, | |
| "learning_rate": 1.557093425605536e-05, | |
| "loss": 0.0695, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 1.5051903114186849e-05, | |
| "loss": 0.0682, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 23.79, | |
| "learning_rate": 1.4532871972318338e-05, | |
| "loss": 0.0762, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 1.4013840830449827e-05, | |
| "loss": 0.0729, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 1.3494809688581314e-05, | |
| "loss": 0.0704, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 23.92, | |
| "learning_rate": 1.2975778546712801e-05, | |
| "loss": 0.0629, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 23.96, | |
| "learning_rate": 1.2456747404844289e-05, | |
| "loss": 0.0739, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.48862332105636597, | |
| "eval_runtime": 159.9632, | |
| "eval_samples_per_second": 9.515, | |
| "eval_wer": 0.4284849096598365, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 1.1937716262975778e-05, | |
| "loss": 0.075, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 24.05, | |
| "learning_rate": 1.1418685121107265e-05, | |
| "loss": 0.0693, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "learning_rate": 1.0899653979238754e-05, | |
| "loss": 0.0599, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 24.14, | |
| "learning_rate": 1.0380622837370241e-05, | |
| "loss": 0.0598, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 9.861591695501729e-06, | |
| "loss": 0.069, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 24.22, | |
| "learning_rate": 9.342560553633216e-06, | |
| "loss": 0.0602, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 24.27, | |
| "learning_rate": 8.823529411764705e-06, | |
| "loss": 0.0616, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 24.31, | |
| "learning_rate": 8.304498269896194e-06, | |
| "loss": 0.072, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 24.35, | |
| "learning_rate": 7.78546712802768e-06, | |
| "loss": 0.0703, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 24.4, | |
| "learning_rate": 7.266435986159169e-06, | |
| "loss": 0.0583, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 6.747404844290657e-06, | |
| "loss": 0.0663, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 6.228373702422144e-06, | |
| "loss": 0.0681, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 5.7093425605536325e-06, | |
| "loss": 0.0584, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "learning_rate": 5.190311418685121e-06, | |
| "loss": 0.0581, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 24.61, | |
| "learning_rate": 4.671280276816608e-06, | |
| "loss": 0.0757, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 4.152249134948097e-06, | |
| "loss": 0.0675, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "learning_rate": 3.6332179930795844e-06, | |
| "loss": 0.0588, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 24.74, | |
| "learning_rate": 3.114186851211072e-06, | |
| "loss": 0.0774, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 24.78, | |
| "learning_rate": 2.5951557093425604e-06, | |
| "loss": 0.0684, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 24.83, | |
| "learning_rate": 2.0761245674740485e-06, | |
| "loss": 0.0591, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "learning_rate": 1.557093425605536e-06, | |
| "loss": 0.0611, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 1.0380622837370243e-06, | |
| "loss": 0.058, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 24.95, | |
| "learning_rate": 5.190311418685121e-07, | |
| "loss": 0.086, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0505, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.48566901683807373, | |
| "eval_runtime": 159.4769, | |
| "eval_samples_per_second": 9.544, | |
| "eval_wer": 0.42787927727869185, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 4.971181556195965e-05, | |
| "loss": 0.0735, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 4.9279538904899127e-05, | |
| "loss": 0.0769, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 25.13, | |
| "learning_rate": 4.884726224783861e-05, | |
| "loss": 0.0613, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 25.17, | |
| "learning_rate": 4.841498559077809e-05, | |
| "loss": 0.0602, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 25.22, | |
| "learning_rate": 4.798270893371757e-05, | |
| "loss": 0.0509, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 25.26, | |
| "learning_rate": 4.755043227665706e-05, | |
| "loss": 0.0785, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 4.711815561959654e-05, | |
| "loss": 0.0735, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 25.34, | |
| "learning_rate": 4.668587896253602e-05, | |
| "loss": 0.0764, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 25.39, | |
| "learning_rate": 4.6253602305475506e-05, | |
| "loss": 0.0737, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 25.43, | |
| "learning_rate": 4.582132564841498e-05, | |
| "loss": 0.0706, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 25.47, | |
| "learning_rate": 4.538904899135446e-05, | |
| "loss": 0.079, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 25.52, | |
| "learning_rate": 4.495677233429394e-05, | |
| "loss": 0.0556, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "learning_rate": 4.4524495677233426e-05, | |
| "loss": 0.0683, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 4.4092219020172906e-05, | |
| "loss": 0.0973, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 25.65, | |
| "learning_rate": 4.3659942363112386e-05, | |
| "loss": 0.0622, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 4.322766570605187e-05, | |
| "loss": 0.0762, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "learning_rate": 4.279538904899135e-05, | |
| "loss": 0.0716, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 25.77, | |
| "learning_rate": 4.236311239193083e-05, | |
| "loss": 0.0459, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 4.193083573487032e-05, | |
| "loss": 0.0619, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "learning_rate": 4.14985590778098e-05, | |
| "loss": 0.0568, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "learning_rate": 4.106628242074927e-05, | |
| "loss": 0.087, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 4.063400576368875e-05, | |
| "loss": 0.0805, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "learning_rate": 4.020172910662824e-05, | |
| "loss": 0.0513, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.4976740777492523, | |
| "eval_runtime": 157.8423, | |
| "eval_samples_per_second": 9.643, | |
| "eval_wer": 0.429595235691935, | |
| "step": 6032 | |
| }, | |
| { | |
| "epoch": 26.03, | |
| "learning_rate": 3.976945244956772e-05, | |
| "loss": 0.0881, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 3.93371757925072e-05, | |
| "loss": 0.0585, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 26.12, | |
| "learning_rate": 3.8904899135446685e-05, | |
| "loss": 0.0816, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 26.16, | |
| "learning_rate": 3.8472622478386165e-05, | |
| "loss": 0.068, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 26.21, | |
| "learning_rate": 3.8040345821325645e-05, | |
| "loss": 0.0543, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 3.7608069164265125e-05, | |
| "loss": 0.0794, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "learning_rate": 3.7175792507204605e-05, | |
| "loss": 0.0541, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 26.34, | |
| "learning_rate": 3.6743515850144085e-05, | |
| "loss": 0.0509, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 3.631123919308357e-05, | |
| "loss": 0.0729, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 26.42, | |
| "learning_rate": 3.587896253602305e-05, | |
| "loss": 0.057, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 26.46, | |
| "learning_rate": 3.544668587896253e-05, | |
| "loss": 0.0469, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 26.51, | |
| "learning_rate": 3.501440922190201e-05, | |
| "loss": 0.0648, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 3.458213256484149e-05, | |
| "loss": 0.08, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 26.59, | |
| "learning_rate": 3.414985590778098e-05, | |
| "loss": 0.083, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 3.371757925072046e-05, | |
| "loss": 0.0671, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 26.68, | |
| "learning_rate": 3.328530259365994e-05, | |
| "loss": 0.0795, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 3.2853025936599424e-05, | |
| "loss": 0.0695, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 26.77, | |
| "learning_rate": 3.24207492795389e-05, | |
| "loss": 0.0525, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "learning_rate": 3.1988472622478384e-05, | |
| "loss": 0.0615, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 3.1556195965417864e-05, | |
| "loss": 0.0768, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 26.89, | |
| "learning_rate": 3.1123919308357344e-05, | |
| "loss": 0.0719, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 3.069164265129683e-05, | |
| "loss": 0.0514, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "learning_rate": 3.025936599423631e-05, | |
| "loss": 0.0673, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.487693190574646, | |
| "eval_runtime": 160.5521, | |
| "eval_samples_per_second": 9.48, | |
| "eval_wer": 0.4280811547390734, | |
| "step": 6264 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 2.9827089337175787e-05, | |
| "loss": 0.0669, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 27.07, | |
| "learning_rate": 2.939481268011527e-05, | |
| "loss": 0.0484, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 2.8962536023054754e-05, | |
| "loss": 0.0671, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 2.8530259365994234e-05, | |
| "loss": 0.0603, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 2.8097982708933717e-05, | |
| "loss": 0.0593, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 2.7665706051873194e-05, | |
| "loss": 0.0494, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 27.28, | |
| "learning_rate": 2.7233429394812677e-05, | |
| "loss": 0.0747, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 2.680115273775216e-05, | |
| "loss": 0.0635, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 27.37, | |
| "learning_rate": 2.636887608069164e-05, | |
| "loss": 0.09, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "learning_rate": 2.5936599423631124e-05, | |
| "loss": 0.0716, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 27.46, | |
| "learning_rate": 2.5504322766570603e-05, | |
| "loss": 0.0515, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 2.5072046109510083e-05, | |
| "loss": 0.061, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 2.4639769452449563e-05, | |
| "loss": 0.0673, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 2.4207492795389047e-05, | |
| "loss": 0.0603, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 27.63, | |
| "learning_rate": 2.377521613832853e-05, | |
| "loss": 0.0693, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 27.67, | |
| "learning_rate": 2.334293948126801e-05, | |
| "loss": 0.0606, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 27.71, | |
| "learning_rate": 2.291066282420749e-05, | |
| "loss": 0.0683, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 2.247838616714697e-05, | |
| "loss": 0.0758, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "learning_rate": 2.2046109510086453e-05, | |
| "loss": 0.0551, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 2.1613832853025936e-05, | |
| "loss": 0.0528, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "learning_rate": 2.1181556195965416e-05, | |
| "loss": 0.0696, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 27.93, | |
| "learning_rate": 2.07492795389049e-05, | |
| "loss": 0.0681, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 27.97, | |
| "learning_rate": 2.0317002881844376e-05, | |
| "loss": 0.0622, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.491367906332016, | |
| "eval_runtime": 161.8629, | |
| "eval_samples_per_second": 9.403, | |
| "eval_wer": 0.42626425759563946, | |
| "step": 6496 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 1.988472622478386e-05, | |
| "loss": 0.0681, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 1.9452449567723343e-05, | |
| "loss": 0.0502, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 28.1, | |
| "learning_rate": 1.9020172910662823e-05, | |
| "loss": 0.0921, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 28.15, | |
| "learning_rate": 1.8587896253602302e-05, | |
| "loss": 0.0705, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 1.8155619596541786e-05, | |
| "loss": 0.0657, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 28.23, | |
| "learning_rate": 1.7723342939481266e-05, | |
| "loss": 0.0713, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 28.28, | |
| "learning_rate": 1.7291066282420746e-05, | |
| "loss": 0.0914, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 1.685878962536023e-05, | |
| "loss": 0.0531, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 1.6426512968299712e-05, | |
| "loss": 0.0578, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 1.5994236311239192e-05, | |
| "loss": 0.0659, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 28.45, | |
| "learning_rate": 1.5561959654178672e-05, | |
| "loss": 0.0522, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 28.49, | |
| "learning_rate": 1.5129682997118155e-05, | |
| "loss": 0.0738, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 28.53, | |
| "learning_rate": 1.4697406340057635e-05, | |
| "loss": 0.0731, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 28.58, | |
| "learning_rate": 1.4265129682997117e-05, | |
| "loss": 0.0408, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 28.62, | |
| "learning_rate": 1.3832853025936597e-05, | |
| "loss": 0.0617, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 1.340057636887608e-05, | |
| "loss": 0.0476, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 28.71, | |
| "learning_rate": 1.2968299711815562e-05, | |
| "loss": 0.0728, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 1.2536023054755042e-05, | |
| "loss": 0.0487, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "learning_rate": 1.2103746397694523e-05, | |
| "loss": 0.0579, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 28.83, | |
| "learning_rate": 1.1671469740634005e-05, | |
| "loss": 0.0545, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 28.88, | |
| "learning_rate": 1.1239193083573485e-05, | |
| "loss": 0.0668, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 1.0806916426512968e-05, | |
| "loss": 0.0557, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.037463976945245e-05, | |
| "loss": 0.0538, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.4901193082332611, | |
| "eval_runtime": 162.4755, | |
| "eval_samples_per_second": 9.368, | |
| "eval_wer": 0.42353891188048853, | |
| "step": 6728 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 9.94236311239193e-06, | |
| "loss": 0.0581, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 29.05, | |
| "learning_rate": 9.510086455331411e-06, | |
| "loss": 0.0577, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "learning_rate": 9.077809798270893e-06, | |
| "loss": 0.0459, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 8.645533141210373e-06, | |
| "loss": 0.0537, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 29.18, | |
| "learning_rate": 8.213256484149856e-06, | |
| "loss": 0.0763, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "learning_rate": 7.780979827089336e-06, | |
| "loss": 0.0517, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 29.27, | |
| "learning_rate": 7.348703170028818e-06, | |
| "loss": 0.0763, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 29.31, | |
| "learning_rate": 6.916426512968298e-06, | |
| "loss": 0.0468, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 6.484149855907781e-06, | |
| "loss": 0.0573, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 29.4, | |
| "learning_rate": 6.051873198847262e-06, | |
| "loss": 0.0535, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.619596541786742e-06, | |
| "loss": 0.0577, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 29.48, | |
| "learning_rate": 5.187319884726225e-06, | |
| "loss": 0.0643, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "learning_rate": 4.755043227665706e-06, | |
| "loss": 0.0459, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 4.322766570605186e-06, | |
| "loss": 0.0596, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 29.61, | |
| "learning_rate": 3.890489913544668e-06, | |
| "loss": 0.0369, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 29.65, | |
| "learning_rate": 3.458213256484149e-06, | |
| "loss": 0.0723, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 29.7, | |
| "learning_rate": 3.025936599423631e-06, | |
| "loss": 0.0666, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 29.74, | |
| "learning_rate": 2.5936599423631124e-06, | |
| "loss": 0.046, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "learning_rate": 2.161383285302593e-06, | |
| "loss": 0.05, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "learning_rate": 1.7291066282420746e-06, | |
| "loss": 0.0543, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 29.87, | |
| "learning_rate": 1.2968299711815562e-06, | |
| "loss": 0.0571, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "learning_rate": 8.645533141210373e-07, | |
| "loss": 0.078, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "learning_rate": 4.3227665706051865e-07, | |
| "loss": 0.0628, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0481, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.49076756834983826, | |
| "eval_runtime": 163.7648, | |
| "eval_samples_per_second": 9.294, | |
| "eval_wer": 0.4218229534672454, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 30.04, | |
| "learning_rate": 2.695128339444735e-05, | |
| "loss": 0.0523, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 30.09, | |
| "learning_rate": 2.655840754321634e-05, | |
| "loss": 0.048, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 30.13, | |
| "learning_rate": 2.6165531691985332e-05, | |
| "loss": 0.0873, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 30.17, | |
| "learning_rate": 2.577265584075432e-05, | |
| "loss": 0.0555, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 2.537977998952331e-05, | |
| "loss": 0.058, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 30.26, | |
| "learning_rate": 2.49869041382923e-05, | |
| "loss": 0.0639, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 30.3, | |
| "learning_rate": 2.4594028287061287e-05, | |
| "loss": 0.0592, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 30.34, | |
| "learning_rate": 2.4201152435830276e-05, | |
| "loss": 0.053, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 30.39, | |
| "learning_rate": 2.380827658459926e-05, | |
| "loss": 0.0677, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 2.341540073336825e-05, | |
| "loss": 0.0879, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 30.47, | |
| "learning_rate": 2.3022524882137243e-05, | |
| "loss": 0.0505, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 30.52, | |
| "learning_rate": 2.262964903090623e-05, | |
| "loss": 0.0496, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 30.56, | |
| "learning_rate": 2.223677317967522e-05, | |
| "loss": 0.0481, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 30.6, | |
| "learning_rate": 2.184389732844421e-05, | |
| "loss": 0.0528, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 30.65, | |
| "learning_rate": 2.1451021477213198e-05, | |
| "loss": 0.0675, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 2.1058145625982187e-05, | |
| "loss": 0.077, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 30.73, | |
| "learning_rate": 2.0665269774751176e-05, | |
| "loss": 0.1024, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 2.0272393923520165e-05, | |
| "loss": 0.0617, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 30.82, | |
| "learning_rate": 1.9879518072289157e-05, | |
| "loss": 0.0541, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "learning_rate": 1.9486642221058146e-05, | |
| "loss": 0.0581, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 30.9, | |
| "learning_rate": 1.9093766369827135e-05, | |
| "loss": 0.0542, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 30.95, | |
| "learning_rate": 1.870089051859612e-05, | |
| "loss": 0.0494, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 1.830801466736511e-05, | |
| "loss": 0.0637, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.5002039074897766, | |
| "eval_runtime": 155.4344, | |
| "eval_samples_per_second": 9.792, | |
| "eval_wer": 0.42343797315029774, | |
| "step": 7192 | |
| }, | |
| { | |
| "epoch": 31.03, | |
| "learning_rate": 1.79151388161341e-05, | |
| "loss": 0.0592, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 31.08, | |
| "learning_rate": 1.752226296490309e-05, | |
| "loss": 0.083, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 31.12, | |
| "learning_rate": 1.712938711367208e-05, | |
| "loss": 0.0548, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 31.16, | |
| "learning_rate": 1.6736511262441068e-05, | |
| "loss": 0.0679, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 31.21, | |
| "learning_rate": 1.6343635411210057e-05, | |
| "loss": 0.0572, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 1.5950759559979046e-05, | |
| "loss": 0.0431, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 31.29, | |
| "learning_rate": 1.5557883708748035e-05, | |
| "loss": 0.0493, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 31.34, | |
| "learning_rate": 1.5165007857517022e-05, | |
| "loss": 0.0553, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "learning_rate": 1.4772132006286012e-05, | |
| "loss": 0.0437, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 31.42, | |
| "learning_rate": 1.4379256155055001e-05, | |
| "loss": 0.0407, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 31.46, | |
| "learning_rate": 1.398638030382399e-05, | |
| "loss": 0.0591, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 31.51, | |
| "learning_rate": 1.3593504452592979e-05, | |
| "loss": 0.062, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 31.55, | |
| "learning_rate": 1.320062860136197e-05, | |
| "loss": 0.0405, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 31.59, | |
| "learning_rate": 1.2807752750130958e-05, | |
| "loss": 0.0548, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 1.2414876898899946e-05, | |
| "loss": 0.0573, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 31.68, | |
| "learning_rate": 1.2022001047668934e-05, | |
| "loss": 0.0693, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 31.72, | |
| "learning_rate": 1.1629125196437925e-05, | |
| "loss": 0.1054, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 31.77, | |
| "learning_rate": 1.1236249345206914e-05, | |
| "loss": 0.0425, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 31.81, | |
| "learning_rate": 1.0843373493975903e-05, | |
| "loss": 0.0618, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 31.85, | |
| "learning_rate": 1.045049764274489e-05, | |
| "loss": 0.0534, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 31.89, | |
| "learning_rate": 1.005762179151388e-05, | |
| "loss": 0.0515, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "learning_rate": 9.66474594028287e-06, | |
| "loss": 0.0827, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 31.98, | |
| "learning_rate": 9.27187008905186e-06, | |
| "loss": 0.0635, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.5024468898773193, | |
| "eval_runtime": 158.8322, | |
| "eval_samples_per_second": 9.582, | |
| "eval_wer": 0.4231351569597254, | |
| "step": 7424 | |
| }, | |
| { | |
| "epoch": 32.03, | |
| "learning_rate": 8.878994237820847e-06, | |
| "loss": 0.0644, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 32.07, | |
| "learning_rate": 8.486118386589838e-06, | |
| "loss": 0.0466, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 32.11, | |
| "learning_rate": 8.093242535358827e-06, | |
| "loss": 0.064, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 32.15, | |
| "learning_rate": 7.700366684127815e-06, | |
| "loss": 0.0596, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "learning_rate": 7.3074908328968034e-06, | |
| "loss": 0.0634, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 32.24, | |
| "learning_rate": 6.914614981665793e-06, | |
| "loss": 0.0476, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 32.28, | |
| "learning_rate": 6.521739130434782e-06, | |
| "loss": 0.0367, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "learning_rate": 6.128863279203772e-06, | |
| "loss": 0.0649, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 32.37, | |
| "learning_rate": 5.73598742797276e-06, | |
| "loss": 0.0461, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 32.41, | |
| "learning_rate": 5.3431115767417495e-06, | |
| "loss": 0.0726, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 32.46, | |
| "learning_rate": 4.9502357255107375e-06, | |
| "loss": 0.062, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 4.557359874279727e-06, | |
| "loss": 0.0567, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 32.54, | |
| "learning_rate": 4.164484023048716e-06, | |
| "loss": 0.0706, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 32.58, | |
| "learning_rate": 3.7716081718177054e-06, | |
| "loss": 0.0568, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 32.63, | |
| "learning_rate": 3.3787323205866943e-06, | |
| "loss": 0.0491, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "learning_rate": 2.9858564693556836e-06, | |
| "loss": 0.0654, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 32.71, | |
| "learning_rate": 2.5929806181246724e-06, | |
| "loss": 0.0648, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 32.76, | |
| "learning_rate": 2.2001047668936617e-06, | |
| "loss": 0.0631, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "learning_rate": 1.8072289156626506e-06, | |
| "loss": 0.0488, | |
| "step": 7610 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "learning_rate": 1.4143530644316395e-06, | |
| "loss": 0.0547, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 1.0214772132006286e-06, | |
| "loss": 0.061, | |
| "step": 7630 | |
| }, | |
| { | |
| "epoch": 32.93, | |
| "learning_rate": 6.286013619696175e-07, | |
| "loss": 0.0495, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 32.97, | |
| "learning_rate": 2.357255107386066e-07, | |
| "loss": 0.0501, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.49998876452445984, | |
| "eval_runtime": 161.3568, | |
| "eval_samples_per_second": 9.433, | |
| "eval_wer": 0.42152013727667303, | |
| "step": 7656 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 5.248380129589633e-05, | |
| "loss": 0.0542, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 33.06, | |
| "learning_rate": 5.2159827213822885e-05, | |
| "loss": 0.0352, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 33.1, | |
| "learning_rate": 5.183585313174945e-05, | |
| "loss": 0.0387, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 33.15, | |
| "learning_rate": 5.151187904967602e-05, | |
| "loss": 0.065, | |
| "step": 7690 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 5.118790496760259e-05, | |
| "loss": 0.0542, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 33.23, | |
| "learning_rate": 5.086393088552915e-05, | |
| "loss": 0.0498, | |
| "step": 7710 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 5.053995680345572e-05, | |
| "loss": 0.0771, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 33.32, | |
| "learning_rate": 5.021598272138229e-05, | |
| "loss": 0.0614, | |
| "step": 7730 | |
| }, | |
| { | |
| "epoch": 33.36, | |
| "learning_rate": 4.9892008639308855e-05, | |
| "loss": 0.0633, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 4.956803455723542e-05, | |
| "loss": 0.0574, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 33.45, | |
| "learning_rate": 4.924406047516198e-05, | |
| "loss": 0.038, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 33.49, | |
| "learning_rate": 4.8920086393088544e-05, | |
| "loss": 0.0588, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 33.53, | |
| "learning_rate": 4.8596112311015116e-05, | |
| "loss": 0.0484, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "learning_rate": 4.827213822894168e-05, | |
| "loss": 0.0645, | |
| "step": 7790 | |
| }, | |
| { | |
| "epoch": 33.62, | |
| "learning_rate": 4.7948164146868247e-05, | |
| "loss": 0.0545, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 33.66, | |
| "learning_rate": 4.762419006479481e-05, | |
| "loss": 0.0617, | |
| "step": 7810 | |
| }, | |
| { | |
| "epoch": 33.71, | |
| "learning_rate": 4.7300215982721384e-05, | |
| "loss": 0.0899, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 4.697624190064795e-05, | |
| "loss": 0.0613, | |
| "step": 7830 | |
| }, | |
| { | |
| "epoch": 33.79, | |
| "learning_rate": 4.665226781857451e-05, | |
| "loss": 0.065, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "learning_rate": 4.632829373650107e-05, | |
| "loss": 0.0541, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 33.88, | |
| "learning_rate": 4.600431965442764e-05, | |
| "loss": 0.0532, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 33.92, | |
| "learning_rate": 4.568034557235421e-05, | |
| "loss": 0.0704, | |
| "step": 7870 | |
| }, | |
| { | |
| "epoch": 33.96, | |
| "learning_rate": 4.5356371490280775e-05, | |
| "loss": 0.0565, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.3123264014720917, | |
| "eval_runtime": 273.8278, | |
| "eval_samples_per_second": 11.116, | |
| "eval_wer": 0.3369839507418997, | |
| "step": 7888 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 4.503239740820734e-05, | |
| "loss": 0.0576, | |
| "step": 7890 | |
| }, | |
| { | |
| "epoch": 34.05, | |
| "learning_rate": 4.47084233261339e-05, | |
| "loss": 0.0737, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 4.438444924406048e-05, | |
| "loss": 0.0541, | |
| "step": 7910 | |
| }, | |
| { | |
| "epoch": 34.14, | |
| "learning_rate": 4.4060475161987036e-05, | |
| "loss": 0.0416, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 34.18, | |
| "learning_rate": 4.37365010799136e-05, | |
| "loss": 0.0541, | |
| "step": 7930 | |
| }, | |
| { | |
| "epoch": 34.22, | |
| "learning_rate": 4.3412526997840166e-05, | |
| "loss": 0.059, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "learning_rate": 4.308855291576674e-05, | |
| "loss": 0.0538, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 34.31, | |
| "learning_rate": 4.2764578833693303e-05, | |
| "loss": 0.0795, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 34.35, | |
| "learning_rate": 4.244060475161987e-05, | |
| "loss": 0.0618, | |
| "step": 7970 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "learning_rate": 4.2116630669546434e-05, | |
| "loss": 0.0667, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 4.179265658747299e-05, | |
| "loss": 0.0501, | |
| "step": 7990 | |
| }, | |
| { | |
| "epoch": 34.48, | |
| "learning_rate": 4.1468682505399564e-05, | |
| "loss": 0.0564, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 34.52, | |
| "learning_rate": 4.114470842332613e-05, | |
| "loss": 0.0507, | |
| "step": 8010 | |
| }, | |
| { | |
| "epoch": 34.57, | |
| "learning_rate": 4.0820734341252695e-05, | |
| "loss": 0.0785, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 34.61, | |
| "learning_rate": 4.049676025917926e-05, | |
| "loss": 0.0697, | |
| "step": 8030 | |
| }, | |
| { | |
| "epoch": 34.65, | |
| "learning_rate": 4.017278617710583e-05, | |
| "loss": 0.0675, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 34.7, | |
| "learning_rate": 3.98488120950324e-05, | |
| "loss": 0.0516, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 34.74, | |
| "learning_rate": 3.952483801295896e-05, | |
| "loss": 0.0556, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 34.78, | |
| "learning_rate": 3.920086393088552e-05, | |
| "loss": 0.0739, | |
| "step": 8070 | |
| }, | |
| { | |
| "epoch": 34.83, | |
| "learning_rate": 3.887688984881209e-05, | |
| "loss": 0.0584, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 34.87, | |
| "learning_rate": 3.855291576673866e-05, | |
| "loss": 0.0827, | |
| "step": 8090 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "learning_rate": 3.822894168466522e-05, | |
| "loss": 0.0504, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 3.790496760259179e-05, | |
| "loss": 0.0521, | |
| "step": 8110 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.7580993520518354e-05, | |
| "loss": 0.0568, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.30912891030311584, | |
| "eval_runtime": 273.0561, | |
| "eval_samples_per_second": 11.148, | |
| "eval_wer": 0.3364287877258504, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 35.04, | |
| "learning_rate": 3.725701943844492e-05, | |
| "loss": 0.0615, | |
| "step": 8130 | |
| }, | |
| { | |
| "epoch": 35.09, | |
| "learning_rate": 3.693304535637149e-05, | |
| "loss": 0.0569, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 35.13, | |
| "learning_rate": 3.660907127429805e-05, | |
| "loss": 0.0747, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 35.17, | |
| "learning_rate": 3.628509719222462e-05, | |
| "loss": 0.0527, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 35.22, | |
| "learning_rate": 3.5961123110151187e-05, | |
| "loss": 0.0622, | |
| "step": 8170 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 3.563714902807775e-05, | |
| "loss": 0.0689, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 35.3, | |
| "learning_rate": 3.531317494600432e-05, | |
| "loss": 0.0658, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 35.34, | |
| "learning_rate": 3.498920086393088e-05, | |
| "loss": 0.0411, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 35.39, | |
| "learning_rate": 3.466522678185745e-05, | |
| "loss": 0.0732, | |
| "step": 8210 | |
| }, | |
| { | |
| "epoch": 35.43, | |
| "learning_rate": 3.434125269978401e-05, | |
| "loss": 0.0568, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 35.47, | |
| "learning_rate": 3.401727861771058e-05, | |
| "loss": 0.0512, | |
| "step": 8230 | |
| }, | |
| { | |
| "epoch": 35.52, | |
| "learning_rate": 3.369330453563714e-05, | |
| "loss": 0.0373, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 3.3369330453563715e-05, | |
| "loss": 0.0667, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 35.6, | |
| "learning_rate": 3.3045356371490274e-05, | |
| "loss": 0.0433, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 35.65, | |
| "learning_rate": 3.2721382289416845e-05, | |
| "loss": 0.0595, | |
| "step": 8270 | |
| }, | |
| { | |
| "epoch": 35.69, | |
| "learning_rate": 3.239740820734341e-05, | |
| "loss": 0.0569, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 3.2073434125269976e-05, | |
| "loss": 0.0612, | |
| "step": 8290 | |
| }, | |
| { | |
| "epoch": 35.77, | |
| "learning_rate": 3.174946004319654e-05, | |
| "loss": 0.0681, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 35.82, | |
| "learning_rate": 3.1425485961123106e-05, | |
| "loss": 0.0579, | |
| "step": 8310 | |
| }, | |
| { | |
| "epoch": 35.86, | |
| "learning_rate": 3.110151187904967e-05, | |
| "loss": 0.0397, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 3.0777537796976244e-05, | |
| "loss": 0.0604, | |
| "step": 8330 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "learning_rate": 3.0453563714902805e-05, | |
| "loss": 0.0669, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 35.99, | |
| "learning_rate": 3.012958963282937e-05, | |
| "loss": 0.0616, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.31008386611938477, | |
| "eval_runtime": 276.5254, | |
| "eval_samples_per_second": 11.008, | |
| "eval_wer": 0.3399616432825275, | |
| "step": 8352 | |
| }, | |
| { | |
| "epoch": 36.03, | |
| "learning_rate": 2.9805615550755936e-05, | |
| "loss": 0.0434, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 36.08, | |
| "learning_rate": 2.94816414686825e-05, | |
| "loss": 0.0598, | |
| "step": 8370 | |
| }, | |
| { | |
| "epoch": 36.12, | |
| "learning_rate": 2.915766738660907e-05, | |
| "loss": 0.0565, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 36.16, | |
| "learning_rate": 2.8833693304535635e-05, | |
| "loss": 0.056, | |
| "step": 8390 | |
| }, | |
| { | |
| "epoch": 36.21, | |
| "learning_rate": 2.85097192224622e-05, | |
| "loss": 0.0563, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 2.8185745140388765e-05, | |
| "loss": 0.064, | |
| "step": 8410 | |
| }, | |
| { | |
| "epoch": 36.29, | |
| "learning_rate": 2.7861771058315334e-05, | |
| "loss": 0.0466, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 36.34, | |
| "learning_rate": 2.75377969762419e-05, | |
| "loss": 0.0445, | |
| "step": 8430 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 2.7213822894168468e-05, | |
| "loss": 0.0504, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 36.42, | |
| "learning_rate": 2.688984881209503e-05, | |
| "loss": 0.0715, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 36.46, | |
| "learning_rate": 2.6565874730021595e-05, | |
| "loss": 0.0488, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 36.51, | |
| "learning_rate": 2.6241900647948163e-05, | |
| "loss": 0.0493, | |
| "step": 8470 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "learning_rate": 2.5917926565874725e-05, | |
| "loss": 0.0395, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 36.59, | |
| "learning_rate": 2.5593952483801294e-05, | |
| "loss": 0.0683, | |
| "step": 8490 | |
| }, | |
| { | |
| "epoch": 36.64, | |
| "learning_rate": 2.526997840172786e-05, | |
| "loss": 0.0584, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 36.68, | |
| "learning_rate": 2.4946004319654428e-05, | |
| "loss": 0.07, | |
| "step": 8510 | |
| }, | |
| { | |
| "epoch": 36.72, | |
| "learning_rate": 2.462203023758099e-05, | |
| "loss": 0.0448, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 36.77, | |
| "learning_rate": 2.4298056155507558e-05, | |
| "loss": 0.0443, | |
| "step": 8530 | |
| }, | |
| { | |
| "epoch": 36.81, | |
| "learning_rate": 2.3974082073434123e-05, | |
| "loss": 0.0586, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 36.85, | |
| "learning_rate": 2.3650107991360692e-05, | |
| "loss": 0.069, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "learning_rate": 2.3326133909287254e-05, | |
| "loss": 0.0621, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "learning_rate": 2.300215982721382e-05, | |
| "loss": 0.0617, | |
| "step": 8570 | |
| }, | |
| { | |
| "epoch": 36.98, | |
| "learning_rate": 2.2678185745140387e-05, | |
| "loss": 0.0589, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.3041793406009674, | |
| "eval_runtime": 277.9516, | |
| "eval_samples_per_second": 10.952, | |
| "eval_wer": 0.3337034420106995, | |
| "step": 8584 | |
| }, | |
| { | |
| "epoch": 37.03, | |
| "learning_rate": 2.235421166306695e-05, | |
| "loss": 0.0452, | |
| "step": 8590 | |
| }, | |
| { | |
| "epoch": 37.07, | |
| "learning_rate": 2.2030237580993518e-05, | |
| "loss": 0.0503, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 37.11, | |
| "learning_rate": 2.1706263498920083e-05, | |
| "loss": 0.0464, | |
| "step": 8610 | |
| }, | |
| { | |
| "epoch": 37.15, | |
| "learning_rate": 2.1382289416846652e-05, | |
| "loss": 0.0423, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "learning_rate": 2.1058315334773217e-05, | |
| "loss": 0.0625, | |
| "step": 8630 | |
| }, | |
| { | |
| "epoch": 37.24, | |
| "learning_rate": 2.0734341252699782e-05, | |
| "loss": 0.0497, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 37.28, | |
| "learning_rate": 2.0410367170626347e-05, | |
| "loss": 0.0427, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 37.33, | |
| "learning_rate": 2.0086393088552916e-05, | |
| "loss": 0.0562, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "learning_rate": 1.976241900647948e-05, | |
| "loss": 0.0371, | |
| "step": 8670 | |
| }, | |
| { | |
| "epoch": 37.41, | |
| "learning_rate": 1.9438444924406046e-05, | |
| "loss": 0.0661, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 37.46, | |
| "learning_rate": 1.911447084233261e-05, | |
| "loss": 0.0556, | |
| "step": 8690 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 1.8790496760259177e-05, | |
| "loss": 0.0711, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 37.54, | |
| "learning_rate": 1.8466522678185745e-05, | |
| "loss": 0.0568, | |
| "step": 8710 | |
| }, | |
| { | |
| "epoch": 37.58, | |
| "learning_rate": 1.814254859611231e-05, | |
| "loss": 0.0389, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 37.63, | |
| "learning_rate": 1.7818574514038876e-05, | |
| "loss": 0.0668, | |
| "step": 8730 | |
| }, | |
| { | |
| "epoch": 37.67, | |
| "learning_rate": 1.749460043196544e-05, | |
| "loss": 0.0694, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 37.71, | |
| "learning_rate": 1.7170626349892006e-05, | |
| "loss": 0.0704, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 37.76, | |
| "learning_rate": 1.684665226781857e-05, | |
| "loss": 0.0373, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 37.8, | |
| "learning_rate": 1.6522678185745137e-05, | |
| "loss": 0.0595, | |
| "step": 8770 | |
| }, | |
| { | |
| "epoch": 37.84, | |
| "learning_rate": 1.6198704103671705e-05, | |
| "loss": 0.0489, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 37.89, | |
| "learning_rate": 1.587473002159827e-05, | |
| "loss": 0.0448, | |
| "step": 8790 | |
| }, | |
| { | |
| "epoch": 37.93, | |
| "learning_rate": 1.5550755939524836e-05, | |
| "loss": 0.0524, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 37.97, | |
| "learning_rate": 1.5226781857451403e-05, | |
| "loss": 0.0548, | |
| "step": 8810 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.3078618049621582, | |
| "eval_runtime": 282.4379, | |
| "eval_samples_per_second": 10.778, | |
| "eval_wer": 0.3337539113757949, | |
| "step": 8816 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.4902807775377968e-05, | |
| "loss": 0.0635, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 38.06, | |
| "learning_rate": 1.4578833693304535e-05, | |
| "loss": 0.0457, | |
| "step": 8830 | |
| }, | |
| { | |
| "epoch": 38.1, | |
| "learning_rate": 1.42548596112311e-05, | |
| "loss": 0.0474, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 38.15, | |
| "learning_rate": 1.3930885529157667e-05, | |
| "loss": 0.0921, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 1.3606911447084234e-05, | |
| "loss": 0.0377, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 38.23, | |
| "learning_rate": 1.3282937365010797e-05, | |
| "loss": 0.0458, | |
| "step": 8870 | |
| }, | |
| { | |
| "epoch": 38.28, | |
| "learning_rate": 1.2958963282937363e-05, | |
| "loss": 0.0417, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 38.32, | |
| "learning_rate": 1.263498920086393e-05, | |
| "loss": 0.0498, | |
| "step": 8890 | |
| }, | |
| { | |
| "epoch": 38.36, | |
| "learning_rate": 1.2311015118790495e-05, | |
| "loss": 0.0307, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "learning_rate": 1.1987041036717062e-05, | |
| "loss": 0.0378, | |
| "step": 8910 | |
| }, | |
| { | |
| "epoch": 38.45, | |
| "learning_rate": 1.1663066954643627e-05, | |
| "loss": 0.0489, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 38.49, | |
| "learning_rate": 1.1339092872570194e-05, | |
| "loss": 0.0526, | |
| "step": 8930 | |
| }, | |
| { | |
| "epoch": 38.53, | |
| "learning_rate": 1.1015118790496759e-05, | |
| "loss": 0.0483, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 38.58, | |
| "learning_rate": 1.0691144708423326e-05, | |
| "loss": 0.0721, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 38.62, | |
| "learning_rate": 1.0367170626349891e-05, | |
| "loss": 0.052, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 38.66, | |
| "learning_rate": 1.0043196544276458e-05, | |
| "loss": 0.0487, | |
| "step": 8970 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 9.719222462203023e-06, | |
| "loss": 0.0369, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 9.395248380129588e-06, | |
| "loss": 0.0776, | |
| "step": 8990 | |
| }, | |
| { | |
| "epoch": 38.79, | |
| "learning_rate": 9.071274298056155e-06, | |
| "loss": 0.0454, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 38.83, | |
| "learning_rate": 8.74730021598272e-06, | |
| "loss": 0.0452, | |
| "step": 9010 | |
| }, | |
| { | |
| "epoch": 38.88, | |
| "learning_rate": 8.423326133909286e-06, | |
| "loss": 0.0601, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "learning_rate": 8.099352051835853e-06, | |
| "loss": 0.0488, | |
| "step": 9030 | |
| }, | |
| { | |
| "epoch": 38.96, | |
| "learning_rate": 7.775377969762418e-06, | |
| "loss": 0.0614, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.31897786259651184, | |
| "eval_runtime": 287.468, | |
| "eval_samples_per_second": 10.589, | |
| "eval_wer": 0.3349651761380842, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 7.451403887688984e-06, | |
| "loss": 0.0615, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 39.05, | |
| "learning_rate": 7.12742980561555e-06, | |
| "loss": 0.0412, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 39.09, | |
| "learning_rate": 6.803455723542117e-06, | |
| "loss": 0.0496, | |
| "step": 9070 | |
| }, | |
| { | |
| "epoch": 39.14, | |
| "learning_rate": 6.479481641468681e-06, | |
| "loss": 0.0524, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 39.18, | |
| "learning_rate": 6.155507559395247e-06, | |
| "loss": 0.0485, | |
| "step": 9090 | |
| }, | |
| { | |
| "epoch": 39.22, | |
| "learning_rate": 5.831533477321813e-06, | |
| "loss": 0.0646, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 39.27, | |
| "learning_rate": 5.5075593952483795e-06, | |
| "loss": 0.0602, | |
| "step": 9110 | |
| }, | |
| { | |
| "epoch": 39.31, | |
| "learning_rate": 5.1835853131749455e-06, | |
| "loss": 0.0623, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 39.35, | |
| "learning_rate": 4.859611231101512e-06, | |
| "loss": 0.0399, | |
| "step": 9130 | |
| }, | |
| { | |
| "epoch": 39.4, | |
| "learning_rate": 4.535637149028078e-06, | |
| "loss": 0.0571, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 4.211663066954643e-06, | |
| "loss": 0.0668, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 39.48, | |
| "learning_rate": 3.887688984881209e-06, | |
| "loss": 0.0374, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 39.52, | |
| "learning_rate": 3.563714902807775e-06, | |
| "loss": 0.0424, | |
| "step": 9170 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 3.2397408207343406e-06, | |
| "loss": 0.047, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 39.61, | |
| "learning_rate": 2.9157667386609067e-06, | |
| "loss": 0.0562, | |
| "step": 9190 | |
| }, | |
| { | |
| "epoch": 39.65, | |
| "learning_rate": 2.5917926565874728e-06, | |
| "loss": 0.0789, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 39.7, | |
| "learning_rate": 2.267818574514039e-06, | |
| "loss": 0.0485, | |
| "step": 9210 | |
| }, | |
| { | |
| "epoch": 39.74, | |
| "learning_rate": 1.9438444924406045e-06, | |
| "loss": 0.0513, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 39.78, | |
| "learning_rate": 1.6198704103671703e-06, | |
| "loss": 0.0518, | |
| "step": 9230 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "learning_rate": 1.2958963282937364e-06, | |
| "loss": 0.0334, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 39.87, | |
| "learning_rate": 9.719222462203022e-07, | |
| "loss": 0.0257, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 39.91, | |
| "learning_rate": 6.479481641468682e-07, | |
| "loss": 0.055, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "learning_rate": 3.239740820734341e-07, | |
| "loss": 0.0444, | |
| "step": 9270 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0732, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.31733959913253784, | |
| "eval_runtime": 284.3146, | |
| "eval_samples_per_second": 10.706, | |
| "eval_wer": 0.3336529726456041, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 9280, | |
| "total_flos": 5.602791262432019e+19, | |
| "train_runtime": 9410.6193, | |
| "train_samples_per_second": 0.986 | |
| } | |
| ], | |
| "max_steps": 9280, | |
| "num_train_epochs": 40, | |
| "total_flos": 5.602791262432019e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |