| { | |
| "best_metric": 0.47945896840617747, | |
| "best_model_checkpoint": "/workspace/data2/el/wav2vec2-large-xlsr-greek/checkpoint-1740", | |
| "epoch": 14.995708154506438, | |
| "global_step": 1740, | |
| "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": 15.0, | |
| "step": 1740, | |
| "total_flos": 1.1283763966907363e+19, | |
| "train_runtime": 24181.2335, | |
| "train_samples_per_second": 0.072 | |
| } | |
| ], | |
| "max_steps": 1740, | |
| "num_train_epochs": 15, | |
| "total_flos": 1.1283763966907363e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |