| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 28.88888888888889, | |
| "global_step": 2600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 12.0901, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 11.5786, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 12.4996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 12.1575, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 11.6027, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 9.5766, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.2e-05, | |
| "loss": 7.3941, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 4.7536, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 3.7347, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.1484, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 2.928152322769165, | |
| "eval_runtime": 166.6108, | |
| "eval_samples_per_second": 4.309, | |
| "eval_steps_per_second": 0.54, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 2.8961, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 2.7846, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 7.8e-05, | |
| "loss": 2.7632, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.4e-05, | |
| "loss": 2.6963, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.7072, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 2.6889, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.000102, | |
| "loss": 2.6548, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 2.7483, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 2.6067, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.69, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 2.6755106449127197, | |
| "eval_runtime": 166.1686, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 0.542, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 2.6435, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 2.6126, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.000138, | |
| "loss": 2.6488, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 2.6612, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6615, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.000156, | |
| "loss": 2.6005, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.000162, | |
| "loss": 2.7924, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.000168, | |
| "loss": 2.5926, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 2.6799, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.6133, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 2.637242078781128, | |
| "eval_runtime": 154.1101, | |
| "eval_samples_per_second": 4.659, | |
| "eval_steps_per_second": 0.584, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.000186, | |
| "loss": 2.6176, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 2.6436, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.000198, | |
| "loss": 2.6309, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.000204, | |
| "loss": 2.6305, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.5714, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 2.6415, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00022199999999999998, | |
| "loss": 2.5131, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 2.4668, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.000234, | |
| "loss": 2.4911, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2501, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "eval_loss": 2.055128335952759, | |
| "eval_runtime": 153.8268, | |
| "eval_samples_per_second": 4.668, | |
| "eval_steps_per_second": 0.585, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.00024599999999999996, | |
| "loss": 2.0839, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.00025199999999999995, | |
| "loss": 1.8988, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 0.000258, | |
| "loss": 1.6222, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 1.2373, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00027, | |
| "loss": 1.078, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.000276, | |
| "loss": 0.866, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 0.7399, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 0.7751, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 0.000294, | |
| "loss": 0.6117, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6642, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_loss": 0.3055833578109741, | |
| "eval_runtime": 154.0205, | |
| "eval_samples_per_second": 4.662, | |
| "eval_steps_per_second": 0.584, | |
| "eval_wer": 0.39202622673434856, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00029249999999999995, | |
| "loss": 0.469, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.000285, | |
| "loss": 0.4959, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.00027749999999999997, | |
| "loss": 0.4317, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00027, | |
| "loss": 0.3656, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0002625, | |
| "loss": 0.3608, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 0.2853, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.00024749999999999994, | |
| "loss": 0.3534, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.2887, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 0.3348, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.000225, | |
| "loss": 0.2755, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_loss": 0.1520056277513504, | |
| "eval_runtime": 153.988, | |
| "eval_samples_per_second": 4.663, | |
| "eval_steps_per_second": 0.584, | |
| "eval_wer": 0.2118231810490694, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.00021749999999999997, | |
| "loss": 0.2901, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.2485, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0002025, | |
| "loss": 0.2533, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.000195, | |
| "loss": 0.2502, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.00018749999999999998, | |
| "loss": 0.1834, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.2201, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 0.00017249999999999996, | |
| "loss": 0.2079, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.000165, | |
| "loss": 0.226, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.00015749999999999998, | |
| "loss": 0.1831, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1749, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_loss": 0.10200744867324829, | |
| "eval_runtime": 153.705, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 0.586, | |
| "eval_wer": 0.1515439932318105, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 0.0001425, | |
| "loss": 0.163, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.000135, | |
| "loss": 0.1567, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 0.00012749999999999998, | |
| "loss": 0.1884, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.1245, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.145, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 0.1196, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 9.75e-05, | |
| "loss": 0.1875, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.1603, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 8.25e-05, | |
| "loss": 0.1459, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.1404, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_loss": 0.08183874934911728, | |
| "eval_runtime": 154.0029, | |
| "eval_samples_per_second": 4.662, | |
| "eval_steps_per_second": 0.584, | |
| "eval_wer": 0.13293147208121828, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.11, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.1284, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 0.1055, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.1459, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.1028, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.1635, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.1315, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.1215, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.157, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1064, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.07435603439807892, | |
| "eval_runtime": 154.0414, | |
| "eval_samples_per_second": 4.661, | |
| "eval_steps_per_second": 0.584, | |
| "eval_wer": 0.12531725888324874, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.00024409090909090905, | |
| "loss": 6.6354, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0002427272727272727, | |
| "loss": 3.0269, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 0.00024136363636363635, | |
| "loss": 2.7006, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.6422, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 0.0002386363636363636, | |
| "loss": 2.6196, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.00023727272727272724, | |
| "loss": 2.5681, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 0.0002359090909090909, | |
| "loss": 2.4665, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 0.00023454545454545454, | |
| "loss": 2.0804, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 0.00023318181818181814, | |
| "loss": 1.3389, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 0.0002318181818181818, | |
| "loss": 0.5882, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "eval_loss": 0.21222124993801117, | |
| "eval_runtime": 150.6754, | |
| "eval_samples_per_second": 4.765, | |
| "eval_steps_per_second": 0.597, | |
| "eval_wer": 0.2306472081218274, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00023045454545454544, | |
| "loss": 0.2554, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 0.00022909090909090907, | |
| "loss": 0.2722, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 0.0002277272727272727, | |
| "loss": 0.2067, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.00022636363636363633, | |
| "loss": 0.2437, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.000225, | |
| "loss": 0.1675, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 0.00022363636363636363, | |
| "loss": 0.181, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 0.00022227272727272726, | |
| "loss": 0.1562, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.0002209090909090909, | |
| "loss": 0.1805, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 0.00021954545454545452, | |
| "loss": 0.2045, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 0.00021818181818181816, | |
| "loss": 0.1813, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "eval_loss": 0.0888812392950058, | |
| "eval_runtime": 150.0493, | |
| "eval_samples_per_second": 4.785, | |
| "eval_steps_per_second": 0.6, | |
| "eval_wer": 0.14075719120135363, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 0.00021681818181818182, | |
| "loss": 0.2353, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 0.00021545454545454542, | |
| "loss": 0.1769, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 0.00021409090909090906, | |
| "loss": 0.1727, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 0.00021272727272727272, | |
| "loss": 0.1213, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 0.00021136363636363635, | |
| "loss": 0.1829, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.1414, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 0.00020863636363636361, | |
| "loss": 0.132, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 0.00020727272727272725, | |
| "loss": 0.1344, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 0.0002059090909090909, | |
| "loss": 0.1064, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.0002045454545454545, | |
| "loss": 0.1166, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "eval_loss": 0.06592676788568497, | |
| "eval_runtime": 149.9746, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 0.6, | |
| "eval_wer": 0.11928934010152284, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 0.00020318181818181815, | |
| "loss": 0.1118, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 0.0002018181818181818, | |
| "loss": 0.1629, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 0.00020045454545454544, | |
| "loss": 0.1198, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 0.0001990909090909091, | |
| "loss": 0.1352, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 0.0001977272727272727, | |
| "loss": 0.132, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 0.00019636363636363634, | |
| "loss": 0.1223, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 0.000195, | |
| "loss": 0.1334, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 0.00019363636363636363, | |
| "loss": 0.1102, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 0.00019227272727272723, | |
| "loss": 0.1369, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 0.0001909090909090909, | |
| "loss": 0.0871, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "eval_loss": 0.05411907657980919, | |
| "eval_runtime": 149.6406, | |
| "eval_samples_per_second": 4.798, | |
| "eval_steps_per_second": 0.601, | |
| "eval_wer": 0.11072335025380711, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 0.00018954545454545453, | |
| "loss": 0.1193, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 0.0001881818181818182, | |
| "loss": 0.0963, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 0.0001868181818181818, | |
| "loss": 0.1135, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.00018545454545454543, | |
| "loss": 0.0891, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.00018409090909090909, | |
| "loss": 0.0724, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.00018272727272727272, | |
| "loss": 0.1289, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 0.00018136363636363632, | |
| "loss": 0.0639, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0868, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 0.00017863636363636362, | |
| "loss": 0.0749, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 0.00017727272727272728, | |
| "loss": 0.091, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "eval_loss": 0.046893950551748276, | |
| "eval_runtime": 149.6721, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 0.601, | |
| "eval_wer": 0.10046531302876481, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.67, | |
| "learning_rate": 0.00017590909090909088, | |
| "loss": 0.0819, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.78, | |
| "learning_rate": 0.00017454545454545452, | |
| "loss": 0.0966, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 0.00017318181818181818, | |
| "loss": 0.0823, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 0.0001718181818181818, | |
| "loss": 0.0958, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 0.00017045454545454547, | |
| "loss": 0.1276, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.22, | |
| "learning_rate": 0.00016909090909090907, | |
| "loss": 0.0855, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 0.0001677272727272727, | |
| "loss": 0.1032, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 0.00016636363636363637, | |
| "loss": 0.0683, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 0.000165, | |
| "loss": 0.0988, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.0001636363636363636, | |
| "loss": 0.0551, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "eval_loss": 0.043081216514110565, | |
| "eval_runtime": 150.166, | |
| "eval_samples_per_second": 4.781, | |
| "eval_steps_per_second": 0.599, | |
| "eval_wer": 0.10268612521150593, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 0.00016227272727272726, | |
| "loss": 0.067, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 0.0001609090909090909, | |
| "loss": 0.0667, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 0.00015954545454545453, | |
| "loss": 0.0639, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 0.00015818181818181816, | |
| "loss": 0.0994, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 0.0001568181818181818, | |
| "loss": 0.0515, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 0.00015545454545454546, | |
| "loss": 0.0911, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 0.0001540909090909091, | |
| "loss": 0.0771, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 17.56, | |
| "learning_rate": 0.0001527272727272727, | |
| "loss": 0.0706, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 17.67, | |
| "learning_rate": 0.00015136363636363635, | |
| "loss": 0.0716, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0679, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "eval_loss": 0.043587520718574524, | |
| "eval_runtime": 149.9856, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 0.6, | |
| "eval_wer": 0.09898477157360407, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "learning_rate": 0.00014863636363636362, | |
| "loss": 0.0822, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 0.00014727272727272725, | |
| "loss": 0.0655, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 0.0001459090909090909, | |
| "loss": 0.1081, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 0.00014454545454545452, | |
| "loss": 0.0488, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 0.00014318181818181818, | |
| "loss": 0.0739, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 0.0001418181818181818, | |
| "loss": 0.0711, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 0.00014045454545454544, | |
| "loss": 0.0893, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 0.00013909090909090908, | |
| "loss": 0.0419, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 0.0001377272727272727, | |
| "loss": 0.0625, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 0.00013636363636363634, | |
| "loss": 0.0497, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "eval_loss": 0.030962202697992325, | |
| "eval_runtime": 150.4238, | |
| "eval_samples_per_second": 4.773, | |
| "eval_steps_per_second": 0.598, | |
| "eval_wer": 0.09443739424703891, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 0.000135, | |
| "loss": 0.0405, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 0.0001336363636363636, | |
| "loss": 0.0697, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 0.00013227272727272727, | |
| "loss": 0.0434, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "learning_rate": 0.0001309090909090909, | |
| "loss": 0.0696, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 0.00012954545454545453, | |
| "loss": 0.0538, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 0.00012818181818181817, | |
| "loss": 0.0951, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 0.0001268181818181818, | |
| "loss": 0.0545, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 0.00012545454545454543, | |
| "loss": 0.0622, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 0.0001240909090909091, | |
| "loss": 0.0884, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00012272727272727272, | |
| "loss": 0.0669, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.026656057685613632, | |
| "eval_runtime": 150.2929, | |
| "eval_samples_per_second": 4.777, | |
| "eval_steps_per_second": 0.599, | |
| "eval_wer": 0.0942258883248731, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.11, | |
| "learning_rate": 0.00012136363636363636, | |
| "loss": 0.066, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.0337, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 0.00011863636363636362, | |
| "loss": 0.0766, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 0.00011727272727272727, | |
| "loss": 0.0625, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "learning_rate": 0.0001159090909090909, | |
| "loss": 0.0539, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 20.67, | |
| "learning_rate": 0.00011454545454545453, | |
| "loss": 0.0605, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 20.78, | |
| "learning_rate": 0.00011318181818181817, | |
| "loss": 0.0465, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 0.00011181818181818181, | |
| "loss": 0.0642, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 0.00011045454545454545, | |
| "loss": 0.047, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "learning_rate": 0.00010909090909090908, | |
| "loss": 0.0532, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "eval_loss": 0.02508886530995369, | |
| "eval_runtime": 150.8935, | |
| "eval_samples_per_second": 4.758, | |
| "eval_steps_per_second": 0.596, | |
| "eval_wer": 0.09105329949238579, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 21.22, | |
| "learning_rate": 0.00010772727272727271, | |
| "loss": 0.0245, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 0.00010636363636363636, | |
| "loss": 0.0614, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 0.0333, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 21.56, | |
| "learning_rate": 0.00010363636363636362, | |
| "loss": 0.0463, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 21.67, | |
| "learning_rate": 0.00010227272727272726, | |
| "loss": 0.0509, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 0.0001009090909090909, | |
| "loss": 0.0522, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "learning_rate": 9.954545454545455e-05, | |
| "loss": 0.032, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 9.818181818181817e-05, | |
| "loss": 0.0491, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 22.11, | |
| "learning_rate": 9.681818181818181e-05, | |
| "loss": 0.0603, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 9.545454545454545e-05, | |
| "loss": 0.0269, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "eval_loss": 0.02213282324373722, | |
| "eval_runtime": 150.9545, | |
| "eval_samples_per_second": 4.756, | |
| "eval_steps_per_second": 0.596, | |
| "eval_wer": 0.09020727580372251, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 9.40909090909091e-05, | |
| "loss": 0.0544, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 9.272727272727271e-05, | |
| "loss": 0.0331, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 9.136363636363636e-05, | |
| "loss": 0.0502, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0493, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 8.863636363636364e-05, | |
| "loss": 0.0579, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 8.727272727272726e-05, | |
| "loss": 0.0392, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.59090909090909e-05, | |
| "loss": 0.0423, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 8.454545454545454e-05, | |
| "loss": 0.0696, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 23.22, | |
| "learning_rate": 8.318181818181818e-05, | |
| "loss": 0.0304, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 8.18181818181818e-05, | |
| "loss": 0.0686, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "eval_loss": 0.020356198772788048, | |
| "eval_runtime": 151.0382, | |
| "eval_samples_per_second": 4.754, | |
| "eval_steps_per_second": 0.596, | |
| "eval_wer": 0.08745769881556684, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 8.045454545454545e-05, | |
| "loss": 0.0523, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 23.56, | |
| "learning_rate": 7.909090909090908e-05, | |
| "loss": 0.0583, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 23.67, | |
| "learning_rate": 7.772727272727273e-05, | |
| "loss": 0.0495, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 23.78, | |
| "learning_rate": 7.636363636363635e-05, | |
| "loss": 0.0476, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0321, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 7.363636363636363e-05, | |
| "loss": 0.0393, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 24.11, | |
| "learning_rate": 7.227272727272726e-05, | |
| "loss": 0.0425, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 24.22, | |
| "learning_rate": 7.09090909090909e-05, | |
| "loss": 0.064, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 24.33, | |
| "learning_rate": 6.954545454545454e-05, | |
| "loss": 0.048, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 6.818181818181817e-05, | |
| "loss": 0.0242, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "eval_loss": 0.018909653648734093, | |
| "eval_runtime": 151.2527, | |
| "eval_samples_per_second": 4.747, | |
| "eval_steps_per_second": 0.595, | |
| "eval_wer": 0.08724619289340102, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 24.56, | |
| "learning_rate": 6.68181818181818e-05, | |
| "loss": 0.0481, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 24.67, | |
| "learning_rate": 6.545454545454545e-05, | |
| "loss": 0.0442, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 24.78, | |
| "learning_rate": 6.409090909090908e-05, | |
| "loss": 0.05, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 6.272727272727272e-05, | |
| "loss": 0.0474, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 6.136363636363636e-05, | |
| "loss": 0.0391, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.068, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 25.22, | |
| "learning_rate": 5.8636363636363634e-05, | |
| "loss": 0.0189, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 5.727272727272727e-05, | |
| "loss": 0.0396, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 5.590909090909091e-05, | |
| "loss": 0.0317, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "learning_rate": 5.454545454545454e-05, | |
| "loss": 0.0454, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "eval_loss": 0.01684204488992691, | |
| "eval_runtime": 150.5397, | |
| "eval_samples_per_second": 4.77, | |
| "eval_steps_per_second": 0.598, | |
| "eval_wer": 0.08513113367174281, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 25.67, | |
| "learning_rate": 5.318181818181818e-05, | |
| "loss": 0.0317, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "learning_rate": 5.181818181818181e-05, | |
| "loss": 0.0315, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "learning_rate": 5.045454545454545e-05, | |
| "loss": 0.0302, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 4.9090909090909084e-05, | |
| "loss": 0.0359, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 4.7727272727272724e-05, | |
| "loss": 0.0433, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 4.6363636363636356e-05, | |
| "loss": 0.0222, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 26.33, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.0474, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 26.44, | |
| "learning_rate": 4.363636363636363e-05, | |
| "loss": 0.026, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 4.227272727272727e-05, | |
| "loss": 0.0391, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 4.09090909090909e-05, | |
| "loss": 0.0424, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "eval_loss": 0.016244513913989067, | |
| "eval_runtime": 151.2464, | |
| "eval_samples_per_second": 4.747, | |
| "eval_steps_per_second": 0.595, | |
| "eval_wer": 0.08555414551607445, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 26.78, | |
| "learning_rate": 3.954545454545454e-05, | |
| "loss": 0.035, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 26.89, | |
| "learning_rate": 3.8181818181818174e-05, | |
| "loss": 0.0218, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 3.681818181818181e-05, | |
| "loss": 0.0363, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 3.545454545454545e-05, | |
| "loss": 0.0285, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 3.4090909090909085e-05, | |
| "loss": 0.0257, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 3.2727272727272725e-05, | |
| "loss": 0.0466, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 27.44, | |
| "learning_rate": 3.136363636363636e-05, | |
| "loss": 0.0194, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 27.56, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.0579, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 27.67, | |
| "learning_rate": 2.8636363636363634e-05, | |
| "loss": 0.0414, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 2.727272727272727e-05, | |
| "loss": 0.0641, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "eval_loss": 0.01549264881759882, | |
| "eval_runtime": 151.2416, | |
| "eval_samples_per_second": 4.747, | |
| "eval_steps_per_second": 0.595, | |
| "eval_wer": 0.0850253807106599, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "learning_rate": 2.5909090909090906e-05, | |
| "loss": 0.0307, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.4545454545454542e-05, | |
| "loss": 0.0327, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 28.11, | |
| "learning_rate": 2.3181818181818178e-05, | |
| "loss": 0.0472, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 28.22, | |
| "learning_rate": 2.1818181818181814e-05, | |
| "loss": 0.0312, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 28.33, | |
| "learning_rate": 2.045454545454545e-05, | |
| "loss": 0.0543, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 1.9090909090909087e-05, | |
| "loss": 0.0294, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 28.56, | |
| "learning_rate": 1.7727272727272726e-05, | |
| "loss": 0.044, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 28.67, | |
| "learning_rate": 1.6363636363636363e-05, | |
| "loss": 0.0359, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 28.78, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.0294, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 1.3636363636363635e-05, | |
| "loss": 0.0188, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "eval_loss": 0.014889966696500778, | |
| "eval_runtime": 151.5825, | |
| "eval_samples_per_second": 4.737, | |
| "eval_steps_per_second": 0.594, | |
| "eval_wer": 0.08491962774957698, | |
| "step": 2600 | |
| } | |
| ], | |
| "max_steps": 2700, | |
| "num_train_epochs": 30, | |
| "total_flos": 9.754561830239207e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |