| { | |
| "best_metric": 0.40934863686561584, | |
| "best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-13k_onset-drums_fold_3/checkpoint-1330", | |
| "epoch": 49.99644128113879, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.1395, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.4091, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.2012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.3575, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00015, | |
| "loss": 0.3829, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.2312, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.4557, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.579447865486145, | |
| "eval_runtime": 61.0909, | |
| "eval_samples_per_second": 9.068, | |
| "eval_steps_per_second": 2.275, | |
| "eval_wer": 0.11969282372671904, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.000237, | |
| "loss": 0.1655, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.000267, | |
| "loss": 0.4363, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 0.2276, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002992058823529411, | |
| "loss": 0.4259, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00029832352941176467, | |
| "loss": 0.3656, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002974411764705882, | |
| "loss": 0.2647, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00029655882352941175, | |
| "loss": 0.6796, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5726304054260254, | |
| "eval_runtime": 60.2808, | |
| "eval_samples_per_second": 9.19, | |
| "eval_steps_per_second": 2.306, | |
| "eval_wer": 0.13880307176273282, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002956764705882353, | |
| "loss": 0.1551, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002947941176470588, | |
| "loss": 0.4401, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00029391176470588233, | |
| "loss": 0.2292, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00029302941176470587, | |
| "loss": 0.3019, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002921470588235294, | |
| "loss": 0.4165, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002912647058823529, | |
| "loss": 0.2171, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00029038235294117645, | |
| "loss": 0.4511, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.629001259803772, | |
| "eval_runtime": 59.9911, | |
| "eval_samples_per_second": 9.235, | |
| "eval_steps_per_second": 2.317, | |
| "eval_wer": 0.12423867949510106, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0002895, | |
| "loss": 0.16, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0002886176470588235, | |
| "loss": 0.4099, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.000287735294117647, | |
| "loss": 0.2922, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 0.00028685294117647056, | |
| "loss": 0.3454, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0002859705882352941, | |
| "loss": 0.3749, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00028508823529411765, | |
| "loss": 0.2179, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0002842941176470588, | |
| "loss": 0.609, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.7111949920654297, | |
| "eval_runtime": 61.6827, | |
| "eval_samples_per_second": 8.981, | |
| "eval_steps_per_second": 2.253, | |
| "eval_wer": 0.11872186424221026, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00028341176470588234, | |
| "loss": 0.1461, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.00028252941176470583, | |
| "loss": 0.4796, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.0002816470588235294, | |
| "loss": 0.2129, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0002807647058823529, | |
| "loss": 0.338, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 0.00027988235294117646, | |
| "loss": 0.4499, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.000279, | |
| "loss": 0.2257, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0002781176470588235, | |
| "loss": 0.4082, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.8274657726287842, | |
| "eval_runtime": 60.9118, | |
| "eval_samples_per_second": 9.095, | |
| "eval_steps_per_second": 2.282, | |
| "eval_wer": 0.19648689204695913, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.00027723529411764704, | |
| "loss": 0.1456, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.0002763529411764706, | |
| "loss": 0.5257, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00027547058823529407, | |
| "loss": 0.2441, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.0002745882352941176, | |
| "loss": 0.3545, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00027370588235294116, | |
| "loss": 0.3446, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.0002728235294117647, | |
| "loss": 0.238, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00027194117647058824, | |
| "loss": 0.4638, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.4767338037490845, | |
| "eval_runtime": 60.9324, | |
| "eval_samples_per_second": 9.092, | |
| "eval_steps_per_second": 2.281, | |
| "eval_wer": 0.15244063906787889, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00027105882352941173, | |
| "loss": 0.1649, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.0002701764705882353, | |
| "loss": 0.4053, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 0.0002692941176470588, | |
| "loss": 0.2435, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.0002684117647058823, | |
| "loss": 0.3678, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 0.00026752941176470585, | |
| "loss": 0.4237, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 0.0002666470588235294, | |
| "loss": 0.1854, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00026576470588235293, | |
| "loss": 0.4446, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.5091004371643066, | |
| "eval_runtime": 60.5634, | |
| "eval_samples_per_second": 9.147, | |
| "eval_steps_per_second": 2.295, | |
| "eval_wer": 0.13756730514608526, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.0002648823529411764, | |
| "loss": 0.1857, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 0.455, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 0.0002631176470588235, | |
| "loss": 0.2588, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 0.00026223529411764705, | |
| "loss": 0.3395, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 0.0002613529411764706, | |
| "loss": 0.4188, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.0002604705882352941, | |
| "loss": 0.2152, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.0002595882352941176, | |
| "loss": 0.4337, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6622414588928223, | |
| "eval_runtime": 60.9399, | |
| "eval_samples_per_second": 9.091, | |
| "eval_steps_per_second": 2.281, | |
| "eval_wer": 0.1169564833612852, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 0.0002587058823529411, | |
| "loss": 0.1494, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.00025782352941176466, | |
| "loss": 0.4347, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 0.0002569411764705882, | |
| "loss": 0.1981, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.00025605882352941174, | |
| "loss": 0.3448, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0002551764705882353, | |
| "loss": 0.3804, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 0.0002542941176470588, | |
| "loss": 0.1973, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.0002534117647058823, | |
| "loss": 0.4604, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.7241520285606384, | |
| "eval_runtime": 61.8545, | |
| "eval_samples_per_second": 8.957, | |
| "eval_steps_per_second": 2.247, | |
| "eval_wer": 0.16003177685585665, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00025252941176470586, | |
| "loss": 0.1438, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 0.0002516470588235294, | |
| "loss": 0.4328, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 0.00025076470588235295, | |
| "loss": 0.2, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00024988235294117644, | |
| "loss": 0.3489, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.000249, | |
| "loss": 0.3614, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 0.0002481176470588235, | |
| "loss": 0.2214, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.000247235294117647, | |
| "loss": 0.4462, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.7297729253768921, | |
| "eval_runtime": 61.4641, | |
| "eval_samples_per_second": 9.013, | |
| "eval_steps_per_second": 2.261, | |
| "eval_wer": 0.1382734574984553, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 0.00024635294117647056, | |
| "loss": 0.1855, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 0.0002454705882352941, | |
| "loss": 0.3853, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.00024458823529411764, | |
| "loss": 0.237, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 0.00024370588235294116, | |
| "loss": 0.3814, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 0.0002428235294117647, | |
| "loss": 0.4028, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 0.00024194117647058822, | |
| "loss": 0.2268, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 0.0002411470588235294, | |
| "loss": 0.4201, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.8057843446731567, | |
| "eval_runtime": 60.5672, | |
| "eval_samples_per_second": 9.147, | |
| "eval_steps_per_second": 2.295, | |
| "eval_wer": 0.1361550004413452, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 0.00024026470588235294, | |
| "loss": 0.138, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 0.00023938235294117645, | |
| "loss": 0.4324, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.0002385, | |
| "loss": 0.212, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 0.0002376176470588235, | |
| "loss": 0.3338, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 0.00023673529411764703, | |
| "loss": 0.2872, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 0.00023585294117647054, | |
| "loss": 0.182, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.0002349705882352941, | |
| "loss": 0.4204, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.62545245885849, | |
| "eval_runtime": 61.0475, | |
| "eval_samples_per_second": 9.075, | |
| "eval_steps_per_second": 2.277, | |
| "eval_wer": 0.10993909435960808, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 0.00023408823529411763, | |
| "loss": 0.1244, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 0.00023320588235294115, | |
| "loss": 0.3727, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 0.0002323235294117647, | |
| "loss": 0.2171, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 0.0002314411764705882, | |
| "loss": 0.4511, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 0.00023055882352941175, | |
| "loss": 0.3043, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.0002296764705882353, | |
| "loss": 0.182, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 0.0002287941176470588, | |
| "loss": 0.461, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.5204018354415894, | |
| "eval_runtime": 61.1638, | |
| "eval_samples_per_second": 9.058, | |
| "eval_steps_per_second": 2.273, | |
| "eval_wer": 0.11086591932209375, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 0.00022791176470588235, | |
| "loss": 0.1363, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00022702941176470584, | |
| "loss": 0.3638, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 0.00022614705882352938, | |
| "loss": 0.181, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 0.00022526470588235293, | |
| "loss": 0.3474, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00022438235294117644, | |
| "loss": 0.3108, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 0.00022349999999999998, | |
| "loss": 0.19, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 0.0002226176470588235, | |
| "loss": 0.3779, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.6911052465438843, | |
| "eval_runtime": 61.2588, | |
| "eval_samples_per_second": 9.044, | |
| "eval_steps_per_second": 2.269, | |
| "eval_wer": 0.11254303115897255, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 0.00022173529411764704, | |
| "loss": 0.1216, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 0.0002208529411764706, | |
| "loss": 0.4949, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 0.0002199705882352941, | |
| "loss": 0.1981, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.00021908823529411765, | |
| "loss": 0.366, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 0.00021820588235294113, | |
| "loss": 0.3375, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 0.00021732352941176468, | |
| "loss": 0.1859, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 0.0002164411764705882, | |
| "loss": 0.3403, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.5862817764282227, | |
| "eval_runtime": 62.3222, | |
| "eval_samples_per_second": 8.889, | |
| "eval_steps_per_second": 2.23, | |
| "eval_wer": 0.11876599876423338, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 0.00021555882352941174, | |
| "loss": 0.132, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 0.00021467647058823528, | |
| "loss": 0.3601, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 0.0002137941176470588, | |
| "loss": 0.1589, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 0.00021291176470588234, | |
| "loss": 0.3223, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 0.00021202941176470588, | |
| "loss": 0.4736, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 0.0002111470588235294, | |
| "loss": 0.3431, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 0.00021035294117647058, | |
| "loss": 0.6223, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.6366881132125854, | |
| "eval_runtime": 61.0383, | |
| "eval_samples_per_second": 9.076, | |
| "eval_steps_per_second": 2.277, | |
| "eval_wer": 0.11470562273810575, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 0.0002094705882352941, | |
| "loss": 0.1578, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 0.00020858823529411763, | |
| "loss": 0.3961, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 0.00020770588235294118, | |
| "loss": 0.1761, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 0.0002068235294117647, | |
| "loss": 0.278, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 0.00020594117647058824, | |
| "loss": 0.3555, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.85, | |
| "learning_rate": 0.00020505882352941173, | |
| "loss": 0.2907, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 0.00020417647058823527, | |
| "loss": 0.3827, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.6265905499458313, | |
| "eval_runtime": 63.2959, | |
| "eval_samples_per_second": 8.753, | |
| "eval_steps_per_second": 2.196, | |
| "eval_wer": 0.12927001500573748, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.00020329411764705878, | |
| "loss": 0.1743, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 0.00020241176470588233, | |
| "loss": 0.4271, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 0.00020152941176470587, | |
| "loss": 0.2163, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 0.00020064705882352939, | |
| "loss": 0.3818, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 0.00019976470588235293, | |
| "loss": 0.3243, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 0.00019888235294117647, | |
| "loss": 0.1859, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 0.000198, | |
| "loss": 0.3055, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.4865553081035614, | |
| "eval_runtime": 62.6413, | |
| "eval_samples_per_second": 8.844, | |
| "eval_steps_per_second": 2.219, | |
| "eval_wer": 0.10949774913937682, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 0.00019711764705882353, | |
| "loss": 0.14, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 0.00019623529411764705, | |
| "loss": 0.333, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 18.43, | |
| "learning_rate": 0.00019535294117647056, | |
| "loss": 0.1916, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 0.00019447058823529408, | |
| "loss": 0.3596, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 0.00019358823529411762, | |
| "loss": 0.3389, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 0.00019270588235294117, | |
| "loss": 0.1745, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 0.00019182352941176468, | |
| "loss": 0.3917, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.40934863686561584, | |
| "eval_runtime": 61.2696, | |
| "eval_samples_per_second": 9.042, | |
| "eval_steps_per_second": 2.269, | |
| "eval_wer": 0.12498896636949422, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 0.00019094117647058822, | |
| "loss": 0.1308, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 19.28, | |
| "learning_rate": 0.00019005882352941174, | |
| "loss": 0.4134, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 0.00018917647058823528, | |
| "loss": 0.1628, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 0.00018829411764705883, | |
| "loss": 0.2364, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 0.00018741176470588234, | |
| "loss": 0.3563, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 0.00018652941176470586, | |
| "loss": 0.1755, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00018564705882352937, | |
| "loss": 0.3912, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.45144104957580566, | |
| "eval_runtime": 60.6538, | |
| "eval_samples_per_second": 9.134, | |
| "eval_steps_per_second": 2.292, | |
| "eval_wer": 0.10768823373642863, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 0.00018476470588235292, | |
| "loss": 0.1099, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 20.28, | |
| "learning_rate": 0.00018388235294117646, | |
| "loss": 0.3581, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 0.00018299999999999998, | |
| "loss": 0.1691, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "learning_rate": 0.00018211764705882352, | |
| "loss": 0.26, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 0.00018123529411764703, | |
| "loss": 0.3123, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 20.85, | |
| "learning_rate": 0.00018035294117647058, | |
| "loss": 0.163, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 0.00017947058823529412, | |
| "loss": 0.3861, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.5043449401855469, | |
| "eval_runtime": 61.5082, | |
| "eval_samples_per_second": 9.007, | |
| "eval_steps_per_second": 2.26, | |
| "eval_wer": 0.11558831317856827, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 21.14, | |
| "learning_rate": 0.00017858823529411764, | |
| "loss": 0.1451, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 0.00017770588235294118, | |
| "loss": 0.3931, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 0.00017682352941176467, | |
| "loss": 0.2034, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 0.0001759411764705882, | |
| "loss": 0.2406, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 21.71, | |
| "learning_rate": 0.00017505882352941173, | |
| "loss": 0.2293, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 0.00017417647058823527, | |
| "loss": 0.1814, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 0.00017329411764705881, | |
| "loss": 0.3659, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.5679603219032288, | |
| "eval_runtime": 61.2195, | |
| "eval_samples_per_second": 9.049, | |
| "eval_steps_per_second": 2.271, | |
| "eval_wer": 0.1091446729631918, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 0.00017241176470588233, | |
| "loss": 0.1197, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 22.28, | |
| "learning_rate": 0.00017152941176470587, | |
| "loss": 0.3333, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 22.43, | |
| "learning_rate": 0.00017064705882352942, | |
| "loss": 0.1489, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 0.00016976470588235293, | |
| "loss": 0.2818, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 22.71, | |
| "learning_rate": 0.00016888235294117647, | |
| "loss": 0.3418, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 22.85, | |
| "learning_rate": 0.000168, | |
| "loss": 0.1835, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 0.0001671176470588235, | |
| "loss": 0.3536, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.7939728498458862, | |
| "eval_runtime": 61.589, | |
| "eval_samples_per_second": 8.995, | |
| "eval_steps_per_second": 2.257, | |
| "eval_wer": 0.10287757083590784, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 23.14, | |
| "learning_rate": 0.00016623529411764702, | |
| "loss": 0.1243, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "learning_rate": 0.00016535294117647057, | |
| "loss": 0.3339, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 23.43, | |
| "learning_rate": 0.0001644705882352941, | |
| "loss": 0.1624, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 0.00016358823529411762, | |
| "loss": 0.2548, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 23.71, | |
| "learning_rate": 0.00016270588235294117, | |
| "loss": 0.2613, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 23.85, | |
| "learning_rate": 0.00016182352941176468, | |
| "loss": 0.1547, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 0.00016094117647058823, | |
| "loss": 0.3559, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.587660014629364, | |
| "eval_runtime": 63.2209, | |
| "eval_samples_per_second": 8.763, | |
| "eval_steps_per_second": 2.199, | |
| "eval_wer": 0.11011563244770059, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 24.14, | |
| "learning_rate": 0.00016005882352941177, | |
| "loss": 0.1093, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 24.28, | |
| "learning_rate": 0.00015917647058823529, | |
| "loss": 0.2855, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 24.43, | |
| "learning_rate": 0.0001582941176470588, | |
| "loss": 0.1729, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "learning_rate": 0.00015741176470588232, | |
| "loss": 0.2575, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "learning_rate": 0.00015652941176470586, | |
| "loss": 0.2951, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "learning_rate": 0.0001556470588235294, | |
| "loss": 0.1565, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 0.00015476470588235292, | |
| "loss": 0.3274, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.44608035683631897, | |
| "eval_runtime": 62.0115, | |
| "eval_samples_per_second": 8.934, | |
| "eval_steps_per_second": 2.242, | |
| "eval_wer": 0.10587871833348045, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 25.14, | |
| "learning_rate": 0.00015388235294117646, | |
| "loss": 0.1207, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 0.00015299999999999998, | |
| "loss": 0.3352, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 25.43, | |
| "learning_rate": 0.00015211764705882352, | |
| "loss": 0.1703, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 0.00015123529411764706, | |
| "loss": 0.2749, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 0.00015035294117647058, | |
| "loss": 0.2942, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.85, | |
| "learning_rate": 0.0001494705882352941, | |
| "loss": 0.2039, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 0.00014858823529411764, | |
| "loss": 0.5232, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 1.2050672769546509, | |
| "eval_runtime": 62.8751, | |
| "eval_samples_per_second": 8.811, | |
| "eval_steps_per_second": 2.211, | |
| "eval_wer": 0.10684967781798924, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 26.14, | |
| "learning_rate": 0.00014770588235294116, | |
| "loss": 0.1191, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "learning_rate": 0.0001468235294117647, | |
| "loss": 0.3539, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 0.00014594117647058821, | |
| "loss": 0.1653, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 0.00014505882352941176, | |
| "loss": 0.2465, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 26.71, | |
| "learning_rate": 0.00014417647058823527, | |
| "loss": 0.2764, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 0.00014329411764705882, | |
| "loss": 0.1561, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 0.00014241176470588236, | |
| "loss": 0.3241, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.8716017603874207, | |
| "eval_runtime": 61.46, | |
| "eval_samples_per_second": 9.014, | |
| "eval_steps_per_second": 2.262, | |
| "eval_wer": 0.10985082531556183, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 0.00014152941176470588, | |
| "loss": 0.1404, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 27.28, | |
| "learning_rate": 0.0001406470588235294, | |
| "loss": 0.3247, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 27.43, | |
| "learning_rate": 0.00013976470588235293, | |
| "loss": 0.1811, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "learning_rate": 0.00013888235294117645, | |
| "loss": 0.2521, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 27.71, | |
| "learning_rate": 0.000138, | |
| "loss": 0.2443, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 27.85, | |
| "learning_rate": 0.0001371176470588235, | |
| "loss": 0.1426, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 0.00013623529411764705, | |
| "loss": 0.3169, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.6752051711082458, | |
| "eval_runtime": 62.1375, | |
| "eval_samples_per_second": 8.916, | |
| "eval_steps_per_second": 2.237, | |
| "eval_wer": 0.10817371347868303, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 28.14, | |
| "learning_rate": 0.00013535294117647057, | |
| "loss": 0.1185, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 28.28, | |
| "learning_rate": 0.0001344705882352941, | |
| "loss": 0.5584, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 0.00013358823529411763, | |
| "loss": 0.1511, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.00013270588235294117, | |
| "loss": 0.3996, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 28.71, | |
| "learning_rate": 0.00013182352941176469, | |
| "loss": 0.2446, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.00013094117647058823, | |
| "loss": 0.1531, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 0.00013005882352941175, | |
| "loss": 0.2938, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.6023386120796204, | |
| "eval_runtime": 62.9125, | |
| "eval_samples_per_second": 8.806, | |
| "eval_steps_per_second": 2.209, | |
| "eval_wer": 0.10711448495012799, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 0.0001291764705882353, | |
| "loss": 0.1146, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 0.00012829411764705883, | |
| "loss": 0.341, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 29.43, | |
| "learning_rate": 0.00012741176470588235, | |
| "loss": 0.198, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 0.00012652941176470586, | |
| "loss": 0.2276, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 29.71, | |
| "learning_rate": 0.0001256470588235294, | |
| "loss": 0.2366, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 0.00012476470588235292, | |
| "loss": 0.1465, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.00012388235294117647, | |
| "loss": 0.3022, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.6121745705604553, | |
| "eval_runtime": 61.3732, | |
| "eval_samples_per_second": 9.027, | |
| "eval_steps_per_second": 2.265, | |
| "eval_wer": 0.1146173536940595, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 0.00012299999999999998, | |
| "loss": 0.115, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 0.00012211764705882352, | |
| "loss": 0.2745, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 0.00012123529411764705, | |
| "loss": 0.1518, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 30.57, | |
| "learning_rate": 0.00012035294117647058, | |
| "loss": 0.2631, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 30.71, | |
| "learning_rate": 0.00011947058823529411, | |
| "loss": 0.2748, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 30.85, | |
| "learning_rate": 0.00011858823529411763, | |
| "loss": 0.151, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 0.00011770588235294116, | |
| "loss": 0.4245, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.5734956860542297, | |
| "eval_runtime": 61.7174, | |
| "eval_samples_per_second": 8.976, | |
| "eval_steps_per_second": 2.252, | |
| "eval_wer": 0.11024803601376996, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 31.14, | |
| "learning_rate": 0.00011682352941176469, | |
| "loss": 0.1072, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 31.28, | |
| "learning_rate": 0.00011594117647058823, | |
| "loss": 0.3154, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 0.00011505882352941176, | |
| "loss": 0.1464, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "learning_rate": 0.00011417647058823529, | |
| "loss": 0.3405, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 31.71, | |
| "learning_rate": 0.0001132941176470588, | |
| "loss": 0.2523, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 31.85, | |
| "learning_rate": 0.00011241176470588233, | |
| "loss": 0.139, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 0.00011152941176470588, | |
| "loss": 0.3095, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.44760027527809143, | |
| "eval_runtime": 64.5226, | |
| "eval_samples_per_second": 8.586, | |
| "eval_steps_per_second": 2.154, | |
| "eval_wer": 0.10424574101862477, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "learning_rate": 0.00011064705882352941, | |
| "loss": 0.0991, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 32.28, | |
| "learning_rate": 0.00010976470588235294, | |
| "loss": 0.3751, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 32.43, | |
| "learning_rate": 0.00010888235294117645, | |
| "loss": 0.1436, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 32.57, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 0.2354, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 32.71, | |
| "learning_rate": 0.00010711764705882353, | |
| "loss": 0.2672, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 32.85, | |
| "learning_rate": 0.00010623529411764705, | |
| "loss": 0.1488, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 0.00010535294117647058, | |
| "loss": 0.4062, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.6338868141174316, | |
| "eval_runtime": 62.7876, | |
| "eval_samples_per_second": 8.823, | |
| "eval_steps_per_second": 2.214, | |
| "eval_wer": 0.11298437637920382, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 33.14, | |
| "learning_rate": 0.0001044705882352941, | |
| "loss": 0.097, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 0.00010358823529411763, | |
| "loss": 0.3635, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 33.43, | |
| "learning_rate": 0.00010270588235294116, | |
| "loss": 0.1574, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "learning_rate": 0.0001018235294117647, | |
| "loss": 0.29, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 33.71, | |
| "learning_rate": 0.00010094117647058823, | |
| "loss": 0.2742, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 0.00010005882352941176, | |
| "loss": 0.1525, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 9.917647058823528e-05, | |
| "loss": 0.3202, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.4100561738014221, | |
| "eval_runtime": 63.085, | |
| "eval_samples_per_second": 8.782, | |
| "eval_steps_per_second": 2.203, | |
| "eval_wer": 0.10773236825845176, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 34.14, | |
| "learning_rate": 9.829411764705881e-05, | |
| "loss": 0.1267, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 34.28, | |
| "learning_rate": 9.741176470588235e-05, | |
| "loss": 0.3309, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 34.43, | |
| "learning_rate": 9.652941176470588e-05, | |
| "loss": 0.1499, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 34.57, | |
| "learning_rate": 9.564705882352941e-05, | |
| "loss": 0.3999, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 34.71, | |
| "learning_rate": 9.476470588235292e-05, | |
| "loss": 0.2331, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 34.85, | |
| "learning_rate": 9.388235294117645e-05, | |
| "loss": 0.1546, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 9.3e-05, | |
| "loss": 0.2952, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.482459157705307, | |
| "eval_runtime": 62.1602, | |
| "eval_samples_per_second": 8.912, | |
| "eval_steps_per_second": 2.236, | |
| "eval_wer": 0.10764409921440551, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 35.14, | |
| "learning_rate": 9.211764705882353e-05, | |
| "loss": 0.086, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 35.28, | |
| "learning_rate": 9.123529411764706e-05, | |
| "loss": 0.2821, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 35.43, | |
| "learning_rate": 9.035294117647057e-05, | |
| "loss": 0.1255, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "learning_rate": 8.94705882352941e-05, | |
| "loss": 0.2398, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 8.858823529411763e-05, | |
| "loss": 0.2614, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 35.85, | |
| "learning_rate": 8.770588235294117e-05, | |
| "loss": 0.1592, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 8.68235294117647e-05, | |
| "loss": 0.2945, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.49982911348342896, | |
| "eval_runtime": 61.8993, | |
| "eval_samples_per_second": 8.95, | |
| "eval_steps_per_second": 2.246, | |
| "eval_wer": 0.1057904492894342, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 36.14, | |
| "learning_rate": 8.594117647058823e-05, | |
| "loss": 0.1133, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 36.28, | |
| "learning_rate": 8.505882352941175e-05, | |
| "loss": 0.3159, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 8.417647058823528e-05, | |
| "loss": 0.1241, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 36.57, | |
| "learning_rate": 8.329411764705882e-05, | |
| "loss": 0.2015, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 36.71, | |
| "learning_rate": 8.241176470588235e-05, | |
| "loss": 0.2569, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 36.85, | |
| "learning_rate": 8.152941176470588e-05, | |
| "loss": 0.1456, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 8.06470588235294e-05, | |
| "loss": 0.336, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.5490187406539917, | |
| "eval_runtime": 62.1361, | |
| "eval_samples_per_second": 8.916, | |
| "eval_steps_per_second": 2.237, | |
| "eval_wer": 0.10605525642157296, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 37.14, | |
| "learning_rate": 7.976470588235293e-05, | |
| "loss": 0.1051, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 37.28, | |
| "learning_rate": 7.888235294117647e-05, | |
| "loss": 0.2763, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 37.43, | |
| "learning_rate": 7.8e-05, | |
| "loss": 0.1541, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 37.57, | |
| "learning_rate": 7.711764705882353e-05, | |
| "loss": 0.251, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 37.71, | |
| "learning_rate": 7.623529411764704e-05, | |
| "loss": 0.2262, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 37.85, | |
| "learning_rate": 7.535294117647057e-05, | |
| "loss": 0.1579, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 7.44705882352941e-05, | |
| "loss": 0.2912, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.4803949296474457, | |
| "eval_runtime": 63.1147, | |
| "eval_samples_per_second": 8.778, | |
| "eval_steps_per_second": 2.202, | |
| "eval_wer": 0.1038043957983935, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 38.14, | |
| "learning_rate": 7.358823529411765e-05, | |
| "loss": 0.0978, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 38.28, | |
| "learning_rate": 7.270588235294116e-05, | |
| "loss": 0.3715, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 38.43, | |
| "learning_rate": 7.18235294117647e-05, | |
| "loss": 0.1421, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 7.094117647058823e-05, | |
| "loss": 0.2745, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 7.005882352941175e-05, | |
| "loss": 0.2492, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "learning_rate": 6.91764705882353e-05, | |
| "loss": 0.15, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 6.829411764705882e-05, | |
| "loss": 0.282, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.4775891900062561, | |
| "eval_runtime": 63.4921, | |
| "eval_samples_per_second": 8.726, | |
| "eval_steps_per_second": 2.189, | |
| "eval_wer": 0.10221555300556096, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 39.14, | |
| "learning_rate": 6.741176470588235e-05, | |
| "loss": 0.1008, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 39.28, | |
| "learning_rate": 6.652941176470588e-05, | |
| "loss": 0.2443, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 39.43, | |
| "learning_rate": 6.56470588235294e-05, | |
| "loss": 0.1629, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 6.476470588235294e-05, | |
| "loss": 0.2152, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 39.71, | |
| "learning_rate": 6.388235294117647e-05, | |
| "loss": 0.2261, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 39.85, | |
| "learning_rate": 6.299999999999999e-05, | |
| "loss": 0.1623, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 6.211764705882353e-05, | |
| "loss": 0.4359, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.437634140253067, | |
| "eval_runtime": 62.5272, | |
| "eval_samples_per_second": 8.86, | |
| "eval_steps_per_second": 2.223, | |
| "eval_wer": 0.10437814458469415, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 6.123529411764706e-05, | |
| "loss": 0.0806, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 40.28, | |
| "learning_rate": 6.035294117647058e-05, | |
| "loss": 0.2599, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 40.43, | |
| "learning_rate": 5.947058823529411e-05, | |
| "loss": 0.1453, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 40.57, | |
| "learning_rate": 5.858823529411764e-05, | |
| "loss": 0.2781, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 40.71, | |
| "learning_rate": 5.770588235294117e-05, | |
| "loss": 0.2219, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 40.85, | |
| "learning_rate": 5.6823529411764706e-05, | |
| "loss": 0.1356, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 5.594117647058823e-05, | |
| "loss": 0.2698, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.5608607530593872, | |
| "eval_runtime": 62.2619, | |
| "eval_samples_per_second": 8.898, | |
| "eval_steps_per_second": 2.233, | |
| "eval_wer": 0.10976255627151559, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 41.14, | |
| "learning_rate": 5.505882352941176e-05, | |
| "loss": 0.0819, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 5.4176470588235295e-05, | |
| "loss": 0.2799, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 41.43, | |
| "learning_rate": 5.329411764705882e-05, | |
| "loss": 0.1072, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 41.57, | |
| "learning_rate": 5.241176470588235e-05, | |
| "loss": 0.2492, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 41.71, | |
| "learning_rate": 5.1529411764705876e-05, | |
| "loss": 0.2309, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 41.85, | |
| "learning_rate": 5.0647058823529406e-05, | |
| "loss": 0.1523, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 4.976470588235294e-05, | |
| "loss": 0.3004, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.5258119106292725, | |
| "eval_runtime": 62.0226, | |
| "eval_samples_per_second": 8.932, | |
| "eval_steps_per_second": 2.241, | |
| "eval_wer": 0.1083061170447524, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 42.14, | |
| "learning_rate": 4.8882352941176465e-05, | |
| "loss": 0.103, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 42.28, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.3089, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 42.43, | |
| "learning_rate": 4.711764705882353e-05, | |
| "loss": 0.1507, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 42.57, | |
| "learning_rate": 4.6235294117647053e-05, | |
| "loss": 0.2187, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 42.71, | |
| "learning_rate": 4.535294117647059e-05, | |
| "loss": 0.2196, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 42.85, | |
| "learning_rate": 4.447058823529411e-05, | |
| "loss": 0.1112, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 4.358823529411764e-05, | |
| "loss": 0.2873, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.48103272914886475, | |
| "eval_runtime": 62.3965, | |
| "eval_samples_per_second": 8.879, | |
| "eval_steps_per_second": 2.228, | |
| "eval_wer": 0.10693794686203549, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 43.14, | |
| "learning_rate": 4.270588235294118e-05, | |
| "loss": 0.1005, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 43.28, | |
| "learning_rate": 4.18235294117647e-05, | |
| "loss": 0.2451, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "learning_rate": 4.094117647058823e-05, | |
| "loss": 0.133, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "learning_rate": 4.005882352941176e-05, | |
| "loss": 0.2834, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 43.71, | |
| "learning_rate": 3.917647058823529e-05, | |
| "loss": 0.2281, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 43.85, | |
| "learning_rate": 3.8294117647058826e-05, | |
| "loss": 0.1366, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 3.741176470588235e-05, | |
| "loss": 0.3413, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.4960844814777374, | |
| "eval_runtime": 62.3955, | |
| "eval_samples_per_second": 8.879, | |
| "eval_steps_per_second": 2.228, | |
| "eval_wer": 0.1079530408685674, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 44.14, | |
| "learning_rate": 3.652941176470588e-05, | |
| "loss": 0.0883, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 44.28, | |
| "learning_rate": 3.564705882352941e-05, | |
| "loss": 0.3934, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 44.43, | |
| "learning_rate": 3.476470588235294e-05, | |
| "loss": 0.1466, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 44.57, | |
| "learning_rate": 3.3882352941176466e-05, | |
| "loss": 0.2407, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 44.71, | |
| "learning_rate": 3.2999999999999996e-05, | |
| "loss": 0.1993, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 44.85, | |
| "learning_rate": 3.2117647058823525e-05, | |
| "loss": 0.1387, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 3.1235294117647055e-05, | |
| "loss": 0.2802, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.6849678158760071, | |
| "eval_runtime": 63.8829, | |
| "eval_samples_per_second": 8.672, | |
| "eval_steps_per_second": 2.176, | |
| "eval_wer": 0.10759996469238238, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 45.14, | |
| "learning_rate": 3.0352941176470588e-05, | |
| "loss": 0.0803, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 45.28, | |
| "learning_rate": 2.9470588235294114e-05, | |
| "loss": 0.2896, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 45.43, | |
| "learning_rate": 2.8588235294117643e-05, | |
| "loss": 0.1362, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 2.7705882352941173e-05, | |
| "loss": 0.2389, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "learning_rate": 2.6823529411764706e-05, | |
| "loss": 0.2265, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 45.85, | |
| "learning_rate": 2.594117647058823e-05, | |
| "loss": 0.1175, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 2.505882352941176e-05, | |
| "loss": 0.2584, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.721015214920044, | |
| "eval_runtime": 62.1469, | |
| "eval_samples_per_second": 8.914, | |
| "eval_steps_per_second": 2.237, | |
| "eval_wer": 0.10817371347868303, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 46.14, | |
| "learning_rate": 2.417647058823529e-05, | |
| "loss": 0.0896, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 46.28, | |
| "learning_rate": 2.3294117647058824e-05, | |
| "loss": 0.2182, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 46.43, | |
| "learning_rate": 2.241176470588235e-05, | |
| "loss": 0.1297, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 46.57, | |
| "learning_rate": 2.152941176470588e-05, | |
| "loss": 0.1778, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 46.71, | |
| "learning_rate": 2.064705882352941e-05, | |
| "loss": 0.2218, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 46.85, | |
| "learning_rate": 1.976470588235294e-05, | |
| "loss": 0.1266, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 1.888235294117647e-05, | |
| "loss": 0.3282, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.6178598999977112, | |
| "eval_runtime": 61.9027, | |
| "eval_samples_per_second": 8.95, | |
| "eval_steps_per_second": 2.245, | |
| "eval_wer": 0.1053049695471798, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 47.14, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 0.085, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 47.28, | |
| "learning_rate": 1.711764705882353e-05, | |
| "loss": 0.2761, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 47.43, | |
| "learning_rate": 1.6235294117647056e-05, | |
| "loss": 0.178, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 1.535294117647059e-05, | |
| "loss": 0.2117, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 47.71, | |
| "learning_rate": 1.4470588235294115e-05, | |
| "loss": 0.2157, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 47.85, | |
| "learning_rate": 1.3588235294117646e-05, | |
| "loss": 0.1065, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.2705882352941174e-05, | |
| "loss": 0.2666, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.7673476338386536, | |
| "eval_runtime": 62.1409, | |
| "eval_samples_per_second": 8.915, | |
| "eval_steps_per_second": 2.237, | |
| "eval_wer": 0.107467561126313, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 48.14, | |
| "learning_rate": 1.1823529411764705e-05, | |
| "loss": 0.0933, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 48.28, | |
| "learning_rate": 1.0941176470588233e-05, | |
| "loss": 0.2291, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 48.43, | |
| "learning_rate": 1.0058823529411764e-05, | |
| "loss": 0.1521, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "learning_rate": 9.176470588235294e-06, | |
| "loss": 0.2739, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 48.71, | |
| "learning_rate": 8.294117647058823e-06, | |
| "loss": 0.2092, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 48.85, | |
| "learning_rate": 7.411764705882352e-06, | |
| "loss": 0.1173, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 6.529411764705881e-06, | |
| "loss": 0.2989, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 0.770989716053009, | |
| "eval_runtime": 63.0426, | |
| "eval_samples_per_second": 8.788, | |
| "eval_steps_per_second": 2.205, | |
| "eval_wer": 0.10790890634654426, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 49.14, | |
| "learning_rate": 5.647058823529411e-06, | |
| "loss": 0.0867, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 49.28, | |
| "learning_rate": 4.76470588235294e-06, | |
| "loss": 0.2886, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 49.43, | |
| "learning_rate": 3.882352941176471e-06, | |
| "loss": 0.1437, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 2.9999999999999997e-06, | |
| "loss": 0.2037, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 49.71, | |
| "learning_rate": 2.117647058823529e-06, | |
| "loss": 0.2123, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 49.85, | |
| "learning_rate": 1.2352941176470588e-06, | |
| "loss": 0.1577, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3.5294117647058817e-07, | |
| "loss": 0.2676, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.7655378580093384, | |
| "eval_runtime": 62.3062, | |
| "eval_samples_per_second": 8.892, | |
| "eval_steps_per_second": 2.231, | |
| "eval_wer": 0.10759996469238238, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 3500, | |
| "total_flos": 8.256324461882147e+18, | |
| "train_loss": 0.25776124070371903, | |
| "train_runtime": 11593.642, | |
| "train_samples_per_second": 4.843, | |
| "train_steps_per_second": 0.302 | |
| } | |
| ], | |
| "max_steps": 3500, | |
| "num_train_epochs": 50, | |
| "total_flos": 8.256324461882147e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |