| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "global_step": 2900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9e-07, | |
| "loss": 9.7737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9e-06, | |
| "loss": 8.4934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9e-06, | |
| "loss": 7.8114, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.8e-06, | |
| "loss": 8.0834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 7.1211, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.8e-06, | |
| "loss": 6.1102, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 5.2533, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.7e-06, | |
| "loss": 5.3192, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.7e-06, | |
| "loss": 4.6205, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.7e-06, | |
| "loss": 4.2068, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 4.080197811126709, | |
| "eval_runtime": 61.9535, | |
| "eval_samples_per_second": 27.117, | |
| "eval_steps_per_second": 27.117, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.0700000000000001e-05, | |
| "loss": 4.0423, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.1700000000000001e-05, | |
| "loss": 3.7734, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.27e-05, | |
| "loss": 3.5267, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3700000000000001e-05, | |
| "loss": 3.3545, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.47e-05, | |
| "loss": 3.3332, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.5700000000000002e-05, | |
| "loss": 3.1573, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.6700000000000003e-05, | |
| "loss": 3.0766, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.77e-05, | |
| "loss": 3.0596, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.87e-05, | |
| "loss": 3.0288, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.97e-05, | |
| "loss": 2.9806, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.979235887527466, | |
| "eval_runtime": 61.729, | |
| "eval_samples_per_second": 27.216, | |
| "eval_steps_per_second": 27.216, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.07e-05, | |
| "loss": 2.9737, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.1700000000000002e-05, | |
| "loss": 2.9834, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.2700000000000003e-05, | |
| "loss": 2.9707, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.37e-05, | |
| "loss": 2.9485, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.47e-05, | |
| "loss": 2.9432, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.57e-05, | |
| "loss": 2.9906, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.6700000000000002e-05, | |
| "loss": 2.9363, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.7700000000000002e-05, | |
| "loss": 2.9439, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.87e-05, | |
| "loss": 3.0115, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.97e-05, | |
| "loss": 2.9781, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.9407591819763184, | |
| "eval_runtime": 62.0192, | |
| "eval_samples_per_second": 27.088, | |
| "eval_steps_per_second": 27.088, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.07e-05, | |
| "loss": 2.9261, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.1700000000000005e-05, | |
| "loss": 2.9347, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.27e-05, | |
| "loss": 2.9749, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.3700000000000006e-05, | |
| "loss": 2.9323, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.4699999999999996e-05, | |
| "loss": 2.9314, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.57e-05, | |
| "loss": 2.9367, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.6700000000000004e-05, | |
| "loss": 2.9382, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.77e-05, | |
| "loss": 2.9148, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.8700000000000006e-05, | |
| "loss": 2.9224, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.97e-05, | |
| "loss": 2.9656, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.914335012435913, | |
| "eval_runtime": 61.8283, | |
| "eval_samples_per_second": 27.172, | |
| "eval_steps_per_second": 27.172, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.07e-05, | |
| "loss": 2.9156, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.17e-05, | |
| "loss": 2.8979, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.27e-05, | |
| "loss": 2.8957, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.3700000000000005e-05, | |
| "loss": 2.9542, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.47e-05, | |
| "loss": 2.8907, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.5700000000000006e-05, | |
| "loss": 2.8882, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.6700000000000003e-05, | |
| "loss": 2.8962, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 4.77e-05, | |
| "loss": 2.9122, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.87e-05, | |
| "loss": 2.8862, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.97e-05, | |
| "loss": 2.8953, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 2.8774032592773438, | |
| "eval_runtime": 61.89, | |
| "eval_samples_per_second": 27.145, | |
| "eval_steps_per_second": 27.145, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.0700000000000006e-05, | |
| "loss": 2.9153, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 5.17e-05, | |
| "loss": 2.8849, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.270000000000001e-05, | |
| "loss": 2.8637, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.3700000000000004e-05, | |
| "loss": 2.8881, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 5.470000000000001e-05, | |
| "loss": 2.9057, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 5.5700000000000005e-05, | |
| "loss": 2.8631, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 5.6699999999999996e-05, | |
| "loss": 2.844, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.77e-05, | |
| "loss": 2.8526, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 5.87e-05, | |
| "loss": 2.8439, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.97e-05, | |
| "loss": 2.7714, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_loss": 2.777448892593384, | |
| "eval_runtime": 61.9349, | |
| "eval_samples_per_second": 27.125, | |
| "eval_steps_per_second": 27.125, | |
| "eval_wer": 0.9999310867617669, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 6.07e-05, | |
| "loss": 2.772, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 6.170000000000001e-05, | |
| "loss": 2.8175, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.27e-05, | |
| "loss": 2.7637, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.37e-05, | |
| "loss": 2.7476, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 6.47e-05, | |
| "loss": 2.7451, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6.570000000000001e-05, | |
| "loss": 2.7698, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6.670000000000001e-05, | |
| "loss": 2.6918, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.77e-05, | |
| "loss": 2.7045, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6.87e-05, | |
| "loss": 2.775, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.97e-05, | |
| "loss": 2.6883, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 2.655168294906616, | |
| "eval_runtime": 61.9601, | |
| "eval_samples_per_second": 27.114, | |
| "eval_steps_per_second": 27.114, | |
| "eval_wer": 0.9853903934945903, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 7.07e-05, | |
| "loss": 2.6235, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 7.17e-05, | |
| "loss": 2.6454, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.27e-05, | |
| "loss": 2.7134, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 7.37e-05, | |
| "loss": 2.6114, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 7.47e-05, | |
| "loss": 2.5768, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 7.570000000000001e-05, | |
| "loss": 2.6549, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 7.670000000000001e-05, | |
| "loss": 2.6445, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 7.77e-05, | |
| "loss": 2.5427, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 7.87e-05, | |
| "loss": 2.5433, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 7.970000000000001e-05, | |
| "loss": 2.6477, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 2.5424375534057617, | |
| "eval_runtime": 62.1641, | |
| "eval_samples_per_second": 27.025, | |
| "eval_steps_per_second": 27.025, | |
| "eval_wer": 1.0113706843084556, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 8.070000000000001e-05, | |
| "loss": 2.5609, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 8.17e-05, | |
| "loss": 2.4538, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 8.27e-05, | |
| "loss": 2.521, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 8.37e-05, | |
| "loss": 2.6379, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 8.47e-05, | |
| "loss": 2.4359, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.57e-05, | |
| "loss": 2.4555, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.67e-05, | |
| "loss": 2.542, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 8.77e-05, | |
| "loss": 2.5067, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 8.87e-05, | |
| "loss": 2.3783, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 8.970000000000001e-05, | |
| "loss": 2.3607, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_loss": 2.4291484355926514, | |
| "eval_runtime": 62.2969, | |
| "eval_samples_per_second": 26.968, | |
| "eval_steps_per_second": 26.968, | |
| "eval_wer": 1.101233546964372, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 9.070000000000001e-05, | |
| "loss": 2.584, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 9.17e-05, | |
| "loss": 2.4121, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 9.27e-05, | |
| "loss": 2.363, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 9.370000000000001e-05, | |
| "loss": 2.4513, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 9.47e-05, | |
| "loss": 2.5266, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 9.57e-05, | |
| "loss": 2.261, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 9.67e-05, | |
| "loss": 2.2193, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 9.77e-05, | |
| "loss": 2.5063, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 9.87e-05, | |
| "loss": 2.3737, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 9.970000000000001e-05, | |
| "loss": 2.1048, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 2.2525901794433594, | |
| "eval_runtime": 62.0939, | |
| "eval_samples_per_second": 27.056, | |
| "eval_steps_per_second": 27.056, | |
| "eval_wer": 0.9743642753773, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 9.963157894736843e-05, | |
| "loss": 2.2737, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 9.910526315789475e-05, | |
| "loss": 2.4889, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 9.857894736842106e-05, | |
| "loss": 2.1847, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 9.805263157894737e-05, | |
| "loss": 2.135, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 9.752631578947369e-05, | |
| "loss": 2.3103, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 9.7e-05, | |
| "loss": 2.3921, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 9.647368421052631e-05, | |
| "loss": 2.0108, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 9.594736842105264e-05, | |
| "loss": 2.1143, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 9.542105263157895e-05, | |
| "loss": 2.4364, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 9.489473684210527e-05, | |
| "loss": 2.2448, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "eval_loss": 2.169701099395752, | |
| "eval_runtime": 62.1876, | |
| "eval_samples_per_second": 27.015, | |
| "eval_steps_per_second": 27.015, | |
| "eval_wer": 0.9332230721521604, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 9.436842105263158e-05, | |
| "loss": 1.9274, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 9.384210526315789e-05, | |
| "loss": 2.1163, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 9.331578947368422e-05, | |
| "loss": 2.3358, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 9.278947368421053e-05, | |
| "loss": 1.9315, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 9.226315789473686e-05, | |
| "loss": 1.9978, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.173684210526317e-05, | |
| "loss": 2.338, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.121052631578948e-05, | |
| "loss": 2.2001, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.06842105263158e-05, | |
| "loss": 1.894, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.015789473684211e-05, | |
| "loss": 2.0173, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 8.963157894736842e-05, | |
| "loss": 2.3525, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 2.042870044708252, | |
| "eval_runtime": 62.0448, | |
| "eval_samples_per_second": 27.077, | |
| "eval_steps_per_second": 27.077, | |
| "eval_wer": 0.8720970298394322, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.910526315789474e-05, | |
| "loss": 1.8758, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.857894736842106e-05, | |
| "loss": 1.8701, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 8.805263157894737e-05, | |
| "loss": 2.1876, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.752631578947369e-05, | |
| "loss": 2.2548, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.7e-05, | |
| "loss": 1.8274, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.647368421052631e-05, | |
| "loss": 1.9417, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 8.594736842105263e-05, | |
| "loss": 2.3158, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 8.542105263157894e-05, | |
| "loss": 2.0282, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 8.489473684210527e-05, | |
| "loss": 1.7798, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 8.436842105263158e-05, | |
| "loss": 2.099, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 2.0076003074645996, | |
| "eval_runtime": 62.3855, | |
| "eval_samples_per_second": 26.929, | |
| "eval_steps_per_second": 26.929, | |
| "eval_wer": 0.9182688994555854, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 8.38421052631579e-05, | |
| "loss": 2.2983, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 8.331578947368422e-05, | |
| "loss": 1.7612, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 8.278947368421053e-05, | |
| "loss": 1.7982, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 8.226315789473684e-05, | |
| "loss": 2.1745, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 8.173684210526317e-05, | |
| "loss": 2.1586, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 8.121052631578948e-05, | |
| "loss": 1.8252, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 8.06842105263158e-05, | |
| "loss": 1.9301, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 8.015789473684211e-05, | |
| "loss": 2.2251, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 7.963157894736842e-05, | |
| "loss": 1.8685, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 7.910526315789474e-05, | |
| "loss": 1.8236, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 1.9694862365722656, | |
| "eval_runtime": 62.2724, | |
| "eval_samples_per_second": 26.978, | |
| "eval_steps_per_second": 26.978, | |
| "eval_wer": 0.8262697264144442, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 7.857894736842105e-05, | |
| "loss": 2.1524, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 7.805263157894738e-05, | |
| "loss": 2.2737, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.752631578947369e-05, | |
| "loss": 1.7647, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 7.7e-05, | |
| "loss": 1.857, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.647368421052631e-05, | |
| "loss": 2.1688, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 7.594736842105263e-05, | |
| "loss": 2.0013, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 7.542105263157895e-05, | |
| "loss": 1.6881, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 7.489473684210527e-05, | |
| "loss": 1.8441, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 7.43684210526316e-05, | |
| "loss": 2.2788, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 7.38421052631579e-05, | |
| "loss": 1.6602, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "eval_loss": 1.932761311531067, | |
| "eval_runtime": 62.3067, | |
| "eval_samples_per_second": 26.963, | |
| "eval_steps_per_second": 26.963, | |
| "eval_wer": 0.8536971952312039, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 7.331578947368422e-05, | |
| "loss": 1.7309, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 7.278947368421053e-05, | |
| "loss": 2.0171, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 7.226315789473685e-05, | |
| "loss": 2.1863, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 7.173684210526316e-05, | |
| "loss": 1.7332, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 7.121052631578947e-05, | |
| "loss": 1.9525, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 7.06842105263158e-05, | |
| "loss": 2.2204, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 7.015789473684211e-05, | |
| "loss": 1.8776, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 6.963157894736842e-05, | |
| "loss": 1.7232, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 6.910526315789474e-05, | |
| "loss": 1.8677, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.857894736842105e-05, | |
| "loss": 2.2146, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 1.879468321800232, | |
| "eval_runtime": 62.2267, | |
| "eval_samples_per_second": 26.998, | |
| "eval_steps_per_second": 26.998, | |
| "eval_wer": 0.8443249948315071, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 6.805263157894736e-05, | |
| "loss": 1.7176, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 6.752631578947368e-05, | |
| "loss": 1.7268, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 6.7e-05, | |
| "loss": 2.0447, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 6.647368421052632e-05, | |
| "loss": 2.0887, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 6.594736842105264e-05, | |
| "loss": 1.7193, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 6.542105263157895e-05, | |
| "loss": 1.8665, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.489473684210527e-05, | |
| "loss": 2.2249, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 6.436842105263158e-05, | |
| "loss": 1.7308, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 6.384210526315791e-05, | |
| "loss": 1.6378, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 6.331578947368422e-05, | |
| "loss": 1.9278, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "eval_loss": 1.874898076057434, | |
| "eval_runtime": 62.4749, | |
| "eval_samples_per_second": 26.891, | |
| "eval_steps_per_second": 26.891, | |
| "eval_wer": 0.8074564123768175, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 6.278947368421053e-05, | |
| "loss": 2.167, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 6.226315789473685e-05, | |
| "loss": 1.6498, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 6.173684210526316e-05, | |
| "loss": 1.7843, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.121052631578947e-05, | |
| "loss": 2.1545, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 6.0684210526315785e-05, | |
| "loss": 1.9012, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 6.015789473684211e-05, | |
| "loss": 1.6388, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 5.9631578947368425e-05, | |
| "loss": 1.8509, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 5.9105263157894744e-05, | |
| "loss": 2.1512, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 5.857894736842106e-05, | |
| "loss": 1.6984, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 5.805263157894737e-05, | |
| "loss": 1.6324, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "eval_loss": 1.850366234779358, | |
| "eval_runtime": 62.1197, | |
| "eval_samples_per_second": 27.045, | |
| "eval_steps_per_second": 27.045, | |
| "eval_wer": 0.8091103300944111, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 5.752631578947368e-05, | |
| "loss": 2.0102, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 2.0616, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 5.647368421052632e-05, | |
| "loss": 1.6063, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 5.5947368421052636e-05, | |
| "loss": 1.718, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 5.542105263157895e-05, | |
| "loss": 2.0991, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 5.489473684210527e-05, | |
| "loss": 1.841, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 5.436842105263158e-05, | |
| "loss": 1.6345, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 5.3842105263157895e-05, | |
| "loss": 1.8546, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.331578947368421e-05, | |
| "loss": 2.1289, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 5.2789473684210534e-05, | |
| "loss": 1.6517, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "eval_loss": 1.8227797746658325, | |
| "eval_runtime": 62.3551, | |
| "eval_samples_per_second": 26.942, | |
| "eval_steps_per_second": 26.942, | |
| "eval_wer": 0.8233064571704224, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 5.226315789473685e-05, | |
| "loss": 1.7168, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 5.173684210526316e-05, | |
| "loss": 1.924, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 5.121052631578947e-05, | |
| "loss": 1.9177, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 5.068421052631579e-05, | |
| "loss": 1.64, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 5.0157894736842106e-05, | |
| "loss": 1.6953, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 4.9631578947368426e-05, | |
| "loss": 2.1591, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 4.910526315789474e-05, | |
| "loss": 1.7455, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 4.857894736842106e-05, | |
| "loss": 1.5742, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 4.805263157894737e-05, | |
| "loss": 1.9511, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 4.7526315789473684e-05, | |
| "loss": 2.0463, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "eval_loss": 1.819372296333313, | |
| "eval_runtime": 62.2592, | |
| "eval_samples_per_second": 26.984, | |
| "eval_steps_per_second": 26.984, | |
| "eval_wer": 0.8563848115222934, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.5744, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 4.647368421052632e-05, | |
| "loss": 1.6679, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.594736842105264e-05, | |
| "loss": 1.9124, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 4.542105263157895e-05, | |
| "loss": 1.8303, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 4.489473684210527e-05, | |
| "loss": 1.5034, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 4.436842105263158e-05, | |
| "loss": 1.7662, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 4.3842105263157895e-05, | |
| "loss": 2.1269, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 4.3315789473684215e-05, | |
| "loss": 1.6707, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 4.278947368421053e-05, | |
| "loss": 1.6393, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 4.226315789473684e-05, | |
| "loss": 1.8736, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_loss": 1.7949970960617065, | |
| "eval_runtime": 62.2709, | |
| "eval_samples_per_second": 26.979, | |
| "eval_steps_per_second": 26.979, | |
| "eval_wer": 0.8224794983116257, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 4.1736842105263154e-05, | |
| "loss": 1.9396, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 4.1210526315789474e-05, | |
| "loss": 1.555, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 4.0684210526315794e-05, | |
| "loss": 1.7577, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 4.015789473684211e-05, | |
| "loss": 2.0354, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 3.9631578947368426e-05, | |
| "loss": 1.7073, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 3.910526315789474e-05, | |
| "loss": 1.4961, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 3.857894736842105e-05, | |
| "loss": 1.7068, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 3.8052631578947365e-05, | |
| "loss": 2.0397, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 3.7526315789473685e-05, | |
| "loss": 1.5849, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 3.7e-05, | |
| "loss": 1.6233, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "eval_loss": 1.7896100282669067, | |
| "eval_runtime": 62.05, | |
| "eval_samples_per_second": 27.075, | |
| "eval_steps_per_second": 27.075, | |
| "eval_wer": 0.8429467300668458, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 3.647368421052632e-05, | |
| "loss": 1.8936, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 3.594736842105264e-05, | |
| "loss": 1.8176, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.542105263157895e-05, | |
| "loss": 1.5963, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 3.4894736842105264e-05, | |
| "loss": 1.6365, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 3.436842105263158e-05, | |
| "loss": 2.0577, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 3.3842105263157896e-05, | |
| "loss": 1.5942, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 3.331578947368421e-05, | |
| "loss": 1.5867, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 3.278947368421052e-05, | |
| "loss": 1.8733, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 3.226315789473684e-05, | |
| "loss": 2.0624, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 3.173684210526316e-05, | |
| "loss": 1.4982, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "eval_loss": 1.7793470621109009, | |
| "eval_runtime": 62.0626, | |
| "eval_samples_per_second": 27.069, | |
| "eval_steps_per_second": 27.069, | |
| "eval_wer": 0.8441182551168079, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 3.1210526315789475e-05, | |
| "loss": 1.6152, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.0684210526315795e-05, | |
| "loss": 1.9853, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 3.0157894736842108e-05, | |
| "loss": 1.8096, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 2.963157894736842e-05, | |
| "loss": 1.4931, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 2.910526315789474e-05, | |
| "loss": 1.6762, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 2.8578947368421057e-05, | |
| "loss": 2.041, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 2.805263157894737e-05, | |
| "loss": 1.5446, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 2.7526315789473683e-05, | |
| "loss": 1.5859, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.804, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 2.647368421052632e-05, | |
| "loss": 1.8955, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 1.7640429735183716, | |
| "eval_runtime": 62.2013, | |
| "eval_samples_per_second": 27.009, | |
| "eval_steps_per_second": 27.009, | |
| "eval_wer": 0.805802494659224, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 2.5947368421052632e-05, | |
| "loss": 1.4801, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 2.542105263157895e-05, | |
| "loss": 1.6412, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 2.4894736842105264e-05, | |
| "loss": 1.9778, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 2.436842105263158e-05, | |
| "loss": 1.6648, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 2.3842105263157897e-05, | |
| "loss": 1.5288, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 2.331578947368421e-05, | |
| "loss": 1.6835, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 2.2789473684210527e-05, | |
| "loss": 1.9791, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 2.2263157894736843e-05, | |
| "loss": 1.478, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 2.173684210526316e-05, | |
| "loss": 1.5269, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 2.1210526315789476e-05, | |
| "loss": 1.8253, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "eval_loss": 1.766750693321228, | |
| "eval_runtime": 62.056, | |
| "eval_samples_per_second": 27.072, | |
| "eval_steps_per_second": 27.072, | |
| "eval_wer": 0.8133829508648611, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 2.068421052631579e-05, | |
| "loss": 1.8498, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 2.0157894736842105e-05, | |
| "loss": 1.4217, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 1.963157894736842e-05, | |
| "loss": 1.6156, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 1.9105263157894738e-05, | |
| "loss": 1.9255, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 1.8578947368421054e-05, | |
| "loss": 1.6055, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 1.8052631578947367e-05, | |
| "loss": 1.5202, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 1.7526315789473683e-05, | |
| "loss": 1.7571, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.893, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 1.6473684210526316e-05, | |
| "loss": 1.4591, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 1.5947368421052633e-05, | |
| "loss": 1.5332, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "eval_loss": 1.7611440420150757, | |
| "eval_runtime": 62.4578, | |
| "eval_samples_per_second": 26.898, | |
| "eval_steps_per_second": 26.898, | |
| "eval_wer": 0.801460960650541, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.5421052631578946e-05, | |
| "loss": 1.9193, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 1.4894736842105264e-05, | |
| "loss": 1.7022, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 1.4368421052631582e-05, | |
| "loss": 1.4093, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 1.3842105263157895e-05, | |
| "loss": 1.6191, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 1.3315789473684213e-05, | |
| "loss": 1.9511, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 1.2789473684210526e-05, | |
| "loss": 1.487, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 1.2263157894736844e-05, | |
| "loss": 1.4701, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 1.1736842105263158e-05, | |
| "loss": 1.7986, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 1.1210526315789475e-05, | |
| "loss": 1.7998, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 1.068421052631579e-05, | |
| "loss": 1.452, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "eval_loss": 1.7497012615203857, | |
| "eval_runtime": 62.4753, | |
| "eval_samples_per_second": 26.891, | |
| "eval_steps_per_second": 26.891, | |
| "eval_wer": 0.8071807594238853, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 1.0157894736842106e-05, | |
| "loss": 1.5828, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 9.631578947368422e-06, | |
| "loss": 1.9231, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 9.105263157894737e-06, | |
| "loss": 1.5695, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 8.578947368421053e-06, | |
| "loss": 1.5435, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "learning_rate": 8.052631578947368e-06, | |
| "loss": 1.6403, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 7.526315789473684e-06, | |
| "loss": 1.85, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.4523, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 6.473684210526316e-06, | |
| "loss": 1.488, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 5.947368421052632e-06, | |
| "loss": 1.8365, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 5.421052631578947e-06, | |
| "loss": 1.7609, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "eval_loss": 1.7463784217834473, | |
| "eval_runtime": 62.7099, | |
| "eval_samples_per_second": 26.79, | |
| "eval_steps_per_second": 26.79, | |
| "eval_wer": 0.8062159740886224, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 4.894736842105263e-06, | |
| "loss": 1.4567, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 4.368421052631579e-06, | |
| "loss": 1.5592, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.842105263157895e-06, | |
| "loss": 1.961, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 3.368421052631579e-06, | |
| "loss": 1.4964, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 2.842105263157895e-06, | |
| "loss": 1.4505, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 2.315789473684211e-06, | |
| "loss": 1.7141, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.7894736842105262e-06, | |
| "loss": 1.8701, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 1.2631578947368422e-06, | |
| "loss": 1.4216, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 7.368421052631579e-07, | |
| "loss": 1.5857, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.105263157894737e-07, | |
| "loss": 1.7743, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.742971658706665, | |
| "eval_runtime": 62.4332, | |
| "eval_samples_per_second": 26.909, | |
| "eval_steps_per_second": 26.909, | |
| "eval_wer": 0.808972503617945, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 2900, | |
| "total_flos": 1.1463619274186412e+18, | |
| "train_loss": 2.308333969445064, | |
| "train_runtime": 4034.046, | |
| "train_samples_per_second": 22.905, | |
| "train_steps_per_second": 0.719 | |
| } | |
| ], | |
| "max_steps": 2900, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.1463619274186412e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |