| { | |
| "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": 9.0434, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9e-06, | |
| "loss": 8.4547, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9e-06, | |
| "loss": 8.0214, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.9e-06, | |
| "loss": 8.1758, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.9000000000000005e-06, | |
| "loss": 8.2741, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.9e-06, | |
| "loss": 7.8918, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.900000000000001e-06, | |
| "loss": 7.2641, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.8e-06, | |
| "loss": 7.7513, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.8e-06, | |
| "loss": 7.1069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 6.2516, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.86376953125, | |
| "eval_runtime": 74.6223, | |
| "eval_samples_per_second": 22.513, | |
| "eval_steps_per_second": 22.513, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.08e-05, | |
| "loss": 5.41, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.18e-05, | |
| "loss": 4.5224, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 3.747, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 3.3738, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.48e-05, | |
| "loss": 3.2164, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.58e-05, | |
| "loss": 3.0884, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 3.0205, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.78e-05, | |
| "loss": 3.0113, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.88e-05, | |
| "loss": 2.9943, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.9800000000000004e-05, | |
| "loss": 2.9596, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.9550368785858154, | |
| "eval_runtime": 74.3756, | |
| "eval_samples_per_second": 22.588, | |
| "eval_steps_per_second": 22.588, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.08e-05, | |
| "loss": 2.9448, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.18e-05, | |
| "loss": 2.9503, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.2800000000000002e-05, | |
| "loss": 2.9387, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.38e-05, | |
| "loss": 2.9161, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.48e-05, | |
| "loss": 2.9074, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.58e-05, | |
| "loss": 2.9282, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.6800000000000004e-05, | |
| "loss": 2.8814, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.7800000000000005e-05, | |
| "loss": 2.8904, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.88e-05, | |
| "loss": 2.8916, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.98e-05, | |
| "loss": 2.8831, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.854661226272583, | |
| "eval_runtime": 75.315, | |
| "eval_samples_per_second": 22.306, | |
| "eval_steps_per_second": 22.306, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.08e-05, | |
| "loss": 2.8292, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.18e-05, | |
| "loss": 2.8147, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.2800000000000004e-05, | |
| "loss": 2.8365, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.38e-05, | |
| "loss": 2.7823, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.48e-05, | |
| "loss": 2.7294, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.58e-05, | |
| "loss": 2.6776, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.68e-05, | |
| "loss": 2.6469, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.7800000000000004e-05, | |
| "loss": 2.5029, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.88e-05, | |
| "loss": 2.3966, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.9800000000000005e-05, | |
| "loss": 2.3223, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.2044448852539062, | |
| "eval_runtime": 74.9333, | |
| "eval_samples_per_second": 22.42, | |
| "eval_steps_per_second": 22.42, | |
| "eval_wer": 1.006340017917442, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.08e-05, | |
| "loss": 2.1489, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.18e-05, | |
| "loss": 1.97, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.2800000000000004e-05, | |
| "loss": 1.8801, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.38e-05, | |
| "loss": 1.8871, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.4800000000000005e-05, | |
| "loss": 1.5991, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.58e-05, | |
| "loss": 1.5167, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.6800000000000006e-05, | |
| "loss": 1.4989, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 4.78e-05, | |
| "loss": 1.4523, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.88e-05, | |
| "loss": 1.2192, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.9800000000000004e-05, | |
| "loss": 1.2104, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 1.0845389366149902, | |
| "eval_runtime": 75.2589, | |
| "eval_samples_per_second": 22.323, | |
| "eval_steps_per_second": 22.323, | |
| "eval_wer": 0.770587829922128, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.08e-05, | |
| "loss": 1.2928, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 5.1800000000000005e-05, | |
| "loss": 1.0174, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.28e-05, | |
| "loss": 0.9433, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.380000000000001e-05, | |
| "loss": 1.06, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 5.4800000000000004e-05, | |
| "loss": 1.0888, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 5.580000000000001e-05, | |
| "loss": 0.8666, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 5.68e-05, | |
| "loss": 0.872, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.7799999999999995e-05, | |
| "loss": 1.0218, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 5.88e-05, | |
| "loss": 0.8507, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.9800000000000003e-05, | |
| "loss": 0.6779, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_loss": 0.7341921925544739, | |
| "eval_runtime": 75.0058, | |
| "eval_samples_per_second": 22.398, | |
| "eval_steps_per_second": 22.398, | |
| "eval_wer": 0.5663289917993246, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 6.08e-05, | |
| "loss": 0.7491, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 6.18e-05, | |
| "loss": 0.9254, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.280000000000001e-05, | |
| "loss": 0.6681, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.38e-05, | |
| "loss": 0.6991, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 6.48e-05, | |
| "loss": 0.7718, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6.58e-05, | |
| "loss": 0.8087, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6.680000000000001e-05, | |
| "loss": 0.6035, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.780000000000001e-05, | |
| "loss": 0.6768, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6.879999999999999e-05, | |
| "loss": 0.8125, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.98e-05, | |
| "loss": 0.6319, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.6053794622421265, | |
| "eval_runtime": 75.0843, | |
| "eval_samples_per_second": 22.375, | |
| "eval_steps_per_second": 22.375, | |
| "eval_wer": 0.4881124664047964, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 7.08e-05, | |
| "loss": 0.5354, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 7.18e-05, | |
| "loss": 0.6299, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.280000000000001e-05, | |
| "loss": 0.7239, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 7.38e-05, | |
| "loss": 0.4925, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 7.48e-05, | |
| "loss": 0.5066, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 7.58e-05, | |
| "loss": 0.6244, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 0.6078, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 7.780000000000001e-05, | |
| "loss": 0.4581, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 7.88e-05, | |
| "loss": 0.5191, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 7.98e-05, | |
| "loss": 0.664, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 0.5808180570602417, | |
| "eval_runtime": 74.9544, | |
| "eval_samples_per_second": 22.414, | |
| "eval_steps_per_second": 22.414, | |
| "eval_wer": 0.4912824753635173, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 8.080000000000001e-05, | |
| "loss": 0.4881, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 8.18e-05, | |
| "loss": 0.4375, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 8.28e-05, | |
| "loss": 0.5298, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 8.38e-05, | |
| "loss": 0.6362, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 8.48e-05, | |
| "loss": 0.4132, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.58e-05, | |
| "loss": 0.4377, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.680000000000001e-05, | |
| "loss": 0.6038, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 8.78e-05, | |
| "loss": 0.4272, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 8.88e-05, | |
| "loss": 0.3369, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 8.98e-05, | |
| "loss": 0.402, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_loss": 0.5647366642951965, | |
| "eval_runtime": 76.2203, | |
| "eval_samples_per_second": 22.041, | |
| "eval_steps_per_second": 22.041, | |
| "eval_wer": 0.46109847701743506, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 9.080000000000001e-05, | |
| "loss": 0.576, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 9.180000000000001e-05, | |
| "loss": 0.3906, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 9.28e-05, | |
| "loss": 0.3845, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 9.38e-05, | |
| "loss": 0.4633, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 9.48e-05, | |
| "loss": 0.5117, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 9.58e-05, | |
| "loss": 0.3322, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 9.680000000000001e-05, | |
| "loss": 0.3723, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 9.78e-05, | |
| "loss": 0.6006, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 9.88e-05, | |
| "loss": 0.4215, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 9.98e-05, | |
| "loss": 0.3176, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 0.5211185812950134, | |
| "eval_runtime": 75.0129, | |
| "eval_samples_per_second": 22.396, | |
| "eval_steps_per_second": 22.396, | |
| "eval_wer": 0.44400799393563506, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 9.957894736842106e-05, | |
| "loss": 0.3914, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 9.905263157894737e-05, | |
| "loss": 0.5073, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 9.852631578947368e-05, | |
| "loss": 0.305, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.2935, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 9.747368421052632e-05, | |
| "loss": 0.4133, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 9.694736842105264e-05, | |
| "loss": 0.4044, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 9.642105263157896e-05, | |
| "loss": 0.2689, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 9.589473684210528e-05, | |
| "loss": 0.3232, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 9.536842105263159e-05, | |
| "loss": 0.4688, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 9.48421052631579e-05, | |
| "loss": 0.3392, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "eval_loss": 0.5186533331871033, | |
| "eval_runtime": 75.1413, | |
| "eval_samples_per_second": 22.358, | |
| "eval_steps_per_second": 22.358, | |
| "eval_wer": 0.43587623182413343, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 9.431578947368421e-05, | |
| "loss": 0.2731, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 9.378947368421053e-05, | |
| "loss": 0.3368, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 9.326315789473684e-05, | |
| "loss": 0.4131, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 9.273684210526317e-05, | |
| "loss": 0.2641, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 9.221052631578948e-05, | |
| "loss": 0.3041, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.16842105263158e-05, | |
| "loss": 0.456, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.11578947368421e-05, | |
| "loss": 0.2855, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.063157894736842e-05, | |
| "loss": 0.2136, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.010526315789473e-05, | |
| "loss": 0.2516, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 8.957894736842106e-05, | |
| "loss": 0.3888, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 0.5501277446746826, | |
| "eval_runtime": 75.2531, | |
| "eval_samples_per_second": 22.325, | |
| "eval_steps_per_second": 22.325, | |
| "eval_wer": 0.4391151540210875, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.905263157894737e-05, | |
| "loss": 0.2299, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.852631578947368e-05, | |
| "loss": 0.2377, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.3282, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.747368421052632e-05, | |
| "loss": 0.3498, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.694736842105264e-05, | |
| "loss": 0.2184, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.642105263157895e-05, | |
| "loss": 0.2401, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 8.589473684210528e-05, | |
| "loss": 0.3815, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 8.536842105263159e-05, | |
| "loss": 0.2578, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 8.48421052631579e-05, | |
| "loss": 0.2257, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 8.431578947368422e-05, | |
| "loss": 0.2874, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 0.5249279141426086, | |
| "eval_runtime": 75.4265, | |
| "eval_samples_per_second": 22.273, | |
| "eval_steps_per_second": 22.273, | |
| "eval_wer": 0.41478878092481564, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 8.378947368421053e-05, | |
| "loss": 0.3298, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 8.326315789473684e-05, | |
| "loss": 0.1898, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 8.273684210526315e-05, | |
| "loss": 0.195, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 8.221052631578948e-05, | |
| "loss": 0.2913, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 8.16842105263158e-05, | |
| "loss": 0.28, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 8.115789473684211e-05, | |
| "loss": 0.181, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 8.063157894736842e-05, | |
| "loss": 0.2243, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 8.010526315789473e-05, | |
| "loss": 0.3422, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 7.957894736842106e-05, | |
| "loss": 0.2012, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 7.905263157894737e-05, | |
| "loss": 0.208, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 0.540692150592804, | |
| "eval_runtime": 75.3909, | |
| "eval_samples_per_second": 22.284, | |
| "eval_steps_per_second": 22.284, | |
| "eval_wer": 0.41520226035421404, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 7.852631578947369e-05, | |
| "loss": 0.2488, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.297, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.747368421052633e-05, | |
| "loss": 0.1888, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 7.694736842105264e-05, | |
| "loss": 0.1876, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.642105263157895e-05, | |
| "loss": 0.3355, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 7.589473684210526e-05, | |
| "loss": 0.193, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 7.536842105263158e-05, | |
| "loss": 0.1544, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 7.48421052631579e-05, | |
| "loss": 0.1913, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 7.431578947368422e-05, | |
| "loss": 0.3024, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 7.378947368421053e-05, | |
| "loss": 0.1457, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "eval_loss": 0.5721660256385803, | |
| "eval_runtime": 75.4875, | |
| "eval_samples_per_second": 22.255, | |
| "eval_steps_per_second": 22.255, | |
| "eval_wer": 0.4154779133071463, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 7.326315789473684e-05, | |
| "loss": 0.1592, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 7.273684210526316e-05, | |
| "loss": 0.2549, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 7.221052631578947e-05, | |
| "loss": 0.2457, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 7.16842105263158e-05, | |
| "loss": 0.1581, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 7.115789473684211e-05, | |
| "loss": 0.1964, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 7.063157894736842e-05, | |
| "loss": 0.2817, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 7.010526315789473e-05, | |
| "loss": 0.1836, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 6.957894736842106e-05, | |
| "loss": 0.1526, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 6.905263157894737e-05, | |
| "loss": 0.2107, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.852631578947369e-05, | |
| "loss": 0.2375, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 0.5779726505279541, | |
| "eval_runtime": 75.8176, | |
| "eval_samples_per_second": 22.158, | |
| "eval_steps_per_second": 22.158, | |
| "eval_wer": 0.4058989731927503, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.155, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 6.747368421052633e-05, | |
| "loss": 0.1481, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 6.694736842105264e-05, | |
| "loss": 0.2316, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 6.642105263157895e-05, | |
| "loss": 0.1977, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 6.589473684210526e-05, | |
| "loss": 0.1506, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 6.536842105263158e-05, | |
| "loss": 0.18, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.484210526315789e-05, | |
| "loss": 0.2611, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 6.431578947368422e-05, | |
| "loss": 0.1609, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 6.378947368421053e-05, | |
| "loss": 0.1388, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 6.326315789473684e-05, | |
| "loss": 0.2111, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "eval_loss": 0.5822769403457642, | |
| "eval_runtime": 75.9225, | |
| "eval_samples_per_second": 22.128, | |
| "eval_steps_per_second": 22.128, | |
| "eval_wer": 0.4094135483426366, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 6.273684210526316e-05, | |
| "loss": 0.2459, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 6.221052631578947e-05, | |
| "loss": 0.137, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 6.168421052631578e-05, | |
| "loss": 0.1799, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.115789473684211e-05, | |
| "loss": 0.2693, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 6.063157894736843e-05, | |
| "loss": 0.1452, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 6.010526315789474e-05, | |
| "loss": 0.1384, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 5.9578947368421055e-05, | |
| "loss": 0.1719, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 5.905263157894737e-05, | |
| "loss": 0.2236, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 5.852631578947369e-05, | |
| "loss": 0.1483, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.1422, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "eval_loss": 0.5754124522209167, | |
| "eval_runtime": 75.6112, | |
| "eval_samples_per_second": 22.219, | |
| "eval_steps_per_second": 22.219, | |
| "eval_wer": 0.39769829784301564, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 5.747368421052633e-05, | |
| "loss": 0.2102, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 5.694736842105264e-05, | |
| "loss": 0.2036, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 5.642105263157895e-05, | |
| "loss": 0.1295, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 5.5894736842105266e-05, | |
| "loss": 0.1574, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 5.536842105263158e-05, | |
| "loss": 0.2162, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 5.484210526315789e-05, | |
| "loss": 0.1423, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 5.431578947368421e-05, | |
| "loss": 0.1292, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 5.378947368421053e-05, | |
| "loss": 0.1785, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.326315789473685e-05, | |
| "loss": 0.2204, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 5.2736842105263164e-05, | |
| "loss": 0.125, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "eval_loss": 0.5784134864807129, | |
| "eval_runtime": 75.1289, | |
| "eval_samples_per_second": 22.362, | |
| "eval_steps_per_second": 22.362, | |
| "eval_wer": 0.4031424436634277, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 5.221052631578948e-05, | |
| "loss": 0.1367, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 5.168421052631579e-05, | |
| "loss": 0.166, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 5.11578947368421e-05, | |
| "loss": 0.1524, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 5.0631578947368416e-05, | |
| "loss": 0.1291, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 5.010526315789474e-05, | |
| "loss": 0.1596, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 4.9578947368421055e-05, | |
| "loss": 0.2428, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 4.9052631578947375e-05, | |
| "loss": 0.1274, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 4.852631578947369e-05, | |
| "loss": 0.1253, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.1946, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 4.747368421052632e-05, | |
| "loss": 0.1996, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "eval_loss": 0.5629692673683167, | |
| "eval_runtime": 75.3733, | |
| "eval_samples_per_second": 22.289, | |
| "eval_steps_per_second": 22.289, | |
| "eval_wer": 0.39556198745779064, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 4.6947368421052634e-05, | |
| "loss": 0.1063, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 4.642105263157895e-05, | |
| "loss": 0.1258, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.589473684210526e-05, | |
| "loss": 0.2092, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 4.536842105263158e-05, | |
| "loss": 0.1216, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 4.48421052631579e-05, | |
| "loss": 0.1174, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 4.431578947368421e-05, | |
| "loss": 0.1354, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 4.378947368421053e-05, | |
| "loss": 0.2055, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 4.3263157894736845e-05, | |
| "loss": 0.1084, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 4.273684210526316e-05, | |
| "loss": 0.1441, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 4.221052631578948e-05, | |
| "loss": 0.1747, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_loss": 0.5880140662193298, | |
| "eval_runtime": 75.8694, | |
| "eval_samples_per_second": 22.143, | |
| "eval_steps_per_second": 22.143, | |
| "eval_wer": 0.39638894631658744, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 4.168421052631579e-05, | |
| "loss": 0.1686, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 4.1157894736842104e-05, | |
| "loss": 0.1039, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 4.0631578947368424e-05, | |
| "loss": 0.1322, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 4.010526315789474e-05, | |
| "loss": 0.2271, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 3.9578947368421056e-05, | |
| "loss": 0.121, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 3.905263157894737e-05, | |
| "loss": 0.118, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 3.852631578947369e-05, | |
| "loss": 0.1413, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.1767, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 3.7473684210526315e-05, | |
| "loss": 0.1057, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 3.6947368421052635e-05, | |
| "loss": 0.1263, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "eval_loss": 0.598685085773468, | |
| "eval_runtime": 75.3049, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 22.309, | |
| "eval_wer": 0.3950795947901592, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 3.642105263157895e-05, | |
| "loss": 0.1861, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 3.589473684210527e-05, | |
| "loss": 0.1416, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.536842105263158e-05, | |
| "loss": 0.1155, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 3.48421052631579e-05, | |
| "loss": 0.1238, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 3.431578947368421e-05, | |
| "loss": 0.1935, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 3.3789473684210526e-05, | |
| "loss": 0.1119, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 3.3263157894736846e-05, | |
| "loss": 0.1122, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 3.273684210526316e-05, | |
| "loss": 0.1786, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 3.221052631578947e-05, | |
| "loss": 0.1699, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 3.168421052631579e-05, | |
| "loss": 0.11, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "eval_loss": 0.5688443183898926, | |
| "eval_runtime": 75.157, | |
| "eval_samples_per_second": 22.353, | |
| "eval_steps_per_second": 22.353, | |
| "eval_wer": 0.39638894631658744, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 3.115789473684211e-05, | |
| "loss": 0.115, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.0631578947368425e-05, | |
| "loss": 0.2203, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 3.0105263157894737e-05, | |
| "loss": 0.1013, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 2.9578947368421057e-05, | |
| "loss": 0.1074, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 2.905263157894737e-05, | |
| "loss": 0.1466, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 2.8526315789473683e-05, | |
| "loss": 0.1922, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.1038, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 2.747368421052632e-05, | |
| "loss": 0.1226, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.6947368421052632e-05, | |
| "loss": 0.1617, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 2.6421052631578945e-05, | |
| "loss": 0.1411, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 0.6223032474517822, | |
| "eval_runtime": 75.6646, | |
| "eval_samples_per_second": 22.203, | |
| "eval_steps_per_second": 22.203, | |
| "eval_wer": 0.39060023430501, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 2.5894736842105265e-05, | |
| "loss": 0.0909, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 2.536842105263158e-05, | |
| "loss": 0.1332, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 2.4842105263157898e-05, | |
| "loss": 0.1807, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 2.431578947368421e-05, | |
| "loss": 0.1147, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 2.3789473684210527e-05, | |
| "loss": 0.1064, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 2.3263157894736844e-05, | |
| "loss": 0.1276, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 2.273684210526316e-05, | |
| "loss": 0.1614, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 2.2210526315789476e-05, | |
| "loss": 0.1039, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 2.168421052631579e-05, | |
| "loss": 0.1139, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 2.1157894736842106e-05, | |
| "loss": 0.1647, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "eval_loss": 0.6135303378105164, | |
| "eval_runtime": 75.9868, | |
| "eval_samples_per_second": 22.109, | |
| "eval_steps_per_second": 22.109, | |
| "eval_wer": 0.3960443801254221, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 2.0631578947368422e-05, | |
| "loss": 0.1123, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 2.010526315789474e-05, | |
| "loss": 0.0834, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 1.957894736842105e-05, | |
| "loss": 0.115, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 1.9052631578947368e-05, | |
| "loss": 0.177, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 1.8526315789473687e-05, | |
| "loss": 0.1005, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.102, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 1.7473684210526317e-05, | |
| "loss": 0.1472, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 1.694736842105263e-05, | |
| "loss": 0.1592, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 1.642105263157895e-05, | |
| "loss": 0.0835, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 1.5894736842105266e-05, | |
| "loss": 0.1162, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "eval_loss": 0.6224440932273865, | |
| "eval_runtime": 75.2862, | |
| "eval_samples_per_second": 22.315, | |
| "eval_steps_per_second": 22.315, | |
| "eval_wer": 0.39597546688718904, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.536842105263158e-05, | |
| "loss": 0.1747, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 1.4842105263157895e-05, | |
| "loss": 0.1015, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 1.431578947368421e-05, | |
| "loss": 0.1063, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 1.3789473684210526e-05, | |
| "loss": 0.1274, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 1.3263157894736844e-05, | |
| "loss": 0.1802, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 1.2736842105263157e-05, | |
| "loss": 0.097, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 1.2210526315789474e-05, | |
| "loss": 0.103, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 1.168421052631579e-05, | |
| "loss": 0.1553, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 1.1157894736842106e-05, | |
| "loss": 0.1418, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 1.0631578947368421e-05, | |
| "loss": 0.098, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "eval_loss": 0.6016908884048462, | |
| "eval_runtime": 75.2579, | |
| "eval_samples_per_second": 22.323, | |
| "eval_steps_per_second": 22.323, | |
| "eval_wer": 0.3907380607814761, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 1.0105263157894738e-05, | |
| "loss": 0.122, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 9.578947368421052e-06, | |
| "loss": 0.1587, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 9.05263157894737e-06, | |
| "loss": 0.0882, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 8.526315789473685e-06, | |
| "loss": 0.094, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.1387, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 7.473684210526316e-06, | |
| "loss": 0.157, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 6.9473684210526315e-06, | |
| "loss": 0.0854, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 6.421052631578947e-06, | |
| "loss": 0.1104, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 5.8947368421052634e-06, | |
| "loss": 0.1527, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 5.36842105263158e-06, | |
| "loss": 0.1183, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "eval_loss": 0.6120738983154297, | |
| "eval_runtime": 75.3076, | |
| "eval_samples_per_second": 22.309, | |
| "eval_steps_per_second": 22.309, | |
| "eval_wer": 0.388463923919785, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 4.842105263157895e-06, | |
| "loss": 0.0954, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 4.315789473684211e-06, | |
| "loss": 0.1377, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.789473684210527e-06, | |
| "loss": 0.1595, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 3.2631578947368423e-06, | |
| "loss": 0.099, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 2.7368421052631583e-06, | |
| "loss": 0.0991, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 2.2105263157894738e-06, | |
| "loss": 0.1279, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.6842105263157895e-06, | |
| "loss": 0.1355, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 1.1578947368421055e-06, | |
| "loss": 0.081, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 6.315789473684211e-07, | |
| "loss": 0.107, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.0526315789473685e-07, | |
| "loss": 0.1717, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.6074367761611938, | |
| "eval_runtime": 75.6617, | |
| "eval_samples_per_second": 22.204, | |
| "eval_steps_per_second": 22.204, | |
| "eval_wer": 0.38798153125215357, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 2900, | |
| "total_flos": 8.88017577624112e+18, | |
| "train_loss": 0.8719474144228574, | |
| "train_runtime": 6976.9166, | |
| "train_samples_per_second": 13.244, | |
| "train_steps_per_second": 0.416 | |
| } | |
| ], | |
| "max_steps": 2900, | |
| "num_train_epochs": 20, | |
| "total_flos": 8.88017577624112e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |