| { | |
| "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": 9.1137, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9e-06, | |
| "loss": 8.4051, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9e-06, | |
| "loss": 7.7484, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.8e-06, | |
| "loss": 7.4819, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 7.0253, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.8e-06, | |
| "loss": 6.0543, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 5.1796, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.8e-06, | |
| "loss": 5.0354, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.8e-06, | |
| "loss": 4.5542, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 4.1554, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 4.053138256072998, | |
| "eval_runtime": 72.4668, | |
| "eval_samples_per_second": 23.183, | |
| "eval_steps_per_second": 23.183, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.08e-05, | |
| "loss": 3.8952, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.18e-05, | |
| "loss": 3.7272, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 3.4985, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 3.3278, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.48e-05, | |
| "loss": 3.2449, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.58e-05, | |
| "loss": 3.1355, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 3.0556, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.78e-05, | |
| "loss": 3.034, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.88e-05, | |
| "loss": 2.9962, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.9800000000000004e-05, | |
| "loss": 2.9584, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.977475643157959, | |
| "eval_runtime": 71.877, | |
| "eval_samples_per_second": 23.373, | |
| "eval_steps_per_second": 23.373, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.08e-05, | |
| "loss": 2.9505, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.18e-05, | |
| "loss": 2.9527, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.2800000000000002e-05, | |
| "loss": 2.9569, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.38e-05, | |
| "loss": 2.9286, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.48e-05, | |
| "loss": 2.9256, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.58e-05, | |
| "loss": 2.9423, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.6800000000000004e-05, | |
| "loss": 2.9096, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.7800000000000005e-05, | |
| "loss": 2.9218, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.88e-05, | |
| "loss": 2.9453, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.98e-05, | |
| "loss": 2.9355, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.9411780834198, | |
| "eval_runtime": 71.4798, | |
| "eval_samples_per_second": 23.503, | |
| "eval_steps_per_second": 23.503, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.08e-05, | |
| "loss": 2.8964, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.18e-05, | |
| "loss": 2.9011, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.2800000000000004e-05, | |
| "loss": 2.9182, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.38e-05, | |
| "loss": 2.9111, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.48e-05, | |
| "loss": 2.8983, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.58e-05, | |
| "loss": 2.9013, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.68e-05, | |
| "loss": 2.9018, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.7800000000000004e-05, | |
| "loss": 2.8843, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.88e-05, | |
| "loss": 2.8906, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.9800000000000005e-05, | |
| "loss": 2.9048, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.9143226146698, | |
| "eval_runtime": 72.4169, | |
| "eval_samples_per_second": 23.199, | |
| "eval_steps_per_second": 23.199, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.08e-05, | |
| "loss": 2.8922, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.18e-05, | |
| "loss": 2.8697, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.2800000000000004e-05, | |
| "loss": 2.8645, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.38e-05, | |
| "loss": 2.9111, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.4800000000000005e-05, | |
| "loss": 2.8674, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.58e-05, | |
| "loss": 2.8603, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.6800000000000006e-05, | |
| "loss": 2.858, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 4.78e-05, | |
| "loss": 2.883, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.88e-05, | |
| "loss": 2.8584, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.9800000000000004e-05, | |
| "loss": 2.8568, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 2.878626585006714, | |
| "eval_runtime": 72.7252, | |
| "eval_samples_per_second": 23.101, | |
| "eval_steps_per_second": 23.101, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.08e-05, | |
| "loss": 2.86, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 5.1800000000000005e-05, | |
| "loss": 2.8582, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.28e-05, | |
| "loss": 2.8348, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.380000000000001e-05, | |
| "loss": 2.8496, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 5.4800000000000004e-05, | |
| "loss": 2.8642, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 5.580000000000001e-05, | |
| "loss": 2.8257, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 5.68e-05, | |
| "loss": 2.796, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.7799999999999995e-05, | |
| "loss": 2.7954, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 5.88e-05, | |
| "loss": 2.8045, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.9800000000000003e-05, | |
| "loss": 2.7248, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_loss": 2.7552971839904785, | |
| "eval_runtime": 72.4023, | |
| "eval_samples_per_second": 23.204, | |
| "eval_steps_per_second": 23.204, | |
| "eval_wer": 0.9832540831093654, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 6.08e-05, | |
| "loss": 2.7032, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 6.18e-05, | |
| "loss": 2.7207, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.280000000000001e-05, | |
| "loss": 2.6933, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.38e-05, | |
| "loss": 2.6425, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 6.48e-05, | |
| "loss": 2.6579, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6.58e-05, | |
| "loss": 2.6758, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6.680000000000001e-05, | |
| "loss": 2.5976, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.780000000000001e-05, | |
| "loss": 2.6003, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6.879999999999999e-05, | |
| "loss": 2.6394, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.98e-05, | |
| "loss": 2.6124, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 2.5874478816986084, | |
| "eval_runtime": 72.2581, | |
| "eval_samples_per_second": 23.25, | |
| "eval_steps_per_second": 23.25, | |
| "eval_wer": 1.0510647095307009, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 7.08e-05, | |
| "loss": 2.5232, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 7.18e-05, | |
| "loss": 2.5713, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.280000000000001e-05, | |
| "loss": 2.6144, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 7.38e-05, | |
| "loss": 2.5095, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 7.48e-05, | |
| "loss": 2.4838, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 7.58e-05, | |
| "loss": 2.5541, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 2.5471, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 7.780000000000001e-05, | |
| "loss": 2.4351, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 7.88e-05, | |
| "loss": 2.4678, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 7.98e-05, | |
| "loss": 2.5463, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 2.4629976749420166, | |
| "eval_runtime": 72.2879, | |
| "eval_samples_per_second": 23.24, | |
| "eval_steps_per_second": 23.24, | |
| "eval_wer": 1.0883467714147887, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 8.080000000000001e-05, | |
| "loss": 2.4432, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 8.18e-05, | |
| "loss": 2.4039, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 8.28e-05, | |
| "loss": 2.4578, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 8.38e-05, | |
| "loss": 2.5401, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 8.48e-05, | |
| "loss": 2.3699, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.58e-05, | |
| "loss": 2.3765, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.680000000000001e-05, | |
| "loss": 2.4682, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 8.78e-05, | |
| "loss": 2.4733, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 8.88e-05, | |
| "loss": 2.322, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 8.98e-05, | |
| "loss": 2.3302, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_loss": 2.394815444946289, | |
| "eval_runtime": 72.3077, | |
| "eval_samples_per_second": 23.234, | |
| "eval_steps_per_second": 23.234, | |
| "eval_wer": 1.065054096892013, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 9.080000000000001e-05, | |
| "loss": 2.4985, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 9.180000000000001e-05, | |
| "loss": 2.359, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 9.28e-05, | |
| "loss": 2.3208, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 9.38e-05, | |
| "loss": 2.3997, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 9.48e-05, | |
| "loss": 2.4434, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 9.58e-05, | |
| "loss": 2.2, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 9.680000000000001e-05, | |
| "loss": 2.187, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 9.78e-05, | |
| "loss": 2.4585, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 9.88e-05, | |
| "loss": 2.3281, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 9.98e-05, | |
| "loss": 2.0669, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 2.2227554321289062, | |
| "eval_runtime": 72.5814, | |
| "eval_samples_per_second": 23.146, | |
| "eval_steps_per_second": 23.146, | |
| "eval_wer": 0.9920060643649645, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 9.957894736842106e-05, | |
| "loss": 2.2318, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 9.905263157894737e-05, | |
| "loss": 2.4545, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 9.852631578947368e-05, | |
| "loss": 2.1879, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 9.8e-05, | |
| "loss": 2.0836, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 9.747368421052632e-05, | |
| "loss": 2.2671, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 9.694736842105264e-05, | |
| "loss": 2.3343, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 9.642105263157896e-05, | |
| "loss": 1.9379, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 9.589473684210528e-05, | |
| "loss": 2.0721, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 9.536842105263159e-05, | |
| "loss": 2.3738, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 9.48421052631579e-05, | |
| "loss": 2.1991, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "eval_loss": 2.0815486907958984, | |
| "eval_runtime": 72.7547, | |
| "eval_samples_per_second": 23.091, | |
| "eval_steps_per_second": 23.091, | |
| "eval_wer": 0.9184756391702846, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 9.431578947368421e-05, | |
| "loss": 1.894, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 9.378947368421053e-05, | |
| "loss": 2.0673, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 9.326315789473684e-05, | |
| "loss": 2.2889, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 9.273684210526317e-05, | |
| "loss": 1.8846, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 9.221052631578948e-05, | |
| "loss": 1.9944, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.16842105263158e-05, | |
| "loss": 2.2969, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.11578947368421e-05, | |
| "loss": 2.2064, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.063157894736842e-05, | |
| "loss": 1.8752, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.010526315789473e-05, | |
| "loss": 1.9839, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 8.957894736842106e-05, | |
| "loss": 2.293, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 2.0229156017303467, | |
| "eval_runtime": 72.8641, | |
| "eval_samples_per_second": 23.057, | |
| "eval_steps_per_second": 23.057, | |
| "eval_wer": 0.8674109296395838, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.905263157894737e-05, | |
| "loss": 1.8509, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.852631578947368e-05, | |
| "loss": 1.8529, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 2.1446, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.747368421052632e-05, | |
| "loss": 2.1791, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.694736842105264e-05, | |
| "loss": 1.7817, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.642105263157895e-05, | |
| "loss": 1.8903, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 8.589473684210528e-05, | |
| "loss": 2.2622, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 8.536842105263159e-05, | |
| "loss": 1.9584, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 8.48421052631579e-05, | |
| "loss": 1.7396, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 8.431578947368422e-05, | |
| "loss": 2.0366, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 1.9590282440185547, | |
| "eval_runtime": 72.3447, | |
| "eval_samples_per_second": 23.222, | |
| "eval_steps_per_second": 23.222, | |
| "eval_wer": 0.9164771552615257, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 8.378947368421053e-05, | |
| "loss": 2.2349, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 8.326315789473684e-05, | |
| "loss": 1.6997, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 8.273684210526315e-05, | |
| "loss": 1.7567, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 8.221052631578948e-05, | |
| "loss": 2.1089, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 8.16842105263158e-05, | |
| "loss": 2.0903, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 8.115789473684211e-05, | |
| "loss": 1.7575, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 8.063157894736842e-05, | |
| "loss": 1.8904, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 8.010526315789473e-05, | |
| "loss": 2.1946, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 7.957894736842106e-05, | |
| "loss": 1.8283, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 7.905263157894737e-05, | |
| "loss": 1.767, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 1.9129446744918823, | |
| "eval_runtime": 72.6019, | |
| "eval_samples_per_second": 23.14, | |
| "eval_steps_per_second": 23.14, | |
| "eval_wer": 0.8124870787678313, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 7.852631578947369e-05, | |
| "loss": 2.0462, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 2.2074, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.747368421052633e-05, | |
| "loss": 1.6767, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 7.694736842105264e-05, | |
| "loss": 1.794, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.642105263157895e-05, | |
| "loss": 2.0682, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 7.589473684210526e-05, | |
| "loss": 1.9451, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 7.536842105263158e-05, | |
| "loss": 1.6441, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 7.48421052631579e-05, | |
| "loss": 1.8124, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 7.431578947368422e-05, | |
| "loss": 2.221, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 7.378947368421053e-05, | |
| "loss": 1.6222, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "eval_loss": 1.8867629766464233, | |
| "eval_runtime": 72.6044, | |
| "eval_samples_per_second": 23.139, | |
| "eval_steps_per_second": 23.139, | |
| "eval_wer": 0.8258562469850458, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 7.326315789473684e-05, | |
| "loss": 1.6811, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 7.273684210526316e-05, | |
| "loss": 1.9881, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 7.221052631578947e-05, | |
| "loss": 2.1143, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 7.16842105263158e-05, | |
| "loss": 1.6932, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 7.115789473684211e-05, | |
| "loss": 1.9069, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 7.063157894736842e-05, | |
| "loss": 2.1833, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 7.010526315789473e-05, | |
| "loss": 1.8623, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 6.957894736842106e-05, | |
| "loss": 1.7111, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 6.905263157894737e-05, | |
| "loss": 1.8365, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.852631578947369e-05, | |
| "loss": 2.173, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 1.869093418121338, | |
| "eval_runtime": 72.9861, | |
| "eval_samples_per_second": 23.018, | |
| "eval_steps_per_second": 23.018, | |
| "eval_wer": 0.8661015781131556, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.6774, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 6.747368421052633e-05, | |
| "loss": 1.6742, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 6.694736842105264e-05, | |
| "loss": 1.9821, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 6.642105263157895e-05, | |
| "loss": 2.0149, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 6.589473684210526e-05, | |
| "loss": 1.6565, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 6.536842105263158e-05, | |
| "loss": 1.7984, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.484210526315789e-05, | |
| "loss": 2.1405, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 6.431578947368422e-05, | |
| "loss": 1.6816, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 6.378947368421053e-05, | |
| "loss": 1.5845, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 6.326315789473684e-05, | |
| "loss": 1.8614, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "eval_loss": 1.838814377784729, | |
| "eval_runtime": 72.6721, | |
| "eval_samples_per_second": 23.118, | |
| "eval_steps_per_second": 23.118, | |
| "eval_wer": 0.8250292881262491, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 6.273684210526316e-05, | |
| "loss": 2.0775, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 6.221052631578947e-05, | |
| "loss": 1.5785, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 6.168421052631578e-05, | |
| "loss": 1.755, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.115789473684211e-05, | |
| "loss": 2.075, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 6.063157894736843e-05, | |
| "loss": 1.863, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 6.010526315789474e-05, | |
| "loss": 1.583, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 5.9578947368421055e-05, | |
| "loss": 1.7871, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 5.905263157894737e-05, | |
| "loss": 2.1129, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 5.852631578947369e-05, | |
| "loss": 1.6468, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.5928, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "eval_loss": 1.8527811765670776, | |
| "eval_runtime": 72.6282, | |
| "eval_samples_per_second": 23.131, | |
| "eval_steps_per_second": 23.131, | |
| "eval_wer": 0.7772035007925022, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 5.747368421052633e-05, | |
| "loss": 1.9437, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 5.694736842105264e-05, | |
| "loss": 2.0138, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 5.642105263157895e-05, | |
| "loss": 1.5605, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 5.5894736842105266e-05, | |
| "loss": 1.6621, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 5.536842105263158e-05, | |
| "loss": 2.0522, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 5.484210526315789e-05, | |
| "loss": 1.7832, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 5.431578947368421e-05, | |
| "loss": 1.5737, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 5.378947368421053e-05, | |
| "loss": 1.7934, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.326315789473685e-05, | |
| "loss": 2.0458, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 5.2736842105263164e-05, | |
| "loss": 1.5978, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "eval_loss": 1.8002482652664185, | |
| "eval_runtime": 72.3724, | |
| "eval_samples_per_second": 23.213, | |
| "eval_steps_per_second": 23.213, | |
| "eval_wer": 0.7891944042450555, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 5.221052631578948e-05, | |
| "loss": 1.6475, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 5.168421052631579e-05, | |
| "loss": 1.8777, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 5.11578947368421e-05, | |
| "loss": 1.8604, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 5.0631578947368416e-05, | |
| "loss": 1.6094, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 5.010526315789474e-05, | |
| "loss": 1.6582, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 4.9578947368421055e-05, | |
| "loss": 2.1104, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 4.9052631578947375e-05, | |
| "loss": 1.6908, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 4.852631578947369e-05, | |
| "loss": 1.5252, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.919, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 4.747368421052632e-05, | |
| "loss": 1.9886, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "eval_loss": 1.7848409414291382, | |
| "eval_runtime": 72.7789, | |
| "eval_samples_per_second": 23.084, | |
| "eval_steps_per_second": 23.084, | |
| "eval_wer": 0.8448073874991385, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 4.6947368421052634e-05, | |
| "loss": 1.5232, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 4.642105263157895e-05, | |
| "loss": 1.6242, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.589473684210526e-05, | |
| "loss": 1.8527, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 4.536842105263158e-05, | |
| "loss": 1.7781, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 4.48421052631579e-05, | |
| "loss": 1.4409, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 4.431578947368421e-05, | |
| "loss": 1.7067, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 4.378947368421053e-05, | |
| "loss": 2.0791, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 4.3263157894736845e-05, | |
| "loss": 1.6208, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 4.273684210526316e-05, | |
| "loss": 1.6079, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 4.221052631578948e-05, | |
| "loss": 1.8042, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_loss": 1.7818946838378906, | |
| "eval_runtime": 71.0121, | |
| "eval_samples_per_second": 23.658, | |
| "eval_steps_per_second": 23.658, | |
| "eval_wer": 0.8155881744883192, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 4.168421052631579e-05, | |
| "loss": 1.8973, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 4.1157894736842104e-05, | |
| "loss": 1.5267, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 4.0631578947368424e-05, | |
| "loss": 1.7287, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 4.010526315789474e-05, | |
| "loss": 1.9913, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 3.9578947368421056e-05, | |
| "loss": 1.6745, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 3.905263157894737e-05, | |
| "loss": 1.4516, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 3.852631578947369e-05, | |
| "loss": 1.6448, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.9553, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 3.7473684210526315e-05, | |
| "loss": 1.5075, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 3.6947368421052635e-05, | |
| "loss": 1.5488, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "eval_loss": 1.7614949941635132, | |
| "eval_runtime": 71.3707, | |
| "eval_samples_per_second": 23.539, | |
| "eval_steps_per_second": 23.539, | |
| "eval_wer": 0.8227551512645579, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 3.642105263157895e-05, | |
| "loss": 1.8287, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 3.589473684210527e-05, | |
| "loss": 1.7579, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.536842105263158e-05, | |
| "loss": 1.5378, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 3.48421052631579e-05, | |
| "loss": 1.5749, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 3.431578947368421e-05, | |
| "loss": 1.9909, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 3.3789473684210526e-05, | |
| "loss": 1.5317, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 3.3263157894736846e-05, | |
| "loss": 1.5424, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 3.273684210526316e-05, | |
| "loss": 1.819, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 3.221052631578947e-05, | |
| "loss": 1.9687, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 3.168421052631579e-05, | |
| "loss": 1.4468, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "eval_loss": 1.756456971168518, | |
| "eval_runtime": 71.2139, | |
| "eval_samples_per_second": 23.591, | |
| "eval_steps_per_second": 23.591, | |
| "eval_wer": 0.7945696368272345, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 3.115789473684211e-05, | |
| "loss": 1.5571, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.0631578947368425e-05, | |
| "loss": 1.9013, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 3.0105263157894737e-05, | |
| "loss": 1.7373, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 2.9578947368421057e-05, | |
| "loss": 1.4294, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 2.905263157894737e-05, | |
| "loss": 1.6095, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 2.8526315789473683e-05, | |
| "loss": 1.9819, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.4882, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 2.747368421052632e-05, | |
| "loss": 1.53, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.6947368421052632e-05, | |
| "loss": 1.7475, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 2.6421052631578945e-05, | |
| "loss": 1.8153, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 1.7536742687225342, | |
| "eval_runtime": 71.6632, | |
| "eval_samples_per_second": 23.443, | |
| "eval_steps_per_second": 23.443, | |
| "eval_wer": 0.8340569223347805, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 2.5894736842105265e-05, | |
| "loss": 1.4362, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 2.536842105263158e-05, | |
| "loss": 1.5779, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 2.4842105263157898e-05, | |
| "loss": 1.9271, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 2.431578947368421e-05, | |
| "loss": 1.6156, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 2.3789473684210527e-05, | |
| "loss": 1.486, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 2.3263157894736844e-05, | |
| "loss": 1.6086, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 2.273684210526316e-05, | |
| "loss": 1.9037, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 2.2210526315789476e-05, | |
| "loss": 1.4369, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 2.168421052631579e-05, | |
| "loss": 1.4858, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 2.1157894736842106e-05, | |
| "loss": 1.77, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "eval_loss": 1.7527410984039307, | |
| "eval_runtime": 71.241, | |
| "eval_samples_per_second": 23.582, | |
| "eval_steps_per_second": 23.582, | |
| "eval_wer": 0.7958100751154297, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 2.0631578947368422e-05, | |
| "loss": 1.8011, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 2.010526315789474e-05, | |
| "loss": 1.368, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 1.957894736842105e-05, | |
| "loss": 1.5566, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 1.9052631578947368e-05, | |
| "loss": 1.8702, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 1.8526315789473687e-05, | |
| "loss": 1.5503, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.4542, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 1.7473684210526317e-05, | |
| "loss": 1.6839, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 1.694736842105263e-05, | |
| "loss": 1.8379, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 1.642105263157895e-05, | |
| "loss": 1.422, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 1.5894736842105266e-05, | |
| "loss": 1.4742, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "eval_loss": 1.7592216730117798, | |
| "eval_runtime": 71.3803, | |
| "eval_samples_per_second": 23.536, | |
| "eval_steps_per_second": 23.536, | |
| "eval_wer": 0.7849906967128385, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.536842105263158e-05, | |
| "loss": 1.8645, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 1.4842105263157895e-05, | |
| "loss": 1.6385, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 1.431578947368421e-05, | |
| "loss": 1.3692, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 1.3789473684210526e-05, | |
| "loss": 1.5574, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 1.3263157894736844e-05, | |
| "loss": 1.8886, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 1.2736842105263157e-05, | |
| "loss": 1.4443, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 1.2210526315789474e-05, | |
| "loss": 1.4329, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 1.168421052631579e-05, | |
| "loss": 1.7405, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 1.1157894736842106e-05, | |
| "loss": 1.7542, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 1.0631578947368421e-05, | |
| "loss": 1.4088, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "eval_loss": 1.742145299911499, | |
| "eval_runtime": 71.2352, | |
| "eval_samples_per_second": 23.584, | |
| "eval_steps_per_second": 23.584, | |
| "eval_wer": 0.8148990421059885, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 1.0105263157894738e-05, | |
| "loss": 1.5163, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 9.578947368421052e-06, | |
| "loss": 1.86, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 9.05263157894737e-06, | |
| "loss": 1.5346, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 8.526315789473685e-06, | |
| "loss": 1.4966, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.5937, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 7.473684210526316e-06, | |
| "loss": 1.7928, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 6.9473684210526315e-06, | |
| "loss": 1.3874, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 6.421052631578947e-06, | |
| "loss": 1.4221, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 5.8947368421052634e-06, | |
| "loss": 1.7668, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 5.36842105263158e-06, | |
| "loss": 1.7066, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "eval_loss": 1.73816978931427, | |
| "eval_runtime": 71.1848, | |
| "eval_samples_per_second": 23.601, | |
| "eval_steps_per_second": 23.601, | |
| "eval_wer": 0.7977396457859555, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 4.842105263157895e-06, | |
| "loss": 1.4119, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 4.315789473684211e-06, | |
| "loss": 1.5033, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.789473684210527e-06, | |
| "loss": 1.8575, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 3.2631578947368423e-06, | |
| "loss": 1.4447, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 2.7368421052631583e-06, | |
| "loss": 1.3956, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 2.2105263157894738e-06, | |
| "loss": 1.6589, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.6842105263157895e-06, | |
| "loss": 1.784, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 1.1578947368421055e-06, | |
| "loss": 1.3676, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 6.315789473684211e-07, | |
| "loss": 1.5221, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.0526315789473685e-07, | |
| "loss": 1.7068, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.7356616258621216, | |
| "eval_runtime": 71.2787, | |
| "eval_samples_per_second": 23.569, | |
| "eval_steps_per_second": 23.569, | |
| "eval_wer": 0.7935359382537386, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 2900, | |
| "total_flos": 1.1463619274186412e+18, | |
| "train_loss": 2.2490714783504093, | |
| "train_runtime": 4828.6822, | |
| "train_samples_per_second": 19.136, | |
| "train_steps_per_second": 0.601 | |
| } | |
| ], | |
| "max_steps": 2900, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.1463619274186412e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |