| { | |
| "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": 8.000000000000001e-07, | |
| "loss": 9.6309, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.8e-06, | |
| "loss": 8.4667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 7.9705, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.7e-06, | |
| "loss": 8.6971, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.7e-06, | |
| "loss": 8.1432, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.7000000000000005e-06, | |
| "loss": 7.5103, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.700000000000001e-06, | |
| "loss": 6.3957, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.6e-06, | |
| "loss": 5.9202, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.599999999999999e-06, | |
| "loss": 4.0808, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 3.3838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.2528371810913086, | |
| "eval_runtime": 56.3198, | |
| "eval_samples_per_second": 29.83, | |
| "eval_steps_per_second": 29.83, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.06e-05, | |
| "loss": 3.225, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.16e-05, | |
| "loss": 3.1006, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.2600000000000001e-05, | |
| "loss": 3.0419, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 3.0098, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.4599999999999999e-05, | |
| "loss": 3.0554, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.56e-05, | |
| "loss": 3.0022, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.66e-05, | |
| "loss": 2.9796, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.76e-05, | |
| "loss": 2.9955, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.86e-05, | |
| "loss": 2.9974, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 2.9608, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.9681849479675293, | |
| "eval_runtime": 56.3669, | |
| "eval_samples_per_second": 29.805, | |
| "eval_steps_per_second": 29.805, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.06e-05, | |
| "loss": 2.9543, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.16e-05, | |
| "loss": 2.9804, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.26e-05, | |
| "loss": 2.9606, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.36e-05, | |
| "loss": 2.9395, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.46e-05, | |
| "loss": 2.9356, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.5600000000000002e-05, | |
| "loss": 2.9696, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.6600000000000003e-05, | |
| "loss": 2.9255, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.7600000000000003e-05, | |
| "loss": 2.9392, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.86e-05, | |
| "loss": 2.9647, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.96e-05, | |
| "loss": 2.9574, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.9345755577087402, | |
| "eval_runtime": 56.4891, | |
| "eval_samples_per_second": 29.74, | |
| "eval_steps_per_second": 29.74, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.06e-05, | |
| "loss": 2.9146, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.16e-05, | |
| "loss": 2.9128, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.26e-05, | |
| "loss": 2.94, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 2.9084, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.46e-05, | |
| "loss": 2.9017, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.56e-05, | |
| "loss": 2.9015, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.66e-05, | |
| "loss": 2.9236, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.76e-05, | |
| "loss": 2.8774, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.86e-05, | |
| "loss": 2.8468, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.960000000000001e-05, | |
| "loss": 2.8555, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.761167049407959, | |
| "eval_runtime": 56.4787, | |
| "eval_samples_per_second": 29.746, | |
| "eval_steps_per_second": 29.746, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.0600000000000004e-05, | |
| "loss": 2.7772, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.16e-05, | |
| "loss": 2.6713, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.26e-05, | |
| "loss": 2.6037, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.36e-05, | |
| "loss": 2.5791, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.46e-05, | |
| "loss": 2.388, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.5600000000000004e-05, | |
| "loss": 2.2561, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.660000000000001e-05, | |
| "loss": 2.1583, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 4.76e-05, | |
| "loss": 2.0585, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.86e-05, | |
| "loss": 1.8282, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 4.96e-05, | |
| "loss": 1.7418, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 1.573166012763977, | |
| "eval_runtime": 56.5585, | |
| "eval_samples_per_second": 29.704, | |
| "eval_steps_per_second": 29.704, | |
| "eval_wer": 0.9856660464475225, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 5.0600000000000003e-05, | |
| "loss": 1.7797, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 5.16e-05, | |
| "loss": 1.5095, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 5.2600000000000005e-05, | |
| "loss": 1.3923, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 5.360000000000001e-05, | |
| "loss": 1.5058, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 5.4600000000000006e-05, | |
| "loss": 1.4846, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 5.560000000000001e-05, | |
| "loss": 1.2265, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 5.66e-05, | |
| "loss": 1.2093, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.76e-05, | |
| "loss": 1.3418, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 5.86e-05, | |
| "loss": 1.2013, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.96e-05, | |
| "loss": 0.9606, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_loss": 1.0014290809631348, | |
| "eval_runtime": 56.9613, | |
| "eval_samples_per_second": 29.494, | |
| "eval_steps_per_second": 29.494, | |
| "eval_wer": 0.7051891668389497, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 6.06e-05, | |
| "loss": 1.0301, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 6.16e-05, | |
| "loss": 1.2172, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.26e-05, | |
| "loss": 0.9271, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.36e-05, | |
| "loss": 0.9462, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 6.460000000000001e-05, | |
| "loss": 1.0384, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6.560000000000001e-05, | |
| "loss": 1.0549, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6.66e-05, | |
| "loss": 0.8307, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.76e-05, | |
| "loss": 0.9221, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6.860000000000001e-05, | |
| "loss": 1.0544, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.96e-05, | |
| "loss": 0.8334, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 0.769131600856781, | |
| "eval_runtime": 56.7008, | |
| "eval_samples_per_second": 29.629, | |
| "eval_steps_per_second": 29.629, | |
| "eval_wer": 0.6160843498035973, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 7.06e-05, | |
| "loss": 0.7341, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 7.16e-05, | |
| "loss": 0.8495, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 7.26e-05, | |
| "loss": 0.973, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 7.36e-05, | |
| "loss": 0.6632, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 7.46e-05, | |
| "loss": 0.6896, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 7.560000000000001e-05, | |
| "loss": 0.8501, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 7.66e-05, | |
| "loss": 0.8078, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 7.76e-05, | |
| "loss": 0.628, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 7.860000000000001e-05, | |
| "loss": 0.6806, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 7.960000000000001e-05, | |
| "loss": 0.852, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "eval_loss": 0.7168668508529663, | |
| "eval_runtime": 56.6076, | |
| "eval_samples_per_second": 29.678, | |
| "eval_steps_per_second": 29.678, | |
| "eval_wer": 0.5996829991041279, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 8.060000000000001e-05, | |
| "loss": 0.6486, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 8.16e-05, | |
| "loss": 0.5965, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 8.26e-05, | |
| "loss": 0.7368, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 8.36e-05, | |
| "loss": 0.8306, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 8.46e-05, | |
| "loss": 0.5529, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.560000000000001e-05, | |
| "loss": 0.6078, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.66e-05, | |
| "loss": 0.7776, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 8.76e-05, | |
| "loss": 0.571, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 8.86e-05, | |
| "loss": 0.4976, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 8.960000000000001e-05, | |
| "loss": 0.5707, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_loss": 0.6820988059043884, | |
| "eval_runtime": 56.4488, | |
| "eval_samples_per_second": 29.761, | |
| "eval_steps_per_second": 29.761, | |
| "eval_wer": 0.5526841706291779, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 9.06e-05, | |
| "loss": 0.766, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 9.16e-05, | |
| "loss": 0.521, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 9.260000000000001e-05, | |
| "loss": 0.5305, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 9.360000000000001e-05, | |
| "loss": 0.6219, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 9.46e-05, | |
| "loss": 0.6439, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 9.56e-05, | |
| "loss": 0.4465, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 9.66e-05, | |
| "loss": 0.5203, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 9.76e-05, | |
| "loss": 0.7278, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 9.86e-05, | |
| "loss": 0.546, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 9.960000000000001e-05, | |
| "loss": 0.4235, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_loss": 0.6078075766563416, | |
| "eval_runtime": 56.804, | |
| "eval_samples_per_second": 29.575, | |
| "eval_steps_per_second": 29.575, | |
| "eval_wer": 0.5139549307421956, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 9.968421052631578e-05, | |
| "loss": 0.5458, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 9.915789473684211e-05, | |
| "loss": 0.6398, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 9.863157894736842e-05, | |
| "loss": 0.3998, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 9.810526315789475e-05, | |
| "loss": 0.4046, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 9.757894736842106e-05, | |
| "loss": 0.5476, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 9.705263157894738e-05, | |
| "loss": 0.5076, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 9.652631578947369e-05, | |
| "loss": 0.3436, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.4287, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 9.547368421052632e-05, | |
| "loss": 0.6136, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 9.494736842105264e-05, | |
| "loss": 0.4357, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "eval_loss": 0.5927475094795227, | |
| "eval_runtime": 56.5623, | |
| "eval_samples_per_second": 29.702, | |
| "eval_steps_per_second": 29.702, | |
| "eval_wer": 0.49824271242505686, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 9.442105263157895e-05, | |
| "loss": 0.3723, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 9.389473684210527e-05, | |
| "loss": 0.4614, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 9.336842105263158e-05, | |
| "loss": 0.5398, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 9.28421052631579e-05, | |
| "loss": 0.3471, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 9.231578947368421e-05, | |
| "loss": 0.4024, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.178947368421052e-05, | |
| "loss": 0.5329, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.126315789473685e-05, | |
| "loss": 0.389, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.073684210526316e-05, | |
| "loss": 0.2866, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.021052631578947e-05, | |
| "loss": 0.3588, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 8.96842105263158e-05, | |
| "loss": 0.5004, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 0.5813701748847961, | |
| "eval_runtime": 56.4112, | |
| "eval_samples_per_second": 29.781, | |
| "eval_steps_per_second": 29.781, | |
| "eval_wer": 0.4825994073461512, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.915789473684211e-05, | |
| "loss": 0.3059, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.863157894736842e-05, | |
| "loss": 0.3087, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 8.810526315789475e-05, | |
| "loss": 0.4345, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.757894736842106e-05, | |
| "loss": 0.4485, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.705263157894738e-05, | |
| "loss": 0.2801, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 8.652631578947369e-05, | |
| "loss": 0.3428, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.4939, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 8.547368421052632e-05, | |
| "loss": 0.3254, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 8.494736842105263e-05, | |
| "loss": 0.3021, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 8.442105263157896e-05, | |
| "loss": 0.3757, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_loss": 0.5951181054115295, | |
| "eval_runtime": 56.2548, | |
| "eval_samples_per_second": 29.864, | |
| "eval_steps_per_second": 29.864, | |
| "eval_wer": 0.4643373992143891, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 8.389473684210527e-05, | |
| "loss": 0.4357, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 8.336842105263158e-05, | |
| "loss": 0.2338, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 8.28421052631579e-05, | |
| "loss": 0.2847, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 8.231578947368421e-05, | |
| "loss": 0.3848, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 8.178947368421052e-05, | |
| "loss": 0.3488, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 8.126315789473685e-05, | |
| "loss": 0.2357, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 8.073684210526316e-05, | |
| "loss": 0.2925, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 8.021052631578949e-05, | |
| "loss": 0.3927, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 7.96842105263158e-05, | |
| "loss": 0.2634, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 7.915789473684211e-05, | |
| "loss": 0.2579, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "eval_loss": 0.599000096321106, | |
| "eval_runtime": 56.5431, | |
| "eval_samples_per_second": 29.712, | |
| "eval_steps_per_second": 29.712, | |
| "eval_wer": 0.4580662945351802, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 7.863157894736843e-05, | |
| "loss": 0.3388, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 7.810526315789474e-05, | |
| "loss": 0.3973, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.757894736842105e-05, | |
| "loss": 0.2391, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 7.705263157894738e-05, | |
| "loss": 0.272, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.652631578947369e-05, | |
| "loss": 0.4072, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.2573, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 7.547368421052632e-05, | |
| "loss": 0.2134, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 7.494736842105263e-05, | |
| "loss": 0.2591, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 7.442105263157894e-05, | |
| "loss": 0.3908, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 7.389473684210527e-05, | |
| "loss": 0.2087, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "eval_loss": 0.5863637328147888, | |
| "eval_runtime": 56.4185, | |
| "eval_samples_per_second": 29.777, | |
| "eval_steps_per_second": 29.777, | |
| "eval_wer": 0.4487630073737165, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 7.336842105263158e-05, | |
| "loss": 0.229, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 7.28421052631579e-05, | |
| "loss": 0.3118, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 7.231578947368421e-05, | |
| "loss": 0.3177, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 7.178947368421054e-05, | |
| "loss": 0.2062, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 7.126315789473685e-05, | |
| "loss": 0.2668, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 7.073684210526316e-05, | |
| "loss": 0.3432, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 7.021052631578949e-05, | |
| "loss": 0.2328, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 6.96842105263158e-05, | |
| "loss": 0.2029, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 6.915789473684211e-05, | |
| "loss": 0.2662, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.863157894736843e-05, | |
| "loss": 0.3155, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 0.5836004614830017, | |
| "eval_runtime": 56.1874, | |
| "eval_samples_per_second": 29.9, | |
| "eval_steps_per_second": 29.9, | |
| "eval_wer": 0.4464199572737923, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 6.810526315789474e-05, | |
| "loss": 0.1775, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 6.757894736842105e-05, | |
| "loss": 0.1857, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 6.705263157894737e-05, | |
| "loss": 0.3008, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 6.652631578947369e-05, | |
| "loss": 0.2501, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.1811, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 6.547368421052632e-05, | |
| "loss": 0.2156, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.494736842105263e-05, | |
| "loss": 0.3433, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 6.442105263157894e-05, | |
| "loss": 0.1917, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 6.389473684210526e-05, | |
| "loss": 0.1897, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 6.336842105263158e-05, | |
| "loss": 0.2701, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "eval_loss": 0.6045300960540771, | |
| "eval_runtime": 56.6248, | |
| "eval_samples_per_second": 29.669, | |
| "eval_steps_per_second": 29.669, | |
| "eval_wer": 0.43484253325063743, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 6.28421052631579e-05, | |
| "loss": 0.3133, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 6.231578947368422e-05, | |
| "loss": 0.1561, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 6.178947368421054e-05, | |
| "loss": 0.2225, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.126315789473685e-05, | |
| "loss": 0.3342, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 6.073684210526316e-05, | |
| "loss": 0.1887, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 6.0210526315789475e-05, | |
| "loss": 0.1706, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 5.968421052631579e-05, | |
| "loss": 0.2167, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 5.9157894736842114e-05, | |
| "loss": 0.2971, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 5.863157894736843e-05, | |
| "loss": 0.1613, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 5.810526315789474e-05, | |
| "loss": 0.172, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "eval_loss": 0.6493738889694214, | |
| "eval_runtime": 56.5446, | |
| "eval_samples_per_second": 29.711, | |
| "eval_steps_per_second": 29.711, | |
| "eval_wer": 0.4344290538212391, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 5.7578947368421053e-05, | |
| "loss": 0.2779, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 5.7052631578947366e-05, | |
| "loss": 0.2399, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 5.652631578947368e-05, | |
| "loss": 0.1499, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.1919, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 5.547368421052632e-05, | |
| "loss": 0.2683, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 5.494736842105264e-05, | |
| "loss": 0.1663, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 5.442105263157895e-05, | |
| "loss": 0.1597, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 5.3894736842105265e-05, | |
| "loss": 0.2265, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 5.336842105263158e-05, | |
| "loss": 0.2389, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 5.284210526315789e-05, | |
| "loss": 0.1529, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "eval_loss": 0.591465950012207, | |
| "eval_runtime": 56.5515, | |
| "eval_samples_per_second": 29.707, | |
| "eval_steps_per_second": 29.707, | |
| "eval_wer": 0.42409206808627936, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 5.231578947368422e-05, | |
| "loss": 0.1739, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 5.178947368421053e-05, | |
| "loss": 0.2318, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 5.126315789473684e-05, | |
| "loss": 0.1797, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 5.073684210526316e-05, | |
| "loss": 0.1469, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 5.0210526315789476e-05, | |
| "loss": 0.1917, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 4.9684210526315796e-05, | |
| "loss": 0.2931, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 4.915789473684211e-05, | |
| "loss": 0.1528, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 4.863157894736842e-05, | |
| "loss": 0.1535, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 4.8105263157894735e-05, | |
| "loss": 0.2489, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 4.7578947368421054e-05, | |
| "loss": 0.2411, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "eval_loss": 0.615635871887207, | |
| "eval_runtime": 56.2351, | |
| "eval_samples_per_second": 29.875, | |
| "eval_steps_per_second": 29.875, | |
| "eval_wer": 0.4245744607539108, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 4.705263157894737e-05, | |
| "loss": 0.1373, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 4.652631578947369e-05, | |
| "loss": 0.164, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.2577, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 4.547368421052632e-05, | |
| "loss": 0.1481, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 4.494736842105263e-05, | |
| "loss": 0.1299, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 4.442105263157895e-05, | |
| "loss": 0.1767, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 4.3894736842105266e-05, | |
| "loss": 0.2631, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 4.336842105263158e-05, | |
| "loss": 0.1356, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 4.284210526315789e-05, | |
| "loss": 0.1595, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 4.231578947368421e-05, | |
| "loss": 0.2348, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_loss": 0.6363445520401001, | |
| "eval_runtime": 56.3827, | |
| "eval_samples_per_second": 29.796, | |
| "eval_steps_per_second": 29.796, | |
| "eval_wer": 0.4206464061746261, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 4.178947368421053e-05, | |
| "loss": 0.2066, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 4.1263157894736844e-05, | |
| "loss": 0.1278, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 4.0736842105263164e-05, | |
| "loss": 0.1942, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 4.021052631578948e-05, | |
| "loss": 0.2502, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 14.83, | |
| "learning_rate": 3.968421052631579e-05, | |
| "loss": 0.1388, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 3.91578947368421e-05, | |
| "loss": 0.1254, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 3.863157894736842e-05, | |
| "loss": 0.1711, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 3.8105263157894735e-05, | |
| "loss": 0.2085, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 3.7578947368421055e-05, | |
| "loss": 0.1183, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 3.7052631578947375e-05, | |
| "loss": 0.1429, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "eval_loss": 0.6394490599632263, | |
| "eval_runtime": 56.3483, | |
| "eval_samples_per_second": 29.815, | |
| "eval_steps_per_second": 29.815, | |
| "eval_wer": 0.4160981324512439, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 3.652631578947369e-05, | |
| "loss": 0.2156, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.1578, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.547368421052632e-05, | |
| "loss": 0.1341, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 3.4947368421052634e-05, | |
| "loss": 0.1594, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 3.442105263157895e-05, | |
| "loss": 0.2551, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 3.389473684210526e-05, | |
| "loss": 0.117, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 15.66, | |
| "learning_rate": 3.336842105263158e-05, | |
| "loss": 0.1331, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 3.28421052631579e-05, | |
| "loss": 0.2143, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 3.231578947368421e-05, | |
| "loss": 0.1883, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 3.178947368421053e-05, | |
| "loss": 0.1151, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "eval_loss": 0.618624746799469, | |
| "eval_runtime": 56.5131, | |
| "eval_samples_per_second": 29.728, | |
| "eval_steps_per_second": 29.728, | |
| "eval_wer": 0.4167183515953415, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 3.1263157894736845e-05, | |
| "loss": 0.1411, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.073684210526316e-05, | |
| "loss": 0.2432, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 3.021052631578947e-05, | |
| "loss": 0.1205, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 2.968421052631579e-05, | |
| "loss": 0.118, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 2.9157894736842107e-05, | |
| "loss": 0.1565, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 16.28, | |
| "learning_rate": 2.863157894736842e-05, | |
| "loss": 0.2138, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 2.810526315789474e-05, | |
| "loss": 0.1112, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 2.7578947368421053e-05, | |
| "loss": 0.138, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.705263157894737e-05, | |
| "loss": 0.1801, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 2.652631578947369e-05, | |
| "loss": 0.1723, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "eval_loss": 0.6497763395309448, | |
| "eval_runtime": 56.5754, | |
| "eval_samples_per_second": 29.695, | |
| "eval_steps_per_second": 29.695, | |
| "eval_wer": 0.4123768175866584, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.1073, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 16.69, | |
| "learning_rate": 2.5473684210526315e-05, | |
| "loss": 0.1439, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 2.4947368421052635e-05, | |
| "loss": 0.2264, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 2.4421052631578948e-05, | |
| "loss": 0.1329, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 2.3894736842105264e-05, | |
| "loss": 0.1273, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 2.336842105263158e-05, | |
| "loss": 0.164, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 2.2842105263157897e-05, | |
| "loss": 0.1856, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 2.2315789473684213e-05, | |
| "loss": 0.1101, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 2.1789473684210526e-05, | |
| "loss": 0.1334, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 2.1263157894736842e-05, | |
| "loss": 0.1997, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "eval_loss": 0.6540533304214478, | |
| "eval_runtime": 57.2509, | |
| "eval_samples_per_second": 29.345, | |
| "eval_steps_per_second": 29.345, | |
| "eval_wer": 0.40762180414857696, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 2.073684210526316e-05, | |
| "loss": 0.1572, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 2.0210526315789475e-05, | |
| "loss": 0.099, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 1.968421052631579e-05, | |
| "loss": 0.1358, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 1.9157894736842104e-05, | |
| "loss": 0.1907, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 1.863157894736842e-05, | |
| "loss": 0.1132, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 17.66, | |
| "learning_rate": 1.810526315789474e-05, | |
| "loss": 0.122, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 17.72, | |
| "learning_rate": 1.7578947368421054e-05, | |
| "loss": 0.171, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 17.79, | |
| "learning_rate": 1.705263157894737e-05, | |
| "loss": 0.179, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 1.6526315789473683e-05, | |
| "loss": 0.1014, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.1297, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "eval_loss": 0.654592752456665, | |
| "eval_runtime": 57.1287, | |
| "eval_samples_per_second": 29.407, | |
| "eval_steps_per_second": 29.407, | |
| "eval_wer": 0.41168768520432775, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.5473684210526316e-05, | |
| "loss": 0.1979, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 1.4947368421052632e-05, | |
| "loss": 0.1121, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 1.4421052631578948e-05, | |
| "loss": 0.0982, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 1.3894736842105263e-05, | |
| "loss": 0.1454, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 18.28, | |
| "learning_rate": 1.336842105263158e-05, | |
| "loss": 0.1949, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 1.2842105263157894e-05, | |
| "loss": 0.1097, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 1.231578947368421e-05, | |
| "loss": 0.1126, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 1.1789473684210527e-05, | |
| "loss": 0.1803, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 1.1263157894736842e-05, | |
| "loss": 0.155, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 1.073684210526316e-05, | |
| "loss": 0.101, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "eval_loss": 0.6470673084259033, | |
| "eval_runtime": 57.3973, | |
| "eval_samples_per_second": 29.27, | |
| "eval_steps_per_second": 29.27, | |
| "eval_wer": 0.4074839776721108, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 1.0210526315789474e-05, | |
| "loss": 0.1404, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 9.68421052631579e-06, | |
| "loss": 0.1989, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 9.157894736842105e-06, | |
| "loss": 0.0993, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 8.631578947368422e-06, | |
| "loss": 0.1216, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "learning_rate": 8.105263157894736e-06, | |
| "loss": 0.162, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 7.578947368421054e-06, | |
| "loss": 0.1653, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 7.052631578947369e-06, | |
| "loss": 0.0955, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 6.526315789473685e-06, | |
| "loss": 0.1158, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 6e-06, | |
| "loss": 0.1904, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 5.4736842105263165e-06, | |
| "loss": 0.1272, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "eval_loss": 0.6586117744445801, | |
| "eval_runtime": 56.8995, | |
| "eval_samples_per_second": 29.526, | |
| "eval_steps_per_second": 29.526, | |
| "eval_wer": 0.40645027909861486, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 4.947368421052632e-06, | |
| "loss": 0.097, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 4.4210526315789476e-06, | |
| "loss": 0.1309, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.894736842105264e-06, | |
| "loss": 0.1702, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 3.368421052631579e-06, | |
| "loss": 0.1035, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 2.842105263157895e-06, | |
| "loss": 0.1024, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 2.315789473684211e-06, | |
| "loss": 0.1567, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.7894736842105262e-06, | |
| "loss": 0.1576, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 1.2631578947368422e-06, | |
| "loss": 0.1008, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 7.368421052631579e-07, | |
| "loss": 0.11, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.105263157894737e-07, | |
| "loss": 0.1901, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.6549025177955627, | |
| "eval_runtime": 57.4128, | |
| "eval_samples_per_second": 29.262, | |
| "eval_steps_per_second": 29.262, | |
| "eval_wer": 0.4051409275721866, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 2900, | |
| "total_flos": 2.6571394113263534e+18, | |
| "train_loss": 0.9290403553329665, | |
| "train_runtime": 4751.1406, | |
| "train_samples_per_second": 19.448, | |
| "train_steps_per_second": 0.61 | |
| } | |
| ], | |
| "max_steps": 2900, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.6571394113263534e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |