| { |
| "best_metric": 46.68450950404195, |
| "best_model_checkpoint": "whisper-small-mn-1/checkpoint-1000", |
| "epoch": 4.25531914893617, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 4.2000000000000006e-07, |
| "loss": 5.6118, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 9.200000000000001e-07, |
| "loss": 4.1038, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.42e-06, |
| "loss": 3.0469, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 1.9200000000000003e-06, |
| "loss": 2.3402, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 2.42e-06, |
| "loss": 1.8563, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 2.92e-06, |
| "loss": 1.5393, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 3.4200000000000007e-06, |
| "loss": 1.2931, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 3.920000000000001e-06, |
| "loss": 1.1391, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 4.42e-06, |
| "loss": 1.0085, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 4.92e-06, |
| "loss": 0.9081, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 5.420000000000001e-06, |
| "loss": 0.799, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 5.92e-06, |
| "loss": 0.7243, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 6.42e-06, |
| "loss": 0.6708, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 6.92e-06, |
| "loss": 0.6082, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 7.420000000000001e-06, |
| "loss": 0.5165, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 7.92e-06, |
| "loss": 0.508, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 8.42e-06, |
| "loss": 0.4601, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 8.920000000000001e-06, |
| "loss": 0.4402, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 9.42e-06, |
| "loss": 0.4018, |
| "step": 475 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 9.920000000000002e-06, |
| "loss": 0.321, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 9.58e-06, |
| "loss": 0.3206, |
| "step": 525 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 9.080000000000001e-06, |
| "loss": 0.2949, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 8.580000000000001e-06, |
| "loss": 0.2875, |
| "step": 575 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 8.08e-06, |
| "loss": 0.2795, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 7.58e-06, |
| "loss": 0.2773, |
| "step": 625 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 7.08e-06, |
| "loss": 0.272, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 6.5800000000000005e-06, |
| "loss": 0.2581, |
| "step": 675 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 6.08e-06, |
| "loss": 0.2452, |
| "step": 700 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 5.580000000000001e-06, |
| "loss": 0.1737, |
| "step": 725 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 5.0800000000000005e-06, |
| "loss": 0.1631, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 4.58e-06, |
| "loss": 0.1633, |
| "step": 775 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 4.08e-06, |
| "loss": 0.1502, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.51, |
| "learning_rate": 3.58e-06, |
| "loss": 0.1572, |
| "step": 825 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 3.08e-06, |
| "loss": 0.1527, |
| "step": 850 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 2.5800000000000003e-06, |
| "loss": 0.1572, |
| "step": 875 |
| }, |
| { |
| "epoch": 3.83, |
| "learning_rate": 2.08e-06, |
| "loss": 0.1475, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 1.5800000000000001e-06, |
| "loss": 0.154, |
| "step": 925 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 1.08e-06, |
| "loss": 0.1399, |
| "step": 950 |
| }, |
| { |
| "epoch": 4.15, |
| "learning_rate": 5.800000000000001e-07, |
| "loss": 0.1113, |
| "step": 975 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 8e-08, |
| "loss": 0.1121, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.26, |
| "eval_cer": 16.169474642348053, |
| "eval_loss": 0.45367762446403503, |
| "eval_runtime": 754.8724, |
| "eval_samples_per_second": 2.498, |
| "eval_steps_per_second": 0.156, |
| "eval_wer": 46.68450950404195, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.26, |
| "step": 1000, |
| "total_flos": 9.20933729501184e+18, |
| "train_loss": 0.8078537247180939, |
| "train_runtime": 2154.9671, |
| "train_samples_per_second": 14.849, |
| "train_steps_per_second": 0.464 |
| }, |
| { |
| "epoch": 4.26, |
| "eval_cer": 16.169474642348053, |
| "eval_loss": 0.45367762446403503, |
| "eval_runtime": 757.0424, |
| "eval_samples_per_second": 2.491, |
| "eval_steps_per_second": 0.156, |
| "eval_wer": 46.68450950404195, |
| "step": 1000 |
| } |
| ], |
| "max_steps": 1000, |
| "num_train_epochs": 5, |
| "total_flos": 9.20933729501184e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
