| { | |
| "best_metric": 87.8, | |
| "best_model_checkpoint": "mskov/whisper_esc50/checkpoint-1000", | |
| "epoch": 15.873015873015873, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 6.7514, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 5.6562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.5e-06, | |
| "loss": 4.0209, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.5856, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.5934, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3e-06, | |
| "loss": 0.2997, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.2029, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1297, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0937, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0809, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.0521, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0477, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.0271, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0308, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0385, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0473, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 8.5e-06, | |
| "loss": 0.0313, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0246, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.0227, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0236, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 9.92857142857143e-06, | |
| "loss": 0.014, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 9.857142857142859e-06, | |
| "loss": 0.0144, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 9.785714285714286e-06, | |
| "loss": 0.0086, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 9.714285714285715e-06, | |
| "loss": 0.0119, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 9.642857142857144e-06, | |
| "loss": 0.0044, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 9.571428571428573e-06, | |
| "loss": 0.0052, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.0017, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 9.42857142857143e-06, | |
| "loss": 0.0034, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 9.357142857142859e-06, | |
| "loss": 0.0055, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 0.0021, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 9.214285714285715e-06, | |
| "loss": 0.0028, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 0.0007, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 9.071428571428573e-06, | |
| "loss": 0.0027, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0003, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.0001, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 8.857142857142858e-06, | |
| "loss": 0.0001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 8.785714285714286e-06, | |
| "loss": 0.0001, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 8.714285714285715e-06, | |
| "loss": 0.0001, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 8.642857142857144e-06, | |
| "loss": 0.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "eval_loss": 0.1191895380616188, | |
| "eval_runtime": 460.7316, | |
| "eval_samples_per_second": 2.17, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 87.8, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 4000, | |
| "num_train_epochs": 64, | |
| "total_flos": 4.5827361570816e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |