| { | |
| "best_metric": 111.76470588235294, | |
| "best_model_checkpoint": "mskov/whisper_miso/checkpoint-1000", | |
| "epoch": 333.3333333333333, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 4.8805, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 3.3934, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.6092, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.1399, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0008, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0002, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0001, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0001, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0001, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0001, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 91.67, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 108.33, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 116.67, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 133.33, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 141.67, | |
| "learning_rate": 8.5e-06, | |
| "loss": 0.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 158.33, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 9.92857142857143e-06, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 183.33, | |
| "learning_rate": 9.857142857142859e-06, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 191.67, | |
| "learning_rate": 9.785714285714286e-06, | |
| "loss": 0.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 9.714285714285715e-06, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 208.33, | |
| "learning_rate": 9.642857142857144e-06, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 216.67, | |
| "learning_rate": 9.571428571428573e-06, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 225.0, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 233.33, | |
| "learning_rate": 9.42857142857143e-06, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 241.67, | |
| "learning_rate": 9.357142857142859e-06, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 258.33, | |
| "learning_rate": 9.214285714285715e-06, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 266.67, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 275.0, | |
| "learning_rate": 9.071428571428573e-06, | |
| "loss": 0.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 283.33, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 291.67, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "learning_rate": 8.857142857142858e-06, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 308.33, | |
| "learning_rate": 8.785714285714286e-06, | |
| "loss": 0.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 316.67, | |
| "learning_rate": 8.714285714285715e-06, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 325.0, | |
| "learning_rate": 8.642857142857144e-06, | |
| "loss": 0.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 333.33, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 333.33, | |
| "eval_loss": 0.3114524483680725, | |
| "eval_runtime": 13.4346, | |
| "eval_samples_per_second": 1.265, | |
| "eval_steps_per_second": 0.223, | |
| "eval_wer": 111.76470588235294, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 4000, | |
| "num_train_epochs": 1334, | |
| "total_flos": 2.11648532594688e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |