| { | |
| "best_metric": 7.904606892647371, | |
| "best_model_checkpoint": "./checkpoint-1000", | |
| "epoch": 2.00802407221665, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 2.983, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 2.4843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.42e-06, | |
| "loss": 1.6336, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.1537, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.42e-06, | |
| "loss": 0.8284, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.2948, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.1898, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.1784, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.1658, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.1603, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.1459, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.1448, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.1413, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.1349, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.1372, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.1304, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.128, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.1228, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.1198, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.1176, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.10957513749599457, | |
| "eval_runtime": 2168.1929, | |
| "eval_samples_per_second": 1.78, | |
| "eval_steps_per_second": 0.056, | |
| "eval_wer": 10.749416177199066, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.953333333333333e-06, | |
| "loss": 0.0829, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.89777777777778e-06, | |
| "loss": 0.0721, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 9.842222222222223e-06, | |
| "loss": 0.0747, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.786666666666667e-06, | |
| "loss": 0.0781, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.731111111111113e-06, | |
| "loss": 0.0769, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.675555555555555e-06, | |
| "loss": 0.0755, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.620000000000001e-06, | |
| "loss": 0.0805, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 9.564444444444445e-06, | |
| "loss": 0.0733, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.508888888888889e-06, | |
| "loss": 0.0696, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.453333333333335e-06, | |
| "loss": 0.0682, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.397777777777779e-06, | |
| "loss": 0.0727, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.342222222222223e-06, | |
| "loss": 0.0724, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.286666666666667e-06, | |
| "loss": 0.0688, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.231111111111111e-06, | |
| "loss": 0.0672, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 9.175555555555557e-06, | |
| "loss": 0.0705, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 9.12e-06, | |
| "loss": 0.0714, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 9.064444444444447e-06, | |
| "loss": 0.0635, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 9.008888888888889e-06, | |
| "loss": 0.0639, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.953333333333335e-06, | |
| "loss": 0.0728, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.897777777777779e-06, | |
| "loss": 0.0605, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.08087032288312912, | |
| "eval_runtime": 2054.0453, | |
| "eval_samples_per_second": 1.879, | |
| "eval_steps_per_second": 0.059, | |
| "eval_wer": 7.904606892647371, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 11, | |
| "total_flos": 6.532075529109504e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |