| { | |
| "best_metric": 10.749416177199066, | |
| "best_model_checkpoint": "./checkpoint-500", | |
| "epoch": 1.004012036108325, | |
| "global_step": 500, | |
| "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 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 11, | |
| "total_flos": 3.266037764554752e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |