| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 111.0001, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.85e-06, | |
| "loss": 0.716, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 9.85e-06, | |
| "loss": 0.0615, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0043, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.002, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0008, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0006, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0004, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0003, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0003, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_loss": 0.21552081406116486, | |
| "eval_runtime": 10.773, | |
| "eval_samples_per_second": 1.671, | |
| "eval_steps_per_second": 0.093, | |
| "eval_wer": 9.75609756097561, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.96032852393984e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |