| { | |
| "best_metric": 115.42439147433473, | |
| "best_model_checkpoint": "./output/checkpoint-15", | |
| "epoch": 1.0, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6e-06, | |
| "loss": 3.675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7e-06, | |
| "loss": 3.2974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.686, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.679447650909424, | |
| "eval_runtime": 455.8706, | |
| "eval_samples_per_second": 2.194, | |
| "eval_steps_per_second": 0.138, | |
| "eval_wer": 115.42439147433473, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 15, | |
| "total_flos": 2.36341297152e+16, | |
| "train_loss": 3.2194599151611327, | |
| "train_runtime": 862.9787, | |
| "train_samples_per_second": 1.112, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "max_steps": 15, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.36341297152e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |