| { | |
| "best_metric": 95.61808118081181, | |
| "best_model_checkpoint": "./checkpoint-100", | |
| "epoch": 1.0, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2442, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1382, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1442, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1432, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.2337646484375, | |
| "eval_runtime": 1865.6333, | |
| "eval_samples_per_second": 8.319, | |
| "eval_steps_per_second": 0.26, | |
| "eval_wer": 95.61808118081181, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 100, | |
| "total_flos": 6.531871475907953e+18, | |
| "train_loss": 0.1674322509765625, | |
| "train_runtime": 2968.1959, | |
| "train_samples_per_second": 2.156, | |
| "train_steps_per_second": 0.034 | |
| } | |
| ], | |
| "max_steps": 100, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 6.531871475907953e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |