| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 26.666666666666668, | |
| "eval_steps": 50, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 11.11111111111111, | |
| "eval_cer": 1.0, | |
| "eval_loss": 5.89304256439209, | |
| "eval_runtime": 0.9784, | |
| "eval_samples_per_second": 9.198, | |
| "eval_steps_per_second": 1.022, | |
| "eval_wer": 1.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "eval_cer": 1.0, | |
| "eval_loss": 2.4281415939331055, | |
| "eval_runtime": 0.8402, | |
| "eval_samples_per_second": 10.711, | |
| "eval_steps_per_second": 1.19, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "step": 120, | |
| "total_flos": 5.3095066035971686e+17, | |
| "train_loss": 7.207664489746094, | |
| "train_runtime": 305.0878, | |
| "train_samples_per_second": 13.373, | |
| "train_steps_per_second": 0.393 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.3095066035971686e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |