| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013651877133105802, | |
| "eval_steps": 500, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006825938566552901, | |
| "grad_norm": 29.01302146911621, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013651877133105802, | |
| "grad_norm": 26.415725708007812, | |
| "learning_rate": 0.0, | |
| "loss": 1.7687, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013651877133105802, | |
| "step": 2, | |
| "total_flos": 8665747207225344.0, | |
| "train_loss": 1.8449461460113525, | |
| "train_runtime": 310.7619, | |
| "train_samples_per_second": 0.412, | |
| "train_steps_per_second": 0.006 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 2, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8665747207225344.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |