| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5945945945945947, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8648648648648649, | |
| "eval_loss": 1.290932059288025, | |
| "eval_runtime": 6.9909, | |
| "eval_samples_per_second": 8.869, | |
| "eval_steps_per_second": 0.286, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.7297297297297298, | |
| "eval_loss": 1.2912956476211548, | |
| "eval_runtime": 7.1821, | |
| "eval_samples_per_second": 8.633, | |
| "eval_steps_per_second": 0.278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5945945945945947, | |
| "eval_loss": 1.2107875347137451, | |
| "eval_runtime": 7.2062, | |
| "eval_samples_per_second": 8.604, | |
| "eval_steps_per_second": 0.278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.5945945945945947, | |
| "step": 6, | |
| "total_flos": 9945533644800.0, | |
| "train_loss": 1.2644638220469158, | |
| "train_runtime": 1282.1967, | |
| "train_samples_per_second": 2.726, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 9945533644800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |