| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.2857142857142856, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7619047619047619, | |
| "eval_loss": 1.2543432712554932, | |
| "eval_runtime": 12.2168, | |
| "eval_samples_per_second": 8.595, | |
| "eval_steps_per_second": 0.327, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "eval_loss": 1.1833806037902832, | |
| "eval_runtime": 12.3175, | |
| "eval_samples_per_second": 8.524, | |
| "eval_steps_per_second": 0.325, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "eval_loss": 1.153542399406433, | |
| "eval_runtime": 12.9628, | |
| "eval_samples_per_second": 8.1, | |
| "eval_steps_per_second": 0.309, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "step": 9, | |
| "total_flos": 14970645381120.0, | |
| "train_loss": 1.2536535263061523, | |
| "train_runtime": 1609.5914, | |
| "train_samples_per_second": 3.711, | |
| "train_steps_per_second": 0.006 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9, | |
| "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": 14970645381120.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |