| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 468, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.19158411026001, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.6929, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6137184115523465, | |
| "eval_loss": 0.6584985852241516, | |
| "eval_runtime": 1.191, | |
| "eval_samples_per_second": 232.585, | |
| "eval_steps_per_second": 29.388, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.83151912689209, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5631, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.6389040350914001, | |
| "eval_runtime": 1.1821, | |
| "eval_samples_per_second": 234.336, | |
| "eval_steps_per_second": 29.609, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 7.651352882385254, | |
| "learning_rate": 0.0, | |
| "loss": 0.3937, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.6961731910705566, | |
| "eval_runtime": 1.1913, | |
| "eval_samples_per_second": 232.528, | |
| "eval_steps_per_second": 29.381, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 468, | |
| "total_flos": 1965439583539200.0, | |
| "train_loss": 0.5499022394163996, | |
| "train_runtime": 117.9582, | |
| "train_samples_per_second": 63.328, | |
| "train_steps_per_second": 3.968 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 468, | |
| "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": 1965439583539200.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |