| { | |
| "best_metric": 3.128293514251709, | |
| "best_model_checkpoint": "/tmp/test-egy_aragpt/checkpoint-500", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 638, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.567398119122257, | |
| "grad_norm": 1.3536401987075806, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.567398119122257, | |
| "eval_bleu": 0.11424038411303619, | |
| "eval_loss": 3.128293514251709, | |
| "eval_rouge1": 0.3297614987151056, | |
| "eval_rouge2": 0.08429294540985294, | |
| "eval_rougeL": 0.2561476738686219, | |
| "eval_runtime": 26.7734, | |
| "eval_samples_per_second": 31.636, | |
| "eval_steps_per_second": 3.959, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 638, | |
| "total_flos": 2000451796992000.0, | |
| "train_loss": 4.049833530916316, | |
| "train_runtime": 263.3387, | |
| "train_samples_per_second": 19.382, | |
| "train_steps_per_second": 2.423 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 638, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2000451796992000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |