| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2, | |
| "eval_steps": 5, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 17.72800636291504, | |
| "learning_rate": 2e-05, | |
| "loss": 4.9597, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "eval_loss": 3.594600200653076, | |
| "eval_runtime": 0.7611, | |
| "eval_samples_per_second": 2.628, | |
| "eval_steps_per_second": 1.314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 9.56978988647461, | |
| "learning_rate": 4e-05, | |
| "loss": 3.6803, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 5.929644584655762, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0466, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 21.923559188842773, | |
| "learning_rate": 8e-05, | |
| "loss": 7.1725, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 35615265521664.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |