| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005435767349157456, | |
| "eval_steps": 100, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002717883674578728, | |
| "grad_norm": 4.251254558563232, | |
| "learning_rate": 2e-05, | |
| "loss": 5.3201, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002717883674578728, | |
| "eval_loss": 5.817660331726074, | |
| "eval_runtime": 740.7465, | |
| "eval_samples_per_second": 6.275, | |
| "eval_steps_per_second": 1.569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005435767349157456, | |
| "grad_norm": 6.6031174659729, | |
| "learning_rate": 4e-05, | |
| "loss": 5.8911, | |
| "step": 2 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 2, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "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": 4525540736237568.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |