| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 25, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 93.79705047607422, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.5058, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.867682933807373, | |
| "eval_runtime": 0.0855, | |
| "eval_samples_per_second": 81.887, | |
| "eval_steps_per_second": 11.698, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 32.13396453857422, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.4015, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 30.29521942138672, | |
| "learning_rate": 0.0, | |
| "loss": 1.955, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 5000498352488448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |