| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04423963133640553, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014746543778801843, | |
| "grad_norm": 2.212881326675415, | |
| "learning_rate": 1e-05, | |
| "loss": 3.5787, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014746543778801843, | |
| "eval_loss": NaN, | |
| "eval_runtime": 78.8407, | |
| "eval_samples_per_second": 1.459, | |
| "eval_steps_per_second": 0.736, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029493087557603687, | |
| "grad_norm": 2.1416406631469727, | |
| "learning_rate": 2e-05, | |
| "loss": 3.488, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04423963133640553, | |
| "grad_norm": 1.9657536745071411, | |
| "learning_rate": 3e-05, | |
| "loss": 3.2804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04423963133640553, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.6465, | |
| "eval_samples_per_second": 24.75, | |
| "eval_steps_per_second": 12.483, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4182326510616576.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |