| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 15808, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3085336685180664, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.8583, | |
| "step": 7904 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6763963103294373, | |
| "eval_runtime": 30.5391, | |
| "eval_samples_per_second": 32.745, | |
| "eval_steps_per_second": 4.093, | |
| "step": 7904 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.34101805090904236, | |
| "learning_rate": 0.0, | |
| "loss": 0.7036, | |
| "step": 15808 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6498508453369141, | |
| "eval_runtime": 30.6026, | |
| "eval_samples_per_second": 32.677, | |
| "eval_steps_per_second": 4.085, | |
| "step": 15808 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 15808, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.781888623771648e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |