| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4, | |
| "eval_steps": 10, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000168, | |
| "loss": 5.0883, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 47.44880294799805, | |
| "learning_rate": 0.000152, | |
| "loss": 1.8313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.8116276264190674, | |
| "eval_runtime": 65.2786, | |
| "eval_samples_per_second": 3.064, | |
| "eval_steps_per_second": 1.532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 8.983357429504395, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.5976, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 3.9880592823028564, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.3371765613555908, | |
| "eval_runtime": 64.2071, | |
| "eval_samples_per_second": 3.115, | |
| "eval_steps_per_second": 1.557, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.457772731781006, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.284, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1864510458066432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |