| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9883231273797637e-05, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.961077091265878e-06, | |
| "grad_norm": 10.275520324707031, | |
| "learning_rate": 2e-05, | |
| "loss": 28.3132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.961077091265878e-06, | |
| "eval_loss": 7.1797685623168945, | |
| "eval_runtime": 2183.9928, | |
| "eval_samples_per_second": 19.354, | |
| "eval_steps_per_second": 9.677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.9922154182531756e-05, | |
| "grad_norm": 11.051509857177734, | |
| "learning_rate": 4e-05, | |
| "loss": 30.5221, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.9883231273797637e-05, | |
| "grad_norm": 9.985577583312988, | |
| "learning_rate": 6e-05, | |
| "loss": 28.8905, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.9883231273797637e-05, | |
| "eval_loss": 7.147799015045166, | |
| "eval_runtime": 2176.4219, | |
| "eval_samples_per_second": 19.422, | |
| "eval_steps_per_second": 9.711, | |
| "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": 949867291607040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |