{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 7, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.7142857142857143, "grad_norm": 1.5405463980844654, "learning_rate": 1e-05, "loss": 1.1878, "mean_token_accuracy": 0.783553683757782, "num_tokens": 278937.0, "step": 5 }, { "epoch": 1.0, "mean_token_accuracy": 0.8935140669345856, "num_tokens": 375257.0, "step": 7, "total_flos": 469676195840.0, "train_loss": 1.156841584614345, "train_runtime": 50.0775, "train_samples_per_second": 1.018, "train_steps_per_second": 0.14 } ], "logging_steps": 5, "max_steps": 7, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 469676195840.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }