{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.166666666666667, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.0833333333333335, "grad_norm": 0.33437681198120117, "learning_rate": 0.00015151515151515152, "loss": 2.0496, "step": 25 }, { "epoch": 2.0833333333333335, "eval_loss": 1.1585125923156738, "eval_runtime": 1.2434, "eval_samples_per_second": 9.651, "eval_steps_per_second": 1.608, "step": 25 }, { "epoch": 4.166666666666667, "grad_norm": 0.3806462287902832, "learning_rate": 0.00010101010101010102, "loss": 1.0128, "step": 50 }, { "epoch": 4.166666666666667, "eval_loss": 0.8326404094696045, "eval_runtime": 1.129, "eval_samples_per_second": 10.629, "eval_steps_per_second": 1.772, "step": 50 } ], "logging_steps": 25, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 9, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 132486878822400.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }