{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.01841258930105811, "eval_steps": 500, "global_step": 1500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00613752976701937, "grad_norm": 0.7345873117446899, "learning_rate": 4.9897707837216344e-05, "loss": 1.0473, "step": 500 }, { "epoch": 0.01227505953403874, "grad_norm": 1.5779420137405396, "learning_rate": 4.9795415674432687e-05, "loss": 1.0447, "step": 1000 }, { "epoch": 0.01841258930105811, "grad_norm": 1.1132322549819946, "learning_rate": 4.969312351164903e-05, "loss": 1.0383, "step": 1500 } ], "logging_steps": 500, "max_steps": 244398, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }