{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.25, "eval_steps": 500, "global_step": 4500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5, "grad_norm": 5.349377632141113, "learning_rate": 8.336666666666668e-06, "loss": 0.5106, "step": 1000 }, { "epoch": 1.0, "grad_norm": 9.39653491973877, "learning_rate": 6.6700000000000005e-06, "loss": 0.3259, "step": 2000 }, { "epoch": 1.5, "grad_norm": 0.49256208539009094, "learning_rate": 5.0049999999999995e-06, "loss": 0.2533, "step": 3000 }, { "epoch": 2.0, "grad_norm": 15.07694149017334, "learning_rate": 3.3383333333333333e-06, "loss": 0.2193, "step": 4000 } ], "logging_steps": 1000, "max_steps": 6000, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 0.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }