{ "best_metric": 1.0932432413101196, "best_model_checkpoint": "./outputs/checkpoint-100", "epoch": 0.13333333333333333, "eval_steps": 100, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.13, "learning_rate": 0.0002, "loss": 0.9997, "step": 100 }, { "epoch": 0.13, "eval_loss": 1.0932432413101196, "eval_runtime": 721.0711, "eval_samples_per_second": 2.677, "eval_steps_per_second": 0.336, "step": 100 } ], "logging_steps": 100, "max_steps": 2250, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "total_flos": 2.590619614224384e+16, "trial_name": null, "trial_params": null }