{ "best_metric": 1.0926024913787842, "best_model_checkpoint": "./outputs/checkpoint-100", "epoch": 0.14204545454545456, "eval_steps": 100, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.14, "learning_rate": 0.0002, "loss": 1.5836, "step": 100 }, { "epoch": 0.14, "eval_loss": 1.0926024913787842, "eval_runtime": 92.4288, "eval_samples_per_second": 16.142, "eval_steps_per_second": 2.023, "step": 100 } ], "logging_steps": 100, "max_steps": 2112, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "total_flos": 5530295581655040.0, "trial_name": null, "trial_params": null }