{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_loss": 9.421496391296387, "eval_runtime": 0.858, "eval_samples_per_second": 2.331, "eval_steps_per_second": 2.331, "step": 1 }, { "epoch": 2.0, "eval_loss": 6.097255706787109, "eval_runtime": 0.8528, "eval_samples_per_second": 2.345, "eval_steps_per_second": 2.345, "step": 2 }, { "epoch": 3.0, "eval_loss": 4.5291948318481445, "eval_runtime": 0.7724, "eval_samples_per_second": 2.589, "eval_steps_per_second": 2.589, "step": 3 }, { "epoch": 3.0, "step": 3, "total_flos": 17398068019200.0, "train_loss": 10.406506856282553, "train_runtime": 53.0496, "train_samples_per_second": 0.339, "train_steps_per_second": 0.057 } ], "logging_steps": 500, "max_steps": 3, "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": true }, "attributes": {} } }, "total_flos": 17398068019200.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }