{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.08771929824561403, "eval_steps": 5, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.017543859649122806, "eval_loss": 10.366873741149902, "eval_runtime": 0.1727, "eval_samples_per_second": 555.877, "eval_steps_per_second": 69.485, "step": 1 }, { "epoch": 0.05263157894736842, "grad_norm": 0.07264672964811325, "learning_rate": 3e-05, "loss": 10.3711, "step": 3 }, { "epoch": 0.08771929824561403, "eval_loss": 10.366547584533691, "eval_runtime": 0.1674, "eval_samples_per_second": 573.519, "eval_steps_per_second": 71.69, "step": 5 } ], "logging_steps": 3, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 557753303040.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }