{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.011286681715575621, "eval_steps": 5, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002257336343115124, "eval_loss": 10.37696647644043, "eval_runtime": 1.3605, "eval_samples_per_second": 549.072, "eval_steps_per_second": 69.093, "step": 1 }, { "epoch": 0.006772009029345372, "grad_norm": 0.5311530232429504, "learning_rate": 3e-05, "loss": 10.3708, "step": 3 }, { "epoch": 0.011286681715575621, "eval_loss": 10.375223159790039, "eval_runtime": 1.3445, "eval_samples_per_second": 555.583, "eval_steps_per_second": 69.913, "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 }