{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.09411764705882353, "eval_steps": 5, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.018823529411764704, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.018823529411764704, "eval_loss": NaN, "eval_runtime": 75.4827, "eval_samples_per_second": 4.743, "eval_steps_per_second": 0.596, "step": 1 }, { "epoch": 0.03764705882352941, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.05647058823529412, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.07529411764705882, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.09411764705882353, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.09411764705882353, "eval_loss": NaN, "eval_runtime": 5.977, "eval_samples_per_second": 59.897, "eval_steps_per_second": 7.529, "step": 5 } ], "logging_steps": 1, "max_steps": 20, "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": 2.090030138916864e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }