{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.000507292327203551, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001690974424011837, "grad_norm": 0.45045530796051025, "learning_rate": 2e-05, "loss": 0.8337, "step": 1 }, { "epoch": 0.0001690974424011837, "eval_loss": 0.7358970642089844, "eval_runtime": 73.8094, "eval_samples_per_second": 33.736, "eval_steps_per_second": 16.868, "step": 1 }, { "epoch": 0.0003381948848023674, "grad_norm": 0.40704986453056335, "learning_rate": 4e-05, "loss": 0.6735, "step": 2 }, { "epoch": 0.000507292327203551, "grad_norm": 0.44953006505966187, "learning_rate": 6e-05, "loss": 0.8433, "step": 3 }, { "epoch": 0.000507292327203551, "eval_loss": 0.7347161173820496, "eval_runtime": 73.2045, "eval_samples_per_second": 34.014, "eval_steps_per_second": 17.007, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 51196944187392.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }