{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.004783258594917788, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009566517189835576, "grad_norm": 0.02000294253230095, "learning_rate": 1e-05, "loss": 11.935, "step": 1 }, { "epoch": 0.0009566517189835576, "eval_loss": 11.929906845092773, "eval_runtime": 14.2122, "eval_samples_per_second": 123.908, "eval_steps_per_second": 61.989, "step": 1 }, { "epoch": 0.0019133034379671151, "grad_norm": 0.020504001528024673, "learning_rate": 2e-05, "loss": 11.9351, "step": 2 }, { "epoch": 0.0019133034379671151, "eval_loss": 11.92990493774414, "eval_runtime": 2.2759, "eval_samples_per_second": 773.751, "eval_steps_per_second": 387.095, "step": 2 }, { "epoch": 0.0028699551569506725, "grad_norm": 0.019890565425157547, "learning_rate": 3e-05, "loss": 11.9341, "step": 3 }, { "epoch": 0.0038266068759342303, "grad_norm": 0.017157334834337234, "learning_rate": 4e-05, "loss": 11.9252, "step": 4 }, { "epoch": 0.0038266068759342303, "eval_loss": 11.929898262023926, "eval_runtime": 2.3066, "eval_samples_per_second": 763.45, "eval_steps_per_second": 381.942, "step": 4 }, { "epoch": 0.004783258594917788, "grad_norm": 0.021077081561088562, "learning_rate": 5e-05, "loss": 11.9276, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2363228160.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }