{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006255864873318737, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006255864873318737, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0006255864873318737, "eval_loss": NaN, "eval_runtime": 189.6188, "eval_samples_per_second": 14.202, "eval_steps_per_second": 7.104, "step": 1 }, { "epoch": 0.0012511729746637473, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.001876759461995621, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0025023459493274947, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0031279324366593683, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0031279324366593683, "eval_loss": NaN, "eval_runtime": 27.5644, "eval_samples_per_second": 97.699, "eval_steps_per_second": 48.867, "step": 5 }, { "epoch": 0.003753518923991242, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.004379105411323116, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.005004691898654989, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.005630278385986863, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.006255864873318737, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.006255864873318737, "eval_loss": NaN, "eval_runtime": 27.5562, "eval_samples_per_second": 97.728, "eval_steps_per_second": 48.882, "step": 10 } ], "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": 366481560698880.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }