{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.011933174224343675, "eval_steps": 3, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002386634844868735, "grad_norm": 1.0092898607254028, "learning_rate": 2e-05, "loss": 1.1095, "step": 1 }, { "epoch": 0.002386634844868735, "eval_loss": 1.0069401264190674, "eval_runtime": 27.2083, "eval_samples_per_second": 6.505, "eval_steps_per_second": 3.271, "step": 1 }, { "epoch": 0.00477326968973747, "grad_norm": 0.777765154838562, "learning_rate": 4e-05, "loss": 0.8552, "step": 2 }, { "epoch": 0.007159904534606206, "grad_norm": 0.7151408195495605, "learning_rate": 6e-05, "loss": 1.0173, "step": 3 }, { "epoch": 0.007159904534606206, "eval_loss": 1.0022640228271484, "eval_runtime": 27.1923, "eval_samples_per_second": 6.509, "eval_steps_per_second": 3.273, "step": 3 }, { "epoch": 0.00954653937947494, "grad_norm": 0.569198489189148, "learning_rate": 8e-05, "loss": 0.8199, "step": 4 }, { "epoch": 0.011933174224343675, "grad_norm": 0.684947669506073, "learning_rate": 0.0001, "loss": 0.7825, "step": 5 } ], "logging_steps": 1, "max_steps": 10, "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": 967722569564160.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }