{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.036312849162011177, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002793296089385475, "eval_loss": 2.4049742221832275, "eval_runtime": 13.2901, "eval_samples_per_second": 11.362, "eval_steps_per_second": 5.719, "step": 1 }, { "epoch": 0.013966480446927373, "grad_norm": 2.8598062992095947, "learning_rate": 5e-05, "loss": 9.1267, "step": 5 }, { "epoch": 0.027932960893854747, "grad_norm": 4.437131881713867, "learning_rate": 0.0001, "loss": 8.7871, "step": 10 }, { "epoch": 0.027932960893854747, "eval_loss": 2.1106879711151123, "eval_runtime": 12.4419, "eval_samples_per_second": 12.136, "eval_steps_per_second": 6.108, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3708646965903360.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }