{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.010283793137545733, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0007910610105804411, "eval_loss": NaN, "eval_runtime": 164.1202, "eval_samples_per_second": 51.889, "eval_steps_per_second": 6.489, "step": 1 }, { "epoch": 0.00791061010580441, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.00791061010580441, "eval_loss": NaN, "eval_runtime": 162.7431, "eval_samples_per_second": 52.328, "eval_steps_per_second": 6.544, "step": 10 } ], "logging_steps": 10, "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": 6745403777089536.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }