{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.015267175572519083, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.007633587786259542, "grad_norm": 0.22314991056919098, "learning_rate": 1e-05, "loss": 11.7765, "step": 1 }, { "epoch": 0.007633587786259542, "eval_loss": 11.783448219299316, "eval_runtime": 14.3889, "eval_samples_per_second": 15.359, "eval_steps_per_second": 7.714, "step": 1 }, { "epoch": 0.015267175572519083, "grad_norm": 0.19315843284130096, "learning_rate": 2e-05, "loss": 11.7877, "step": 2 }, { "epoch": 0.015267175572519083, "eval_loss": 11.783392906188965, "eval_runtime": 0.3005, "eval_samples_per_second": 735.458, "eval_steps_per_second": 369.393, "step": 2 } ], "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": false }, "attributes": {} } }, "total_flos": 406242459648.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }