{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.5555555555555554, "eval_steps": 500, "global_step": 12, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5925925925925926, "grad_norm": 1.0607314109802246, "learning_rate": 0.0001666666666666667, "loss": 9.4749, "step": 2 }, { "epoch": 1.1851851851851851, "grad_norm": 1.2989342212677002, "learning_rate": 0.00013333333333333334, "loss": 9.1331, "step": 4 }, { "epoch": 1.7777777777777777, "grad_norm": 2.0942795276641846, "learning_rate": 0.0001, "loss": 8.7015, "step": 6 }, { "epoch": 2.3703703703703702, "grad_norm": 2.3627431392669678, "learning_rate": 6.666666666666667e-05, "loss": 8.235, "step": 8 }, { "epoch": 2.962962962962963, "grad_norm": 1.63328218460083, "learning_rate": 3.3333333333333335e-05, "loss": 7.8734, "step": 10 }, { "epoch": 3.5555555555555554, "grad_norm": 2.139130115509033, "learning_rate": 0.0, "loss": 7.7671, "step": 12 }, { "epoch": 3.5555555555555554, "step": 12, "total_flos": 56669875934856.0, "train_loss": 8.530826091766357, "train_runtime": 310.5596, "train_samples_per_second": 0.696, "train_steps_per_second": 0.039 } ], "logging_steps": 2, "max_steps": 12, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 56669875934856.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }