{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.657142857142857, "eval_steps": 500, "global_step": 16, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.45714285714285713, "grad_norm": 1.0250402688980103, "learning_rate": 0.000175, "loss": 9.4331, "step": 2 }, { "epoch": 0.9142857142857143, "grad_norm": 1.659826636314392, "learning_rate": 0.00015000000000000001, "loss": 9.1118, "step": 4 }, { "epoch": 1.3714285714285714, "grad_norm": 1.8041411638259888, "learning_rate": 0.000125, "loss": 8.6231, "step": 6 }, { "epoch": 1.8285714285714287, "grad_norm": 2.312595844268799, "learning_rate": 0.0001, "loss": 8.0853, "step": 8 }, { "epoch": 2.2857142857142856, "grad_norm": 2.5195796489715576, "learning_rate": 7.500000000000001e-05, "loss": 8.0783, "step": 10 }, { "epoch": 2.742857142857143, "grad_norm": 2.0339744091033936, "learning_rate": 5e-05, "loss": 7.5323, "step": 12 }, { "epoch": 3.2, "grad_norm": 2.324352979660034, "learning_rate": 2.5e-05, "loss": 7.7034, "step": 14 }, { "epoch": 3.657142857142857, "grad_norm": 1.4060308933258057, "learning_rate": 0.0, "loss": 7.3291, "step": 16 }, { "epoch": 3.657142857142857, "step": 16, "total_flos": 72209284366944.0, "train_loss": 8.23705530166626, "train_runtime": 438.6831, "train_samples_per_second": 0.638, "train_steps_per_second": 0.036 } ], "logging_steps": 2, "max_steps": 16, "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": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 72209284366944.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }