{ "effective_tokens_per_sec": 151.98800620935165, "epoch": 3.0, "total_flos": 1.0795094318314947e+18, "train_loss": 0.14432617937002265, "train_runtime": 3312.6808, "train_samples_per_second": 13.186, "train_steps_per_second": 0.206 }