{ "effective_tokens_per_sec": 8290.126142481631, "epoch": 4.0, "total_flos": 3.4175049861232067e+18, "train_loss": 0.759928425279923, "train_runtime": 7985.8505, "train_samples_per_second": 6.777, "train_steps_per_second": 0.226 }