{ "effective_tokens_per_sec": 934.667920697108, "epoch": 3.0, "total_flos": 2.799606877430743e+17, "train_loss": 0.49932229929956895, "train_runtime": 513.7568, "train_samples_per_second": 21.652, "train_steps_per_second": 0.169 }