{ "effective_tokens_per_sec": 147.5977248231877, "epoch": 3.0, "total_flos": 5.409409897081078e+17, "train_loss": 0.1565390659049589, "train_runtime": 1705.6081, "train_samples_per_second": 12.805, "train_steps_per_second": 0.201 }