{ "effective_tokens_per_sec": 984.6867068393703, "epoch": 3.0, "total_flos": 1.1649211674300252e+18, "train_loss": 0.2605089543634637, "train_runtime": 3793.9194, "train_samples_per_second": 3.09, "train_steps_per_second": 0.097 }