{ "effective_tokens_per_sec": 7202.248603192874, "epoch": 4.0, "total_flos": 3.4175049861232067e+18, "train_loss": 0.8579487466323551, "train_runtime": 9192.0887, "train_samples_per_second": 5.888, "train_steps_per_second": 0.196 }