{ "effective_tokens_per_sec": 8121.0972769057125, "epoch": 4.0, "total_flos": 3.4175049861232067e+18, "train_loss": 0.7412061936664963, "train_runtime": 8152.0644, "train_samples_per_second": 6.639, "train_steps_per_second": 0.221 }