{ "effective_tokens_per_sec": 700.7739741426446, "epoch": 3.0, "total_flos": 2.906371548002648e+18, "train_loss": 4.493374055164515, "train_runtime": 8201.4497, "train_samples_per_second": 7.165, "train_steps_per_second": 0.112 }