{ "effective_tokens_per_sec": 7974.771452779717, "epoch": 4.0, "total_flos": 3.4175049861232067e+18, "train_loss": 0.6816160985415268, "train_runtime": 8301.6433, "train_samples_per_second": 6.519, "train_steps_per_second": 0.217 }