{ "entropy": 1.693359375, "epoch": 1.0, "mean_token_accuracy": 0.7858945379654566, "num_tokens": 2504216233.0, "total_flos": 4000231083835392.0, "train_loss": 1.1146164414391346, "train_runtime": 104826.0086, "train_samples": 9904577, "train_samples_per_second": 23.488, "train_steps_per_second": 0.184, "weight_norm": 259.1283465775213 }