{ "entropy": 1.6328125, "epoch": 1.0, "mean_token_accuracy": 0.7037371794382731, "num_tokens": 785524633.0, "total_flos": 1254725330468864.0, "train_loss": 1.377876113716714, "train_runtime": 31760.1021, "train_samples": 1871956, "train_samples_per_second": 24.347, "train_steps_per_second": 0.19, "weight_norm": 259.0048262098604 }