[ 1460, 0.6625166618660705, { "train_runtime": 7921.6312, "train_samples_per_second": 3.661, "train_steps_per_second": 0.915, "total_flos": 3.015155661857096e+17, "train_loss": 0.6625166618660705, "epoch": 2.01 } ]