d1_math_shortest/all_results.json

{
    "epoch": 5.0,
    "total_flos": 4.620475786573382e+18,
    "train_loss": 0.3420306665453351,
    "train_runtime": 57470.9786,
    "train_samples_per_second": 2.749,
    "train_steps_per_second": 0.021
}