{
    "epoch": 1.0,
    "eval_accuracy": 1.0,
    "eval_loss": 0.9172223210334778,
    "eval_margin": 0.109375,
    "eval_max_reward": 2.6875,
    "eval_mean_reward": 2.6328125,
    "eval_min_reward": 2.578125,
    "eval_num_tokens": 1778.0,
    "eval_runtime": 0.7199,
    "eval_samples_per_second": 1.389,
    "eval_steps_per_second": 1.389,
    "train_loss": 0.9093897938728333,
    "train_runtime": 9.4012,
    "train_samples_per_second": 0.011,
    "train_steps_per_second": 0.106
}