{
    "epoch": 2.999098751126561,
    "eval_kl/chosen": 0.0006550672114826739,
    "eval_kl/rejected": -6.322663102764636e-05,
    "eval_logits/chosen": -1.2890625,
    "eval_logits/rejected": -1.2578125,
    "eval_logps/chosen": -324.0,
    "eval_logps/rejected": -300.0,
    "eval_loss": 0.8606816530227661,
    "eval_nll_loss": 1.0625,
    "eval_ref_probs/chosen": 0.0038271306548267603,
    "eval_ref_probs/rejected": 0.0034569373819977045,
    "eval_rejected_term/max": -6.322663102764636e-05,
    "eval_rejected_term/min": -6.322663102764636e-05,
    "eval_rewards/accuracies": 0.4399999976158142,
    "eval_rewards/chosen": -0.314453125,
    "eval_rewards/margins": -0.0654296875,
    "eval_rewards/rejected": -0.248046875,
    "eval_runtime": 25.5111,
    "eval_samples_per_second": 39.199,
    "eval_steps_per_second": 9.8
}