eval_results.json

{
    "epoch": 0.9807355516637478,
    "eval_logits/chosen": -12.004097938537598,
    "eval_logits/rejected": -17.047502517700195,
    "eval_logps/chosen": -2.168222427368164,
    "eval_logps/rejected": -4.787535667419434,
    "eval_loss": 1.0162526369094849,
    "eval_mem_cpu_alloc_delta": 466944,
    "eval_mem_cpu_peaked_delta": 0,
    "eval_mem_gpu_alloc_delta": 0,
    "eval_mem_gpu_peaked_delta": 25220711424,
    "eval_rewards/accuracies": 0.9166666865348816,
    "eval_rewards/chosen": -21.682226181030273,
    "eval_rewards/margins": 26.193130493164062,
    "eval_rewards/rejected": -47.875362396240234,
    "eval_runtime": 9.9413,
    "eval_samples_per_second": 9.456,
    "eval_sft_loss": 0.01844729855656624,
    "eval_steps_per_second": 1.207
}