all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.7313623428344727,
    "eval_logits/rejected": -2.6492152214050293,
    "eval_logps/chosen": -291.2025146484375,
    "eval_logps/rejected": -270.01739501953125,
    "eval_loss": 0.6726499795913696,
    "eval_rewards/accuracies": 0.6100000143051147,
    "eval_rewards/chosen": -0.07162749022245407,
    "eval_rewards/margins": 0.05338801071047783,
    "eval_rewards/rejected": -0.1250154972076416,
    "eval_runtime": 393.8336,
    "eval_samples": 2000,
    "eval_samples_per_second": 5.078,
    "eval_steps_per_second": 0.635,
    "train_loss": 0.0,
    "train_runtime": 0.012,
    "train_samples": 19600,
    "train_samples_per_second": 1639445.565,
    "train_steps_per_second": 12797.713
}