all_results.json

{
    "epoch": 2.994495412844037,
    "eval_logits/chosen": -0.13572698831558228,
    "eval_logits/rejected": -1.339600920677185,
    "eval_logps/chosen": -277.6737060546875,
    "eval_logps/rejected": -238.95631408691406,
    "eval_loss": 0.12411908805370331,
    "eval_rewards/accuracies": 0.9777777791023254,
    "eval_rewards/chosen": -1.0706360340118408,
    "eval_rewards/margins": 4.546375274658203,
    "eval_rewards/rejected": -5.617011070251465,
    "eval_runtime": 9.0092,
    "eval_samples_per_second": 4.995,
    "eval_steps_per_second": 4.995,
    "total_flos": 7.837376281021809e+17,
    "train_loss": 0.23205441671113172,
    "train_runtime": 8090.8922,
    "train_samples_per_second": 1.616,
    "train_steps_per_second": 0.05
}