all_results.json

{
    "epoch": 0.995910949568378,
    "eval_logits/chosen": -10.091446876525879,
    "eval_logits/rejected": -9.818441390991211,
    "eval_logps/chosen": -0.8267378211021423,
    "eval_logps/rejected": -0.9961459040641785,
    "eval_loss": 3.9708292484283447,
    "eval_rewards/accuracies": 0.7049180269241333,
    "eval_rewards/chosen": -8.267377853393555,
    "eval_rewards/margins": 1.6940813064575195,
    "eval_rewards/rejected": -9.96146011352539,
    "eval_runtime": 86.365,
    "eval_samples": 1941,
    "eval_samples_per_second": 22.474,
    "eval_steps_per_second": 1.413,
    "total_flos": 0.0,
    "train_loss": 4.865393144370866,
    "train_runtime": 3024.5765,
    "train_samples": 17605,
    "train_samples_per_second": 5.821,
    "train_steps_per_second": 0.045
}