all_results.json

{
    "epoch": 0.9221902017291066,
    "eval_logits/chosen": -0.040584832429885864,
    "eval_logits/rejected": 0.1219257190823555,
    "eval_logps/chosen": -137.93557739257812,
    "eval_logps/ref_chosen": -138.21275329589844,
    "eval_logps/ref_rejected": -174.99253845214844,
    "eval_logps/rejected": -174.6787567138672,
    "eval_loss": 0.6933349967002869,
    "eval_rewards/accuracies": 0.48055556416511536,
    "eval_rewards/chosen": 0.00277182599529624,
    "eval_rewards/margins": -0.00036603162880055606,
    "eval_rewards/rejected": 0.0031378574203699827,
    "eval_runtime": 144.8376,
    "eval_samples": 1080,
    "eval_samples_per_second": 7.457,
    "eval_steps_per_second": 1.864,
    "total_flos": 0.0,
    "train_loss": 0.6936326384544372,
    "train_runtime": 616.2156,
    "train_samples": 1387,
    "train_samples_per_second": 2.251,
    "train_steps_per_second": 0.016
}