all_results.json

{
    "epoch": 0.9997382884061764,
    "eval_logits/chosen": -0.42172786593437195,
    "eval_logits/rejected": -0.39140966534614563,
    "eval_logps/chosen": -291.23876953125,
    "eval_logps/rejected": -283.9595947265625,
    "eval_loss": 0.5199193358421326,
    "eval_rewards/accuracies": 0.7260000109672546,
    "eval_rewards/chosen": -0.14773716032505035,
    "eval_rewards/margins": 0.8024731278419495,
    "eval_rewards/rejected": -0.9502103328704834,
    "eval_runtime": 348.2733,
    "eval_samples": 2000,
    "eval_samples_per_second": 5.743,
    "eval_steps_per_second": 0.359,
    "total_flos": 0.0,
    "train_loss": 0.543355998318857,
    "train_runtime": 19333.2554,
    "train_samples": 61135,
    "train_samples_per_second": 3.162,
    "train_steps_per_second": 0.049
}