all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.7333760261535645,
    "eval_logits/rejected": -2.687427043914795,
    "eval_logps/chosen": -425.93402099609375,
    "eval_logps/rejected": -314.981201171875,
    "eval_loss": 0.6931471824645996,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 6.0564,
    "eval_samples": 100,
    "eval_samples_per_second": 16.512,
    "eval_steps_per_second": 0.33,
    "total_flos": 0.0,
    "train_loss": 0.24032984673976898,
    "train_runtime": 97.8271,
    "train_samples": 100,
    "train_samples_per_second": 1.022,
    "train_steps_per_second": 0.01
}