all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.550062417984009,
    "eval_logits/rejected": -2.519716262817383,
    "eval_logps/chosen": -309.5232849121094,
    "eval_logps/rejected": -306.5199279785156,
    "eval_loss": 0.5869344472885132,
    "eval_rewards/accuracies": 0.7089999914169312,
    "eval_rewards/chosen": -0.2480395883321762,
    "eval_rewards/margins": 0.3042061924934387,
    "eval_rewards/rejected": -0.5522457957267761,
    "eval_runtime": 469.9661,
    "eval_samples": 2000,
    "eval_samples_per_second": 4.256,
    "eval_steps_per_second": 1.064,
    "train_loss": 0.6071469678956156,
    "train_runtime": 31823.939,
    "train_samples": 61135,
    "train_samples_per_second": 1.921,
    "train_steps_per_second": 0.24
}