all_results.json

{
    "epoch": 0.9182209469153515,
    "eval_logits/chosen": 0.010207059793174267,
    "eval_logits/rejected": 0.1653471440076828,
    "eval_logps/chosen": -140.33753967285156,
    "eval_logps/ref_chosen": -140.22314453125,
    "eval_logps/ref_rejected": -177.01461791992188,
    "eval_logps/rejected": -177.1112518310547,
    "eval_loss": 0.6932401061058044,
    "eval_rewards/accuracies": 0.4888888895511627,
    "eval_rewards/chosen": -0.001143624889664352,
    "eval_rewards/margins": -0.00017715863941702992,
    "eval_rewards/rejected": -0.0009664662647992373,
    "eval_runtime": 142.6879,
    "eval_samples": 1080,
    "eval_samples_per_second": 7.569,
    "eval_steps_per_second": 1.892,
    "total_flos": 0.0,
    "train_loss": 0.6935156106948852,
    "train_runtime": 611.1413,
    "train_samples": 1393,
    "train_samples_per_second": 2.279,
    "train_steps_per_second": 0.016
}