all_results.json

{
    "epoch": 1.57,
    "eval_logits/chosen": -2.3900513648986816,
    "eval_logits/rejected": -2.3497886657714844,
    "eval_logps/chosen": -310.23736572265625,
    "eval_logps/rejected": -312.59942626953125,
    "eval_loss": 0.4916023015975952,
    "eval_rewards/accuracies": 0.7579365372657776,
    "eval_rewards/chosen": -0.6958636045455933,
    "eval_rewards/margins": 1.3472286462783813,
    "eval_rewards/rejected": -2.0430922508239746,
    "eval_runtime": 406.1845,
    "eval_samples": 2000,
    "eval_samples_per_second": 4.924,
    "eval_steps_per_second": 0.155,
    "train_loss": 0.4390208276112874,
    "train_runtime": 42485.337,
    "train_samples": 61135,
    "train_samples_per_second": 2.26,
    "train_steps_per_second": 0.035
}