all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.2230520248413086,
    "eval_logits/rejected": -2.2182328701019287,
    "eval_logps/chosen": -34.07753372192383,
    "eval_logps/rejected": -37.60981750488281,
    "eval_loss": 0.9658033847808838,
    "eval_rewards/accuracies": 0.5278239250183105,
    "eval_rewards/chosen": -0.03008819743990898,
    "eval_rewards/margins": 0.03515118733048439,
    "eval_rewards/rejected": -0.06523937731981277,
    "eval_runtime": 145.6671,
    "eval_samples": 343,
    "eval_samples_per_second": 2.355,
    "eval_steps_per_second": 0.295,
    "train_loss": 0.8438688600218142,
    "train_runtime": 3250.9917,
    "train_samples": 3079,
    "train_samples_per_second": 0.947,
    "train_steps_per_second": 0.118
}