all_results.json

{
    "epoch": 0.9983492901947838,
    "eval_logits/chosen": -2.375783920288086,
    "eval_logits/rejected": -2.3758819103240967,
    "eval_logps/chosen": -218.0917205810547,
    "eval_logps/rejected": -221.27059936523438,
    "eval_loss": 0.6741424202919006,
    "eval_rewards/accuracies": 0.564338207244873,
    "eval_rewards/chosen": -0.5671599507331848,
    "eval_rewards/margins": 0.056060947477817535,
    "eval_rewards/rejected": -0.6232209205627441,
    "eval_runtime": 162.069,
    "eval_samples": 8652,
    "eval_samples_per_second": 53.385,
    "eval_steps_per_second": 0.839,
    "total_flos": 0.0,
    "train_loss": 0.6782766637347993,
    "train_runtime": 9304.817,
    "train_samples": 193800,
    "train_samples_per_second": 20.828,
    "train_steps_per_second": 0.041
}