lambda-qwen2.5-32b-dpo-test / eval_results.json
tanliboy's picture
End of training
675b60d verified
raw
history blame
563 Bytes
{
"epoch": 1.0,
"eval_logits/chosen": -0.05997615307569504,
"eval_logits/rejected": -0.31538692116737366,
"eval_logps/chosen": -1372.8902587890625,
"eval_logps/rejected": -3049.527099609375,
"eval_loss": 0.00032760968315415084,
"eval_rewards/accuracies": 1.0,
"eval_rewards/chosen": -10.161836624145508,
"eval_rewards/margins": 15.953170776367188,
"eval_rewards/rejected": -26.115005493164062,
"eval_runtime": 107.6139,
"eval_samples": 643,
"eval_samples_per_second": 5.975,
"eval_steps_per_second": 0.381
}