llama-8b-dpo-full / eval_results.json
fenguhao's picture
Model save
b002b79 verified
raw
history blame
566 Bytes
{
"epoch": 1.0,
"eval_logits/chosen": -1.4751973152160645,
"eval_logits/rejected": -1.4288278818130493,
"eval_logps/chosen": -2603.783203125,
"eval_logps/rejected": -2200.0751953125,
"eval_loss": 0.6315724849700928,
"eval_rewards/accuracies": 0.6600000262260437,
"eval_rewards/chosen": 0.6899210810661316,
"eval_rewards/margins": 0.3855075538158417,
"eval_rewards/rejected": 0.30441343784332275,
"eval_runtime": 298.7044,
"eval_samples": 2000,
"eval_samples_per_second": 6.696,
"eval_steps_per_second": 0.418
}