SDiaReward-3B / all_results.json
MYJOKERML's picture
Add SDiaReward-3B weights and model card
14e4523 verified
Raw History Blame Contribute Delete
404 Bytes
{
"epoch": 2.0,
"eval_accuracy": 0.9172453703703703,
"eval_loss": 0.418969064950943,
"eval_margin": 0.8687698929398148,
"eval_max_reward": 1.382568359375,
"eval_mean_reward": -0.11189778645833333,
"eval_min_reward": -1.5139612268518519,
"eval_num_tokens": 92427959.0,
"eval_runtime": 403.7554,
"eval_samples_per_second": 4.275,
"eval_steps_per_second": 0.134
}