atutej's picture
Best train reward at step 15 (reward=0.217, pass@8=0.219). This is the exact best step. Base model: Qwen/Qwen3-32B, dataset: exp_rpt_stack-bash-withtests-gpt5mini.
751f73a verified
raw
history blame contribute delete
214 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.57.6"
}