mzio/aprm-tw-treasure-hunter-medium-gpt5m_med-gs4-s0-train
收藏Hugging Face2026-03-23 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/mzio/aprm-tw-treasure-hunter-medium-gpt5m_med-gs4-s0-train
下载链接
链接失效反馈官方服务:
资源简介:
---
{}
---
# Act-PRM Rollout Dataset
## Run Metadata
- **env_config**: `textworld/treasure_hunter_medium`
- **model_config**: `oai_gpt5m_med`
- **model**: `gpt-5-mini`
- **split**: `train`
- **group_size**: `4`
- **seed**: `0`
- **num_samples**: `80`
- **num_trajectories**: `320`
- **accuracy**: `78.1%`
- **mean_reward**: `0.781`
- **run_cmd**: `main_api.py --env_config textworld/treasure_hunter_medium --model_config oai_gpt5m_med --split train --group_size 4 --max_concurrent 5 --checkpoint_every 100 --dataset_name mzio/aprm-tw-treasure-hunter-medium-gpt5m_med-gs4-s0-train --seed 0 --verbose`
提供机构:
mzio



