Skip to content
Merged

Evo #1322

Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions rdagent/app/data_science/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -201,7 +201,7 @@ class DataScienceBasePropSetting(KaggleBasePropSetting):
enable_reward_model_selection: bool = True
"""Enable reward model based hypothesis selection."""

reward_model_path: str ="/data/Blob_EastUS/FinetuneAgenticLLM/reward_ckpt/last_run_6" #"/data/userdata/v-lijingyuan/last_run_2"# "/data/userdata/v-lijingyuan/last_run_2"#"/data/Blob_EastUS/FinetuneAgenticLLM/reward_ckpt/last_run_2"
reward_model_path: str ="/data/Blob_EastUS/FinetuneAgenticLLM/reward_ckpt/last_run_8" #"/data/userdata/v-lijingyuan/last_run_2"# "/data/userdata/v-lijingyuan/last_run_2"#"/data/Blob_EastUS/FinetuneAgenticLLM/reward_ckpt/last_run_2"

#"/data/Blob_EastUS/FinetuneAgenticLLM/reward_ckpt/last_run_2"
#"/data/userdata/v-lijingyuan/last_run_2"
Expand All @@ -216,7 +216,7 @@ class DataScienceBasePropSetting(KaggleBasePropSetting):
#competition_mapping_path: str = "/data/userdata/v-lijingyuan/dpo/comp_to_scen.json"


reward_base_model: str = "Qwen/Qwen3-0.6B"
reward_base_model: str = "Qwen/Qwen3-4B"
""" Backbone of the reward model"""

max_length : int = 2300
Expand Down
Loading