Skip to content

feat: add llm judge metrics #22

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
junjzhang merged 2 commits into from
Jul 1, 2025
Merged

feat: add llm judge metrics #22

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
96eadb2
feat: add llm judge metrics
jing-4369 Jul 1, 2025
a544130
chore: use placeholder for IP address.
jing-4369 Jul 1, 2025
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
14 changes: 7 additions & 7 deletions evaluation/nb_agent_eval/config/sampler_config_direct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
traj_sampler:
model_id: Qwen/Qwen2.5-7B-Instruct
max_concurrency: 64
max_retries: 3
task_timeout: 1200
max_concurrency: 256
max_retries: 1
task_timeout: 600
agent_type: nb_agent
executor_type: remote
remote_exec_server_url:
- http://10.80.78.178:8000
- http://{your_ip_address}:8000
agent:
uuid: abc
openai_server_model:
model_id: "qwen2"
base_url: "http://10.80.82.249:30000/v1"
base_url: "http://{your_ip_address}:30000/v1"
server_mode: sglang
nb_agent:
uuid: abc
Expand All @@ -30,7 +30,7 @@ traj_sampler:
file_path: null
log_path: "./log"
evaluator:
data_dir: "./eval_datasets/data"
save_dir: "./results/qwen2.5-7b-direct-0626"
data_dir: "hf"
save_dir: "./results/qwen2.5-7b-direct"
mode: "direct"
n_samples: 1
12 changes: 6 additions & 6 deletions evaluation/nb_agent_eval/config/sampler_config_scafford.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
traj_sampler:
model_id: Qwen/Qwen2.5-7B-Instruct
max_concurrency: 256
max_retries: 3
max_retries: 1
task_timeout: 600
agent_type: nb_agent
executor_type: remote
remote_exec_server_url:
- http://10.80.78.178:8000
- http://{your_ip_address}:8000
agent:
uuid: abc
openai_server_model:
model_id: "qwen2"
base_url: "http://10.80.82.249:29999/v1"
base_url: "http://{your_ip_address}:29999/v1"
server_mode: sglang
nb_agent:
uuid: abc
Expand All @@ -29,7 +29,7 @@ traj_sampler:
max_steps: 10
log_path: "./log"
evaluator:
data_dir: "./eval_datasets/data"
save_dir: "./results/qwen2.5-7b-scafford-0626"
data_dir: "hf"
save_dir: "./results/qwen2.5-7b-scafford"
mode: "nb_agent"
n_samples: 1
n_samples: 3
10 changes: 5 additions & 5 deletions evaluation/nb_agent_eval/config/sampler_config_train.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
traj_sampler:
model_id: Qwen/Qwen2.5-7B-Instruct
max_concurrency: 256
max_retries: 3
max_retries: 1
task_timeout: 600
agent_type: nb_agent
executor_type: remote
remote_exec_server_url:
- http://10.80.78.178:8000
- http://{your_ip_address}:8000
agent:
uuid: abc
openai_server_model:
model_id: "qwen2"
base_url: "http://10.80.78.150:7999/v1"
base_url: "http://{your_ip_address}:7999/v1"
server_mode: sglang
nb_agent:
uuid: abc
Expand All @@ -30,7 +30,7 @@ traj_sampler:
file_path: null
log_path: "./log"
evaluator:
data_dir: "./eval_datasets/data"
save_dir: "./results/qwen2.5-3b-dapo-0627-avg3"
data_dir: "hf"
save_dir: "./results/qwen2.5-7b-train"
mode: "nb_agent"
n_samples: 3
Loading