CharlesYang030
244e346b83
- Skill optimization framework with training loop analogy - 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen) - WebUI for browser-based training control - Pluggable architecture for extending benchmarks and backends
37 lines
560 B
YAML
37 lines
560 B
YAML
_base_: ../_base_/default.yaml
|
|
|
|
model:
|
|
reasoning_effort: medium
|
|
|
|
train:
|
|
batch_size: 20
|
|
accumulation: 1
|
|
|
|
gradient:
|
|
minibatch_size: 4
|
|
merge_batch_size: 8
|
|
|
|
optimizer:
|
|
learning_rate: 4
|
|
|
|
evaluation:
|
|
sel_env_num: 0
|
|
test_env_num: 0
|
|
|
|
env:
|
|
name: swebench
|
|
skill_init: skillopt/envs/swebench/skills/initial.md
|
|
split_mode: ratio
|
|
split_ratio: "2:1:7"
|
|
split_dir: ""
|
|
data_path: ""
|
|
split_output_dir: ""
|
|
dataset_name: lite
|
|
hf_split: test
|
|
workers: 8
|
|
eval_workers: 8
|
|
step_limit: 50
|
|
cost_limit: 3.0
|
|
timeout_per_instance: 600
|
|
limit: 0
|