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
31 lines
512 B
YAML
31 lines
512 B
YAML
_base_: ../_base_/default.yaml
|
|
|
|
train:
|
|
train_size: 0
|
|
accumulation: 1
|
|
|
|
gradient:
|
|
minibatch_size: 8
|
|
merge_batch_size: 8
|
|
|
|
optimizer:
|
|
learning_rate: 4
|
|
use_meta_reflect: false
|
|
|
|
evaluation:
|
|
sel_env_num: 0
|
|
test_env_num: 0
|
|
|
|
env:
|
|
name: alfworld
|
|
skill_init: skillopt/envs/alfworld/skills/initial.md
|
|
split_mode: split_dir
|
|
split_ratio: "2:1:7"
|
|
split_dir: data/ablation_splits/alfworld/2-1-7_seed42
|
|
data_path: ""
|
|
split_output_dir: ""
|
|
max_steps: 50
|
|
workers: 8
|
|
max_api_workers: 8
|
|
limit: 0
|