Cuzyoung
4a1b984d87
- Rename teacher -> optimizer, student -> target across all code, configs, docs, prompts - CLI: --teacher_model -> --optimizer_model, --student_model -> --target_model - Remove best_skill files, keep only initial skills - Fix slow update gate (force write into skill) - Fix SLOW_UPDATE marker stripping - Remove deep_reflect and meta_reflect mechanisms - Update .env.example with export prefix and azure_cli docs - Add endpoint empty validation in azure_openai.py Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
30 lines
486 B
YAML
30 lines
486 B
YAML
_base_: ../_base_/default.yaml
|
|
|
|
train:
|
|
train_size: 0
|
|
accumulation: 1
|
|
|
|
gradient:
|
|
minibatch_size: 8
|
|
merge_batch_size: 8
|
|
|
|
optimizer:
|
|
learning_rate: 4
|
|
|
|
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
|