wehub-resource-sync
56 lines
2.9 KiB
YAML
56 lines
2.9 KiB
YAML
# ──────────────────────────────────────────────────
|
|
# SkillOpt Config Template — <Your Benchmark Name>
|
|
# ──────────────────────────────────────────────────
|
|
# Copy this file to configs/<your_benchmark>/default.yaml
|
|
# and customize the values below.
|
|
|
|
# Inherit global defaults.
|
|
# NOTE: `_base_` is a string path, not a list.
|
|
_base_: ../_base_/default.yaml
|
|
|
|
# ── Environment ──────────────────────────────────
|
|
env:
|
|
name: your_benchmark # Must match the key registered in scripts/train.py
|
|
# Optional: a seed skill document. Create this file yourself before the
|
|
# first run, or omit the key to start from an empty skill.
|
|
# skill_init: skillopt/envs/your_benchmark/skills/initial.md
|
|
data_path: data/your_benchmark # Path to your data (for split_mode: ratio)
|
|
split_dir: "" # Set this and use split_mode: split_dir for pre-split data
|
|
split_mode: ratio # "ratio" or "split_dir"
|
|
split_ratio: "2:1:7" # train:val:test (used when split_mode: ratio)
|
|
workers: 4 # Parallel rollout workers
|
|
max_completion_tokens: 4096 # Cap per target-model call
|
|
limit: 0 # 0 = no limit; small int = debug sample
|
|
|
|
# ── Training ─────────────────────────────────────
|
|
train:
|
|
num_epochs: 4
|
|
batch_size: 40
|
|
accumulation: 1
|
|
seed: 42
|
|
|
|
# ── Gradient (Reflection) ───────────────────────
|
|
gradient:
|
|
analyst_workers: 16 # Parallel reflection workers
|
|
minibatch_size: 8
|
|
merge_batch_size: 8
|
|
|
|
# ── Optimizer ────────────────────────────────────
|
|
optimizer:
|
|
learning_rate: 4 # Max edits per step (edit budget)
|
|
lr_scheduler: cosine # cosine | linear | constant | autonomous
|
|
use_slow_update: true # Epoch-boundary momentum
|
|
use_meta_skill: true # Cross-epoch optimizer memory
|
|
|
|
# ── Evaluation ───────────────────────────────────
|
|
evaluation:
|
|
use_gate: true # Validation gating
|
|
eval_test: true # Run test eval after training
|
|
|
|
# ── Model ────────────────────────────────────────
|
|
# Override only what differs from the inherited defaults.
|
|
model:
|
|
optimizer_backend: openai_chat # openai_chat | claude_chat | qwen_chat | minimax_chat
|
|
target_backend: openai_chat # … plus codex_exec / claude_code_exec for target only
|
|
reasoning_effort: medium
|