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>
46 lines
2.3 KiB
YAML
46 lines
2.3 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
|
|
_base_: ['../_base_/default.yaml']
|
|
|
|
# ── Environment ──────────────────────────────────
|
|
env:
|
|
name: your_benchmark # Must match registry key
|
|
data_path: data/your_benchmark # Path to your data
|
|
split_mode: ratio # "ratio" or "split_dir"
|
|
split_ratio: "2:1:7" # train:val:test
|
|
exec_timeout: 120 # Per-task timeout (seconds)
|
|
|
|
# ── Training ─────────────────────────────────────
|
|
train:
|
|
num_epochs: 4 # Number of epochs
|
|
batch_size: 40 # Tasks per step (batch size)
|
|
seed: 42
|
|
|
|
# ── Gradient (Reflection) ───────────────────────
|
|
gradient:
|
|
analyst_workers: 16 # Parallel reflection workers
|
|
minibatch_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 ────────────────────────────────────────
|
|
model:
|
|
backend: azure_openai # azure_openai | openai_chat | claude_code_exec | qwen
|
|
optimizer: gpt-4o
|
|
target: gpt-4o
|