refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update
- 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>
This commit is contained in:
Cuzyoung
+80
-80
@@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env python3
|
||||
"""ReflACT eval-only: run a single skill on a dataset without training.
|
||||
"""SkillOpt eval-only: run a single skill on a dataset without training.
|
||||
|
||||
Usage
|
||||
-----
|
||||
@@ -29,10 +29,10 @@ from skillopt.model import (
|
||||
configure_claude_code_exec,
|
||||
configure_codex_exec,
|
||||
set_reasoning_effort,
|
||||
set_student_backend,
|
||||
set_student_deployment,
|
||||
set_teacher_backend,
|
||||
set_teacher_deployment,
|
||||
set_target_backend,
|
||||
set_target_deployment,
|
||||
set_optimizer_backend,
|
||||
set_optimizer_deployment,
|
||||
)
|
||||
from skillopt.model.common import default_model_for_backend, normalize_backend_name
|
||||
|
||||
@@ -126,7 +126,7 @@ _BOOL = lambda x: str(x).lower() in ("true", "1", "yes") # noqa: E731
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
p = argparse.ArgumentParser(description="ReflACT eval-only")
|
||||
p = argparse.ArgumentParser(description="SkillOpt eval-only")
|
||||
p.add_argument("--config", type=str, required=True)
|
||||
p.add_argument("--skill", type=str, required=True,
|
||||
help="Path to skill .md file to evaluate")
|
||||
@@ -138,10 +138,10 @@ def parse_args() -> argparse.Namespace:
|
||||
p.add_argument("--env", type=str)
|
||||
p.add_argument("--backend", type=str,
|
||||
choices=["azure_openai", "codex", "codex_exec", "claude", "claude_chat", "claude_code_exec"])
|
||||
p.add_argument("--teacher_model", type=str)
|
||||
p.add_argument("--student_model", type=str)
|
||||
p.add_argument("--teacher_backend", type=str)
|
||||
p.add_argument("--student_backend", type=str)
|
||||
p.add_argument("--optimizer_model", type=str)
|
||||
p.add_argument("--target_model", type=str)
|
||||
p.add_argument("--optimizer_backend", type=str)
|
||||
p.add_argument("--target_backend", type=str)
|
||||
p.add_argument("--reasoning_effort", type=str,
|
||||
choices=["", "low", "medium", "high", "xhigh", "max"])
|
||||
p.add_argument("--azure_endpoint", type=str)
|
||||
@@ -153,18 +153,18 @@ def parse_args() -> argparse.Namespace:
|
||||
p.add_argument("--azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--teacher_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--teacher_azure_openai_api_version", type=str)
|
||||
p.add_argument("--teacher_azure_openai_api_key", type=str)
|
||||
p.add_argument("--teacher_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--teacher_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--teacher_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--student_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--student_azure_openai_api_version", type=str)
|
||||
p.add_argument("--student_azure_openai_api_key", type=str)
|
||||
p.add_argument("--student_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--student_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--student_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_api_version", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_api_key", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--target_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--target_azure_openai_api_version", type=str)
|
||||
p.add_argument("--target_azure_openai_api_key", type=str)
|
||||
p.add_argument("--target_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--target_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--target_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--codex_exec_path", type=str)
|
||||
p.add_argument("--codex_exec_sandbox", type=str)
|
||||
p.add_argument("--codex_exec_profile", type=str)
|
||||
@@ -214,10 +214,10 @@ def main() -> None:
|
||||
from skillopt.config import apply_overrides
|
||||
_MAP = {
|
||||
"backend": "model.backend",
|
||||
"teacher_model": "model.teacher",
|
||||
"student_model": "model.student",
|
||||
"teacher_backend": "model.teacher_backend",
|
||||
"student_backend": "model.student_backend",
|
||||
"optimizer_model": "model.optimizer",
|
||||
"target_model": "model.target",
|
||||
"optimizer_backend": "model.optimizer_backend",
|
||||
"target_backend": "model.target_backend",
|
||||
"reasoning_effort": "model.reasoning_effort",
|
||||
"azure_endpoint": "model.azure_endpoint",
|
||||
"azure_api_version": "model.azure_api_version",
|
||||
@@ -228,18 +228,18 @@ def main() -> None:
|
||||
"azure_openai_auth_mode": "model.azure_openai_auth_mode",
|
||||
"azure_openai_ad_scope": "model.azure_openai_ad_scope",
|
||||
"azure_openai_managed_identity_client_id": "model.azure_openai_managed_identity_client_id",
|
||||
"teacher_azure_openai_endpoint": "model.teacher_azure_openai_endpoint",
|
||||
"teacher_azure_openai_api_version": "model.teacher_azure_openai_api_version",
|
||||
"teacher_azure_openai_api_key": "model.teacher_azure_openai_api_key",
|
||||
"teacher_azure_openai_auth_mode": "model.teacher_azure_openai_auth_mode",
|
||||
"teacher_azure_openai_ad_scope": "model.teacher_azure_openai_ad_scope",
|
||||
"teacher_azure_openai_managed_identity_client_id": "model.teacher_azure_openai_managed_identity_client_id",
|
||||
"student_azure_openai_endpoint": "model.student_azure_openai_endpoint",
|
||||
"student_azure_openai_api_version": "model.student_azure_openai_api_version",
|
||||
"student_azure_openai_api_key": "model.student_azure_openai_api_key",
|
||||
"student_azure_openai_auth_mode": "model.student_azure_openai_auth_mode",
|
||||
"student_azure_openai_ad_scope": "model.student_azure_openai_ad_scope",
|
||||
"student_azure_openai_managed_identity_client_id": "model.student_azure_openai_managed_identity_client_id",
|
||||
"optimizer_azure_openai_endpoint": "model.optimizer_azure_openai_endpoint",
|
||||
"optimizer_azure_openai_api_version": "model.optimizer_azure_openai_api_version",
|
||||
"optimizer_azure_openai_api_key": "model.optimizer_azure_openai_api_key",
|
||||
"optimizer_azure_openai_auth_mode": "model.optimizer_azure_openai_auth_mode",
|
||||
"optimizer_azure_openai_ad_scope": "model.optimizer_azure_openai_ad_scope",
|
||||
"optimizer_azure_openai_managed_identity_client_id": "model.optimizer_azure_openai_managed_identity_client_id",
|
||||
"target_azure_openai_endpoint": "model.target_azure_openai_endpoint",
|
||||
"target_azure_openai_api_version": "model.target_azure_openai_api_version",
|
||||
"target_azure_openai_api_key": "model.target_azure_openai_api_key",
|
||||
"target_azure_openai_auth_mode": "model.target_azure_openai_auth_mode",
|
||||
"target_azure_openai_ad_scope": "model.target_azure_openai_ad_scope",
|
||||
"target_azure_openai_managed_identity_client_id": "model.target_azure_openai_managed_identity_client_id",
|
||||
"codex_exec_path": "model.codex_exec_path",
|
||||
"codex_exec_sandbox": "model.codex_exec_sandbox",
|
||||
"codex_exec_profile": "model.codex_exec_profile",
|
||||
@@ -288,7 +288,7 @@ def main() -> None:
|
||||
explicit_backend = str(option).split("=", 1)[1].strip()
|
||||
break
|
||||
|
||||
backend = normalize_backend_name(cfg.get("model_backend") or cfg.get("student_backend") or "azure_openai")
|
||||
backend = normalize_backend_name(cfg.get("model_backend") or cfg.get("target_backend") or "azure_openai")
|
||||
|
||||
def _has_model_override(dotted_key: str, legacy_key: str) -> bool:
|
||||
if getattr(args, legacy_key, None) is not None:
|
||||
@@ -303,43 +303,43 @@ def main() -> None:
|
||||
backend = normalize_backend_name(explicit_backend)
|
||||
cfg["model_backend"] = backend
|
||||
if backend in {"claude", "claude_chat"}:
|
||||
cfg.setdefault("teacher_backend", "claude_chat")
|
||||
cfg.setdefault("student_backend", "claude_chat")
|
||||
cfg.setdefault("optimizer_backend", "claude_chat")
|
||||
cfg.setdefault("target_backend", "claude_chat")
|
||||
elif backend in {"codex", "codex_exec"}:
|
||||
cfg.setdefault("teacher_backend", "openai_chat")
|
||||
cfg.setdefault("student_backend", "codex_exec")
|
||||
cfg.setdefault("optimizer_backend", "openai_chat")
|
||||
cfg.setdefault("target_backend", "codex_exec")
|
||||
elif backend == "claude_code_exec":
|
||||
cfg.setdefault("teacher_backend", "openai_chat")
|
||||
cfg.setdefault("student_backend", "claude_code_exec")
|
||||
cfg.setdefault("optimizer_backend", "openai_chat")
|
||||
cfg.setdefault("target_backend", "claude_code_exec")
|
||||
else:
|
||||
cfg.setdefault("teacher_backend", "openai_chat")
|
||||
cfg.setdefault("student_backend", "openai_chat")
|
||||
cfg.setdefault("optimizer_backend", "openai_chat")
|
||||
cfg.setdefault("target_backend", "openai_chat")
|
||||
else:
|
||||
cfg.setdefault("teacher_backend", "openai_chat")
|
||||
cfg.setdefault("student_backend", "openai_chat")
|
||||
cfg.setdefault("optimizer_backend", "openai_chat")
|
||||
cfg.setdefault("target_backend", "openai_chat")
|
||||
|
||||
if cfg.get("teacher_backend") == "claude_chat":
|
||||
if cfg.get("optimizer_backend") == "claude_chat":
|
||||
if (
|
||||
str(cfg.get("teacher_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.teacher", "teacher_model")
|
||||
str(cfg.get("optimizer_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.optimizer", "optimizer_model")
|
||||
):
|
||||
cfg["teacher_model"] = default_model_for_backend("claude_chat")
|
||||
if cfg.get("student_backend") == "claude_chat":
|
||||
cfg["optimizer_model"] = default_model_for_backend("claude_chat")
|
||||
if cfg.get("target_backend") == "claude_chat":
|
||||
if (
|
||||
str(cfg.get("student_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.student", "student_model")
|
||||
str(cfg.get("target_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.target", "target_model")
|
||||
):
|
||||
cfg["student_model"] = default_model_for_backend("claude_chat")
|
||||
if cfg.get("student_backend") == "claude_code_exec":
|
||||
cfg["target_model"] = default_model_for_backend("claude_chat")
|
||||
if cfg.get("target_backend") == "claude_code_exec":
|
||||
if (
|
||||
str(cfg.get("student_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.student", "student_model")
|
||||
str(cfg.get("target_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.target", "target_model")
|
||||
):
|
||||
cfg["student_model"] = default_model_for_backend("claude_chat")
|
||||
cfg["target_model"] = default_model_for_backend("claude_chat")
|
||||
|
||||
if not cfg.get("out_root"):
|
||||
env = cfg.get("env", "unknown")
|
||||
model = cfg.get("student_model", "unknown").replace("/", "-")
|
||||
model = cfg.get("target_model", "unknown").replace("/", "-")
|
||||
ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
cfg["out_root"] = os.path.join("outputs", f"eval_{env}_{model}_{ts}")
|
||||
|
||||
@@ -362,27 +362,27 @@ def main() -> None:
|
||||
auth_mode=cfg.get("azure_openai_auth_mode") or None,
|
||||
ad_scope=cfg.get("azure_openai_ad_scope") or None,
|
||||
managed_identity_client_id=cfg.get("azure_openai_managed_identity_client_id") or None,
|
||||
teacher_endpoint=cfg.get("teacher_azure_openai_endpoint") or None,
|
||||
teacher_api_version=cfg.get("teacher_azure_openai_api_version") or None,
|
||||
teacher_api_key=cfg.get("teacher_azure_openai_api_key") or None,
|
||||
teacher_auth_mode=cfg.get("teacher_azure_openai_auth_mode") or None,
|
||||
teacher_ad_scope=cfg.get("teacher_azure_openai_ad_scope") or None,
|
||||
teacher_managed_identity_client_id=(
|
||||
cfg.get("teacher_azure_openai_managed_identity_client_id") or None
|
||||
optimizer_endpoint=cfg.get("optimizer_azure_openai_endpoint") or None,
|
||||
optimizer_api_version=cfg.get("optimizer_azure_openai_api_version") or None,
|
||||
optimizer_api_key=cfg.get("optimizer_azure_openai_api_key") or None,
|
||||
optimizer_auth_mode=cfg.get("optimizer_azure_openai_auth_mode") or None,
|
||||
optimizer_ad_scope=cfg.get("optimizer_azure_openai_ad_scope") or None,
|
||||
optimizer_managed_identity_client_id=(
|
||||
cfg.get("optimizer_azure_openai_managed_identity_client_id") or None
|
||||
),
|
||||
student_endpoint=cfg.get("student_azure_openai_endpoint") or None,
|
||||
student_api_version=cfg.get("student_azure_openai_api_version") or None,
|
||||
student_api_key=cfg.get("student_azure_openai_api_key") or None,
|
||||
student_auth_mode=cfg.get("student_azure_openai_auth_mode") or None,
|
||||
student_ad_scope=cfg.get("student_azure_openai_ad_scope") or None,
|
||||
student_managed_identity_client_id=(
|
||||
cfg.get("student_azure_openai_managed_identity_client_id") or None
|
||||
target_endpoint=cfg.get("target_azure_openai_endpoint") or None,
|
||||
target_api_version=cfg.get("target_azure_openai_api_version") or None,
|
||||
target_api_key=cfg.get("target_azure_openai_api_key") or None,
|
||||
target_auth_mode=cfg.get("target_azure_openai_auth_mode") or None,
|
||||
target_ad_scope=cfg.get("target_azure_openai_ad_scope") or None,
|
||||
target_managed_identity_client_id=(
|
||||
cfg.get("target_azure_openai_managed_identity_client_id") or None
|
||||
),
|
||||
)
|
||||
set_teacher_backend(cfg.get("teacher_backend", "openai_chat"))
|
||||
set_student_backend(cfg.get("student_backend", "openai_chat"))
|
||||
set_teacher_deployment(cfg.get("teacher_model", default_model_for_backend(backend)))
|
||||
set_student_deployment(cfg.get("student_model", default_model_for_backend(backend)))
|
||||
set_optimizer_backend(cfg.get("optimizer_backend", "openai_chat"))
|
||||
set_target_backend(cfg.get("target_backend", "openai_chat"))
|
||||
set_optimizer_deployment(cfg.get("optimizer_model", default_model_for_backend(backend)))
|
||||
set_target_deployment(cfg.get("target_model", default_model_for_backend(backend)))
|
||||
configure_codex_exec(
|
||||
path=cfg.get("codex_exec_path", "codex"),
|
||||
sandbox=cfg.get("codex_exec_sandbox", "workspace-write"),
|
||||
|
||||
+18
-26
@@ -1,28 +1,26 @@
|
||||
#!/usr/bin/env bash
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
# ReflACT — ALFWorld training launch script
|
||||
# SkillOpt — ALFWorld training launch script
|
||||
#
|
||||
# Prerequisites:
|
||||
# pip install -e ".[alfworld]"
|
||||
# pip install alfworld[full] && alfworld-download
|
||||
#
|
||||
# Usage:
|
||||
# bash scripts/run_alfworld.sh
|
||||
# bash scripts/run_alfworld.sh --num_epochs 2 --edit_budget 6
|
||||
# bash scripts/run_alfworld.sh --split_dir /path/to/alfworld_split
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
set -euo pipefail
|
||||
|
||||
# ── Paths ────────────────────────────────────────────────────────────────────
|
||||
WORKSPACE="${WORKSPACE:-$(cd "$(dirname "$0")/../.." && pwd)}"
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
||||
PROJECT_ROOT="$(dirname "${SCRIPT_DIR}")"
|
||||
|
||||
# Activate conda environment
|
||||
export PATH="${WORKSPACE}/miniconda3/envs/skillopt/bin:${WORKSPACE}/miniconda3/bin:${PATH}"
|
||||
|
||||
# ALFWorld data — uses ~/.cache/alfworld by default (standard alfworld location)
|
||||
export ALFWORLD_DATA="${ALFWORLD_DATA:-${HOME}/.cache/alfworld}"
|
||||
|
||||
# Ensure ReflACT is importable
|
||||
export PYTHONPATH="${PROJECT_ROOT}:${PYTHONPATH:-}"
|
||||
|
||||
# ── Verify ALFWorld data exists ──────────────────────────────────────────────
|
||||
# ALFWorld data — uses ~/.cache/alfworld by default
|
||||
export ALFWORLD_DATA="${ALFWORLD_DATA:-${HOME}/.cache/alfworld}"
|
||||
|
||||
if [ ! -d "${ALFWORLD_DATA}/json_2.1.1" ]; then
|
||||
echo "ERROR: ALFWorld data not found at ${ALFWORLD_DATA}/json_2.1.1"
|
||||
echo ""
|
||||
@@ -34,25 +32,17 @@ if [ ! -d "${ALFWORLD_DATA}/json_2.1.1" ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# ── Azure OpenAI credentials ────────────────────────────────────────────────
|
||||
export AZURE_OPENAI_ENDPOINT="${AZURE_OPENAI_ENDPOINT:?Set AZURE_OPENAI_ENDPOINT}"
|
||||
export AZURE_OPENAI_API_KEY="${AZURE_OPENAI_API_KEY:?Set AZURE_OPENAI_API_KEY}"
|
||||
export AZURE_OPENAI_API_VERSION="${AZURE_OPENAI_API_VERSION:-2025-04-01-preview}"
|
||||
OPTIMIZER_MODEL="${OPTIMIZER_MODEL:-gpt-5.5}"
|
||||
TARGET_MODEL="${TARGET_MODEL:-gpt-5.5}"
|
||||
|
||||
# ── Model configuration ─────────────────────────────────────────────────────
|
||||
export TEACHER_DEPLOYMENT="${TEACHER_DEPLOYMENT:-gpt-5.5}"
|
||||
export STUDENT_DEPLOYMENT="${STUDENT_DEPLOYMENT:-gpt-5.5}"
|
||||
|
||||
# ── Output directory ─────────────────────────────────────────────────────────
|
||||
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
|
||||
DEFAULT_OUT_ROOT="${PROJECT_ROOT}/outputs/skillopt_alfworld_${STUDENT_DEPLOYMENT}_${TIMESTAMP}"
|
||||
DEFAULT_OUT_ROOT="${PROJECT_ROOT}/outputs/skillopt_alfworld_${TARGET_MODEL}_${TIMESTAMP}"
|
||||
|
||||
# ── Run ──────────────────────────────────────────────────────────────────────
|
||||
echo "============================================================"
|
||||
echo " ReflACT — Reflective Agent Tuning (ALFWorld)"
|
||||
echo " SkillOpt — ALFWorld Training"
|
||||
echo "============================================================"
|
||||
echo " Teacher: ${TEACHER_DEPLOYMENT}"
|
||||
echo " Student: ${STUDENT_DEPLOYMENT}"
|
||||
echo " Optimizer: ${OPTIMIZER_MODEL}"
|
||||
echo " Target: ${TARGET_MODEL}"
|
||||
echo " ALFWORLD_DATA: ${ALFWORLD_DATA}"
|
||||
echo " Output: ${DEFAULT_OUT_ROOT}"
|
||||
echo "============================================================"
|
||||
@@ -60,7 +50,9 @@ echo "============================================================"
|
||||
cd "${PROJECT_ROOT}"
|
||||
|
||||
python scripts/train.py \
|
||||
--config configs/alfworld_default.yaml \
|
||||
--config configs/alfworld/default.yaml \
|
||||
--optimizer_model "${OPTIMIZER_MODEL}" \
|
||||
--target_model "${TARGET_MODEL}" \
|
||||
--out_root "${DEFAULT_OUT_ROOT}" \
|
||||
"$@"
|
||||
|
||||
|
||||
+11
-14
@@ -1,41 +1,38 @@
|
||||
#!/usr/bin/env bash
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
# ReflACT — SearchQA training launch script
|
||||
# SkillOpt — SearchQA training launch script
|
||||
#
|
||||
# Usage:
|
||||
# bash scripts/run_searchqa.sh
|
||||
# bash scripts/run_searchqa.sh --data_path data/searchqa_train_2000.json
|
||||
# bash scripts/run_searchqa.sh --num_epochs 2 --edit_budget 6
|
||||
# bash scripts/run_searchqa.sh --split_dir /path/to/searchqa_split
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
set -euo pipefail
|
||||
|
||||
# ── Paths ────────────────────────────────────────────────────────────────────
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
||||
PROJECT_ROOT="$(dirname "${SCRIPT_DIR}")"
|
||||
|
||||
# Ensure ReflACT is importable
|
||||
export PYTHONPATH="${PROJECT_ROOT}:${PYTHONPATH:-}"
|
||||
|
||||
# ── Model configuration ─────────────────────────────────────────────────────
|
||||
export TEACHER_DEPLOYMENT="${TEACHER_DEPLOYMENT:-gpt-5.5}"
|
||||
export STUDENT_DEPLOYMENT="${STUDENT_DEPLOYMENT:-gpt-5.5}"
|
||||
OPTIMIZER_MODEL="${OPTIMIZER_MODEL:-gpt-5.5}"
|
||||
TARGET_MODEL="${TARGET_MODEL:-gpt-5.5}"
|
||||
|
||||
# ── Output directory ─────────────────────────────────────────────────────────
|
||||
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
|
||||
DEFAULT_OUT_ROOT="${PROJECT_ROOT}/outputs/skillopt_searchqa_${STUDENT_DEPLOYMENT}_${TIMESTAMP}"
|
||||
DEFAULT_OUT_ROOT="${PROJECT_ROOT}/outputs/skillopt_searchqa_${TARGET_MODEL}_${TIMESTAMP}"
|
||||
|
||||
# ── Run ──────────────────────────────────────────────────────────────────────
|
||||
echo "============================================================"
|
||||
echo " ReflACT — Reflective Agent Tuning (SearchQA)"
|
||||
echo " SkillOpt — SearchQA Training"
|
||||
echo "============================================================"
|
||||
echo " Teacher: ${TEACHER_DEPLOYMENT}"
|
||||
echo " Student: ${STUDENT_DEPLOYMENT}"
|
||||
echo " Optimizer: ${OPTIMIZER_MODEL}"
|
||||
echo " Target: ${TARGET_MODEL}"
|
||||
echo "============================================================"
|
||||
|
||||
cd "${PROJECT_ROOT}"
|
||||
|
||||
python scripts/train.py \
|
||||
--config configs/searchqa_default.yaml \
|
||||
--config configs/searchqa/default.yaml \
|
||||
--optimizer_model "${OPTIMIZER_MODEL}" \
|
||||
--target_model "${TARGET_MODEL}" \
|
||||
--out_root "${DEFAULT_OUT_ROOT}" \
|
||||
"$@"
|
||||
|
||||
|
||||
@@ -1,46 +1,37 @@
|
||||
#!/usr/bin/env bash
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
# ReflACT — SpreadsheetBench training launch script
|
||||
# SkillOpt — SpreadsheetBench training launch script
|
||||
#
|
||||
# Usage:
|
||||
# bash scripts/run_spreadsheetbench.sh \
|
||||
# --data_root /path/to/data \
|
||||
# --jsonl_path /path/to/benchmark.jsonl
|
||||
#
|
||||
# bash scripts/run_spreadsheetbench.sh \
|
||||
# --data_root /path/to/data \
|
||||
# --jsonl_path /path/to/benchmark.jsonl \
|
||||
# --num_epochs 2 --edit_budget 6
|
||||
# bash scripts/run_spreadsheetbench.sh --split_dir /path/to/split --data_root /path/to/data
|
||||
# bash scripts/run_spreadsheetbench.sh --num_epochs 2 --edit_budget 6
|
||||
# ──────────────────────────────────────────────────────────────────────────────
|
||||
set -euo pipefail
|
||||
|
||||
# ── Paths ────────────────────────────────────────────────────────────────────
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
||||
PROJECT_ROOT="$(dirname "${SCRIPT_DIR}")"
|
||||
|
||||
# Ensure ReflACT is importable
|
||||
export PYTHONPATH="${PROJECT_ROOT}:${PYTHONPATH:-}"
|
||||
|
||||
# ── Model configuration ─────────────────────────────────────────────────────
|
||||
export TEACHER_DEPLOYMENT="${TEACHER_DEPLOYMENT:-gpt-5.5}"
|
||||
export STUDENT_DEPLOYMENT="${STUDENT_DEPLOYMENT:-gpt-5.5}"
|
||||
OPTIMIZER_MODEL="${OPTIMIZER_MODEL:-gpt-5.5}"
|
||||
TARGET_MODEL="${TARGET_MODEL:-gpt-5.5}"
|
||||
|
||||
# ── Output directory ─────────────────────────────────────────────────────────
|
||||
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
|
||||
DEFAULT_OUT_ROOT="${PROJECT_ROOT}/outputs/skillopt_spreadsheetbench_${STUDENT_DEPLOYMENT}_${TIMESTAMP}"
|
||||
DEFAULT_OUT_ROOT="${PROJECT_ROOT}/outputs/skillopt_spreadsheetbench_${TARGET_MODEL}_${TIMESTAMP}"
|
||||
|
||||
# ── Run ──────────────────────────────────────────────────────────────────────
|
||||
echo "============================================================"
|
||||
echo " ReflACT — Reflective Agent Tuning (SpreadsheetBench)"
|
||||
echo " SkillOpt — SpreadsheetBench Training"
|
||||
echo "============================================================"
|
||||
echo " Teacher: ${TEACHER_DEPLOYMENT}"
|
||||
echo " Student: ${STUDENT_DEPLOYMENT}"
|
||||
echo " Optimizer: ${OPTIMIZER_MODEL}"
|
||||
echo " Target: ${TARGET_MODEL}"
|
||||
echo "============================================================"
|
||||
|
||||
cd "${PROJECT_ROOT}"
|
||||
|
||||
python scripts/train.py \
|
||||
--config configs/spreadsheetbench_default.yaml \
|
||||
--config configs/spreadsheetbench/default.yaml \
|
||||
--optimizer_model "${OPTIMIZER_MODEL}" \
|
||||
--target_model "${TARGET_MODEL}" \
|
||||
--out_root "${DEFAULT_OUT_ROOT}" \
|
||||
"$@"
|
||||
|
||||
|
||||
+72
-82
@@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env python3
|
||||
"""ReflACT unified training entry point.
|
||||
"""SkillOpt unified training entry point.
|
||||
|
||||
Usage
|
||||
-----
|
||||
@@ -125,7 +125,7 @@ _BOOL = lambda x: x.lower() in ("true", "1", "yes") # noqa: E731
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
p = argparse.ArgumentParser(
|
||||
description="ReflACT: Reflective Agent Tuning",
|
||||
description="SkillOpt: Executive Strategy for Self-Evolving Agent Skills",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog=__doc__,
|
||||
)
|
||||
@@ -138,10 +138,10 @@ def parse_args() -> argparse.Namespace:
|
||||
p.add_argument("--env", type=str)
|
||||
p.add_argument("--backend", type=str,
|
||||
choices=["azure_openai", "codex", "codex_exec", "claude", "claude_chat", "claude_code_exec", "qwen", "qwen_chat"])
|
||||
p.add_argument("--teacher_model", type=str)
|
||||
p.add_argument("--student_model", type=str)
|
||||
p.add_argument("--teacher_backend", type=str)
|
||||
p.add_argument("--student_backend", type=str)
|
||||
p.add_argument("--optimizer_model", type=str)
|
||||
p.add_argument("--target_model", type=str)
|
||||
p.add_argument("--optimizer_backend", type=str)
|
||||
p.add_argument("--target_backend", type=str)
|
||||
p.add_argument("--reasoning_effort", type=str,
|
||||
choices=["", "low", "medium", "high", "xhigh", "max"])
|
||||
p.add_argument("--rewrite_reasoning_effort", type=str)
|
||||
@@ -155,18 +155,18 @@ def parse_args() -> argparse.Namespace:
|
||||
p.add_argument("--azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--teacher_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--teacher_azure_openai_api_version", type=str)
|
||||
p.add_argument("--teacher_azure_openai_api_key", type=str)
|
||||
p.add_argument("--teacher_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--teacher_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--teacher_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--student_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--student_azure_openai_api_version", type=str)
|
||||
p.add_argument("--student_azure_openai_api_key", type=str)
|
||||
p.add_argument("--student_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--student_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--student_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_api_version", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_api_key", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--optimizer_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--target_azure_openai_endpoint", type=str)
|
||||
p.add_argument("--target_azure_openai_api_version", type=str)
|
||||
p.add_argument("--target_azure_openai_api_key", type=str)
|
||||
p.add_argument("--target_azure_openai_auth_mode", type=str)
|
||||
p.add_argument("--target_azure_openai_ad_scope", type=str)
|
||||
p.add_argument("--target_azure_openai_managed_identity_client_id", type=str)
|
||||
p.add_argument("--qwen_chat_base_url", type=str)
|
||||
p.add_argument("--qwen_chat_api_key", type=str)
|
||||
p.add_argument("--qwen_chat_temperature", type=float)
|
||||
@@ -187,7 +187,7 @@ def parse_args() -> argparse.Namespace:
|
||||
p.add_argument("--claude_code_exec_use_sdk", type=str)
|
||||
p.add_argument("--claude_code_exec_effort", type=str)
|
||||
p.add_argument("--claude_code_exec_max_thinking_tokens", type=int)
|
||||
p.add_argument("--codex_trace_to_teacher", type=_BOOL)
|
||||
p.add_argument("--codex_trace_to_optimizer", type=_BOOL)
|
||||
p.add_argument("--skill_init", type=str)
|
||||
p.add_argument("--num_epochs", type=int)
|
||||
p.add_argument("--train_size", type=int)
|
||||
@@ -212,8 +212,6 @@ def parse_args() -> argparse.Namespace:
|
||||
p.add_argument("--analyst_workers", type=int)
|
||||
p.add_argument("--failure_only", type=_BOOL)
|
||||
p.add_argument("--minibatch_size", type=int)
|
||||
p.add_argument("--use_meta_reflect", type=_BOOL)
|
||||
p.add_argument("--meta_edit_budget", type=int)
|
||||
p.add_argument("--skill_update_mode", type=str,
|
||||
choices=[
|
||||
"patch",
|
||||
@@ -224,9 +222,6 @@ def parse_args() -> argparse.Namespace:
|
||||
"full_rewrite_minibatch",
|
||||
"minibatch_full_rewrite",
|
||||
])
|
||||
p.add_argument("--use_deep_reflect", type=_BOOL)
|
||||
p.add_argument("--deep_reflect_failures", type=int)
|
||||
p.add_argument("--deep_reflect_successes", type=int)
|
||||
p.add_argument("--use_slow_update", type=_BOOL)
|
||||
p.add_argument("--slow_update_samples", type=int)
|
||||
p.add_argument("--longitudinal_pair_policy", type=str,
|
||||
@@ -260,10 +255,10 @@ def parse_args() -> argparse.Namespace:
|
||||
|
||||
_LEGACY_TO_STRUCTURED: dict[str, str] = {
|
||||
"backend": "model.backend",
|
||||
"teacher_model": "model.teacher",
|
||||
"student_model": "model.student",
|
||||
"teacher_backend": "model.teacher_backend",
|
||||
"student_backend": "model.student_backend",
|
||||
"optimizer_model": "model.optimizer",
|
||||
"target_model": "model.target",
|
||||
"optimizer_backend": "model.optimizer_backend",
|
||||
"target_backend": "model.target_backend",
|
||||
"reasoning_effort": "model.reasoning_effort",
|
||||
"rewrite_reasoning_effort": "model.rewrite_reasoning_effort",
|
||||
"rewrite_max_completion_tokens": "model.rewrite_max_completion_tokens",
|
||||
@@ -276,18 +271,18 @@ _LEGACY_TO_STRUCTURED: dict[str, str] = {
|
||||
"azure_openai_auth_mode": "model.azure_openai_auth_mode",
|
||||
"azure_openai_ad_scope": "model.azure_openai_ad_scope",
|
||||
"azure_openai_managed_identity_client_id": "model.azure_openai_managed_identity_client_id",
|
||||
"teacher_azure_openai_endpoint": "model.teacher_azure_openai_endpoint",
|
||||
"teacher_azure_openai_api_version": "model.teacher_azure_openai_api_version",
|
||||
"teacher_azure_openai_api_key": "model.teacher_azure_openai_api_key",
|
||||
"teacher_azure_openai_auth_mode": "model.teacher_azure_openai_auth_mode",
|
||||
"teacher_azure_openai_ad_scope": "model.teacher_azure_openai_ad_scope",
|
||||
"teacher_azure_openai_managed_identity_client_id": "model.teacher_azure_openai_managed_identity_client_id",
|
||||
"student_azure_openai_endpoint": "model.student_azure_openai_endpoint",
|
||||
"student_azure_openai_api_version": "model.student_azure_openai_api_version",
|
||||
"student_azure_openai_api_key": "model.student_azure_openai_api_key",
|
||||
"student_azure_openai_auth_mode": "model.student_azure_openai_auth_mode",
|
||||
"student_azure_openai_ad_scope": "model.student_azure_openai_ad_scope",
|
||||
"student_azure_openai_managed_identity_client_id": "model.student_azure_openai_managed_identity_client_id",
|
||||
"optimizer_azure_openai_endpoint": "model.optimizer_azure_openai_endpoint",
|
||||
"optimizer_azure_openai_api_version": "model.optimizer_azure_openai_api_version",
|
||||
"optimizer_azure_openai_api_key": "model.optimizer_azure_openai_api_key",
|
||||
"optimizer_azure_openai_auth_mode": "model.optimizer_azure_openai_auth_mode",
|
||||
"optimizer_azure_openai_ad_scope": "model.optimizer_azure_openai_ad_scope",
|
||||
"optimizer_azure_openai_managed_identity_client_id": "model.optimizer_azure_openai_managed_identity_client_id",
|
||||
"target_azure_openai_endpoint": "model.target_azure_openai_endpoint",
|
||||
"target_azure_openai_api_version": "model.target_azure_openai_api_version",
|
||||
"target_azure_openai_api_key": "model.target_azure_openai_api_key",
|
||||
"target_azure_openai_auth_mode": "model.target_azure_openai_auth_mode",
|
||||
"target_azure_openai_ad_scope": "model.target_azure_openai_ad_scope",
|
||||
"target_azure_openai_managed_identity_client_id": "model.target_azure_openai_managed_identity_client_id",
|
||||
"qwen_chat_base_url": "model.qwen_chat_base_url",
|
||||
"qwen_chat_api_key": "model.qwen_chat_api_key",
|
||||
"qwen_chat_temperature": "model.qwen_chat_temperature",
|
||||
@@ -308,7 +303,7 @@ _LEGACY_TO_STRUCTURED: dict[str, str] = {
|
||||
"claude_code_exec_use_sdk": "model.claude_code_exec_use_sdk",
|
||||
"claude_code_exec_effort": "model.claude_code_exec_effort",
|
||||
"claude_code_exec_max_thinking_tokens": "model.claude_code_exec_max_thinking_tokens",
|
||||
"codex_trace_to_teacher": "model.codex_trace_to_teacher",
|
||||
"codex_trace_to_optimizer": "model.codex_trace_to_optimizer",
|
||||
"num_epochs": "train.num_epochs",
|
||||
"train_size": "train.train_size",
|
||||
"steps_per_epoch": "train.steps_per_epoch",
|
||||
@@ -320,16 +315,11 @@ _LEGACY_TO_STRUCTURED: dict[str, str] = {
|
||||
"analyst_workers": "gradient.analyst_workers",
|
||||
"max_analyst_rounds": "gradient.max_analyst_rounds",
|
||||
"failure_only": "gradient.failure_only",
|
||||
"use_deep_reflect": "gradient.use_deep_reflect",
|
||||
"deep_reflect_failures": "gradient.deep_reflect_failures",
|
||||
"deep_reflect_successes": "gradient.deep_reflect_successes",
|
||||
"edit_budget": "optimizer.learning_rate",
|
||||
"min_edit_budget": "optimizer.min_learning_rate",
|
||||
"lr_scheduler": "optimizer.lr_scheduler",
|
||||
"lr_control_mode": "optimizer.lr_control_mode",
|
||||
"skill_update_mode": "optimizer.skill_update_mode",
|
||||
"use_meta_reflect": "optimizer.use_meta_reflect",
|
||||
"meta_edit_budget": "optimizer.meta_learning_rate",
|
||||
"use_slow_update": "optimizer.use_slow_update",
|
||||
"slow_update_samples": "optimizer.slow_update_samples",
|
||||
"longitudinal_pair_policy": "optimizer.longitudinal_pair_policy",
|
||||
@@ -387,7 +377,7 @@ def load_config(args: argparse.Namespace) -> dict:
|
||||
explicit_backend = str(option).split("=", 1)[1].strip()
|
||||
break
|
||||
|
||||
backend = normalize_backend_name(flat.get("model_backend") or flat.get("student_backend") or "azure_openai")
|
||||
backend = normalize_backend_name(flat.get("model_backend") or flat.get("target_backend") or "azure_openai")
|
||||
|
||||
def _has_model_override(dotted_key: str, legacy_key: str) -> bool:
|
||||
if getattr(args, legacy_key, None) is not None:
|
||||
@@ -402,53 +392,53 @@ def load_config(args: argparse.Namespace) -> dict:
|
||||
backend = normalize_backend_name(explicit_backend)
|
||||
flat["model_backend"] = backend
|
||||
if backend in {"claude", "claude_chat"}:
|
||||
flat.setdefault("teacher_backend", "claude_chat")
|
||||
flat.setdefault("student_backend", "claude_chat")
|
||||
flat.setdefault("optimizer_backend", "claude_chat")
|
||||
flat.setdefault("target_backend", "claude_chat")
|
||||
elif backend in {"codex", "codex_exec"}:
|
||||
flat.setdefault("teacher_backend", "openai_chat")
|
||||
flat.setdefault("student_backend", "codex_exec")
|
||||
flat.setdefault("optimizer_backend", "openai_chat")
|
||||
flat.setdefault("target_backend", "codex_exec")
|
||||
elif backend == "claude_code_exec":
|
||||
flat.setdefault("teacher_backend", "openai_chat")
|
||||
flat.setdefault("student_backend", "claude_code_exec")
|
||||
flat.setdefault("optimizer_backend", "openai_chat")
|
||||
flat.setdefault("target_backend", "claude_code_exec")
|
||||
elif backend in {"qwen", "qwen_chat"}:
|
||||
flat.setdefault("teacher_backend", "openai_chat")
|
||||
flat.setdefault("student_backend", "qwen_chat")
|
||||
flat.setdefault("optimizer_backend", "openai_chat")
|
||||
flat.setdefault("target_backend", "qwen_chat")
|
||||
else:
|
||||
flat.setdefault("teacher_backend", "openai_chat")
|
||||
flat.setdefault("student_backend", "openai_chat")
|
||||
flat.setdefault("optimizer_backend", "openai_chat")
|
||||
flat.setdefault("target_backend", "openai_chat")
|
||||
else:
|
||||
flat.setdefault("teacher_backend", "openai_chat")
|
||||
flat.setdefault("student_backend", "openai_chat")
|
||||
flat.setdefault("optimizer_backend", "openai_chat")
|
||||
flat.setdefault("target_backend", "openai_chat")
|
||||
|
||||
if flat.get("teacher_backend") == "claude_chat":
|
||||
if flat.get("optimizer_backend") == "claude_chat":
|
||||
if (
|
||||
str(flat.get("teacher_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.teacher", "teacher_model")
|
||||
str(flat.get("optimizer_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.optimizer", "optimizer_model")
|
||||
):
|
||||
flat["teacher_model"] = default_model_for_backend("claude_chat")
|
||||
if flat.get("student_backend") == "claude_chat":
|
||||
flat["optimizer_model"] = default_model_for_backend("claude_chat")
|
||||
if flat.get("target_backend") == "claude_chat":
|
||||
if (
|
||||
str(flat.get("student_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.student", "student_model")
|
||||
str(flat.get("target_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.target", "target_model")
|
||||
):
|
||||
flat["student_model"] = default_model_for_backend("claude_chat")
|
||||
if flat.get("student_backend") == "claude_code_exec":
|
||||
flat["target_model"] = default_model_for_backend("claude_chat")
|
||||
if flat.get("target_backend") == "claude_code_exec":
|
||||
if (
|
||||
str(flat.get("student_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.student", "student_model")
|
||||
str(flat.get("target_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.target", "target_model")
|
||||
):
|
||||
flat["student_model"] = default_model_for_backend("claude_chat")
|
||||
if flat.get("student_backend") == "qwen_chat":
|
||||
flat["target_model"] = default_model_for_backend("claude_chat")
|
||||
if flat.get("target_backend") == "qwen_chat":
|
||||
if (
|
||||
str(flat.get("student_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.student", "student_model")
|
||||
str(flat.get("target_model", "") or "").strip() in _OPENAI_DEFAULT_MODEL_SENTINELS
|
||||
and not _has_model_override("model.target", "target_model")
|
||||
):
|
||||
flat["student_model"] = default_model_for_backend("qwen_chat")
|
||||
flat["target_model"] = default_model_for_backend("qwen_chat")
|
||||
|
||||
# Auto-generate output root
|
||||
if not flat.get("out_root"):
|
||||
env = flat.get("env", "unknown")
|
||||
model = flat.get("teacher_model", "unknown").replace("/", "-")
|
||||
model = flat.get("optimizer_model", "unknown").replace("/", "-")
|
||||
ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
flat["out_root"] = os.path.join("outputs", f"skillopt_{env}_{model}_{ts}")
|
||||
|
||||
@@ -463,13 +453,13 @@ def main() -> None:
|
||||
cfg = load_config(args)
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f" ReflACT — Reflective Agent Tuning")
|
||||
print(f" SkillOpt — Executive Strategy for Self-Evolving Agent Skills")
|
||||
print(f"{'='*60}")
|
||||
print(f" env: {cfg.get('env')}")
|
||||
print(f" teacher_model: {cfg.get('teacher_model')}")
|
||||
print(f" student_model: {cfg.get('student_model')}")
|
||||
print(f" teacher_backend:{cfg.get('teacher_backend', 'openai_chat')}")
|
||||
print(f" student_backend:{cfg.get('student_backend', 'openai_chat')}")
|
||||
print(f" optimizer_model: {cfg.get('optimizer_model')}")
|
||||
print(f" target_model: {cfg.get('target_model')}")
|
||||
print(f" optimizer_backend:{cfg.get('optimizer_backend', 'openai_chat')}")
|
||||
print(f" target_backend:{cfg.get('target_backend', 'openai_chat')}")
|
||||
print(f" reasoning: {cfg.get('reasoning_effort') or 'off'}")
|
||||
print(f" rewrite_effort: {cfg.get('rewrite_reasoning_effort') or 'off'}")
|
||||
print(f" epochs: {cfg.get('num_epochs')}")
|
||||
@@ -482,8 +472,8 @@ def main() -> None:
|
||||
print(f" min_edit_budget:{cfg.get('min_edit_budget', 2)}")
|
||||
print(f" minibatch_size: {cfg.get('minibatch_size')}")
|
||||
print(f" seed: {cfg.get('seed')}")
|
||||
print(f" meta_reflect: {cfg.get('use_meta_reflect', False)}")
|
||||
print(f" meta_skill: {cfg.get('use_meta_skill', False)}")
|
||||
print(f" slow_update: {cfg.get('use_slow_update', False)}")
|
||||
print(f" out_root: {cfg.get('out_root')}")
|
||||
print(f"{'='*60}\n")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user