wangsenhao
b48032e15c
- Auto-inject human-review gate when agent asks question but forgets gate entry - Add complex_dev/complex_base field docs to program.md metric_diff table - Fix submit_sft.sh minor issues - jupyter_runtime improvements Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
66 lines
2.3 KiB
Bash
Executable File
66 lines
2.3 KiB
Bash
Executable File
#!/bin/bash
|
||
# 用 cml custom_train submit 提交 SFT 训练（**只做这一件事**）。
|
||
# 训练完成后请用 scripts/submit_cml_eval.sh 单独起评测，watcher 由 agent 自己挂。
|
||
#
|
||
# 用法：
|
||
# ./submit_sft.sh <SFT_RUNDIC> [PREV_RUNDIC]
|
||
#
|
||
# 推荐调用方式（runDic 由 resolve_run_ids.sh 决定，不要手敲）：
|
||
# eval "$(./scripts/resolve_run_ids.sh)"
|
||
# ./scripts/submit_sft.sh "$SFT_RUNDIC"
|
||
#
|
||
# 语义（与 program.md §746 + §5.2 对齐）：
|
||
# SFT_RUNDIC = R{n-1}.runDic（augment / yaml / 归档全用这个，不 +1）
|
||
# PREV_RUNDIC = SFT_RUNDIC - 1（默认；只用作上一轮 sft_output 改名）
|
||
|
||
set -euo pipefail
|
||
|
||
SFT_RUNDIC=${1:?usage: $0 <SFT_RUNDIC> [PREV_RUNDIC]}
|
||
PREV_RUNDIC=${2:-$((SFT_RUNDIC-1))}
|
||
|
||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
# chat-isolated 时代 AUTORESEARCH_ROOT == AUTORESEARCH_CHAT_ROOT；优先用 chat
|
||
# root，避免 agent 没 export AUTORESEARCH_ROOT 时回退到全局共享路径（已废弃）。
|
||
ROOT=${AUTORESEARCH_ROOT:-${AUTORESEARCH_CHAT_ROOT:-$(dirname "$SCRIPT_DIR")}}
|
||
TPL=${SFT_TRAIN_JOB_TEMPLATE:-$SCRIPT_DIR/sft_train_job.yaml.tpl}
|
||
YAML=/tmp/sft_train_job_r${SFT_RUNDIC}.yaml
|
||
|
||
if [ -f ~/.cloudml-cli/.profile ]; then
|
||
source ~/.cloudml-cli/.profile
|
||
else
|
||
echo "[sft] ❌ 未找到 ~/.cloudml-cli/.profile，请先安装并初始化 cml" >&2
|
||
exit 1
|
||
fi
|
||
|
||
# 1. 渲染 yaml 模板
|
||
sed \
|
||
-e "s|{RUNDIC}|${SFT_RUNDIC}|g" \
|
||
-e "s|{PREV_RUNDIC}|${PREV_RUNDIC}|g" \
|
||
-e "s|{AUTORESEARCH_ROOT}|${ROOT}|g" \
|
||
"$TPL" > "$YAML"
|
||
echo "[sft] yaml: $YAML (SFT_RUNDIC=$SFT_RUNDIC PREV_RUNDIC=$PREV_RUNDIC)"
|
||
|
||
# 2. 提交训练任务
|
||
SUBMIT_OUT=$(cml custom_train submit --filename "$YAML" 2>&1)
|
||
echo "$SUBMIT_OUT"
|
||
JOB_ID=$(echo "$SUBMIT_OUT" | grep -oE 't-[0-9]+-[a-z0-9]+' | head -1)
|
||
if [ -z "$JOB_ID" ]; then
|
||
echo "[sft] ❌ 提交失败" >&2
|
||
exit 1
|
||
fi
|
||
echo "[sft] ✅ JobID: $JOB_ID"
|
||
|
||
cat <<EOF
|
||
|
||
[sft] 任务提交完成，关键命令：
|
||
查看任务状态: cml custom_train describe $JOB_ID
|
||
查看实时日志: cml custom_train logs $JOB_ID --follow
|
||
停止任务: cml custom_train kill $JOB_ID
|
||
|
||
训练成功后产物在: $ROOT/sft_output/_SUCCESS
|
||
随后用 scripts/submit_cml_eval.sh <EVAL_RUNDIC> 起评测（不要在本脚本里串接，避免跨 step bg 任务）。
|
||
|
||
JobID: $JOB_ID
|
||
SFT_RUNDIC: $SFT_RUNDIC (yaml / sft_output 命名)
|
||
EOF
|