330 lines
12 KiB
Bash
330 lines
12 KiB
Bash
|
#!/bin/bash
|
|||
|
|
|
|||
|
|
# ============================================================================
|
|||
|
|
# MiniMind 实验脚本 - Experiment 1.4.0
|
|||
|
|
# ============================================================================
|
|||
|
|
#
|
|||
|
|
# 🎯 实验目标: 构建baseline，使用model_original和默认参数配置
|
|||
|
|
# 🤖 AI构建完成时间: $(date '+%Y-%m-%d %H:%M:%S')
|
|||
|
|
# ============================================================================
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🧑🔬 [人类填写] 实验基本信息
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
EXPERIMENT_VERSION="1_4_0"
|
|||
|
|
EXPERIMENT_DESCRIPTION="Baseline实验：使用model_original构建基准性能指标"
|
|||
|
|
RESEARCHER_NAME="Human+Claude"
|
|||
|
|
EXPERIMENT_DATE="$(date '+%Y-%m-%d %H:%M:%S')"
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 环境配置
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
|
|||
|
|
# Python环境设置 - 使用UV虚拟环境
|
|||
|
|
export VIRTUAL_ENV="/home/pci/ycz/Code/pretrain-worktree/.venv"
|
|||
|
|
source "$VIRTUAL_ENV/bin/activate"
|
|||
|
|
|
|||
|
|
# 调试和监控环境变量
|
|||
|
|
export NCCL_DEBUG=INFO
|
|||
|
|
export PYTHONFAULTHANDLER=1
|
|||
|
|
export CUDA_LAUNCH_BLOCKING=0 # 关闭同步执行以提高性能
|
|||
|
|
|
|||
|
|
# SwanLab 配置
|
|||
|
|
export SWANLAB_PROJECT="MiniMind-Baseline-Experiment"
|
|||
|
|
|
|||
|
|
# 日志配置
|
|||
|
|
LOG_DIR="out/experiment_${EXPERIMENT_VERSION}"
|
|||
|
|
mkdir -p "$LOG_DIR"
|
|||
|
|
LOG_FILE="$LOG_DIR/experiment.log"
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 硬件配置
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
CUDA_VISIBLE_DEVICES="0" # 单GPU训练
|
|||
|
|
NUM_PROCESSES="1" # 单进程
|
|||
|
|
MIXED_PRECISION="bf16" # bfloat16混合精度
|
|||
|
|
MAIN_PROCESS_PORT="29500" # 默认端口
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 模型架构参数 - Baseline配置
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
MODEL_TYPE="model_original" # 使用原始Transformer架构作为baseline
|
|||
|
|
MODEL_SIZE="26.0" # 预估模型大小
|
|||
|
|
DIM="512" # 模型维度
|
|||
|
|
N_LAYERS="8" # Transformer层数
|
|||
|
|
N_HEADS="32" # 注意力头数
|
|||
|
|
MAX_SEQ_LEN="512" # 最大序列长度
|
|||
|
|
USE_MOE="false" # 不使用MOE
|
|||
|
|
|
|||
|
|
# 知识库配置 - 对于baseline不需要
|
|||
|
|
KNOWLEDGE_NUM="1048576" # 保持默认值但不会使用
|
|||
|
|
KNOWLEDGE_LENGTH="32" # 保持默认值但不会使用
|
|||
|
|
DISABLE_DB="true" # 禁用数据库功能
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 训练超参数 - 默认配置
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
EPOCHS="3" # 训练轮次
|
|||
|
|
EMBEDDING_EPOCH="2" # 嵌入层训练轮次
|
|||
|
|
BATCH_SIZE="128" # 批次大小
|
|||
|
|
ACCUMULATION_STEPS="8" # 梯度累积步数（减少显存需求）
|
|||
|
|
LEARNING_RATE="2e-4" # 学习率
|
|||
|
|
DTYPE="bfloat16" # 数据类型
|
|||
|
|
GRAD_CLIP="1.0" # 梯度裁剪阈值
|
|||
|
|
WARMUP_ITERS="0" # 预热迭代数
|
|||
|
|
|
|||
|
|
# 数据和缓存路径
|
|||
|
|
DATA_PATH="/home/pci/ycz/Code/Minimind/dataset/stable/merged_pretrain.jsonl"
|
|||
|
|
DATABASE_INIT_PATH="None" # Baseline不使用数据库
|
|||
|
|
CLUSTER_CACHE_PATH="None" # Baseline不使用聚类缓存
|
|||
|
|
|
|||
|
|
# 训练配置
|
|||
|
|
NUM_WORKERS="1" # 数据加载工作进程数
|
|||
|
|
LOG_INTERVAL="1" # 日志记录间隔
|
|||
|
|
SAVE_INTERVAL="10000" # 模型保存间隔
|
|||
|
|
|
|||
|
|
# 性能分析配置
|
|||
|
|
USE_PROFILE="true" # 启用性能分析
|
|||
|
|
PROFILE_INTERVAL="10" # 性能分析间隔
|
|||
|
|
MEMORY_MONITOR_INTERVAL="10" # 内存监控间隔
|
|||
|
|
|
|||
|
|
# 高级功能
|
|||
|
|
USE_FLASH_ATTN="true" # 使用Flash Attention
|
|||
|
|
FAST_CLUSTERING="false" # 不使用聚类
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 预检查函数
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
check_environment() {
|
|||
|
|
echo "🔍 环境检查中..."
|
|||
|
|
|
|||
|
|
# 检查GPU可用性
|
|||
|
|
if ! nvidia-smi &> /dev/null; then
|
|||
|
|
echo "❌ 错误: 未检测到GPU或nvidia-smi不可用"
|
|||
|
|
exit 1
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
# 检查CUDA设备
|
|||
|
|
IFS=',' read -ra DEVICES <<< "$CUDA_VISIBLE_DEVICES"
|
|||
|
|
for device in "${DEVICES[@]}"; do
|
|||
|
|
if ! nvidia-smi -i "$device" &> /dev/null; then
|
|||
|
|
echo "❌ 错误: GPU $device 不可用"
|
|||
|
|
exit 1
|
|||
|
|
fi
|
|||
|
|
done
|
|||
|
|
|
|||
|
|
# 检查Python环境
|
|||
|
|
if ! python -c "import torch; print(f'PyTorch: {torch.__version__}')" 2>/dev/null; then
|
|||
|
|
echo "❌ 错误: PyTorch未正确安装"
|
|||
|
|
exit 1
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
# 检查数据文件
|
|||
|
|
if [[ ! -f "$DATA_PATH" ]]; then
|
|||
|
|
echo "❌ 错误: 训练数据文件不存在: $DATA_PATH"
|
|||
|
|
exit 1
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
echo "✅ 环境检查通过"
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 实验信息记录
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
log_experiment_info() {
|
|||
|
|
echo "📝 记录实验信息..."
|
|||
|
|
cat > "$LOG_DIR/experiment_info.txt" << EOF
|
|||
|
|
========================================
|
|||
|
|
MiniMind Baseline实验信息
|
|||
|
|
========================================
|
|||
|
|
实验版本: $EXPERIMENT_VERSION
|
|||
|
|
实验描述: $EXPERIMENT_DESCRIPTION
|
|||
|
|
研究者: $RESEARCHER_NAME
|
|||
|
|
开始时间: $EXPERIMENT_DATE
|
|||
|
|
========================================
|
|||
|
|
硬件配置:
|
|||
|
|
GPU设备: $CUDA_VISIBLE_DEVICES
|
|||
|
|
进程数: $NUM_PROCESSES
|
|||
|
|
混合精度: $MIXED_PRECISION
|
|||
|
|
========================================
|
|||
|
|
模型配置:
|
|||
|
|
模型类型: $MODEL_TYPE (Baseline)
|
|||
|
|
模型大小: $MODEL_SIZE MB
|
|||
|
|
维度: $DIM
|
|||
|
|
层数: $N_LAYERS
|
|||
|
|
注意力头数: $N_HEADS
|
|||
|
|
最大序列长度: $MAX_SEQ_LEN
|
|||
|
|
使用MOE: $USE_MOE
|
|||
|
|
禁用数据库: $DISABLE_DB
|
|||
|
|
========================================
|
|||
|
|
训练配置:
|
|||
|
|
训练轮次: $EPOCHS
|
|||
|
|
批次大小: $BATCH_SIZE
|
|||
|
|
学习率: $LEARNING_RATE
|
|||
|
|
梯度累积: $ACCUMULATION_STEPS
|
|||
|
|
数据类型: $DTYPE
|
|||
|
|
========================================
|
|||
|
|
数据路径:
|
|||
|
|
训练数据: $DATA_PATH
|
|||
|
|
数据库初始化: $DATABASE_INIT_PATH
|
|||
|
|
聚类缓存: $CLUSTER_CACHE_PATH
|
|||
|
|
========================================
|
|||
|
|
EOF
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 主执行函数
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
run_experiment() {
|
|||
|
|
echo "🚀 开始执行Baseline实验 $EXPERIMENT_VERSION"
|
|||
|
|
echo "📄 实验描述: $EXPERIMENT_DESCRIPTION"
|
|||
|
|
echo "⏰ 开始时间: $EXPERIMENT_DATE"
|
|||
|
|
|
|||
|
|
# 构建accelerate命令
|
|||
|
|
local accelerate_cmd="CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"
|
|||
|
|
|
|||
|
|
# 根据是否使用uv选择执行方式
|
|||
|
|
if command -v uv &> /dev/null && [[ -f "pyproject.toml" ]]; then
|
|||
|
|
accelerate_cmd+=" uv run python -m accelerate.commands.launch"
|
|||
|
|
else
|
|||
|
|
accelerate_cmd+=" accelerate launch"
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
# 添加accelerate参数
|
|||
|
|
accelerate_cmd+=" --num_processes=$NUM_PROCESSES"
|
|||
|
|
accelerate_cmd+=" --mixed_precision=$MIXED_PRECISION"
|
|||
|
|
accelerate_cmd+=" --main_process_port=$MAIN_PROCESS_PORT"
|
|||
|
|
accelerate_cmd+=" train_pretrain_accelerate.py"
|
|||
|
|
|
|||
|
|
# 添加训练参数
|
|||
|
|
accelerate_cmd+=" --out_dir \"$LOG_DIR\""
|
|||
|
|
accelerate_cmd+=" --epochs $EPOCHS"
|
|||
|
|
accelerate_cmd+=" --embedding_epoch $EMBEDDING_EPOCH"
|
|||
|
|
accelerate_cmd+=" --batch_size $BATCH_SIZE"
|
|||
|
|
accelerate_cmd+=" --learning_rate $LEARNING_RATE"
|
|||
|
|
accelerate_cmd+=" --dtype $DTYPE"
|
|||
|
|
accelerate_cmd+=" --num_workers $NUM_WORKERS"
|
|||
|
|
accelerate_cmd+=" --accumulation_steps $ACCUMULATION_STEPS"
|
|||
|
|
accelerate_cmd+=" --grad_clip $GRAD_CLIP"
|
|||
|
|
accelerate_cmd+=" --warmup_iters $WARMUP_ITERS"
|
|||
|
|
accelerate_cmd+=" --log_interval $LOG_INTERVAL"
|
|||
|
|
accelerate_cmd+=" --save_interval $SAVE_INTERVAL"
|
|||
|
|
accelerate_cmd+=" --dim $DIM"
|
|||
|
|
accelerate_cmd+=" --n_layers $N_LAYERS"
|
|||
|
|
accelerate_cmd+=" --n_heads $N_HEADS"
|
|||
|
|
accelerate_cmd+=" --max_seq_len $MAX_SEQ_LEN"
|
|||
|
|
accelerate_cmd+=" --data_path \"$DATA_PATH\""
|
|||
|
|
accelerate_cmd+=" --knowledge_num $KNOWLEDGE_NUM"
|
|||
|
|
accelerate_cmd+=" --knowledge_length $KNOWLEDGE_LENGTH"
|
|||
|
|
accelerate_cmd+=" --memory_monitor_interval $MEMORY_MONITOR_INTERVAL"
|
|||
|
|
accelerate_cmd+=" --model_type \"$MODEL_TYPE\""
|
|||
|
|
accelerate_cmd+=" --model_size $MODEL_SIZE"
|
|||
|
|
accelerate_cmd+=" --swanlab_online false"
|
|||
|
|
|
|||
|
|
# 可选参数
|
|||
|
|
if [[ "$USE_PROFILE" == "true" ]]; then
|
|||
|
|
accelerate_cmd+=" --profile"
|
|||
|
|
accelerate_cmd+=" --profile_interval $PROFILE_INTERVAL"
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
if [[ "$USE_FLASH_ATTN" == "true" ]]; then
|
|||
|
|
accelerate_cmd+=" --use_flash_attn"
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
if [[ "$DISABLE_DB" == "true" ]]; then
|
|||
|
|
accelerate_cmd+=" --disable_db"
|
|||
|
|
fi
|
|||
|
|
|
|||
|
|
# SwanLab配置
|
|||
|
|
accelerate_cmd+=" --use_swanlab"
|
|||
|
|
accelerate_cmd+=" --swanlab_project \"$SWANLAB_PROJECT\""
|
|||
|
|
|
|||
|
|
echo "📋 执行命令:"
|
|||
|
|
echo "$accelerate_cmd"
|
|||
|
|
echo
|
|||
|
|
|
|||
|
|
# 记录命令到日志文件
|
|||
|
|
echo "执行命令: $accelerate_cmd" >> "$LOG_FILE"
|
|||
|
|
echo "开始时间: $(date)" >> "$LOG_FILE"
|
|||
|
|
|
|||
|
|
# 使用nohup执行训练（后台运行，输出写入日志文件）
|
|||
|
|
echo "🔄 使用nohup后台运行训练，输出将写入日志文件: $LOG_FILE"
|
|||
|
|
echo "开始时间: $(date)" >> "$LOG_FILE"
|
|||
|
|
|
|||
|
|
# 创建训练脚本
|
|||
|
|
train_script="/tmp/train_${EXPERIMENT_VERSION}.sh"
|
|||
|
|
cat > "$train_script" << EOF
|
|||
|
|
#!/bin/bash
|
|||
|
|
cd /home/pci/ycz/Code/pretrain-worktree
|
|||
|
|
source /home/pci/ycz/Code/pretrain-worktree/.venv/bin/activate
|
|||
|
|
$accelerate_cmd
|
|||
|
|
echo "结束时间: \$(date)"
|
|||
|
|
echo "退出代码: \$?"
|
|||
|
|
EOF
|
|||
|
|
chmod +x "$train_script"
|
|||
|
|
|
|||
|
|
# 使用nohup后台运行
|
|||
|
|
nohup bash "$train_script" >> "$LOG_FILE" 2>&1 &
|
|||
|
|
local train_pid=$!
|
|||
|
|
|
|||
|
|
echo "🔥 训练进程已启动，PID: $train_pid"
|
|||
|
|
echo "训练PID: $train_pid" >> "$LOG_FILE"
|
|||
|
|
echo "训练脚本: $train_script" >> "$LOG_FILE"
|
|||
|
|
|
|||
|
|
# 等待几秒确保进程启动
|
|||
|
|
sleep 5
|
|||
|
|
|
|||
|
|
# 检查进程是否还在运行
|
|||
|
|
if kill -0 $train_pid 2>/dev/null; then
|
|||
|
|
echo "✅ 训练进程正在后台运行"
|
|||
|
|
echo "📋 实时查看日志: tail -f $LOG_FILE"
|
|||
|
|
echo "📋 检查进程状态: ps -p $train_pid"
|
|||
|
|
echo "🛑 停止训练: kill $train_pid"
|
|||
|
|
echo "⏰ 预计训练时间: 约17小时"
|
|||
|
|
echo "📈 SwanLab: https://swanlab.cn/project/$SWANLAB_PROJECT"
|
|||
|
|
echo ""
|
|||
|
|
echo "训练正在后台运行，可以安全关闭终端。"
|
|||
|
|
else
|
|||
|
|
echo "❌ 训练进程启动失败"
|
|||
|
|
echo "📋 查看日志: $LOG_FILE"
|
|||
|
|
exit 1
|
|||
|
|
fi
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 清理函数
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
cleanup() {
|
|||
|
|
echo "🧹 清理临时文件..."
|
|||
|
|
# 在这里添加清理逻辑
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 信号处理
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
trap cleanup EXIT
|
|||
|
|
trap 'echo "❌ 实验被中断"; cleanup; exit 130' INT TERM
|
|||
|
|
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
# 🤖 [AI构建] 主程序入口
|
|||
|
|
# ----------------------------------------------------------------------------
|
|||
|
|
main() {
|
|||
|
|
echo "============================================================================"
|
|||
|
|
echo "🧠 MiniMind Baseline预训练实验"
|
|||
|
|
echo "============================================================================"
|
|||
|
|
|
|||
|
|
# 执行检查和初始化
|
|||
|
|
check_environment
|
|||
|
|
log_experiment_info
|
|||
|
|
|
|||
|
|
# 运行实验
|
|||
|
|
run_experiment
|
|||
|
|
|
|||
|
|
echo "============================================================================"
|
|||
|
|
echo "✅ Baseline实验 $EXPERIMENT_VERSION 完成"
|
|||
|
|
echo "📅 完成时间: $(date)"
|
|||
|
|
echo "============================================================================"
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# 执行主程序
|
|||
|
|
main "$@"
|