335 lines
11 KiB
Bash
335 lines
11 KiB
Bash
#!/bin/bash
|
||
|
||
# ============================================================================
|
||
# MiniMind 实验脚本 - Experiment 1.4.1
|
||
# ============================================================================
|
||
#
|
||
# 🎯 实验目标: 基于Product Key Memory的可训练记忆库替代FFN
|
||
# 📝 实验描述: 探索使用门控选择网络+交叉注意力的记忆机制替代Feed Forward层
|
||
# 🔬 研究假设: 去除FFN和KV cache，使用可理解的记忆库实现相同效果
|
||
# ============================================================================
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🧑🔬 实验基本信息
|
||
# ----------------------------------------------------------------------------
|
||
EXPERIMENT_VERSION="1_4_1"
|
||
EXPERIMENT_DESCRIPTION="Product Key Memory based trainable memory bank to replace FFN"
|
||
RESEARCHER_NAME="Human-AI Collaboration"
|
||
EXPERIMENT_DATE="$(date '+%Y-%m-%d %H:%M:%S')"
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 环境配置
|
||
# ----------------------------------------------------------------------------
|
||
|
||
# UV虚拟环境激活
|
||
export PYTHONFAULTHANDLER=1
|
||
export CUDA_LAUNCH_BLOCKING=0 # 设为0以提高性能
|
||
|
||
# SwanLab 配置
|
||
export SWANLAB_PROJECT="MiniMind-Memory-Experiment"
|
||
|
||
# 日志配置
|
||
LOG_DIR="out/experiment_${EXPERIMENT_VERSION}"
|
||
mkdir -p "$LOG_DIR"
|
||
LOG_FILE="$LOG_DIR/experiment.log"
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 硬件配置
|
||
# ----------------------------------------------------------------------------
|
||
CUDA_VISIBLE_DEVICES="0"
|
||
NUM_PROCESSES="1"
|
||
MIXED_PRECISION="bf16"
|
||
MAIN_PROCESS_PORT="29500"
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 模型架构参数
|
||
# ----------------------------------------------------------------------------
|
||
MODEL_TYPE="model_memory"
|
||
MODEL_SIZE="26.0"
|
||
DIM="512"
|
||
N_LAYERS="8"
|
||
N_HEADS="32"
|
||
MAX_SEQ_LEN="512"
|
||
USE_MOE="false"
|
||
|
||
# 记忆库配置
|
||
KNOWLEDGE_NUM="65536" # 64K条记忆（256x256，完全平方数）
|
||
KNOWLEDGE_DIM="128" # 记忆向量维度
|
||
KNOWLEDGE_LENGTH="32" # 单条记忆长度
|
||
NUM_SELECTED="8" # 每次选择的记忆数（减少计算量）
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 训练超参数
|
||
# ----------------------------------------------------------------------------
|
||
EPOCHS="3"
|
||
EMBEDDING_EPOCH="2"
|
||
BATCH_SIZE="64" # 减少批次大小以节省内存
|
||
ACCUMULATION_STEPS="8"
|
||
LEARNING_RATE="2e-4"
|
||
DTYPE="bfloat16"
|
||
GRAD_CLIP="1.0"
|
||
WARMUP_ITERS="0"
|
||
|
||
# 数据路径
|
||
DATA_PATH="/home/pci/ycz/Code/Minimind/dataset/stable/merged_pretrain.jsonl"
|
||
DATABASE_INIT_PATH="None" # 不使用外部数据库初始化，记忆库为可训练参数
|
||
CLUSTER_CACHE_PATH="None"
|
||
|
||
# 训练配置
|
||
NUM_WORKERS="1"
|
||
LOG_INTERVAL="1"
|
||
SAVE_INTERVAL="10000"
|
||
|
||
# 性能分析配置
|
||
USE_PROFILE="true"
|
||
PROFILE_INTERVAL="10"
|
||
MEMORY_MONITOR_INTERVAL="10"
|
||
|
||
# 高级功能
|
||
USE_FLASH_ATTN="true"
|
||
USE_SWANLAB="true"
|
||
SWANLAB_ONLINE="false"
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 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
|
||
if ! nvidia-smi -i "$CUDA_VISIBLE_DEVICES" &> /dev/null; then
|
||
echo "❌ 错误: GPU $CUDA_VISIBLE_DEVICES 不可用"
|
||
exit 1
|
||
fi
|
||
|
||
# 检查Python环境
|
||
if ! .venv/bin/python -c "import torch; print(f'PyTorch: {torch.__version__}')" 2>/dev/null; then
|
||
echo "❌ 错误: PyTorch未正确安装"
|
||
exit 1
|
||
fi
|
||
|
||
# 检查数据文件
|
||
if [[ ! -f "$DATA_PATH" ]]; then
|
||
echo "❌ 错误: 训练数据文件不存在: $DATA_PATH"
|
||
exit 1
|
||
fi
|
||
|
||
# 不再需要检查数据库文件，记忆库使用随机初始化
|
||
|
||
echo "✅ 环境检查通过"
|
||
}
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 实验信息记录
|
||
# ----------------------------------------------------------------------------
|
||
log_experiment_info() {
|
||
echo "📝 记录实验信息..."
|
||
cat > "$LOG_DIR/experiment_info.txt" << EOF
|
||
========================================
|
||
MiniMind 记忆库实验信息
|
||
========================================
|
||
实验版本: $EXPERIMENT_VERSION
|
||
实验描述: $EXPERIMENT_DESCRIPTION
|
||
研究者: $RESEARCHER_NAME
|
||
开始时间: $EXPERIMENT_DATE
|
||
========================================
|
||
核心创新:
|
||
- 使用Product Key Memory进行记忆选择
|
||
- 门控网络 + 交叉注意力替代FFN
|
||
- 完全去除KV cache机制
|
||
- 可训练的1M条记忆库
|
||
========================================
|
||
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
|
||
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
|
||
记忆库条目数: $KNOWLEDGE_NUM
|
||
记忆向量维度: $KNOWLEDGE_DIM
|
||
每次选择记忆数: $NUM_SELECTED
|
||
========================================
|
||
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
|
||
记忆库初始化: $DATABASE_INIT_PATH
|
||
========================================
|
||
EOF
|
||
}
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 主执行函数
|
||
# ----------------------------------------------------------------------------
|
||
run_experiment() {
|
||
echo "🚀 开始执行实验 $EXPERIMENT_VERSION"
|
||
echo "📄 实验描述: $EXPERIMENT_DESCRIPTION"
|
||
echo "⏰ 开始时间: $EXPERIMENT_DATE"
|
||
|
||
# 构建训练命令
|
||
local train_cmd="CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES uv run python -m accelerate.commands.launch"
|
||
train_cmd+=" --num_processes=$NUM_PROCESSES"
|
||
train_cmd+=" --mixed_precision=$MIXED_PRECISION"
|
||
train_cmd+=" --main_process_port=$MAIN_PROCESS_PORT"
|
||
train_cmd+=" train_pretrain_accelerate.py"
|
||
|
||
# 添加训练参数
|
||
train_cmd+=" --out_dir \"$LOG_DIR\""
|
||
train_cmd+=" --epochs $EPOCHS"
|
||
train_cmd+=" --embedding_epoch $EMBEDDING_EPOCH"
|
||
train_cmd+=" --batch_size $BATCH_SIZE"
|
||
train_cmd+=" --learning_rate $LEARNING_RATE"
|
||
train_cmd+=" --dtype $DTYPE"
|
||
train_cmd+=" --num_workers $NUM_WORKERS"
|
||
train_cmd+=" --accumulation_steps $ACCUMULATION_STEPS"
|
||
train_cmd+=" --grad_clip $GRAD_CLIP"
|
||
train_cmd+=" --warmup_iters $WARMUP_ITERS"
|
||
train_cmd+=" --log_interval $LOG_INTERVAL"
|
||
train_cmd+=" --save_interval $SAVE_INTERVAL"
|
||
train_cmd+=" --dim $DIM"
|
||
train_cmd+=" --n_layers $N_LAYERS"
|
||
train_cmd+=" --n_heads $N_HEADS"
|
||
train_cmd+=" --max_seq_len $MAX_SEQ_LEN"
|
||
train_cmd+=" --data_path \"$DATA_PATH\""
|
||
train_cmd+=" --knowledge_num $KNOWLEDGE_NUM"
|
||
train_cmd+=" --knowledge_length $KNOWLEDGE_LENGTH"
|
||
train_cmd+=" --knowledge_dim $KNOWLEDGE_DIM"
|
||
train_cmd+=" --memory_monitor_interval $MEMORY_MONITOR_INTERVAL"
|
||
train_cmd+=" --model_type \"$MODEL_TYPE\""
|
||
train_cmd+=" --model_size $MODEL_SIZE"
|
||
train_cmd+=" --swanlab_online $SWANLAB_ONLINE"
|
||
train_cmd+=" --database_init_path \"$DATABASE_INIT_PATH\""
|
||
|
||
# 可选参数
|
||
if [[ "$USE_PROFILE" == "true" ]]; then
|
||
train_cmd+=" --profile"
|
||
train_cmd+=" --profile_interval $PROFILE_INTERVAL"
|
||
fi
|
||
|
||
if [[ "$USE_FLASH_ATTN" == "true" ]]; then
|
||
train_cmd+=" --use_flash_attn"
|
||
fi
|
||
|
||
if [[ "$USE_SWANLAB" == "true" ]]; then
|
||
train_cmd+=" --use_swanlab"
|
||
train_cmd+=" --swanlab_project \"$SWANLAB_PROJECT\""
|
||
fi
|
||
|
||
echo "📋 执行命令:"
|
||
echo "$train_cmd"
|
||
echo
|
||
|
||
# 记录命令到日志文件
|
||
echo "执行命令: $train_cmd" >> "$LOG_FILE"
|
||
echo "开始时间: $(date)" >> "$LOG_FILE"
|
||
|
||
# 使用nohup执行训练（后台运行）
|
||
echo "🔄 使用nohup后台运行训练，输出将写入日志文件: $LOG_FILE"
|
||
|
||
# 创建训练脚本
|
||
train_script="/tmp/train_${EXPERIMENT_VERSION}.sh"
|
||
cat > "$train_script" << EOF
|
||
#!/bin/bash
|
||
cd /home/pci/ycz/Code/pretrain-worktree
|
||
export PYTHONFAULTHANDLER=1
|
||
export SWANLAB_PROJECT="$SWANLAB_PROJECT"
|
||
$train_cmd
|
||
echo "结束时间: \$(date)"
|
||
echo "退出代码: \$?"
|
||
EOF
|
||
chmod +x "$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 aux | grep train_pretrain_accelerate"
|
||
echo "🛑 停止训练: kill $train_pid"
|
||
echo "⏰ 预计训练时间: 10-15小时 (3 epochs, RTX 4090)"
|
||
echo "📈 SwanLab: 本地模式，输出目录中查看"
|
||
echo ""
|
||
echo "🎯 实验重点:"
|
||
echo " - 观察记忆选择机制的学习过程"
|
||
echo " - 对比FFN替代效果"
|
||
echo " - 监控内存使用和训练稳定性"
|
||
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: $LOG_FILE"
|
||
exit 1
|
||
fi
|
||
}
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 清理函数
|
||
# ----------------------------------------------------------------------------
|
||
cleanup() {
|
||
echo "🧹 清理临时文件..."
|
||
# 清理临时脚本
|
||
if [[ -f "/tmp/train_${EXPERIMENT_VERSION}.sh" ]]; then
|
||
rm -f "/tmp/train_${EXPERIMENT_VERSION}.sh"
|
||
fi
|
||
}
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 信号处理
|
||
# ----------------------------------------------------------------------------
|
||
trap cleanup EXIT
|
||
trap 'echo "❌ 实验被中断"; cleanup; exit 130' INT TERM
|
||
|
||
# ----------------------------------------------------------------------------
|
||
# 🤖 主程序入口
|
||
# ----------------------------------------------------------------------------
|
||
main() {
|
||
echo "============================================================================"
|
||
echo "🧠 MiniMind 记忆库替代FFN实验"
|
||
echo "============================================================================"
|
||
echo "🎯 实验版本: $EXPERIMENT_VERSION"
|
||
echo "📝 实验目标: 使用Product Key Memory + 交叉注意力替代Feed Forward层"
|
||
echo "🔬 核心创新: 门控选择网络 + 可训练记忆库 + 去除KV cache"
|
||
echo "============================================================================"
|
||
|
||
# 执行检查和初始化
|
||
check_environment
|
||
log_experiment_info
|
||
|
||
# 运行实验
|
||
run_experiment
|
||
|
||
echo "============================================================================"
|
||
echo "✅ 实验 $EXPERIMENT_VERSION 已启动"
|
||
echo "📅 启动时间: $(date)"
|
||
echo "============================================================================"
|
||
}
|
||
|
||
# 执行主程序
|
||
main "$@" |