Minimind/run_file/experiment_1_4_5.sh

#!/bin/bash

# ============================================================================
# MiniMind 实验脚本 - Experiment 1.4.5
# ============================================================================
# 
# 🎯 实验目标: 
# 基于实验1.4.4，实现VQ-VAE风格的EMA更新机制替代memory_bank的梯度更新
# 
# 使用方法:
# bash run_file/experiment_1_4_5.sh
# ============================================================================

# ----------------------------------------------------------------------------
# 🧑‍🔬 实验基本信息
# ----------------------------------------------------------------------------
EXPERIMENT_VERSION="1.4.5"
EXPERIMENT_DESCRIPTION="VQ-VAE风格EMA更新机制实验"
RESEARCHER_NAME="AI Assistant"
EXPERIMENT_DATE="$(date '+%Y-%m-%d %H:%M:%S')"

# ----------------------------------------------------------------------------
# 🤖 环境配置
# ----------------------------------------------------------------------------

# 调试和监控环境变量
export NCCL_DEBUG=INFO
export PYTHONFAULTHANDLER=1
export CUDA_LAUNCH_BLOCKING=1

# SwanLab 配置
export SWANLAB_PROJECT="MiniMind-Experiment-1.4.5"

# 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="50.0"
DIM="512"
N_LAYERS="8"
N_HEADS="32"
MAX_SEQ_LEN="512"
USE_MOE="false"

# 知识库配置（使用更大规模测试EMA机制）
KNOWLEDGE_NUM="1048576"  # 1024x1024 = 1048576，更大规模测试EMA
KNOWLEDGE_LENGTH="32"
KNOWLEDGE_DIM="128"
DISABLE_DB="false"

# ----------------------------------------------------------------------------
# 🤖 训练超参数
# ----------------------------------------------------------------------------
EPOCHS="3"
EMBEDDING_EPOCH="2"
BATCH_SIZE="96"
ACCUMULATION_STEPS="8"
LEARNING_RATE="2e-4"
DTYPE="bfloat16"
GRAD_CLIP="1.0"
WARMUP_ITERS="0"

# 平衡损失配置（沿用1.4.4的成功配置）
BALANCE_LOSS_COEF="0.1"

# 数据和缓存路径
DATA_PATH="/home/pci/ycz/Code/Minimind/dataset/stable/merged_pretrain.jsonl"
DATABASE_INIT_PATH="/home/pci/ycz/Code/Minimind/dataset/stable/sentence_trex_data.json"
CLUSTER_CACHE_PATH="None"  # 禁用聚类缓存以测试EMA效果
VAL_DATA_PATH="dataset/stable/eval_data.json"

# 训练配置
NUM_WORKERS="1"
LOG_INTERVAL="100"
VAL_INTERVAL="100"
SAVE_INTERVAL="10000"

# 性能分析配置
USE_PROFILE="true"
PROFILE_INTERVAL="10"
MEMORY_MONITOR_INTERVAL="100"

# 高级功能
USE_FLASH_ATTN="true"
FAST_CLUSTERING="true"

# ----------------------------------------------------------------------------
# 🤖 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
    
    if [[ ! -f "$DATABASE_INIT_PATH" ]]; then
        echo "❌ 错误: 数据库初始化文件不存在: $DATABASE_INIT_PATH"
        exit 1
    fi
    
    # 检查EMA相关模型实现
    if ! .venv/bin/python -c "from model.model_memory import *; print('EMA模型实现检查通过')" 2>/dev/null; then
        echo "❌ 错误: EMA模型实现存在问题"
        exit 1
    fi
    
    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 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
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
知识库大小: $KNOWLEDGE_NUM
知识长度: $KNOWLEDGE_LENGTH
知识维度: $KNOWLEDGE_DIM
========================================
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
平衡损失系数: $BALANCE_LOSS_COEF
========================================
EMA配置:
使用EMA更新: 是（VQ-VAE风格）
EMA衰减率: 0.999（默认配置）
EMA更新频率: 1（每步更新）
========================================
数据路径:
训练数据: $DATA_PATH
验证数据: $VAL_DATA_PATH
数据库初始化: $DATABASE_INIT_PATH
聚类缓存: $CLUSTER_CACHE_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 .venv/bin/python 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+=" --val_interval $VAL_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+=" --val_data_path \"$VAL_DATA_PATH\""
    train_cmd+=" --knowledge_num $KNOWLEDGE_NUM"
    train_cmd+=" --knowledge_length $KNOWLEDGE_LENGTH"
    train_cmd+=" --database_init_path \"$DATABASE_INIT_PATH\""
    train_cmd+=" --memory_monitor_interval $MEMORY_MONITOR_INTERVAL"
    train_cmd+=" --model_type \"$MODEL_TYPE\""
    train_cmd+=" --model_size $MODEL_SIZE"
    train_cmd+=" --balance_loss_coef $BALANCE_LOSS_COEF"
    
    # 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 [[ "$FAST_CLUSTERING" == "true" ]]; then
        train_cmd+=" --fast_clustering"
    fi
    
    if [[ "$CLUSTER_CACHE_PATH" != "None" ]]; then
        train_cmd+=" --cluster_cache_path \"$CLUSTER_CACHE_PATH\""
    fi
    
    # SwanLab配置
    train_cmd+=" --use_swanlab"
    train_cmd+=" --swanlab_project \"$SWANLAB_PROJECT\""
    train_cmd+=" --swanlab_online True"
    
    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，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"
    
    # 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
$train_cmd
echo "结束时间: \$(date)"
echo "退出代码: \$?"
EOF
    chmod +x "$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 -p $train_pid"
        echo "🛑 停止训练: kill $train_pid"        
        echo "📈 SwanLab: https://swanlab.cn/project/$SWANLAB_PROJECT"
        echo ""
        echo "🧠 VQ-VAE风格EMA更新机制正在测试中..."
        echo "   - memory_bank使用EMA更新而非梯度更新"
        echo "   - EMA衰减率: 0.999"
        echo "   - 每步更新频率"
        echo "   - 预期: 更稳定的训练和更好的记忆表示学习"
        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..."
    # 删除临时验证文件
    rm -f /tmp/temp_val.jsonl
}

# ----------------------------------------------------------------------------
# 🤖 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 预训练实验 1.4.5"
    echo "🎯 VQ-VAE风格EMA更新机制 - 替代memory_bank梯度更新"
    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 启动完成"
    echo "📅 启动时间: $(date)"
    echo "============================================================================"
}

# 执行主程序
main "$@"