Minimind/run_file/experiment_1_4_7.sh

#!/bin/bash

#########################################################
# 实验1.4.7 - Memory Bank文本初始化 + 部分冻结机制
# 
# 实验目标:
# 1. 验证使用有意义文本进行memory_bank初始化的效果
# 2. 验证部分memory_bank冻结机制(freeze_ratio=0.2)的效果
#
# 关键特性:
# - 使用sentence_trex_data.json文本数据初始化memory_bank
# - 冻结20%的memory_bank条目，保护重要知识
# - Token-based memory机制 + EMA更新
# - Product Key Memory架构
#########################################################

echo "=========================================="
echo "🚀 开始实验 1.4.7 - Memory Bank优化"
echo "🔥 新特性: 文本初始化 + 部分冻结机制"
echo "=========================================="

# 实验配置
EXPERIMENT_NAME="experiment_1_4_7"
OUTPUT_DIR="out/${EXPERIMENT_NAME}"
LOG_FILE="${OUTPUT_DIR}/experiment.log"
PID_FILE="${OUTPUT_DIR}/train.pid"

# 创建输出目录
mkdir -p $OUTPUT_DIR

echo "📂 实验输出目录: $OUTPUT_DIR"
echo "📝 日志文件: $LOG_FILE"

# 核心参数配置
MODEL_TYPE="model_memory"                    # 🔥 使用memory架构
DIM=512
N_LAYERS=8
N_HEADS=32
MAX_SEQ_LEN=512

# 🔥 Memory Bank配置 - 实验1.4.7关键参数
KNOWLEDGE_NUM=1048576                        # 1M条记忆（2^20）
KNOWLEDGE_LENGTH=8                          # 每条记忆32个token
KNOWLEDGE_DIM=128                           # 记忆向量维度128
FREEZE_RATIO=0.2                            # 🔥 新特性: 冻结20%的记忆条目

# EMA更新配置
USE_EMA_UPDATE="True"
EMA_DECAY=0.9                               # EMA衰减率
EMA_UPDATE_FREQ=5                           # EMA更新频率

# 训练配置
EPOCHS=3
BATCH_SIZE=48
ACCUMULATION_STEPS=8
LEARNING_RATE=2e-4
DTYPE="bfloat16"
GRAD_CLIP=1.0
BALANCE_LOSS_COEF=0.01                      # 平衡损失系数

# 数据路径配置
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"  # 🔥 文本数据初始化
CACHE_PATH="cache/memory_bank_init_${KNOWLEDGE_NUM}_${KNOWLEDGE_LENGTH}.pt"           # 🔥 Memory初始化缓存

# GPU和性能配置
export CUDA_VISIBLE_DEVICES=0
NUM_WORKERS=1
MIXED_PRECISION="bf16"

# 监控配置
USE_SWANLAB="True"
SWANLAB_PROJECT="MiniMind-Experiment-1.4.7"
SWANLAB_ONLINE="False"                      # 离线模式

# 验证和日志配置
LOG_INTERVAL=100
VAL_INTERVAL=200
PROFILE="True"
PROFILE_INTERVAL=10
MEMORY_MONITOR="False"                      # 关闭内存监控降低开销

echo "=========================================="
echo "📋 实验配置摘要"
echo "=========================================="
echo "🔥 核心特性:"
echo "  - Model Type: $MODEL_TYPE"
echo "  - Memory Bank Size: $KNOWLEDGE_NUM 条"
echo "  - Memory Length: $KNOWLEDGE_LENGTH tokens"
echo "  - Freeze Ratio: $FREEZE_RATIO (冻结 $((KNOWLEDGE_NUM * 20 / 100)) 条记忆)"
echo "  - Text Initialization: $DATABASE_INIT_PATH"
echo ""
echo "🏗️ 模型架构:"
echo "  - Dimension: $DIM"
echo "  - Layers: $N_LAYERS" 
echo "  - Heads: $N_HEADS"
echo "  - Max Seq Len: $MAX_SEQ_LEN"
echo ""
echo "📚 训练设置:"
echo "  - Epochs: $EPOCHS"
echo "  - Batch Size: $BATCH_SIZE"
echo "  - Learning Rate: $LEARNING_RATE"
echo "  - Data Type: $DTYPE"
echo ""
echo "⚡ EMA配置:"
echo "  - EMA Decay: $EMA_DECAY"
echo "  - Update Frequency: $EMA_UPDATE_FREQ"
echo ""
echo "📊 监控:"
echo "  - SwanLab Project: $SWANLAB_PROJECT"
echo "  - Log Interval: $LOG_INTERVAL"
echo "=========================================="

# 检查必要文件
echo "🔍 检查必要文件..."
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: Memory初始化数据文件不存在: $DATABASE_INIT_PATH"
    exit 1
fi

echo "✅ 文件检查通过"

# 构建训练命令 - 参考experiment_1_4_6.sh的成功模式
TRAIN_CMD="CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES .venv/bin/python train_pretrain_accelerate.py"
TRAIN_CMD+=" --out_dir \"$OUTPUT_DIR\""
TRAIN_CMD+=" --epochs $EPOCHS"
TRAIN_CMD+=" --embedding_epoch 2"
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 0"
TRAIN_CMD+=" --log_interval $LOG_INTERVAL"
TRAIN_CMD+=" --val_interval $VAL_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 $KNOWLEDGE_DIM"
TRAIN_CMD+=" --database_init_path \"$DATABASE_INIT_PATH\""
TRAIN_CMD+=" --cluster_cache_path \"$CACHE_PATH\""
TRAIN_CMD+=" --model_type \"$MODEL_TYPE\""
TRAIN_CMD+=" --balance_loss_coef $BALANCE_LOSS_COEF"

# 添加可选的flag参数（不需要值的参数）
TRAIN_CMD+=" --use_swanlab"
TRAIN_CMD+=" --profile"
TRAIN_CMD+=" --use_flash_attn"

# 添加有值的可选参数
TRAIN_CMD+=" --swanlab_project \"$SWANLAB_PROJECT\""
TRAIN_CMD+=" --swanlab_online $SWANLAB_ONLINE"
TRAIN_CMD+=" --profile_interval $PROFILE_INTERVAL"

# 添加memory monitor参数（如果启用）
if [[ "$MEMORY_MONITOR" == "True" ]]; then
    TRAIN_CMD+=" --memory_monitor"
fi

echo ""
echo "🚀 启动训练..."
echo "📝 完整训练命令:"
echo "$TRAIN_CMD"
echo ""
echo "⏰ 预计训练时间: 约6-8小时"
echo "📊 实时监控: 查看 $LOG_FILE"
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"

# 创建训练脚本（参考1.4.6的成功模式）
TRAIN_SCRIPT="/tmp/train_1_4_7.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后台运行训练脚本
nohup bash "$TRAIN_SCRIPT" >> "$LOG_FILE" 2>&1 &
TRAIN_PID=$!
echo $TRAIN_PID > $PID_FILE

echo "=========================================="
echo "✅ 实验1.4.7已启动"
echo "🆔 进程ID: $TRAIN_PID"
echo "📝 日志文件: $LOG_FILE"
echo "📊 监控命令: tail -f $LOG_FILE"
echo "🛑 停止命令: kill $TRAIN_PID"
echo "=========================================="
echo ""
echo "🔥 实验1.4.7 - Memory Bank优化特性:"
echo "  ✨ 文本数据初始化 (sentence_trex_data.json)"
echo "  ✨ 部分冻结机制 (freeze_ratio=0.2)"
echo "  ✨ Token-based EMA更新"
echo "  ✨ Product Key Memory架构"
echo ""
echo "📋 监控要点:"
echo "  - 初始化阶段：观察文本数据加载和缓存"
echo "  - 训练阶段：关注frozen_memories统计"
echo "  - EMA更新：监控update_ratio和coverage指标"
echo "  - 生成质量：对比词组连贯性改善"
echo ""
echo "⚡ 进程状态检查:"
echo "ps aux | grep $TRAIN_PID"
echo ""

# 显示初始进程状态
sleep 2
if ps -p $TRAIN_PID > /dev/null; then
    echo "✅ 训练进程正在运行 (PID: $TRAIN_PID)"
    
    # 显示前几行日志
    echo ""
    echo "📋 初始日志预览:"
    echo "----------------------------------------"
    timeout 5 tail -f $LOG_FILE | head -10 || echo "日志文件尚未生成，请稍等..."
    echo "----------------------------------------"
else
    echo "❌ 训练进程启动失败，请检查日志:"
    echo "cat $LOG_FILE"
fi

echo ""
echo "🎯 实验1.4.7核心验证点:"
echo "  1. Memory bank是否成功用文本数据初始化"
echo "  2. 冻结机制是否正常工作 (20%条目不更新)"
echo "  3. 生成质量是否有明显改善"
echo "  4. 训练稳定性是否提升"
echo ""
echo "📖 实验记录: experiment/EXPERIMENT_1_4_7.md"
echo "🚀 实验1.4.7启动完成！"