352 lines
12 KiB
Bash
352 lines
12 KiB
Bash
#!/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: $(date)"
|
||
echo "============================================================================"
|
||
}
|
||
|
||
# 执行主程序
|
||
main "$@" |