| # ============================================================ | |
| # DMC 溶剂 XTB 训练配置 | |
| # 入门级示例：单 GPU，小数据集，参数最少 | |
| # ============================================================ | |
| # 实验名称（用于输出目录和模型文件命名） | |
| name: DMC | |
| # 实验描述 | |
| description: "DMC solvent XTB - 单 GPU 入门示例 (200 训练帧)" | |
| # ============================================================ | |
| # train.py 参数 | |
| # 以下所有字段将被转换为 train.py 的命令行参数 | |
| # 例如 model: MACE -> --model=MACE | |
| # swa: true -> --swa (布尔标志) | |
| # ============================================================ | |
| train_args: | |
| # --- 模型配置 --- | |
| model: MACE # 模型类型 | |
| # --- 数据配置 --- | |
| # 路径中的 ${ONESCIENCE_DATASETS_DIR} 默认指向仓库根目录， | |
| # 下载 ModelScope DMC 数据集到 ./data 后即可使用 可能需根据实际路径进行调整 | |
| train_file: "${ONESCIENCE_DATASETS_DIR}/data/data/DMC/solvent_xtb_train_200.xyz" | |
| test_file: "${ONESCIENCE_DATASETS_DIR}/data/data/DMC/solvent_xtb_test.xyz" | |
| valid_fraction: 0.10 # 从训练集中划分 10% 作为验证集 | |
| energy_key: energy_xtb # XYZ 文件中能量字段名 | |
| forces_key: forces_xtb # XYZ 文件中力字段名 | |
| E0s: average # 原子参考能量方式: average / isolated / 显式字典 | |
| # --- 训练超参 --- | |
| seed: 123 # 随机种子 | |
| device: cuda # 设备: cuda / cpu | |
| r_max: 4.0 # 截断半径 (Angstrom) | |
| batch_size: 10 # 训练批大小 | |
| max_num_epochs: 100 # 最大训练轮数 | |
| eval_interval: 10 # 每 10 个 epoch 评估并打印一次 | |
| # --- SWA (Stochastic Weight Averaging) --- | |
| swa: true # 启用 SWA | |
| # ============================================================ | |
| # 启动配置（控制 python / torchrun / srun 的选择） | |
| # ============================================================ | |
| launch: | |
| launcher: python # 启动方式: python / torchrun (多节点时自动用 srun) | |
| num_nodes: 1 # 节点数 | |
| num_gpus: 8 # 申请的 DCU 卡数 | |
| # ============================================================ | |
| # 环境配置 | |
| # ============================================================ | |
| env: | |
| conda_env: matchem # conda 环境名 | |
| modules: | |
| - sghpc-mpi-gcc/26.3 # 需要加载的 module | |
| # ============================================================ | |
| # SLURM 配置（仅 --submit 模式使用） | |
| # ============================================================ | |
| slurm: | |
| partition: hpctest01 # SLURM 分区 | |
| time: "2:00:00" # 作业时间限制 | |
| cpus_per_task: 128 # CPU 核心数 | |