From fcc3886db15acb9878cd0e15314d5a942b2a94bd Mon Sep 17 00:00:00 2001 From: josc146 Date: Sun, 9 Jul 2023 11:39:44 +0800 Subject: [PATCH] improve error messages for training --- frontend/src/_locales/zh-hans/main.json | 5 +++-- frontend/src/pages/Train.tsx | 7 ++++--- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/frontend/src/_locales/zh-hans/main.json b/frontend/src/_locales/zh-hans/main.json index ba328fa..c64fd52 100644 --- a/frontend/src/_locales/zh-hans/main.json +++ b/frontend/src/_locales/zh-hans/main.json @@ -224,7 +224,7 @@ "Convert Data successfully": "数据转换成功", "Please select a LoRA model": "请选择一个LoRA模型", "You are using sample data for training. For formal training, please make sure to create your own jsonl file.": "你正在使用示例数据训练，对于正式训练场合，请务必创建你自己的jsonl训练数据", - "WSL is not running. You may be using an outdated version of WSL, run \"wsl --update\" to update.": "WSL没有运行。你可能正在使用旧版本的WSL，请在cmd执行\"wsl --update\"以更新", + "WSL is not running, please retry. If it keeps happening, it means you may be using an outdated version of WSL, run \"wsl --update\" to update.": "WSL没有运行，请重试。如果一直出现此错误，意味着你可能正在使用旧版本的WSL，请在cmd执行\"wsl --update\"以更新", "Memory is not enough, try to increase the virtual memory or use a smaller base model.": "内存不足，尝试增加虚拟内存，或使用一个更小规模的基底模型", "VRAM is not enough": "显存不足", "Training data is not enough, reduce context length or add more data for training": "训练数据不足，请减小上下文长度或增加训练数据", @@ -232,5 +232,6 @@ "Matched CUDA is not installed": "未安装匹配的CUDA", "Failed to convert data": "数据转换失败", "Failed to merge model": "合并模型失败", - "The data path should be a directory or a file in jsonl format (more formats will be supported in the future).\n\nWhen you provide a directory path, all the txt files within that directory will be automatically converted into training data. This is commonly used for large-scale training in writing, code generation, or knowledge bases.\n\nThe jsonl format file can be referenced at https://github.com/Abel2076/json2binidx_tool/blob/main/sample.jsonl.\nYou can also write it similar to OpenAI's playground format, as shown in https://platform.openai.com/playground/p/default-chat.\nEven for multi-turn conversations, they must be written in a single line using `\\n` to indicate line breaks. If they are different dialogues or topics, they should be written in separate lines.": "数据路径必须是一个文件夹，或者jsonl格式文件 (未来会支持更多格式)\n\n当你填写的路径是一个文件夹时，该文件夹内的所有txt文件会被自动转换为训练数据，通常这用于大批量训练写作，代码生成或知识库\n\njsonl文件的格式参考 https://github.com/Abel2076/json2binidx_tool/blob/main/sample.jsonl\n你也可以仿照openai的playground编写，参考 https://platform.openai.com/playground/p/default-chat\n即使是多轮对话也必须写在一行，用`\\n`表示换行，如果是不同对话或主题，则另起一行" + "The data path should be a directory or a file in jsonl format (more formats will be supported in the future).\n\nWhen you provide a directory path, all the txt files within that directory will be automatically converted into training data. This is commonly used for large-scale training in writing, code generation, or knowledge bases.\n\nThe jsonl format file can be referenced at https://github.com/Abel2076/json2binidx_tool/blob/main/sample.jsonl.\nYou can also write it similar to OpenAI's playground format, as shown in https://platform.openai.com/playground/p/default-chat.\nEven for multi-turn conversations, they must be written in a single line using `\\n` to indicate line breaks. If they are different dialogues or topics, they should be written in separate lines.": "数据路径必须是一个文件夹，或者jsonl格式文件 (未来会支持更多格式)\n\n当你填写的路径是一个文件夹时，该文件夹内的所有txt文件会被自动转换为训练数据，通常这用于大批量训练写作，代码生成或知识库\n\njsonl文件的格式参考 https://github.com/Abel2076/json2binidx_tool/blob/main/sample.jsonl\n你也可以仿照openai的playground编写，参考 https://platform.openai.com/playground/p/default-chat\n即使是多轮对话也必须写在一行，用`\\n`表示换行，如果是不同对话或主题，则另起一行", + "Size mismatch for blocks. You are attempting to continue training from the LoRA model, but it does not match the base model. Please set LoRA model to None.": "尺寸不匹配块。你正在尝试从LoRA模型继续训练，但该LoRA模型与基底模型不匹配，请将LoRA模型设为空" } \ No newline at end of file diff --git a/frontend/src/pages/Train.tsx b/frontend/src/pages/Train.tsx index c8158a2..9b174ac 100644 --- a/frontend/src/pages/Train.tsx +++ b/frontend/src/pages/Train.tsx @@ -147,17 +147,18 @@ const loraFinetuneParametersOptions: Array<[key: keyof LoraFinetuneParameters, t const showError = (e: any) => { const msg = e.message || e; if (msg === 'wsl not running') { - toast(t('WSL is not running. You may be using an outdated version of WSL, run "wsl --update" to update.'), { type: 'error' }); + toast(t('WSL is not running, please retry. If it keeps happening, it means you may be using an outdated version of WSL, run "wsl --update" to update.'), { type: 'error' }); } else { - toast(t(msg), { type: 'error' }); + toast(t(msg), { type: 'error', toastId: 'train_error' }); } }; const errorsMap = Object.entries({ - 'killed python3 ./finetune/lora/train.py': 'Memory is not enough, try to increase the virtual memory or use a smaller base model.', + 'python3 ./finetune/lora/train.py': 'Memory is not enough, try to increase the virtual memory or use a smaller base model.', 'cuda out of memory': 'VRAM is not enough', 'valueerror: high <= 0': 'Training data is not enough, reduce context length or add more data for training', '+= \'+ptx\'': 'You are using WSL 1 for training, please upgrade to WSL 2. e.g. Run "wsl --set-version Ubuntu-22.04 2"', + 'size mismatch for blocks': 'Size mismatch for blocks. You are attempting to continue training from the LoRA model, but it does not match the base model. Please set LoRA model to None.', 'cuda_home environment variable is not set': 'Matched CUDA is not installed', 'unsupported gpu architecture': 'Matched CUDA is not installed', 'error building extension \'fused_adam\'': 'Matched CUDA is not installed'