Merge pull request #6416 from Zeyi-Lin/main

docs: use swanlab
Former-commit-id: a2ad0738a22f71af453a7f266c350ff7662bf67c
This commit is contained in:
hoshi-hiyouga 2024-12-22 04:08:26 +08:00 committed by GitHub
commit 9d437a5f4f
2 changed files with 41 additions and 2 deletions

View File

@ -54,6 +54,7 @@ Choose your path:
- [Download from ModelScope Hub](#download-from-modelscope-hub) - [Download from ModelScope Hub](#download-from-modelscope-hub)
- [Download from Modelers Hub](#download-from-modelers-hub) - [Download from Modelers Hub](#download-from-modelers-hub)
- [Use W&B Logger](#use-wb-logger) - [Use W&B Logger](#use-wb-logger)
- [Use SwanLab Logger](#use-swanlab-logger)
- [Projects using LLaMA Factory](#projects-using-llama-factory) - [Projects using LLaMA Factory](#projects-using-llama-factory)
- [License](#license) - [License](#license)
- [Citation](#citation) - [Citation](#citation)
@ -66,7 +67,7 @@ Choose your path:
- **Scalable resources**: 16-bit full-tuning, freeze-tuning, LoRA and 2/3/4/5/6/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ. - **Scalable resources**: 16-bit full-tuning, freeze-tuning, LoRA and 2/3/4/5/6/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ.
- **Advanced algorithms**: [GaLore](https://github.com/jiaweizzhao/GaLore), [BAdam](https://github.com/Ledzy/BAdam), [Adam-mini](https://github.com/zyushun/Adam-mini), DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ, PiSSA and Agent tuning. - **Advanced algorithms**: [GaLore](https://github.com/jiaweizzhao/GaLore), [BAdam](https://github.com/Ledzy/BAdam), [Adam-mini](https://github.com/zyushun/Adam-mini), DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ, PiSSA and Agent tuning.
- **Practical tricks**: [FlashAttention-2](https://github.com/Dao-AILab/flash-attention), [Unsloth](https://github.com/unslothai/unsloth), [Liger Kernel](https://github.com/linkedin/Liger-Kernel), RoPE scaling, NEFTune and rsLoRA. - **Practical tricks**: [FlashAttention-2](https://github.com/Dao-AILab/flash-attention), [Unsloth](https://github.com/unslothai/unsloth), [Liger Kernel](https://github.com/linkedin/Liger-Kernel), RoPE scaling, NEFTune and rsLoRA.
- **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, etc. - **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, SwanLab, etc.
- **Faster inference**: OpenAI-style API, Gradio UI and CLI with vLLM worker. - **Faster inference**: OpenAI-style API, Gradio UI and CLI with vLLM worker.
## Benchmark ## Benchmark
@ -86,6 +87,8 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
## Changelog ## Changelog
[24/12/21] We supported **[SwanLab](https://github.com/SwanHubX/SwanLab)** experiment tracking and visualization. See [this section](#use-swanlab-logger) for details.
[24/11/27] We supported fine-tuning the **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** model and the **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** dataset. [24/11/27] We supported fine-tuning the **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** model and the **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** dataset.
[24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)**. See [this tutorial](#download-from-modelers-hub) for usage. [24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)**. See [this tutorial](#download-from-modelers-hub) for usage.
@ -633,6 +636,22 @@ run_name: test_run # optional
Set `WANDB_API_KEY` to [your key](https://wandb.ai/authorize) when launching training tasks to log in with your W&B account. Set `WANDB_API_KEY` to [your key](https://wandb.ai/authorize) when launching training tasks to log in with your W&B account.
### Use SwanLab Logger
To use [SwanLab](https://github.com/SwanHubX/SwanLab) for logging experimental results, you need to add the following arguments to yaml files.
```yaml
use_swanlab: true
swanlab_project: test_project # optional
swanlab_experiment_name: test_experiment # optional
```
When launching training tasks, you can log in to SwanLab in three ways:
1. Add `swanlab_api_key=<your_api_key>` to the yaml file, and set it to your [API key](https://swanlab.cn/settings).
2. Set the environment variable `SWANLAB_API_KEY` to your [API key](https://swanlab.cn/settings).
3. Use the `swanlab login` command to complete the login.
## Projects using LLaMA Factory ## Projects using LLaMA Factory
If you have a project that should be incorporated, please contact via email or create a pull request. If you have a project that should be incorporated, please contact via email or create a pull request.

View File

@ -55,6 +55,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- [从魔搭社区下载](#从魔搭社区下载) - [从魔搭社区下载](#从魔搭社区下载)
- [从魔乐社区下载](#从魔乐社区下载) - [从魔乐社区下载](#从魔乐社区下载)
- [使用 W&B 面板](#使用-wb-面板) - [使用 W&B 面板](#使用-wb-面板)
- [使用 SwanLab 面板](#使用-swanlab-面板)
- [使用了 LLaMA Factory 的项目](#使用了-llama-factory-的项目) - [使用了 LLaMA Factory 的项目](#使用了-llama-factory-的项目)
- [协议](#协议) - [协议](#协议)
- [引用](#引用) - [引用](#引用)
@ -67,7 +68,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- **多种精度**16 比特全参数微调、冻结微调、LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ 的 2/3/4/5/6/8 比特 QLoRA 微调。 - **多种精度**16 比特全参数微调、冻结微调、LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ 的 2/3/4/5/6/8 比特 QLoRA 微调。
- **先进算法**[GaLore](https://github.com/jiaweizzhao/GaLore)、[BAdam](https://github.com/Ledzy/BAdam)、[Adam-mini](https://github.com/zyushun/Adam-mini)、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。 - **先进算法**[GaLore](https://github.com/jiaweizzhao/GaLore)、[BAdam](https://github.com/Ledzy/BAdam)、[Adam-mini](https://github.com/zyushun/Adam-mini)、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
- **实用技巧**[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)、[Unsloth](https://github.com/unslothai/unsloth)、[Liger Kernel](https://github.com/linkedin/Liger-Kernel)、RoPE scaling、NEFTune 和 rsLoRA。 - **实用技巧**[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)、[Unsloth](https://github.com/unslothai/unsloth)、[Liger Kernel](https://github.com/linkedin/Liger-Kernel)、RoPE scaling、NEFTune 和 rsLoRA。
- **实验监控**LlamaBoard、TensorBoard、Wandb、MLflow 等等。 - **实验监控**LlamaBoard、TensorBoard、Wandb、MLflow、SwanLab 等等。
- **极速推理**:基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。 - **极速推理**:基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。
## 性能指标 ## 性能指标
@ -87,6 +88,8 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 更新日志 ## 更新日志
[24/12/21] 我们支持了 **[SwanLab](https://github.com/SwanHubX/SwanLab)** 跟踪与可视化实验。详细用法请参考 [此部分](#使用-wb-面板)。
[24/11/27] 我们支持了 **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** 模型的微调和 **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** 数据集。 [24/11/27] 我们支持了 **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** 模型的微调和 **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** 数据集。
[24/10/09] 我们支持了从 **[魔乐社区](https://modelers.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔乐社区下载)。 [24/10/09] 我们支持了从 **[魔乐社区](https://modelers.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔乐社区下载)。
@ -634,6 +637,23 @@ run_name: test_run # 可选
在启动训练任务时,将 `WANDB_API_KEY` 设置为[密钥](https://wandb.ai/authorize)来登录 W&B 账户。 在启动训练任务时,将 `WANDB_API_KEY` 设置为[密钥](https://wandb.ai/authorize)来登录 W&B 账户。
### 使用 SwanLab 面板
若要使用 [SwanLab](https://github.com/SwanHubX/SwanLab) 记录实验数据,请在 yaml 文件中添加下面的参数。
```yaml
use_swanlab: true
swanlab_project: test_run # 可选
swanlab_experiment_name: test_experiment # 可选
```
在启动训练任务时登录SwanLab账户有以下三种方式
方式一:在 yaml 文件中添加 `swanlab_api_key=<your_api_key>` ,并设置为你的 [API 密钥](https://swanlab.cn/settings)。
方式二:将环境变量 `SWANLAB_API_KEY` 设置为你的 [API 密钥](https://swanlab.cn/settings)。
方式三:启动前使用 `swanlab login` 命令完成登录。
## 使用了 LLaMA Factory 的项目 ## 使用了 LLaMA Factory 的项目
如果您有项目希望添加至下述列表,请通过邮件联系或者创建一个 PR。 如果您有项目希望添加至下述列表,请通过邮件联系或者创建一个 PR。