Skip to content

Update time estimation in README #23

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
garrett4wade merged 24 commits into from
Apr 2, 2025
Merged

Update time estimation in README #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
a00268f
fix: `self.tasks_ids` should also be filtered
Mar 29, 2025
d103743
PullRequest: 67 Update v0.2.0 Dockerfile
garrett4wade Mar 30, 2025
4e72b05
PullRequest: 66 Update v0.2.0 cover letter
garrett4wade Mar 30, 2025
cbbadfb
Merge branch 'main' of https://code.alipay.com/inclusionAI/AReaL
garrett4wade Mar 30, 2025
44064b1
upload 7B zero and 32B sft config
JacksonMei Mar 29, 2025
bfd79fd
Merge branch 'main' of github.com:inclusionAI/AReaL
garrett4wade Mar 31, 2025
1c5b4c9
PullRequest: 71 upload 7B zero and 32B sft quickstart config
JacksonMei Mar 31, 2025
bf686f0
Merge branch 'main' of https://code.alipay.com/inclusionAI/AReaL
garrett4wade Mar 31, 2025
c0090aa
clean ci
garrett4wade Mar 31, 2025
b2a536f
PullRequest: 69 fix: `self.tasks_ids` should also be filtered
Mar 31, 2025
1c289ca
PullRequest: 72 change the condition of using etcd
garrett4wade Mar 31, 2025
141c5d7
PullRequest: 60 Change the default SGLang parameters to avoid precisi…
garrett4wade Mar 31, 2025
d1fa8f9
PullRequest: 73 Fix a setup issue when using ETCD
garrett4wade Mar 31, 2025
93bae42
Merge branch 'main' of https://code.alipay.com/inclusionAI/AReaL
garrett4wade Mar 31, 2025
ec93b64
PullRequest: 75 Fix epoch counter before model function call execution.
garrett4wade Mar 31, 2025
5f0c75d
PullRequest: 76 Update from opensource repository.
Mar 31, 2025
5568822
update readme
Mar 31, 2025
3ec86a4
update readme
Mar 31, 2025
a2d5054
.
garrett4wade Apr 1, 2025
99f7bed
.
garrett4wade Apr 1, 2025
f071b96
.
garrett4wade Apr 1, 2025
bab49d3
PullRequest: 74 update readme
Apr 1, 2025
ef26216
Merge branch 'main' of github.com:inclusionAI/AReaL
garrett4wade Apr 2, 2025
403f0be
Merge branch 'main' of https://code.alipay.com/inclusionAI/AReaL
garrett4wade Apr 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,11 +34,11 @@ Thanks to a series of system-level optimizations, AReaL v0.2 improves its end-to

In the following table, we show the convergence time under different resource settings:

| **Model Size** | **1.5B** | **1.5B** | **1.5B** | **7B** | **7B** | **32B (SFT)** |
| --- | :---: | :---: | :---: | :---: | :---: | :---: |
| #GPU | 8 | 32 | 128 | 32 | 128 | 64 |
| Step | 250 | 250 | 250 | 400 | 400 | 300 |
| Time (h) | ~230 | ~70 | ~25 | ~290 | ~80 | ~3.5 |
| **Model Size** | **1.5B** | **1.5B** | **1.5B** | **7B** | **7B** |**32B (SFT)** |
| --- |:--------:|:--------:|:--------:|:------:|:------:|:-------:|
| #GPU | 8 | 32 | 128 | 32 | 128 | 64 |
| Step | 250 | 250 | 250 | 400 | 400 | 300 |
| Time (h) | ~240 | ~69 | ~27 | ~252 | ~90 | ~3.5 |


#### SOTA 7B model using RL in math reasoning
Expand Down
22 changes: 13 additions & 9 deletions examples/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,19 +5,23 @@
Check if your hardware meets these minimum requirements:


|**Model Size**| **1.5B** |**1.5B**|**1.5B**| **7B** | **7B** |
|---|:---:|:---:|:---:|:---:|:---:|
| **Nodes** | **1** | **4** | **16** | **4** | **16** |
| GPU | 8x H800 |8x H800 per node| 8x H800 per node |8x H800 per node| 8x H800 per node |
| CPU | 48 cores |48 cores per node|48 cores per node| 48 cores per node |48 cores per node|
| Memory | 1 TB |1 TB per node|1 TB per node| 1 TB per node |1 TB per node|
| Network | NVSwitch |NVSwitch + RoCE 3.2 Tbps|NVSwitch + RoCE 3.2 Tbps| NVSwitch + RoCE 3.2 Tbps |NVSwitch + RoCE 3.2 Tbps|
| Storage | 1TB |Shared storage (NAS) 10TB|Shared storage (NAS) 10TB| Shared storage (NAS) 10TB |Shared storage (NAS) 10TB|
| **Total Time (Hours)** | **230** | **70** | **25** | **290** | **80** |
|**Model Size**| **1.5B** |**1.5B**|**1.5B**| **7B** | **7B** | **32B** |
|---|:---:|:---:|:---:|:-------------------------:|:---:|:---:|
| **Nodes** | **1** | **4** | **16** | **4** | **16** | **16** |
| GPU | 8x H800 |8x H800 per node| 8x H800 per node | 8x H800 per node | 8x H800 per node | 8x H800 per node |
| CPU | 48 cores |48 cores per node|48 cores per node| 48 cores per node | 48 cores per node| 48 cores per node|
| Memory | 1 TB |1 TB per node|1 TB per node| 1 TB per node | 1 TB per node| 1 TB per node|
| Network | NVSwitch |NVSwitch + RoCE 3.2 Tbps|NVSwitch + RoCE 3.2 Tbps| NVSwitch + RoCE 3.2 Tbps | NVSwitch + RoCE 3.2 Tbps| NVSwitch + RoCE 3.2 Tbps|
| Storage | 1TB |Shared storage (NAS) 10TB|Shared storage (NAS) 10TB| Shared storage (NAS) 10TB |Shared storage (NAS) 10TB| Shared storage (NAS) 10TB|
| BatchSize x GroupSize | 512x16 | 512x16 | 512x16 | 512x16 | 512x16 | 512x32|
| **Single-step Time (seconds)** | **3461** | **997** | **391** | **2275** | **815** | **6707**|
| **#Steps Until Convergence** | **~250** |**~250** |**~250** |**~400** |**~400** | - |
| **Total Time (Hours)** | **~240** | **~69** | **~27** | **~252** | **~90** | - |

Notes:
- GPUs need to have 80GB memory. Other GPU models with similar specs are acceptable.
- Single-node training can use local storage, but multi-node training requires shared storage.
- We haven't successfully train a powerful 32B model, so we cannot estimate the required steps and time.

## Software Requirements
This tutorial provides a Docker image. Below are the tested software versions:
Expand Down
23 changes: 13 additions & 10 deletions examples/README_zh.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,23 +6,26 @@

为了能正常完成训练流程，请参照下表确认你的硬件是否满足要求：

|**模型大小**| **1.5B** | **1.5B** |**1.5B** |**7B** |**7B** |
|---|---|---|---|---|---|
| 节点 | 1 | 4 | 16 | 4 | 16 |
| GPU | 8 张 H800 | 每节点 8 张 H800 |每节点 8 张 H800 |每节点 8 张 H800 |每节点 8 张 H800 |
| CPU | 48 核 | 每节点 48 核 |每节点 48 核 |每节点 48 核 |每节点 48 核 |
| 内存 | 1 TB |每节点 1 TB|每节点 1 TB |每节点 1 TB |每节点 1 TB |
| 通信 | NVSwitch |NVSwitch+RoCE 带宽 3.2 Tbps|NVSwitch+RoCE 带宽 3.2 Tbps|NVSwitch+RoCE 带宽 3.2 Tbps|NVSwitch+RoCE 带宽 3.2 Tbps|
| 存储 | 1TB |共享存储（NAS）10TB |共享存储（NAS）10TB |共享存储（NAS）10TB |共享存储（NAS）10TB |
|总训练时间（小时）| **230** | **70** | **25** | **290** | **80** |
| **模型大小** | **1.5B** | **1.5B** |**1.5B** | **7B** |**7B** | **32B** |
|---------------------|---|---|---|---------------------------|---|---|
| 节点 | 1 | 4 | 16 | 4 | 16 | 16 |
| GPU | 8 张 H800 | 每节点 8 张 H800 |每节点 8 张 H800 | 每节点 8 张 H800 |每节点 8 张 H800 |每节点 8 张 H800 |
| CPU | 48 核 | 每节点 48 核 |每节点 48 核 | 每节点 48 核 |每节点 48 核 | 每节点 48 核 |
| 内存 | 1 TB |每节点 1 TB|每节点 1 TB | 每节点 1 TB |每节点 1 TB | 每节点 1 TB |
| 通信 | NVSwitch |NVSwitch+RoCE 带宽 3.2 Tbps|NVSwitch+RoCE 带宽 3.2 Tbps| NVSwitch+RoCE 带宽 3.2 Tbps |NVSwitch+RoCE 带宽 3.2 Tbps| NVSwitch+RoCE 带宽 3.2 Tbps|
| 存储 | 1TB |共享存储（NAS）10TB |共享存储（NAS）10TB | 共享存储（NAS）10TB |共享存储（NAS）10TB | 共享存储（NAS）10TB |
| BatchSize x GroupSize | 512x16 | 512x16 | 512x16 | 512x16 | 512x16 | 512x32|
| 单步训练时间（秒） | **3461** | **997** | **391** | **2275** | **815** | **6707**|
| 训练至收敛需要步数 | **~250** |**~250** |**~250** |**~400** |**~400** | - |
| 总训练时间（小时） | **~240** | **~69** | **~27** | **~252** | **~90** | - |

关于硬件要求的说明：

- GPU 需要 80GB 显存，可以选择同级别其他 GPU 型号。

- 单节点训练时可以使用本地存储，但多节点训练必须要提供共享存储，否则无法进行训练。

- 所有训练均采用 16K 的 Context Length
- 目前32B模型没有训练出有意义的结果，所以无法估计训练到收敛需要的步数和时间。


## 软件要求
Expand Down