Commit 9afe07d8 authored by wanglch's avatar wanglch
Browse files

Update README.md

parent f1aa3954
......@@ -200,10 +200,10 @@ python qwen_vl_inference.py
### 精度
测试数据: [assets/mm_tutorial](./assets/mm_tutorial) ,使用的加速卡:V100S/K100。
| device | train_loss |
| :------: | :------: |
| A800 | 1.9149 |
| K100 | 1.9149 |
| device | train_runtime | train_loss | train_samples_per_second |
| :------: | :------: | :------: | :------: |
| A800 | 42.7654 | 1.91875 | 0.436 |
| K100 | 563.5384 | 1.91953125 | 0.027 |
## 应用场景
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment