Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ pipeline_tag: text-generation
|
|
| 17 |
|
| 18 |
## Overview
|
| 19 |
This model is a reproduction of the [agentica-project/deepscaler](https://github.com/agentica-project/deepscaler) project.
|
| 20 |
-
We have reproduced the results in the repo on an **8x80G** node, achieving an average score of **
|
| 21 |
|
| 22 |
|
| 23 |
## Training
|
|
@@ -48,7 +48,7 @@ nohup bash run_deepscaler_1.5b_24k.sh --model $MODEL_PATH > stage3.log 2>&1 &
|
|
| 48 |
| Still-1.5B | 32.5 | 84.4 | 66.7 | 29.0 | 45.4 | 51.6 |
|
| 49 |
| DeepScaleR-1.5B-Preview | 43.1 |87.8 |73.6 | 30.2 |50.0 |57.0 |
|
| 50 |
| [DeepScaleR-1.5B-Preview-Reproduce](https://huggingface.co/junnyu/DeepScaleR-1.5B-Preview-Reproduce) | 40.4 |87.9 | 72.0 | 31.5 | 50.2 |56.4|
|
| 51 |
-
| <strong>🎉 DeepScaleR-1.5B-Preview-Reproduce</strong> | 42.3 |88.0 | 73.2 |
|
| 52 |
| O1-Preview | 40.0 | 81.4 | - | - | - | - |
|
| 53 |
|
| 54 |
|
|
|
|
| 17 |
|
| 18 |
## Overview
|
| 19 |
This model is a reproduction of the [agentica-project/deepscaler](https://github.com/agentica-project/deepscaler) project.
|
| 20 |
+
We have reproduced the results in the repo on an **8x80G** node, achieving an average score of **56.7**.
|
| 21 |
|
| 22 |
|
| 23 |
## Training
|
|
|
|
| 48 |
| Still-1.5B | 32.5 | 84.4 | 66.7 | 29.0 | 45.4 | 51.6 |
|
| 49 |
| DeepScaleR-1.5B-Preview | 43.1 |87.8 |73.6 | 30.2 |50.0 |57.0 |
|
| 50 |
| [DeepScaleR-1.5B-Preview-Reproduce](https://huggingface.co/junnyu/DeepScaleR-1.5B-Preview-Reproduce) | 40.4 |87.9 | 72.0 | 31.5 | 50.2 |56.4|
|
| 51 |
+
| <strong>🎉 DeepScaleR-1.5B-Preview-Reproduce</strong> | 42.3 |88.0 | 73.2 | 30.3 | 49.7 |56.7|
|
| 52 |
| O1-Preview | 40.0 | 81.4 | - | - | - | - |
|
| 53 |
|
| 54 |
|