Update README.md
Browse files
README.md
CHANGED
@@ -53,8 +53,7 @@ Output:
|
|
53 |
|
54 |
- [allenai/prosocial-dialog](https://huggingface.co/datasets/allenai/prosocial-dialog).
|
55 |
- A small subset of [OpenChat](https://huggingface.co/togethercomputer/OpenChaT)'s data to augment `casual` queries.
|
56 |
-
|
57 |
-
The processed data can be found [here](https://drive.google.com/file/d/1ui4SuOYXyoq-5gVEC1NXwzJxs3hwaw0Y/view?usp=drivesdk).
|
58 |
|
59 |
**Training Procedure**
|
60 |
|
@@ -63,6 +62,3 @@ The processed data can be found [here](https://drive.google.com/file/d/1ui4SuOYX
|
|
63 |
- **Gradient Accumulations**: 1
|
64 |
- **Batch:** 16 x 4 = 64
|
65 |
- **Learning rate:** warmup to 1e-5 for 100 steps and then kept constant
|
66 |
-
|
67 |
-
## Evaluation Results
|
68 |
-
\[TODO\]
|
|
|
53 |
|
54 |
- [allenai/prosocial-dialog](https://huggingface.co/datasets/allenai/prosocial-dialog).
|
55 |
- A small subset of [OpenChat](https://huggingface.co/togethercomputer/OpenChaT)'s data to augment `casual` queries.
|
56 |
+
- The processed data can be found [here](https://drive.google.com/file/d/1ui4SuOYXyoq-5gVEC1NXwzJxs3hwaw0Y/view?usp=drivesdk).
|
|
|
57 |
|
58 |
**Training Procedure**
|
59 |
|
|
|
62 |
- **Gradient Accumulations**: 1
|
63 |
- **Batch:** 16 x 4 = 64
|
64 |
- **Learning rate:** warmup to 1e-5 for 100 steps and then kept constant
|
|
|
|
|
|