peler1nl1kelt0s
commited on
Commit
•
c007b55
1
Parent(s):
fc9d969
Update README.md
Browse files
README.md
CHANGED
@@ -18,7 +18,17 @@ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co
|
|
18 |
|
19 |
## Model description
|
20 |
|
21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
|
23 |
## Intended uses & limitations
|
24 |
|
@@ -45,7 +55,6 @@ The following hyperparameters were used during training:
|
|
45 |
### Training results
|
46 |
|
47 |
|
48 |
-
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.44.2
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
21 |
+
This model is fine-tuned for classifying GitHub issues into four categories: New Feature, Improvement, Bug, and Task. The base model used is bert-large-uncased, and it has been trained on an open-source dataset of GitHub issues containing titles and descriptions. This model can efficiently predict the type of issue based on the input of the issue’s title and description.
|
22 |
+
|
23 |
+
### Fine-Tuning Details
|
24 |
+
- Base Model: bert-large-uncased
|
25 |
+
- Fine-Tuning Dataset: GitHub Issues with labels mapped to four categories:
|
26 |
+
- New Feature
|
27 |
+
- Improvement
|
28 |
+
- Bug
|
29 |
+
- Task
|
30 |
+
- Training Framework: Hugging Face Transformers, PyTorch
|
31 |
+
- Training Setup: The model was fine-tuned using a batch size of 64 for a few epochs, with a learning rate of 2e-5.
|
32 |
|
33 |
## Intended uses & limitations
|
34 |
|
|
|
55 |
### Training results
|
56 |
|
57 |
|
|
|
58 |
### Framework versions
|
59 |
|
60 |
- Transformers 4.44.2
|