added README.md
Browse files
README.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- sst2
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
library_name: transformers
|
10 |
+
pipeline_tag: text-classification
|
11 |
+
---
|
12 |
+
|
13 |
+
# bert-base-uncased-finetuned-sst2-v2
|
14 |
+
|
15 |
+
"bert-base-uncased" finetuned on SST-2.
|
16 |
+
|
17 |
+
This model pertains to the "Try it out!" exercise in section 4 of chapter 3 of the Hugging Face "NLP Course" (https://huggingface.co/learn/nlp-course/chapter3/4).
|
18 |
+
|
19 |
+
It was trained using a custom PyTorch loop without Hugging Face Accelerate.
|
20 |
+
|
21 |
+
Code: https://github.com/sambitmukherjee/hf-nlp-course-exercises/blob/main/chapter3/section4.ipynb
|
22 |
+
|
23 |
+
Experiment tracking: https://wandb.ai/sadhaklal/bert-base-uncased-finetuned-sst2-v2
|
24 |
+
|
25 |
+
## Metric
|
26 |
+
|
27 |
+
Accuracy on the `'validation'` split of SST-2: 0.9278
|