Update README.me
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# athrado/bert-finetuned-nli
|
14 |
|
15 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on
|
16 |
It achieves the following results on the evaluation set:
|
17 |
- Train Loss: 0.0671
|
18 |
- Train Accuracy: 0.9806
|
@@ -22,15 +22,16 @@ It achieves the following results on the evaluation set:
|
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
-
|
26 |
|
27 |
## Intended uses & limitations
|
28 |
|
29 |
-
|
|
|
30 |
|
31 |
## Training and evaluation data
|
32 |
|
33 |
-
|
34 |
|
35 |
## Training procedure
|
36 |
|
|
|
12 |
|
13 |
# athrado/bert-finetuned-nli
|
14 |
|
15 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [sick](https://huggingface.co/datasets/sick) dataset for natural language inference.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
- Train Loss: 0.0671
|
18 |
- Train Accuracy: 0.9806
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
+
Example model for educational purposes: fine-tuning the bert-base-uncased model for natural language inference.
|
26 |
|
27 |
## Intended uses & limitations
|
28 |
|
29 |
+
- Learning about transformer model and fine-tuning
|
30 |
+
- Natural language inference fine-tuned on small dataset
|
31 |
|
32 |
## Training and evaluation data
|
33 |
|
34 |
+
The model is evaluated using the sick validation. We report accuracy, and in addition we computed a weighted F1-score of 0.842.
|
35 |
|
36 |
## Training procedure
|
37 |
|