Update README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
27 |
|
28 |
# distilbert-base-uncased-imdb
|
29 |
|
30 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
31 |
It achieves the following results on the evaluation set:
|
32 |
- Loss: 0.6252
|
33 |
- Accuracy: 0.9214
|
@@ -38,11 +38,11 @@ More information needed
|
|
38 |
|
39 |
## Intended uses & limitations
|
40 |
|
41 |
-
|
42 |
|
43 |
## Training and evaluation data
|
44 |
|
45 |
-
|
46 |
|
47 |
## Training procedure
|
48 |
|
|
|
27 |
|
28 |
# distilbert-base-uncased-imdb
|
29 |
|
30 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an imdb dataset where an evaluation of 5000 samples was created by splitting the training set.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
- Loss: 0.6252
|
33 |
- Accuracy: 0.9214
|
|
|
38 |
|
39 |
## Intended uses & limitations
|
40 |
|
41 |
+
This model was trained for the introduction to Natural language processing course of [EPITA](https://www.epita.fr/).
|
42 |
|
43 |
## Training and evaluation data
|
44 |
|
45 |
+
The training/evaluation split was generated using a `seed` of 42 and a `test_size` of 0.2.
|
46 |
|
47 |
## Training procedure
|
48 |
|