mvonwyl commited on
Commit
e78f2fa
1 Parent(s): 2eff85b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
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 the imdb dataset.
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
- More information needed
42
 
43
  ## Training and evaluation data
44
 
45
- More information needed
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