Update README.md
Browse files
README.md
CHANGED
@@ -4,6 +4,59 @@ datasets:
|
|
4 |
language:
|
5 |
- nl
|
6 |
metrics:
|
7 |
-
- accuracy
|
|
|
8 |
pipeline_tag: text-classification
|
9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
language:
|
5 |
- nl
|
6 |
metrics:
|
7 |
+
- name: accuracy
|
8 |
+
value:
|
9 |
pipeline_tag: text-classification
|
10 |
+
---
|
11 |
+
# Model Card for Model ID
|
12 |
+
|
13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
14 |
+
This model is a fine-tuned version of (https://huggingface.co/yhavinga/gpt2-medium-dutch) on (https://huggingface.co/datasets/GroNLP/dutch-cola).
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
|
17 |
+
- Loss: 0.519
|
18 |
+
- Accuracy: 0.7613
|
19 |
+
|
20 |
+
|
21 |
+
### Model Description
|
22 |
+
|
23 |
+
<!-- Provide a longer summary of what this model is. -->
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training Details
|
27 |
+
|
28 |
+
### Training Data
|
29 |
+
|
30 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
31 |
+
|
32 |
+
[More Information Needed]
|
33 |
+
|
34 |
+
### Training Procedure
|
35 |
+
|
36 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
37 |
+
|
38 |
+
#### Preprocessing [optional]
|
39 |
+
|
40 |
+
[More Information Needed]
|
41 |
+
|
42 |
+
|
43 |
+
#### Training Hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
|
47 |
+
- learning rate: 4e-05
|
48 |
+
- train_batch_size: 16
|
49 |
+
- eval_batch_size: 16
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: AdamW with lr=4e-05, weight_decay=0.01, betas=(o.9, 0.999) and epsilon=1e-08
|
52 |
+
- num_epochs=3
|
53 |
+
- fp16=True
|
54 |
+
- gradient_acc_step=1
|
55 |
+
|
56 |
+
|
57 |
+
|
58 |
+
## Evaluation
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
[More Information Needed]
|