Update README.md
Browse files
README.md
CHANGED
|
@@ -7,12 +7,11 @@ model-index:
|
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
| 11 |
-
probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.4221
|
| 18 |
- Train Accuracy: 0.8025
|
|
@@ -20,18 +19,6 @@ It achieves the following results on the evaluation set:
|
|
| 20 |
- Validation Accuracy: 0.8094
|
| 21 |
- Epoch: 2
|
| 22 |
|
| 23 |
-
## Model description
|
| 24 |
-
|
| 25 |
-
More information needed
|
| 26 |
-
|
| 27 |
-
## Intended uses & limitations
|
| 28 |
-
|
| 29 |
-
More information needed
|
| 30 |
-
|
| 31 |
-
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
More information needed
|
| 34 |
-
|
| 35 |
## Training procedure
|
| 36 |
|
| 37 |
### Training hyperparameters
|
|
@@ -54,4 +41,4 @@ The following hyperparameters were used during training:
|
|
| 54 |
- Transformers 4.21.1
|
| 55 |
- TensorFlow 2.8.2
|
| 56 |
- Datasets 2.2.2
|
| 57 |
-
- Tokenizers 0.12.1
|
|
|
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# KIZervus
|
|
|
|
| 11 |
|
| 12 |
+
This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased).
|
| 13 |
+
It is trained to classify german text into the classes "vulgar" speech and "non-vulgar" speech.
|
| 14 |
+
The data set is a collection of other labeled sources in german. For an overview, see the github repository here:
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
- Train Loss: 0.4221
|
| 17 |
- Train Accuracy: 0.8025
|
|
|
|
| 19 |
- Validation Accuracy: 0.8094
|
| 20 |
- Epoch: 2
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Training procedure
|
| 23 |
|
| 24 |
### Training hyperparameters
|
|
|
|
| 41 |
- Transformers 4.21.1
|
| 42 |
- TensorFlow 2.8.2
|
| 43 |
- Datasets 2.2.2
|
| 44 |
+
- Tokenizers 0.12.1
|