update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: xlm-roberta-base-misogyny-sexism-tweets
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# xlm-roberta-base-misogyny-sexism-tweets
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.5009
|
23 |
+
- Accuracy: 0.796
|
24 |
+
- F1: 0.8132
|
25 |
+
- Precision: 0.75
|
26 |
+
- Recall: 0.888
|
27 |
+
- Mae: 0.204
|
28 |
+
- Tn: 352
|
29 |
+
- Fp: 148
|
30 |
+
- Fn: 56
|
31 |
+
- Tp: 444
|
32 |
+
|
33 |
+
## Model description
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Intended uses & limitations
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training and evaluation data
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training procedure
|
46 |
+
|
47 |
+
### Training hyperparameters
|
48 |
+
|
49 |
+
The following hyperparameters were used during training:
|
50 |
+
- learning_rate: 2e-05
|
51 |
+
- train_batch_size: 16
|
52 |
+
- eval_batch_size: 16
|
53 |
+
- seed: 42
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- num_epochs: 4
|
57 |
+
|
58 |
+
### Training results
|
59 |
+
|
60 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Mae | Tn | Fp | Fn | Tp |
|
61 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-----:|:---:|:---:|:--:|:---:|
|
62 |
+
| 0.4947 | 1.0 | 1646 | 0.4683 | 0.765 | 0.7866 | 0.7205 | 0.866 | 0.235 | 332 | 168 | 67 | 433 |
|
63 |
+
| 0.4285 | 2.0 | 3292 | 0.4514 | 0.779 | 0.8004 | 0.7298 | 0.886 | 0.221 | 336 | 164 | 57 | 443 |
|
64 |
+
| 0.3721 | 3.0 | 4938 | 0.4430 | 0.781 | 0.8060 | 0.7234 | 0.91 | 0.219 | 326 | 174 | 45 | 455 |
|
65 |
+
| 0.3127 | 4.0 | 6584 | 0.5009 | 0.796 | 0.8132 | 0.75 | 0.888 | 0.204 | 352 | 148 | 56 | 444 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.20.1
|
71 |
+
- Pytorch 1.12.0+cu102
|
72 |
+
- Datasets 2.3.2
|
73 |
+
- Tokenizers 0.12.1
|