Hugging Face's logo

Pablo94
/
racism-finetuned-detests

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
Pablo94 commited on
Commit
dccde0f
•
1 Parent(s): 744e408

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -18
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,9 +1,12 @@
1
  ---
2
  license: cc
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - accuracy
 
 
7
  model-index:
8
  - name: racism-finetuned-detests
9
  results: []
@@ -16,8 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [davidmasip/racism](https://huggingface.co/davidmasip/racism) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.0150
20
- - Accuracy: 0.8560
 
 
 
 
21
 
22
  ## Model description
23
 
@@ -46,23 +53,23 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | 0.2659 | 1.0 | 153 | 0.3250 | 0.8429 |
52
- | 0.1191 | 2.0 | 306 | 0.5344 | 0.8380 |
53
- | 0.0074 | 3.0 | 459 | 0.8188 | 0.8396 |
54
- | 0.0001 | 4.0 | 612 | 0.9264 | 0.8462 |
55
- | 0.0001 | 5.0 | 765 | 0.9551 | 0.8462 |
56
- | 0.0001 | 6.0 | 918 | 0.9771 | 0.8527 |
57
- | 0.0001 | 7.0 | 1071 | 0.9937 | 0.8527 |
58
- | 0.0001 | 8.0 | 1224 | 1.0054 | 0.8560 |
59
- | 0.0 | 9.0 | 1377 | 1.0126 | 0.8560 |
60
- | 0.0001 | 10.0 | 1530 | 1.0150 | 0.8560 |
61
 
62
 
63
  ### Framework versions
64
 
65
- - Transformers 4.23.1
66
- - Pytorch 1.12.1+cu113
67
- - Datasets 2.6.1
68
- - Tokenizers 0.13.1
 
1
  ---
2
  license: cc
3
+ base_model: davidmasip/racism
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
8
+ - precision
9
+ - recall
10
  model-index:
11
  - name: racism-finetuned-detests
12
  results: []
 
19
 
20
  This model is a fine-tuned version of [davidmasip/racism](https://huggingface.co/davidmasip/racism) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.1626
23
+ - Accuracy: 0.8331
24
+ - F1-score: 0.7625
25
+ - Precision: 0.7625
26
+ - Recall: 0.7625
27
+ - Auc: 0.7625
28
 
29
  ## Model description
30
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.2554 | 1.0 | 174 | 0.3618 | 0.8380 | 0.7340 | 0.7901 | 0.7073 | 0.7073 |
59
+ | 0.0488 | 2.0 | 348 | 0.7445 | 0.8282 | 0.7549 | 0.7556 | 0.7543 | 0.7543 |
60
+ | 0.0005 | 3.0 | 522 | 0.9204 | 0.8429 | 0.7681 | 0.7794 | 0.7587 | 0.7587 |
61
+ | 0.0001 | 4.0 | 696 | 1.0194 | 0.8462 | 0.7741 | 0.7838 | 0.7659 | 0.7659 |
62
+ | 0.0001 | 5.0 | 870 | 1.0721 | 0.8363 | 0.7648 | 0.7676 | 0.7621 | 0.7621 |
63
+ | 0.0001 | 6.0 | 1044 | 1.1081 | 0.8331 | 0.7625 | 0.7625 | 0.7625 | 0.7625 |
64
+ | 0.0 | 7.0 | 1218 | 1.1324 | 0.8331 | 0.7625 | 0.7625 | 0.7625 | 0.7625 |
65
+ | 0.0 | 8.0 | 1392 | 1.1492 | 0.8331 | 0.7625 | 0.7625 | 0.7625 | 0.7625 |
66
+ | 0.0 | 9.0 | 1566 | 1.1592 | 0.8331 | 0.7625 | 0.7625 | 0.7625 | 0.7625 |
67
+ | 0.0 | 10.0 | 1740 | 1.1626 | 0.8331 | 0.7625 | 0.7625 | 0.7625 | 0.7625 |
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.33.1
73
+ - Pytorch 2.0.1+cu118
74
+ - Datasets 2.14.5
75
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bfbc730ad3f3225e992b20a29048c63c1a86190a8228ec6a3f217b303ab555b
3
  size 498648433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cc40dd3d5b8620e2f07b073c1d158c2e98ac74b3310b1e5d805778167db2d4
3
  size 498648433