Hugging Face's logo

annahaz
/
xlm-roberta-base-finetuned-misogyny-sexism

Text Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
2
annahaz commited on
Commit
93e1a9a
•
1 Parent(s): b9911ad

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.0211
23
- - Accuracy: 0.9949
24
- - F1: 0.9948
25
- - Precision: 0.9906
26
- - Recall: 0.9989
27
- - Mae: 0.0051
28
 
29
  ## Model description
30
 
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Mae |
57
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
58
- | 0.3841 | 1.0 | 2778 | 0.4443 | 0.8027 | 0.7919 | 0.8030 | 0.7811 | 0.1973 |
59
- | 0.334 | 2.0 | 5556 | 0.4946 | 0.8058 | 0.8272 | 0.7225 | 0.9674 | 0.1942 |
60
- | 0.2995 | 3.0 | 8334 | 0.2693 | 0.8912 | 0.8951 | 0.8344 | 0.9653 | 0.1088 |
61
- | 0.2675 | 4.0 | 11112 | 0.2575 | 0.9145 | 0.9168 | 0.8612 | 0.98 | 0.0855 |
62
- | 0.2263 | 5.0 | 13890 | 0.1100 | 0.9611 | 0.9598 | 0.9514 | 0.9684 | 0.0389 |
63
- | 0.2089 | 6.0 | 16668 | 0.0999 | 0.9712 | 0.9706 | 0.9524 | 0.9895 | 0.0288 |
64
- | 0.1871 | 7.0 | 19446 | 0.0644 | 0.9782 | 0.9774 | 0.9769 | 0.9779 | 0.0218 |
65
- | 0.1795 | 8.0 | 22224 | 0.0264 | 0.9924 | 0.9922 | 0.9865 | 0.9979 | 0.0076 |
66
- | 0.144 | 9.0 | 25002 | 0.0231 | 0.9924 | 0.9922 | 0.9855 | 0.9989 | 0.0076 |
67
- | 0.1296 | 10.0 | 27780 | 0.0211 | 0.9949 | 0.9948 | 0.9906 | 0.9989 | 0.0051 |
68
 
69
 
70
  ### Framework versions
71
 
72
  - Transformers 4.20.1
73
- - Pytorch 1.9.0+cu111
74
  - Datasets 2.3.2
75
  - Tokenizers 0.12.1
 
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: 0.9064
23
+ - Accuracy: 0.8334
24
+ - F1: 0.3322
25
+ - Precision: 0.2498
26
+ - Recall: 0.4961
27
+ - Mae: 0.1666
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Mae |
57
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
58
+ | 0.3869 | 1.0 | 2395 | 0.2905 | 0.8778 | 0.3528 | 0.3164 | 0.3988 | 0.1222 |
59
+ | 0.3539 | 2.0 | 4790 | 0.4143 | 0.8278 | 0.3465 | 0.2536 | 0.5467 | 0.1722 |
60
+ | 0.3124 | 3.0 | 7185 | 0.3327 | 0.8568 | 0.3583 | 0.2864 | 0.4786 | 0.1432 |
61
+ | 0.2817 | 4.0 | 9580 | 0.5621 | 0.7329 | 0.3092 | 0.1972 | 0.7160 | 0.2671 |
62
+ | 0.2651 | 5.0 | 11975 | 0.4376 | 0.8520 | 0.3607 | 0.2821 | 0.5 | 0.1480 |
63
+ | 0.2249 | 6.0 | 14370 | 0.5581 | 0.8326 | 0.3312 | 0.2485 | 0.4961 | 0.1674 |
64
+ | 0.1958 | 7.0 | 16765 | 0.6728 | 0.8382 | 0.3234 | 0.2484 | 0.4630 | 0.1618 |
65
+ | 0.1899 | 8.0 | 19160 | 0.7404 | 0.8304 | 0.3316 | 0.2471 | 0.5039 | 0.1696 |
66
+ | 0.1619 | 9.0 | 21555 | 0.8309 | 0.8461 | 0.3382 | 0.2639 | 0.4708 | 0.1539 |
67
+ | 0.1453 | 10.0 | 23950 | 0.9064 | 0.8334 | 0.3322 | 0.2498 | 0.4961 | 0.1666 |
68
 
69
 
70
  ### Framework versions
71
 
72
  - Transformers 4.20.1
73
+ - Pytorch 1.12.0+cu102
74
  - Datasets 2.3.2
75
  - Tokenizers 0.12.1