Hugging Face's logo

AIWizards
/
MultiPRIDE-LGBT-Pretrain-it

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
Community
Luca Tedeschini commited on
Commit
8ae85b6
·
verified ·
1 Parent(s): 9334e0a

MultiPRIDE-LGBT-Pretrain-it

Browse files
Files changed (3) hide show
  1. README.md +14 -11
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [nickprock/setfit-italian-hate-speech](https://huggingface.co/nickprock/setfit-italian-hate-speech) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1991
25
- - Accuracy: 0.7607
26
- - F1: 0.8
27
- - Precision: 0.8125
28
- - Recall: 0.7879
29
 
30
  ## Model description
31
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
47
  - learning_rate: 2e-05
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
- - seed: 85
51
  - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - num_epochs: 10
@@ -56,11 +56,14 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
- | 0.1634 | 1.0 | 95 | 0.1197 | 0.7178 | 0.7653 | 0.7732 | 0.7576 |
60
- | 0.1046 | 2.0 | 190 | 0.1295 | 0.7669 | 0.8137 | 0.7905 | 0.8384 |
61
- | 0.031 | 3.0 | 285 | 0.1493 | 0.7178 | 0.7629 | 0.7789 | 0.7475 |
62
- | 0.0158 | 4.0 | 380 | 0.1701 | 0.7362 | 0.7839 | 0.78 | 0.7879 |
63
- | 0.0021 | 5.0 | 475 | 0.1991 | 0.7607 | 0.8 | 0.8125 | 0.7879 |
 
 
 
64
 
65
 
66
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [nickprock/setfit-italian-hate-speech](https://huggingface.co/nickprock/setfit-italian-hate-speech) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1855
25
+ - Accuracy: 0.7669
26
+ - F1: 0.81
27
+ - Precision: 0.8020
28
+ - Recall: 0.8182
29
 
30
  ## Model description
31
 
 
47
  - learning_rate: 2e-05
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
+ - seed: 150
51
  - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - num_epochs: 10
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 0.1659 | 1.0 | 95 | 0.1178 | 0.6994 | 0.7066 | 0.8676 | 0.5960 |
60
+ | 0.0871 | 2.0 | 190 | 0.1135 | 0.7362 | 0.7650 | 0.8333 | 0.7071 |
61
+ | 0.0356 | 3.0 | 285 | 0.1231 | 0.7178 | 0.7356 | 0.8533 | 0.6465 |
62
+ | 0.007 | 4.0 | 380 | 0.1414 | 0.7546 | 0.8077 | 0.7706 | 0.8485 |
63
+ | 0.0021 | 5.0 | 475 | 0.1829 | 0.7607 | 0.8134 | 0.7727 | 0.8586 |
64
+ | 0.0004 | 6.0 | 570 | 0.1654 | 0.7423 | 0.7879 | 0.7879 | 0.7879 |
65
+ | 0.0001 | 7.0 | 665 | 0.1950 | 0.7546 | 0.8039 | 0.7810 | 0.8283 |
66
+ | 0.0001 | 8.0 | 760 | 0.1855 | 0.7669 | 0.81 | 0.8020 | 0.8182 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2e985e257a9bf70273e9539bc45e392ef2b4808ea8ef241677ccfa6df02ff3b
3
  size 439740408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d40017291dbdec3f93e354b0b09f05a72af1c43aebdf1ab59f302759f8a878
3
  size 439740408
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc7acdb78e0c09238a72ffab4b414f30bc5b0bddbc08722013adb1b34b3c8295
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee34ce42bf5247b444b01f93b5bd5d5dd1d31e4e3a00467be22483431b25757
3
  size 5969