Hugging Face's logo

AIWizards
/
MultiPRIDE-LGBT-Pretrain-es

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
 Community
Luca Tedeschini commited on
Commit
e341124
·
verified ·
1 Parent(s): 09da49b

MultiPRIDE-LGBT-Pretrain-es

Browse files
Files changed (3) hide show
  1. README.md +11 -14
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-hate-spanish](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-hate-spanish) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.7451
24
- - Accuracy: 0.8182
25
- - F1: 0.8481
26
- - Precision: 0.8375
27
- - Recall: 0.8590
28
 
29
  ## Model description
30
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
  - train_batch_size: 8
48
  - eval_batch_size: 8
49
- - seed: 42
50
  - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
  - num_epochs: 10
@@ -55,14 +55,11 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
- | 0.7172 | 1.0 | 77 | 0.5342 | 0.7576 | 0.8118 | 0.75 | 0.8846 |
59
- | 0.53 | 2.0 | 154 | 0.5837 | 0.7652 | 0.8268 | 0.7327 | 0.9487 |
60
- | 0.5941 | 3.0 | 231 | 0.7575 | 0.6742 | 0.7817 | 0.6471 | 0.9872 |
61
- | 0.4301 | 4.0 | 308 | 0.5676 | 0.7879 | 0.8272 | 0.7976 | 0.8590 |
62
- | 0.4044 | 5.0 | 385 | 0.4593 | 0.8333 | 0.8553 | 0.8784 | 0.8333 |
63
- | 0.2799 | 6.0 | 462 | 0.6975 | 0.7879 | 0.8056 | 0.8788 | 0.7436 |
64
- | 0.1835 | 7.0 | 539 | 0.8903 | 0.8030 | 0.8415 | 0.8023 | 0.8846 |
65
- | 0.1452 | 8.0 | 616 | 0.7451 | 0.8182 | 0.8481 | 0.8375 | 0.8590 |
66
 
67
 
68
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-hate-spanish](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-hate-spanish) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.9790
24
+ - Accuracy: 0.75
25
+ - F1: 0.7755
26
+ - Precision: 0.8261
27
+ - Recall: 0.7308
28
 
29
  ## Model description
30
 
 
46
  - learning_rate: 2e-05
47
  - train_batch_size: 8
48
  - eval_batch_size: 8
49
+ - seed: 67
50
  - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
  - num_epochs: 10
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
+ | 0.7062 | 1.0 | 77 | 0.4770 | 0.7803 | 0.8221 | 0.7882 | 0.8590 |
59
+ | 0.5449 | 2.0 | 154 | 0.5837 | 0.7803 | 0.8380 | 0.7426 | 0.9615 |
60
+ | 0.4829 | 3.0 | 231 | 0.6046 | 0.7955 | 0.8323 | 0.8072 | 0.8590 |
61
+ | 0.4257 | 4.0 | 308 | 0.6316 | 0.7727 | 0.7761 | 0.9286 | 0.6667 |
62
+ | 0.2458 | 5.0 | 385 | 0.9790 | 0.75 | 0.7755 | 0.8261 | 0.7308 |
 
 
 
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cec03a9258d85b03cdeb6164bfd930c650905e8ffe3b3871d0b651e583cc11b
3
  size 1112205008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102e96799650b3d19909910da099572db9d67b1be74addc7aea469b76b80e1b1
3
  size 1112205008
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff49139eaaac6077168abaa1e8c1d1f8ebb45d13f4432bc5feff514b5376a30a
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d8c7af822df8646a0fb3e43161ff7fe427f15409d3234cf52141b753d007f3
3
  size 5969