Hugging Face's logo

AIWizards
/
MultiPRIDE-LGBT-Pretrain-es

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
 Community
lucatedeschini commited on
Commit
a101f05
·
verified ·
1 Parent(s): 2c4e5e8

MultiPRIDE-LGBT-Pretrain-es

Browse files
Files changed (3) hide show
  1. README.md +15 -16
  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: 0.9596
24
- - Accuracy: 0.8258
25
- - F1: 0.8553
26
- - Precision: 0.8395
27
- - Recall: 0.8718
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: 150
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
@@ -55,16 +55,15 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
- | 0.6373 | 1.0 | 77 | 0.6966 | 0.6894 | 0.6772 | 0.8776 | 0.5513 |
59
- | 0.501 | 2.0 | 154 | 0.5357 | 0.7576 | 0.8095 | 0.7556 | 0.8718 |
60
- | 0.4767 | 3.0 | 231 | 0.5615 | 0.7727 | 0.7945 | 0.8529 | 0.7436 |
61
- | 0.3971 | 4.0 | 308 | 0.5905 | 0.8030 | 0.8194 | 0.8939 | 0.7564 |
62
- | 0.1834 | 5.0 | 385 | 0.5565 | 0.8333 | 0.8590 | 0.8590 | 0.8590 |
63
- | 0.247 | 6.0 | 462 | 0.7815 | 0.8182 | 0.8442 | 0.8553 | 0.8333 |
64
- | 0.2188 | 7.0 | 539 | 0.9196 | 0.8182 | 0.8481 | 0.8375 | 0.8590 |
65
- | 0.0572 | 8.0 | 616 | 1.0110 | 0.8409 | 0.8712 | 0.8353 | 0.9103 |
66
- | 0.0413 | 9.0 | 693 | 1.0312 | 0.8182 | 0.8519 | 0.8214 | 0.8846 |
67
- | 0.0276 | 10.0 | 770 | 0.9596 | 0.8258 | 0.8553 | 0.8395 | 0.8718 |
68
 
69
 
70
  ### 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: 1.4954
24
+ - Accuracy: 0.7652
25
+ - F1: 0.7862
26
+ - Precision: 0.8507
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: 1337
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
+ | 0.6914 | 1.0 | 77 | 0.6991 | 0.75 | 0.7898 | 0.7848 | 0.7949 |
59
+ | 0.495 | 2.0 | 154 | 0.5171 | 0.75 | 0.7898 | 0.7848 | 0.7949 |
60
+ | 0.3892 | 3.0 | 231 | 0.8120 | 0.7348 | 0.7482 | 0.8525 | 0.6667 |
61
+ | 0.2307 | 4.0 | 308 | 1.1109 | 0.7803 | 0.8079 | 0.8356 | 0.7821 |
62
+ | 0.2412 | 5.0 | 385 | 1.3397 | 0.7121 | 0.7246 | 0.8333 | 0.6410 |
63
+ | 0.1925 | 6.0 | 462 | 1.3379 | 0.7955 | 0.8402 | 0.7802 | 0.9103 |
64
+ | 0.0852 | 7.0 | 539 | 1.3290 | 0.7652 | 0.7891 | 0.8406 | 0.7436 |
65
+ | 0.0014 | 8.0 | 616 | 1.3692 | 0.7727 | 0.7973 | 0.8429 | 0.7564 |
66
+ | 0.028 | 9.0 | 693 | 1.4954 | 0.7652 | 0.7862 | 0.8507 | 0.7308 |
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb967e24b3beca2a54fd23ee74f7fb45059b306325540c5c6edf82bd0ca621f2
3
  size 1112205008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96e72c307c1fb1f688b3fa57904a7965082dcdbadffba5037a612af7a7697c6
3
  size 1112205008
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3b0b46fd2978ea9064d3426527924972ce182a4d2f5e5484cfeca47a0210b97
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2449dec20476f5e9edf9391337915e9c938784214ab1db5b6068df544c0054
3
  size 5969