Downloads · 30 days
4
2% of all-time downloads
twitter-roberta-large-hate-latest-abusive-comments-ta
callmesan/twitter-roberta-large-hate-latest-abusive-comments-ta
twitter-roberta-large-hate-latest-abusive-comments-ta is a text classification model from callmesan. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
204
Public
Parameters
355M
35.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Nov 27, 2024
- Updated
- Dec 6, 2024
- SHA
- c340e543
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
twitter-roberta-large-hate-latest-abusive-comments-ta
This model is a fine-tuned version of cardiffnlp/twitter-roberta-large-hate-latest on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8852
- Accuracy: 0.7283
- Precision: 0.5073
- Recall: 0.3724
- F1: 0.3960
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.1012 | 1.0 | 186 | 1.0154 | 0.7177 | 0.3787 | 0.3191 | 0.3198 |
| 0.9155 | 2.0 | 372 | 0.9336 | 0.7204 | 0.4450 | 0.3350 | 0.3497 |
| 0.7858 | 3.0 | 558 | 0.9033 | 0.7419 | 0.4941 | 0.3805 | 0.4130 |
| 0.5357 | 4.0 | 744 | 0.9495 | 0.7245 | 0.4971 | 0.4223 | 0.4381 |
| 0.5788 | 5.0 | 930 | 0.9960 | 0.7083 | 0.4491 | 0.4524 | 0.4408 |
| 0.3806 | 6.0 | 1116 | 1.1853 | 0.7298 | 0.5253 | 0.4417 | 0.4663 |
| 0.2375 | 7.0 | 1302 | 1.3106 | 0.7251 | 0.4946 | 0.4278 | 0.4439 |
| 0.187 | 8.0 | 1488 | 1.4710 | 0.7157 | 0.4674 | 0.4343 | 0.4480 |
| 0.0777 | 9.0 | 1674 | 1.6748 | 0.7110 | 0.4842 | 0.4221 | 0.4442 |
| 0.0589 | 10.0 | 1860 | 1.7426 | 0.7164 | 0.4840 | 0.4431 | 0.4594 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Nov 27, 2024
- Updated
- Dec 6, 2024