Downloads · 30 days
10
5% of all-time downloads
twitter-roberta-large-hate-latest-roman-urdu-binary
callmesan/twitter-roberta-large-hate-latest-roman-urdu-binary
twitter-roberta-large-hate-latest-roman-urdu-binary 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
196
Public
Parameters
355M
28.4 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 26, 2024
- Updated
- Dec 6, 2024
- SHA
- afeef292
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-roman-urdu-binary
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: 0.4537
- Accuracy: 0.9016
- Precision: 0.9015
- Recall: 0.9007
- F1: 0.9011
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: 32
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|---|---|---|
| 0.4956 | 0.9912 | 56 | 0.4878 | 0.8215 | 0.8208 | 0.8202 | 0.8205 |
| 0.3268 | 2.0 | 113 | 0.3194 | 0.8652 | 0.8699 | 0.8611 | 0.8632 |
| 0.2555 | 2.9912 | 169 | 0.3241 | 0.8839 | 0.8894 | 0.8798 | 0.8822 |
| 0.1832 | 4.0 | 226 | 0.3184 | 0.8914 | 0.8930 | 0.8891 | 0.8904 |
| 0.1283 | 4.9912 | 282 | 0.3375 | 0.8976 | 0.9028 | 0.8939 | 0.8962 |
| 0.0815 | 6.0 | 339 | 0.3645 | 0.8939 | 0.8937 | 0.8955 | 0.8937 |
| 0.0961 | 6.9912 | 395 | 0.3691 | 0.9001 | 0.9004 | 0.8988 | 0.8995 |
| 0.0544 | 8.0 | 452 | 0.4781 | 0.8901 | 0.8895 | 0.8910 | 0.8899 |
| 0.0404 | 8.9912 | 508 | 0.4209 | 0.9089 | 0.9104 | 0.9068 | 0.9081 |
| 0.0359 | 9.9115 | 560 | 0.4259 | 0.9051 | 0.9051 | 0.9042 | 0.9046 |
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 26, 2024
- Updated
- Dec 6, 2024