Downloads · 30 days
7
2% of all-time downloads
FakeNews-roberta-base-punct
Denyol/FakeNews-roberta-base-punct
FakeNews-roberta-base-punct is a text classification model from Denyol. 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
286
Public
Repo size
3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Oct 21, 2023
- Updated
- Oct 21, 2023
- SHA
- c114a1e4
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. -->
FakeNews-roberta-base-punct
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3275
- Accuracy: 0.8949
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5092 | 1.0 | 803 | 0.3693 | 0.8855 |
| 0.3593 | 2.0 | 1606 | 0.3815 | 0.8621 |
| 0.3505 | 3.0 | 2409 | 0.4049 | 0.8276 |
| 0.361 | 4.0 | 3212 | 0.4180 | 0.8757 |
| 0.2566 | 5.0 | 4015 | 0.3275 | 0.8949 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Oct 21, 2023
- Updated
- Oct 21, 2023