Downloads · 30 days
21
1% of all-time downloads
roberta-base-finetuned-jigsaw-toxic
affahrizain/roberta-base-finetuned-jigsaw-toxic
roberta-base-finetuned-jigsaw-toxic is a text classification model from affahrizain. 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
1.5K
Public
Repo size
2.5 GB
Likes
1
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
- Jul 29, 2022
- Updated
- Sep 23, 2022
- SHA
- ead426bc
Try a prompt
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. -->
roberta-base-finetuned-jigsaw-toxic
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0859
- Accuracy: 0.9747
- F1: 0.9746
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.1179 | 1.0 | 2116 | 0.0982 | 0.9694 | 0.9694 |
| 0.0748 | 2.0 | 4232 | 0.0859 | 0.9747 | 0.9746 |
| 0.0582 | 3.0 | 6348 | 0.0916 | 0.9750 | 0.9750 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Jul 29, 2022
- Updated
- Sep 23, 2022