Downloads · 30 days
8
14% of all-time downloads
roberta-base-hoeken2024hateful-augmented
ysenarath/roberta-base-hoeken2024hateful-augmented
roberta-base-hoeken2024hateful-augmented is a text classification model from ysenarath. 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
56
Public
Parameters
125M
4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Mar 18, 2025
- Updated
- Mar 18, 2025
- SHA
- bbea025b
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. -->
roberta-base-hoeken2024hateful-augmented
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4811
- Accuracy: 0.7886
- Roc Auc: 0.8349
- Precision: 0.8324
- Recall: 0.8011
- F1: 0.8164
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: 96
- eval_batch_size: 128
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Roc Auc | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 164 | 0.6911 | 0.7792 | 0.8379 | 0.7710 | 0.8871 | 0.825 |
| No log | 2.0 | 328 | 0.6279 | 0.7697 | 0.8346 | 0.8122 | 0.7903 | 0.8011 |
| No log | 3.0 | 492 | 0.7865 | 0.7823 | 0.8562 | 0.8 | 0.8387 | 0.8189 |
| 0.1653 | 4.0 | 656 | 0.9262 | 0.7981 | 0.8420 | 0.8177 | 0.8441 | 0.8307 |
| 0.1653 | 5.0 | 820 | 1.0150 | 0.8107 | 0.8453 | 0.8088 | 0.8871 | 0.8462 |
| 0.1653 | 6.0 | 984 | 1.4682 | 0.7571 | 0.8229 | 0.8187 | 0.7527 | 0.7843 |
| 0.0247 | 7.0 | 1148 | 1.4441 | 0.7918 | 0.8358 | 0.8226 | 0.8226 | 0.8226 |
| 0.0247 | 8.0 | 1312 | 1.4811 | 0.7886 | 0.8349 | 0.8324 | 0.8011 | 0.8164 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Mar 18, 2025
- Updated
- Mar 18, 2025