Downloads · 30 days
17
2% of all-time downloads
afrisenti-original-scratch_scratch
lazymonster/afrisenti-original-scratch_scratch
afrisenti-original-scratch_scratch is a text classification model from lazymonster. 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
709
Public
Parameters
16.1M
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors64.5 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Dec 1, 2025
- Updated
- Dec 2, 2025
- SHA
- 04628e19
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. -->
afrisenti-original-scratch_scratch
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1224
- Accuracy: 0.6538
- F1 Macro: 0.6547
- Composite Score: 0.6440
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: 32
- seed: 42
- optimizer: Use OptimizerNames.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: 20
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Composite Score |
|---|---|---|---|---|---|---|
| No log | 1.0 | 333 | 1.0857 | 0.3420 | 0.1879 | 0.1606 |
| 1.0906 | 2.0 | 666 | 0.9928 | 0.5313 | 0.5103 | 0.5069 |
| 1.0906 | 3.0 | 999 | 0.9174 | 0.5863 | 0.5833 | 0.5833 |
| 0.9428 | 4.0 | 1332 | 0.9778 | 0.6060 | 0.6026 | 0.6026 |
| 0.7419 | 5.0 | 1665 | 1.0314 | 0.6041 | 0.6012 | 0.6012 |
| 0.7419 | 6.0 | 1998 | 1.0533 | 0.6222 | 0.6229 | 0.6216 |
| 0.6288 | 7.0 | 2331 | 1.0885 | 0.6275 | 0.6295 | 0.6226 |
| 0.5511 | 8.0 | 2664 | 1.0611 | 0.6550 | 0.6563 | 0.6559 |
| 0.5511 | 9.0 | 2997 | 1.0931 | 0.6557 | 0.6554 | 0.6498 |
| 0.4899 | 10.0 | 3330 | 1.1306 | 0.6501 | 0.6492 | 0.6362 |
| 0.4521 | 11.0 | 3663 | 1.1224 | 0.6538 | 0.6547 | 0.6440 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Dec 1, 2025
- Updated
- Dec 2, 2025