Downloads · 30 days
9
27% of all-time downloads
roberta-fine-tuned-matching
Kenazin/roberta-fine-tuned-matching
roberta-fine-tuned-matching is a text classification model from Kenazin. 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
33
Public
Parameters
125M
499 MB 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
- May 31, 2025
- Updated
- May 31, 2025
- SHA
- 98738ac9
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-fine-tuned-matching
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2517
- Precision: 0.8397
- Recall: 0.7625
- F1: 0.7992
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: 1e-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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.3947 | 1.0 | 185 | 0.2860 | 0.6930 | 0.6054 | 0.6462 |
| 0.2495 | 2.0 | 370 | 0.2216 | 0.7435 | 0.7663 | 0.7547 |
| 0.1964 | 3.0 | 555 | 0.2044 | 0.7535 | 0.8199 | 0.7853 |
| 0.1765 | 4.0 | 740 | 0.2202 | 0.7035 | 0.8544 | 0.7716 |
| 0.1534 | 5.0 | 925 | 0.2108 | 0.7838 | 0.7778 | 0.7808 |
| 0.1393 | 6.0 | 1110 | 0.2330 | 0.8945 | 0.6820 | 0.7739 |
| 0.1319 | 7.0 | 1295 | 0.2449 | 0.8670 | 0.7241 | 0.7891 |
| 0.1265 | 8.0 | 1480 | 0.2384 | 0.8245 | 0.7739 | 0.7984 |
| 0.1136 | 9.0 | 1665 | 0.2475 | 0.8571 | 0.7356 | 0.7918 |
| 0.1096 | 10.0 | 1850 | 0.2517 | 0.8397 | 0.7625 | 0.7992 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- May 31, 2025
- Updated
- May 31, 2025