Downloads · 30 days
9
13% of all-time downloads
CoLA-FULL_FT-seed30
ekiprop/CoLA-FULL_FT-seed30
CoLA-FULL_FT-seed30 is a text classification model from ekiprop. 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
71
Public
Parameters
125M
5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- c28da866
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. -->
CoLA-FULL_FT-seed30
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4883
- Matthews Correlation: 0.6172
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: 3e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6042 | 0.1866 | 50 | 0.5721 | 0.0 |
| 0.5157 | 0.3731 | 100 | 0.4540 | 0.5097 |
| 0.4776 | 0.5597 | 150 | 0.6128 | 0.4475 |
| 0.4732 | 0.7463 | 200 | 0.4663 | 0.5297 |
| 0.4234 | 0.9328 | 250 | 0.5003 | 0.4995 |
| 0.3765 | 1.1194 | 300 | 0.4617 | 0.5378 |
| 0.3225 | 1.3060 | 350 | 0.5067 | 0.5625 |
| 0.3332 | 1.4925 | 400 | 0.5007 | 0.5648 |
| 0.3557 | 1.6791 | 450 | 0.4567 | 0.5761 |
| 0.301 | 1.8657 | 500 | 0.5245 | 0.5364 |
| 0.2855 | 2.0522 | 550 | 0.5302 | 0.5855 |
| 0.205 | 2.2388 | 600 | 0.5080 | 0.5956 |
| 0.2372 | 2.4254 | 650 | 0.4994 | 0.5855 |
| 0.2296 | 2.6119 | 700 | 0.5107 | 0.5765 |
| 0.199 | 2.7985 | 750 | 0.4883 | 0.6172 |
| 0.2162 | 2.9851 | 800 | 0.5423 | 0.5778 |
| 0.1542 | 3.1716 | 850 | 0.5744 | 0.5976 |
| 0.1538 | 3.3582 | 900 | 0.5566 | 0.6084 |
| 0.14 | 3.5448 | 950 | 0.7562 | 0.5397 |
| 0.1296 | 3.7313 | 1000 | 0.6510 | 0.5729 |
| 0.1385 | 3.9179 | 1050 | 0.6278 | 0.5897 |
| 0.1096 | 4.1045 | 1100 | 0.7611 | 0.5630 |
| 0.0852 | 4.2910 | 1150 | 0.8521 | 0.5804 |
| 0.0942 | 4.4776 | 1200 | 0.8242 | 0.5779 |
| 0.0964 | 4.6642 | 1250 | 0.7841 | 0.5965 |
| 0.0855 | 4.8507 | 1300 | 0.8435 | 0.5831 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.5.1+cu121
- Datasets 4.0.0
- Tokenizers 0.21.4
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025