Downloads · 30 days
5
7% of all-time downloads
CoLA-FULL_FT-seed20
ekiprop/CoLA-FULL_FT-seed20
CoLA-FULL_FT-seed20 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
67
Public
Parameters
125M
5.5 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
- b13de3c5
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-seed20
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6822
- Matthews Correlation: 0.6218
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 |
|---|---|---|---|---|
| 0.6034 | 0.1866 | 50 | 0.5076 | 0.4636 |
| 0.4891 | 0.3731 | 100 | 0.4650 | 0.4965 |
| 0.4784 | 0.5597 | 150 | 0.5836 | 0.4608 |
| 0.4708 | 0.7463 | 200 | 0.5253 | 0.4562 |
| 0.4291 | 0.9328 | 250 | 0.4742 | 0.5417 |
| 0.3673 | 1.1194 | 300 | 0.5231 | 0.5343 |
| 0.334 | 1.3060 | 350 | 0.4990 | 0.5498 |
| 0.3202 | 1.4925 | 400 | 0.4450 | 0.5676 |
| 0.3187 | 1.6791 | 450 | 0.4736 | 0.5599 |
| 0.3081 | 1.8657 | 500 | 0.5331 | 0.5190 |
| 0.2793 | 2.0522 | 550 | 0.5600 | 0.5679 |
| 0.1936 | 2.2388 | 600 | 0.5327 | 0.5704 |
| 0.2194 | 2.4254 | 650 | 0.5325 | 0.5748 |
| 0.2508 | 2.6119 | 700 | 0.5250 | 0.6067 |
| 0.1911 | 2.7985 | 750 | 0.5545 | 0.6060 |
| 0.2102 | 2.9851 | 800 | 0.5349 | 0.5831 |
| 0.142 | 3.1716 | 850 | 0.6030 | 0.5999 |
| 0.1415 | 3.3582 | 900 | 0.5684 | 0.5940 |
| 0.131 | 3.5448 | 950 | 0.7759 | 0.5503 |
| 0.127 | 3.7313 | 1000 | 0.6634 | 0.5902 |
| 0.1305 | 3.9179 | 1050 | 0.6453 | 0.5999 |
| 0.1218 | 4.1045 | 1100 | 0.6743 | 0.5941 |
| 0.0847 | 4.2910 | 1150 | 0.6822 | 0.6218 |
| 0.0969 | 4.4776 | 1200 | 0.7138 | 0.6121 |
| 0.0888 | 4.6642 | 1250 | 0.7562 | 0.5986 |
| 0.105 | 4.8507 | 1300 | 0.7558 | 0.5934 |
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