Downloads · 30 days
3
19% of all-time downloads
CoLA-GLoRA-p40-seed30
ekiprop/CoLA-GLoRA-p40-seed30
CoLA-GLoRA-p40-seed30 is a machine learning model from ekiprop. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
16
Public
Repo size
63.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 MB · 50%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 8b86ae7f
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-GLoRA-p40-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: 0.4094
- Matthews Correlation: 0.6047
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: 0.0003
- 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 |
|---|---|---|---|---|
| 0.6223 | 0.1866 | 50 | 0.5851 | 0.0 |
| 0.5297 | 0.3731 | 100 | 0.5066 | 0.4931 |
| 0.4815 | 0.5597 | 150 | 0.5639 | 0.4181 |
| 0.4675 | 0.7463 | 200 | 0.4727 | 0.5083 |
| 0.4312 | 0.9328 | 250 | 0.5086 | 0.4636 |
| 0.4147 | 1.1194 | 300 | 0.4567 | 0.5289 |
| 0.3967 | 1.3060 | 350 | 0.4927 | 0.5470 |
| 0.3995 | 1.4925 | 400 | 0.4574 | 0.5446 |
| 0.4106 | 1.6791 | 450 | 0.3986 | 0.5733 |
| 0.3629 | 1.8657 | 500 | 0.4919 | 0.5501 |
| 0.3633 | 2.0522 | 550 | 0.5545 | 0.5577 |
| 0.3152 | 2.2388 | 600 | 0.4741 | 0.5788 |
| 0.341 | 2.4254 | 650 | 0.4546 | 0.5836 |
| 0.348 | 2.6119 | 700 | 0.4555 | 0.5676 |
| 0.3199 | 2.7985 | 750 | 0.4094 | 0.6047 |
| 0.3211 | 2.9851 | 800 | 0.4662 | 0.5702 |
| 0.3041 | 3.1716 | 850 | 0.4013 | 0.5946 |
| 0.2818 | 3.3582 | 900 | 0.3895 | 0.5764 |
| 0.2931 | 3.5448 | 950 | 0.5614 | 0.5576 |
| 0.2834 | 3.7313 | 1000 | 0.4156 | 0.5769 |
| 0.3071 | 3.9179 | 1050 | 0.4105 | 0.5863 |
| 0.2906 | 4.1045 | 1100 | 0.4595 | 0.5779 |
| 0.2397 | 4.2910 | 1150 | 0.4862 | 0.5809 |
| 0.2803 | 4.4776 | 1200 | 0.4733 | 0.5830 |
| 0.2727 | 4.6642 | 1250 | 0.4654 | 0.5732 |
| 0.2418 | 4.8507 | 1300 | 0.4916 | 0.5703 |
Framework versions
- PEFT 0.16.0
- Transformers 4.54.1
- Pytorch 2.5.1+cu121
- Datasets 4.0.0
- Tokenizers 0.21.4
- Library
- peft
- License
- mit
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025