Downloads · 30 days
7
28% of all-time downloads
CoLA-GLoRA-p20-seed20
ekiprop/CoLA-GLoRA-p20-seed20
CoLA-GLoRA-p20-seed20 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
25
Public
Repo size
47 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 53%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- beda5bbe
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-p20-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: 0.4049
- Matthews Correlation: 0.5641
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 |
|---|---|---|---|---|
| 0.6301 | 0.1866 | 50 | 0.5987 | 0.0 |
| 0.553 | 0.3731 | 100 | 0.4779 | 0.4418 |
| 0.4807 | 0.5597 | 150 | 0.5589 | 0.3991 |
| 0.4699 | 0.7463 | 200 | 0.4371 | 0.4869 |
| 0.455 | 0.9328 | 250 | 0.5531 | 0.4118 |
| 0.4489 | 1.1194 | 300 | 0.4409 | 0.5382 |
| 0.4378 | 1.3060 | 350 | 0.4869 | 0.5259 |
| 0.4427 | 1.4925 | 400 | 0.4378 | 0.5208 |
| 0.4611 | 1.6791 | 450 | 0.4352 | 0.5021 |
| 0.4207 | 1.8657 | 500 | 0.5470 | 0.4900 |
| 0.4302 | 2.0522 | 550 | 0.4490 | 0.5380 |
| 0.4053 | 2.2388 | 600 | 0.4504 | 0.5323 |
| 0.4022 | 2.4254 | 650 | 0.4169 | 0.5472 |
| 0.4146 | 2.6119 | 700 | 0.4609 | 0.5047 |
| 0.4042 | 2.7985 | 750 | 0.4338 | 0.5606 |
| 0.3884 | 2.9851 | 800 | 0.4666 | 0.5313 |
| 0.4067 | 3.1716 | 850 | 0.4049 | 0.5641 |
| 0.3884 | 3.3582 | 900 | 0.4244 | 0.5605 |
| 0.3772 | 3.5448 | 950 | 0.5465 | 0.5019 |
| 0.3731 | 3.7313 | 1000 | 0.4327 | 0.5550 |
| 0.3683 | 3.9179 | 1050 | 0.4482 | 0.5553 |
| 0.3728 | 4.1045 | 1100 | 0.4515 | 0.5549 |
| 0.3539 | 4.2910 | 1150 | 0.4430 | 0.5606 |
| 0.3552 | 4.4776 | 1200 | 0.4375 | 0.5582 |
| 0.3647 | 4.6642 | 1250 | 0.4537 | 0.5608 |
| 0.3466 | 4.8507 | 1300 | 0.4765 | 0.5523 |
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