Downloads · 30 days
5
20% of all-time downloads
CoLA-Fisher-GLoRA-p10-seed30
ekiprop/CoLA-Fisher-GLoRA-p10-seed30
CoLA-Fisher-GLoRA-p10-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
25
Public
Repo size
40.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 58%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 73a1d4f7
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-Fisher-GLoRA-p10-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: 0.4857
- Matthews Correlation: 0.4453
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 |
|---|---|---|---|---|
| 0.6355 | 0.1866 | 50 | 0.6141 | 0.0 |
| 0.6028 | 0.3731 | 100 | 0.6100 | 0.0 |
| 0.5905 | 0.5597 | 150 | 0.5948 | 0.0 |
| 0.5688 | 0.7463 | 200 | 0.5705 | 0.0464 |
| 0.5587 | 0.9328 | 250 | 0.5439 | 0.1434 |
| 0.528 | 1.1194 | 300 | 0.5247 | 0.2459 |
| 0.497 | 1.3060 | 350 | 0.5007 | 0.3511 |
| 0.4978 | 1.4925 | 400 | 0.5270 | 0.3327 |
| 0.5126 | 1.6791 | 450 | 0.4886 | 0.4086 |
| 0.494 | 1.8657 | 500 | 0.4996 | 0.3847 |
| 0.4929 | 2.0522 | 550 | 0.4634 | 0.4328 |
| 0.4859 | 2.2388 | 600 | 0.5045 | 0.4244 |
| 0.4922 | 2.4254 | 650 | 0.5119 | 0.3886 |
| 0.4851 | 2.6119 | 700 | 0.5271 | 0.3894 |
| 0.4645 | 2.7985 | 750 | 0.5097 | 0.3969 |
| 0.4686 | 2.9851 | 800 | 0.4784 | 0.4442 |
| 0.4854 | 3.1716 | 850 | 0.4705 | 0.4326 |
| 0.4687 | 3.3582 | 900 | 0.4935 | 0.4192 |
| 0.4765 | 3.5448 | 950 | 0.5595 | 0.3742 |
| 0.4517 | 3.7313 | 1000 | 0.5158 | 0.4165 |
| 0.4822 | 3.9179 | 1050 | 0.5135 | 0.4075 |
| 0.4627 | 4.1045 | 1100 | 0.5052 | 0.4239 |
| 0.4557 | 4.2910 | 1150 | 0.4968 | 0.4260 |
| 0.461 | 4.4776 | 1200 | 0.4857 | 0.4453 |
| 0.4631 | 4.6642 | 1250 | 0.5038 | 0.4235 |
| 0.4514 | 4.8507 | 1300 | 0.5050 | 0.4235 |
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