Downloads · 30 days
6
29% of all-time downloads
CoLA-GLoRA-p20-seed62
ekiprop/CoLA-GLoRA-p20-seed62
CoLA-GLoRA-p20-seed62 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
21
Public
Repo size
40.3 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
- 941be413
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-seed62
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4087
- Matthews Correlation: 0.5631
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 |
|---|---|---|---|---|
| 0.6359 | 0.1866 | 50 | 0.6082 | 0.0 |
| 0.5668 | 0.3731 | 100 | 0.5780 | 0.2533 |
| 0.4882 | 0.5597 | 150 | 0.5085 | 0.3918 |
| 0.4638 | 0.7463 | 200 | 0.4518 | 0.4916 |
| 0.4499 | 0.9328 | 250 | 0.5797 | 0.3865 |
| 0.4522 | 1.1194 | 300 | 0.4537 | 0.5065 |
| 0.4329 | 1.3060 | 350 | 0.5070 | 0.4857 |
| 0.4413 | 1.4925 | 400 | 0.4378 | 0.5074 |
| 0.4663 | 1.6791 | 450 | 0.4350 | 0.5073 |
| 0.4218 | 1.8657 | 500 | 0.5336 | 0.4787 |
| 0.4282 | 2.0522 | 550 | 0.4522 | 0.5332 |
| 0.4031 | 2.2388 | 600 | 0.4630 | 0.5109 |
| 0.3994 | 2.4254 | 650 | 0.4240 | 0.5358 |
| 0.4097 | 2.6119 | 700 | 0.4585 | 0.5206 |
| 0.4026 | 2.7985 | 750 | 0.4283 | 0.5530 |
| 0.3846 | 2.9851 | 800 | 0.4612 | 0.5340 |
| 0.4009 | 3.1716 | 850 | 0.4087 | 0.5631 |
| 0.3876 | 3.3582 | 900 | 0.4280 | 0.5347 |
| 0.3795 | 3.5448 | 950 | 0.5347 | 0.5264 |
| 0.3722 | 3.7313 | 1000 | 0.4380 | 0.5499 |
| 0.3737 | 3.9179 | 1050 | 0.4484 | 0.5523 |
| 0.3686 | 4.1045 | 1100 | 0.4458 | 0.5547 |
| 0.3505 | 4.2910 | 1150 | 0.4435 | 0.5601 |
| 0.3555 | 4.4776 | 1200 | 0.4435 | 0.5556 |
| 0.3599 | 4.6642 | 1250 | 0.4617 | 0.5502 |
| 0.3445 | 4.8507 | 1300 | 0.4758 | 0.5522 |
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