Downloads · 30 days
8
31% of all-time downloads
CoLA-GLoRA-p30-seed62
ekiprop/CoLA-GLoRA-p30-seed62
CoLA-GLoRA-p30-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
26
Public
Repo size
44.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 49%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 8d484047
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-p30-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: 0.3955
- Matthews Correlation: 0.6089
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 |
|---|---|---|---|---|
| 0.6334 | 0.1866 | 50 | 0.5843 | 0.0 |
| 0.5321 | 0.3731 | 100 | 0.4646 | 0.4553 |
| 0.496 | 0.5597 | 150 | 0.4913 | 0.4468 |
| 0.4596 | 0.7463 | 200 | 0.4699 | 0.4966 |
| 0.4637 | 0.9328 | 250 | 0.6232 | 0.4026 |
| 0.4595 | 1.1194 | 300 | 0.4133 | 0.5478 |
| 0.4297 | 1.3060 | 350 | 0.5196 | 0.5052 |
| 0.4166 | 1.4925 | 400 | 0.4723 | 0.5074 |
| 0.4378 | 1.6791 | 450 | 0.4155 | 0.5365 |
| 0.3969 | 1.8657 | 500 | 0.5531 | 0.5047 |
| 0.4006 | 2.0522 | 550 | 0.5326 | 0.5265 |
| 0.366 | 2.2388 | 600 | 0.4844 | 0.5495 |
| 0.3758 | 2.4254 | 650 | 0.4342 | 0.5495 |
| 0.3762 | 2.6119 | 700 | 0.4596 | 0.5391 |
| 0.3442 | 2.7985 | 750 | 0.4432 | 0.5895 |
| 0.3476 | 2.9851 | 800 | 0.4487 | 0.5752 |
| 0.3317 | 3.1716 | 850 | 0.3955 | 0.6089 |
| 0.3269 | 3.3582 | 900 | 0.4083 | 0.5860 |
| 0.349 | 3.5448 | 950 | 0.5101 | 0.5580 |
| 0.3432 | 3.7313 | 1000 | 0.4497 | 0.5806 |
| 0.3377 | 3.9179 | 1050 | 0.4184 | 0.5965 |
| 0.339 | 4.1045 | 1100 | 0.4471 | 0.5934 |
| 0.2912 | 4.2910 | 1150 | 0.4566 | 0.5981 |
| 0.3009 | 4.4776 | 1200 | 0.4442 | 0.6057 |
| 0.3101 | 4.6642 | 1250 | 0.4486 | 0.6057 |
| 0.3014 | 4.8507 | 1300 | 0.4649 | 0.5905 |
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