Downloads · 30 days
5
24% of all-time downloads
CoLA-Fisher-GLoRA-p20-seed30
ekiprop/CoLA-Fisher-GLoRA-p20-seed30
CoLA-Fisher-GLoRA-p20-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
21
Public
Repo size
45.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 55%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- b6a88aa4
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-p20-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: 0.4477
- Matthews Correlation: 0.5047
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 |
|---|---|---|---|---|
| 0.6381 | 0.1866 | 50 | 0.6114 | 0.0 |
| 0.6021 | 0.3731 | 100 | 0.6002 | 0.0 |
| 0.5766 | 0.5597 | 150 | 0.5538 | 0.0936 |
| 0.5328 | 0.7463 | 200 | 0.5059 | 0.2972 |
| 0.4955 | 0.9328 | 250 | 0.5002 | 0.3761 |
| 0.4802 | 1.1194 | 300 | 0.4928 | 0.4271 |
| 0.4789 | 1.3060 | 350 | 0.4860 | 0.4095 |
| 0.4859 | 1.4925 | 400 | 0.5234 | 0.3947 |
| 0.4773 | 1.6791 | 450 | 0.4686 | 0.4412 |
| 0.4748 | 1.8657 | 500 | 0.4911 | 0.4123 |
| 0.4523 | 2.0522 | 550 | 0.4639 | 0.4608 |
| 0.4542 | 2.2388 | 600 | 0.4923 | 0.4499 |
| 0.4408 | 2.4254 | 650 | 0.4524 | 0.4858 |
| 0.4358 | 2.6119 | 700 | 0.4870 | 0.4552 |
| 0.4351 | 2.7985 | 750 | 0.5001 | 0.4499 |
| 0.4308 | 2.9851 | 800 | 0.4477 | 0.5047 |
| 0.4433 | 3.1716 | 850 | 0.4649 | 0.4829 |
| 0.4386 | 3.3582 | 900 | 0.4983 | 0.4584 |
| 0.433 | 3.5448 | 950 | 0.5177 | 0.4444 |
| 0.417 | 3.7313 | 1000 | 0.4839 | 0.4637 |
| 0.4393 | 3.9179 | 1050 | 0.4886 | 0.4554 |
| 0.4227 | 4.1045 | 1100 | 0.4936 | 0.4583 |
| 0.4088 | 4.2910 | 1150 | 0.4725 | 0.4664 |
| 0.4145 | 4.4776 | 1200 | 0.4676 | 0.4747 |
| 0.4097 | 4.6642 | 1250 | 0.4694 | 0.4775 |
| 0.411 | 4.8507 | 1300 | 0.4830 | 0.4664 |
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