Downloads · 30 days
4
13% of all-time downloads
CoLA-Fisher-GLoRA-p10-seed20
ekiprop/CoLA-Fisher-GLoRA-p10-seed20
CoLA-Fisher-GLoRA-p10-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
30
Public
Repo size
38 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
- 35fef339
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-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: 0.4763
- Matthews Correlation: 0.4123
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 |
|---|---|---|---|---|
| 0.635 | 0.1866 | 50 | 0.6139 | 0.0 |
| 0.6064 | 0.3731 | 100 | 0.6135 | 0.0 |
| 0.5959 | 0.5597 | 150 | 0.6025 | 0.0 |
| 0.5804 | 0.7463 | 200 | 0.5954 | 0.0 |
| 0.5835 | 0.9328 | 250 | 0.5773 | 0.0 |
| 0.573 | 1.1194 | 300 | 0.5672 | 0.0840 |
| 0.5538 | 1.3060 | 350 | 0.5319 | 0.1860 |
| 0.5206 | 1.4925 | 400 | 0.5409 | 0.1756 |
| 0.5333 | 1.6791 | 450 | 0.5099 | 0.2913 |
| 0.5117 | 1.8657 | 500 | 0.5226 | 0.2775 |
| 0.5141 | 2.0522 | 550 | 0.4805 | 0.3698 |
| 0.5081 | 2.2388 | 600 | 0.5214 | 0.2992 |
| 0.4909 | 2.4254 | 650 | 0.5154 | 0.3128 |
| 0.4879 | 2.6119 | 700 | 0.5116 | 0.3273 |
| 0.4824 | 2.7985 | 750 | 0.5218 | 0.3244 |
| 0.4865 | 2.9851 | 800 | 0.4819 | 0.3980 |
| 0.4819 | 3.1716 | 850 | 0.4763 | 0.4123 |
| 0.4815 | 3.3582 | 900 | 0.4826 | 0.4041 |
| 0.5012 | 3.5448 | 950 | 0.5309 | 0.3308 |
| 0.4595 | 3.7313 | 1000 | 0.5174 | 0.3423 |
| 0.4895 | 3.9179 | 1050 | 0.5162 | 0.3356 |
| 0.4574 | 4.1045 | 1100 | 0.4982 | 0.3707 |
| 0.4623 | 4.2910 | 1150 | 0.4961 | 0.3832 |
| 0.4737 | 4.4776 | 1200 | 0.4930 | 0.3860 |
| 0.4746 | 4.6642 | 1250 | 0.5019 | 0.3643 |
| 0.4636 | 4.8507 | 1300 | 0.5103 | 0.3616 |
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