Downloads · 30 days
6
27% of all-time downloads
CoLA-GLoRA-p40-seed42
ekiprop/CoLA-GLoRA-p40-seed42
CoLA-GLoRA-p40-seed42 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
22
Public
Repo size
68 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 MB · 50%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- aeecdc5e
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-p40-seed42
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4280
- Matthews Correlation: 0.5871
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 |
|---|---|---|---|---|
| 0.6248 | 0.1866 | 50 | 0.5752 | 0.0 |
| 0.5279 | 0.3731 | 100 | 0.5750 | 0.4393 |
| 0.4703 | 0.5597 | 150 | 0.5283 | 0.4783 |
| 0.4639 | 0.7463 | 200 | 0.4692 | 0.4967 |
| 0.4255 | 0.9328 | 250 | 0.4758 | 0.4995 |
| 0.4108 | 1.1194 | 300 | 0.4350 | 0.5435 |
| 0.3931 | 1.3060 | 350 | 0.4603 | 0.5664 |
| 0.3943 | 1.4925 | 400 | 0.4550 | 0.5550 |
| 0.4127 | 1.6791 | 450 | 0.4095 | 0.5653 |
| 0.3645 | 1.8657 | 500 | 0.5263 | 0.5340 |
| 0.3653 | 2.0522 | 550 | 0.5200 | 0.5652 |
| 0.3247 | 2.2388 | 600 | 0.4766 | 0.5504 |
| 0.3398 | 2.4254 | 650 | 0.4525 | 0.5837 |
| 0.3466 | 2.6119 | 700 | 0.4771 | 0.5495 |
| 0.3226 | 2.7985 | 750 | 0.4234 | 0.5848 |
| 0.3216 | 2.9851 | 800 | 0.4483 | 0.5785 |
| 0.305 | 3.1716 | 850 | 0.4043 | 0.5766 |
| 0.2889 | 3.3582 | 900 | 0.3901 | 0.5764 |
| 0.2835 | 3.5448 | 950 | 0.5638 | 0.5469 |
| 0.2818 | 3.7313 | 1000 | 0.4075 | 0.5856 |
| 0.3034 | 3.9179 | 1050 | 0.4280 | 0.5871 |
| 0.288 | 4.1045 | 1100 | 0.4589 | 0.5677 |
| 0.2299 | 4.2910 | 1150 | 0.5008 | 0.5814 |
| 0.2704 | 4.4776 | 1200 | 0.4999 | 0.5780 |
| 0.2624 | 4.6642 | 1250 | 0.5009 | 0.5730 |
| 0.2507 | 4.8507 | 1300 | 0.4970 | 0.5780 |
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