Downloads · 30 days
5
19% of all-time downloads
CoLA-GLoRA-p20-seed42
ekiprop/CoLA-GLoRA-p20-seed42
CoLA-GLoRA-p20-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
27
Public
Repo size
44.6 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
- e86cc1e6
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-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: 0.4262
- Matthews Correlation: 0.5636
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 |
|---|---|---|---|---|
| 0.6376 | 0.1866 | 50 | 0.5925 | 0.0 |
| 0.5539 | 0.3731 | 100 | 0.5291 | 0.3352 |
| 0.4841 | 0.5597 | 150 | 0.5914 | 0.4135 |
| 0.4668 | 0.7463 | 200 | 0.4366 | 0.5203 |
| 0.4485 | 0.9328 | 250 | 0.5346 | 0.4284 |
| 0.4465 | 1.1194 | 300 | 0.4308 | 0.5410 |
| 0.4265 | 1.3060 | 350 | 0.4909 | 0.5136 |
| 0.4431 | 1.4925 | 400 | 0.4340 | 0.5242 |
| 0.4759 | 1.6791 | 450 | 0.4261 | 0.5267 |
| 0.4197 | 1.8657 | 500 | 0.5644 | 0.4633 |
| 0.4147 | 2.0522 | 550 | 0.4404 | 0.5364 |
| 0.4057 | 2.2388 | 600 | 0.4835 | 0.5214 |
| 0.4016 | 2.4254 | 650 | 0.4369 | 0.5380 |
| 0.4094 | 2.6119 | 700 | 0.4337 | 0.5311 |
| 0.3912 | 2.7985 | 750 | 0.4262 | 0.5358 |
| 0.3928 | 2.9851 | 800 | 0.4759 | 0.5180 |
| 0.4007 | 3.1716 | 850 | 0.4125 | 0.5396 |
| 0.3892 | 3.3582 | 900 | 0.4206 | 0.5567 |
| 0.3748 | 3.5448 | 950 | 0.5974 | 0.4970 |
| 0.372 | 3.7313 | 1000 | 0.4262 | 0.5636 |
| 0.3874 | 3.9179 | 1050 | 0.4374 | 0.5480 |
| 0.3708 | 4.1045 | 1100 | 0.4458 | 0.5501 |
| 0.3524 | 4.2910 | 1150 | 0.4446 | 0.5482 |
| 0.3604 | 4.4776 | 1200 | 0.4322 | 0.5541 |
| 0.371 | 4.6642 | 1250 | 0.4445 | 0.5536 |
| 0.3529 | 4.8507 | 1300 | 0.4671 | 0.5548 |
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