Downloads · 30 days
3
12% of all-time downloads
CoLA-HEURISTIC-Standard_LoRA-Q_V-seed30
ekiprop/CoLA-HEURISTIC-Standard_LoRA-Q_V-seed30
CoLA-HEURISTIC-Standard_LoRA-Q_V-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
26
Public
Repo size
49.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 52%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 90fea525
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-HEURISTIC-Standard_LoRA-Q_V-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: 0.4396
- Matthews Correlation: 0.5658
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 | 0.6041 | 0.0 |
| 0.5607 | 0.3731 | 100 | 0.5278 | 0.3948 |
| 0.4858 | 0.5597 | 150 | 0.4994 | 0.4355 |
| 0.4643 | 0.7463 | 200 | 0.4614 | 0.4825 |
| 0.455 | 0.9328 | 250 | 0.5506 | 0.4079 |
| 0.4483 | 1.1194 | 300 | 0.4477 | 0.5265 |
| 0.4142 | 1.3060 | 350 | 0.4742 | 0.5046 |
| 0.4287 | 1.4925 | 400 | 0.4771 | 0.4892 |
| 0.4394 | 1.6791 | 450 | 0.4158 | 0.5387 |
| 0.398 | 1.8657 | 500 | 0.5097 | 0.5100 |
| 0.416 | 2.0522 | 550 | 0.4163 | 0.5343 |
| 0.3792 | 2.2388 | 600 | 0.4432 | 0.5288 |
| 0.4003 | 2.4254 | 650 | 0.4313 | 0.5397 |
| 0.397 | 2.6119 | 700 | 0.4509 | 0.5419 |
| 0.3866 | 2.7985 | 750 | 0.4132 | 0.5475 |
| 0.3732 | 2.9851 | 800 | 0.4433 | 0.5370 |
| 0.3754 | 3.1716 | 850 | 0.4216 | 0.5655 |
| 0.3679 | 3.3582 | 900 | 0.4233 | 0.5582 |
| 0.381 | 3.5448 | 950 | 0.5071 | 0.5325 |
| 0.3613 | 3.7313 | 1000 | 0.4354 | 0.5524 |
| 0.3501 | 3.9179 | 1050 | 0.4290 | 0.5655 |
| 0.3571 | 4.1045 | 1100 | 0.4351 | 0.5650 |
| 0.3348 | 4.2910 | 1150 | 0.4374 | 0.5628 |
| 0.3419 | 4.4776 | 1200 | 0.4317 | 0.5617 |
| 0.3531 | 4.6642 | 1250 | 0.4396 | 0.5658 |
| 0.3481 | 4.8507 | 1300 | 0.4513 | 0.5627 |
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