Downloads · 30 days
3
15% of all-time downloads
CoLA-HEURISTIC-Standard_LoRA-Q_V-seed62
ekiprop/CoLA-HEURISTIC-Standard_LoRA-Q_V-seed62
CoLA-HEURISTIC-Standard_LoRA-Q_V-seed62 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
20
Public
Repo size
46.2 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
- 2f5de05c
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-seed62
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4145
- Matthews Correlation: 0.5705
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 |
|---|---|---|---|---|
| 0.6387 | 0.1866 | 50 | 0.6001 | 0.0 |
| 0.5512 | 0.3731 | 100 | 0.4746 | 0.4554 |
| 0.4916 | 0.5597 | 150 | 0.5234 | 0.4330 |
| 0.4669 | 0.7463 | 200 | 0.4525 | 0.4973 |
| 0.4563 | 0.9328 | 250 | 0.5527 | 0.4428 |
| 0.4436 | 1.1194 | 300 | 0.4537 | 0.5079 |
| 0.4193 | 1.3060 | 350 | 0.4812 | 0.5126 |
| 0.4213 | 1.4925 | 400 | 0.4903 | 0.4887 |
| 0.4418 | 1.6791 | 450 | 0.4170 | 0.5349 |
| 0.3984 | 1.8657 | 500 | 0.5293 | 0.5046 |
| 0.416 | 2.0522 | 550 | 0.4165 | 0.5436 |
| 0.3873 | 2.2388 | 600 | 0.4402 | 0.5492 |
| 0.3976 | 2.4254 | 650 | 0.4288 | 0.5473 |
| 0.3961 | 2.6119 | 700 | 0.4592 | 0.5522 |
| 0.3832 | 2.7985 | 750 | 0.4164 | 0.5622 |
| 0.3777 | 2.9851 | 800 | 0.4362 | 0.5395 |
| 0.3768 | 3.1716 | 850 | 0.4125 | 0.5689 |
| 0.3634 | 3.3582 | 900 | 0.4145 | 0.5705 |
| 0.3783 | 3.5448 | 950 | 0.5121 | 0.5290 |
| 0.3546 | 3.7313 | 1000 | 0.4562 | 0.5445 |
| 0.3508 | 3.9179 | 1050 | 0.4257 | 0.5638 |
| 0.3602 | 4.1045 | 1100 | 0.4366 | 0.5626 |
| 0.33 | 4.2910 | 1150 | 0.4542 | 0.5655 |
| 0.3446 | 4.4776 | 1200 | 0.4452 | 0.5662 |
| 0.3509 | 4.6642 | 1250 | 0.4510 | 0.5682 |
| 0.3455 | 4.8507 | 1300 | 0.4596 | 0.5603 |
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