Downloads · 30 days
4
13% of all-time downloads
CoLA-HEURISTIC-Standard_LoRA-Q_V-seed42
ekiprop/CoLA-HEURISTIC-Standard_LoRA-Q_V-seed42
CoLA-HEURISTIC-Standard_LoRA-Q_V-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
31
Public
Repo size
53.3 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
- e35e6aa7
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-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: 0.4497
- Matthews Correlation: 0.5778
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 |
|---|---|---|---|---|
| 0.6425 | 0.1866 | 50 | 0.6165 | 0.0 |
| 0.6 | 0.3731 | 100 | 0.5837 | 0.0 |
| 0.5384 | 0.5597 | 150 | 0.5459 | 0.3720 |
| 0.4799 | 0.7463 | 200 | 0.4800 | 0.4442 |
| 0.4678 | 0.9328 | 250 | 0.5347 | 0.3916 |
| 0.4486 | 1.1194 | 300 | 0.4605 | 0.5021 |
| 0.4423 | 1.3060 | 350 | 0.5270 | 0.4670 |
| 0.441 | 1.4925 | 400 | 0.5126 | 0.4477 |
| 0.4478 | 1.6791 | 450 | 0.4175 | 0.5147 |
| 0.4033 | 1.8657 | 500 | 0.5001 | 0.4774 |
| 0.4251 | 2.0522 | 550 | 0.4125 | 0.5544 |
| 0.3896 | 2.2388 | 600 | 0.4627 | 0.5240 |
| 0.4054 | 2.4254 | 650 | 0.4311 | 0.5132 |
| 0.4046 | 2.6119 | 700 | 0.4417 | 0.5134 |
| 0.388 | 2.7985 | 750 | 0.4427 | 0.5527 |
| 0.3794 | 2.9851 | 800 | 0.4547 | 0.5573 |
| 0.3768 | 3.1716 | 850 | 0.4349 | 0.5573 |
| 0.3778 | 3.3582 | 900 | 0.4249 | 0.5603 |
| 0.3781 | 3.5448 | 950 | 0.5025 | 0.5209 |
| 0.3677 | 3.7313 | 1000 | 0.4583 | 0.5650 |
| 0.3491 | 3.9179 | 1050 | 0.4299 | 0.5629 |
| 0.353 | 4.1045 | 1100 | 0.4608 | 0.5521 |
| 0.3387 | 4.2910 | 1150 | 0.4588 | 0.5752 |
| 0.3477 | 4.4776 | 1200 | 0.4497 | 0.5778 |
| 0.3514 | 4.6642 | 1250 | 0.4638 | 0.5727 |
| 0.3436 | 4.8507 | 1300 | 0.4671 | 0.5701 |
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