Downloads · 30 days
10
29% of all-time downloads
CoLA-Fisher-Standard_LoRA-Q_V-seed30
ekiprop/CoLA-Fisher-Standard_LoRA-Q_V-seed30
CoLA-Fisher-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
35
Public
Repo size
64 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
- b89279b2
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-Fisher-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: 0.4326
- Matthews Correlation: 0.5957
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 |
|---|---|---|---|---|
| 0.6372 | 0.1866 | 50 | 0.6007 | 0.0 |
| 0.5457 | 0.3731 | 100 | 0.4751 | 0.4708 |
| 0.4924 | 0.5597 | 150 | 0.4750 | 0.4611 |
| 0.4692 | 0.7463 | 200 | 0.4711 | 0.4748 |
| 0.4535 | 0.9328 | 250 | 0.5166 | 0.4642 |
| 0.434 | 1.1194 | 300 | 0.4357 | 0.5295 |
| 0.4153 | 1.3060 | 350 | 0.4778 | 0.5046 |
| 0.419 | 1.4925 | 400 | 0.4798 | 0.4642 |
| 0.4367 | 1.6791 | 450 | 0.4085 | 0.5426 |
| 0.401 | 1.8657 | 500 | 0.4962 | 0.5153 |
| 0.4034 | 2.0522 | 550 | 0.4064 | 0.5815 |
| 0.3763 | 2.2388 | 600 | 0.4500 | 0.5480 |
| 0.4025 | 2.4254 | 650 | 0.4208 | 0.5628 |
| 0.3909 | 2.6119 | 700 | 0.4331 | 0.5560 |
| 0.3875 | 2.7985 | 750 | 0.4030 | 0.5615 |
| 0.3692 | 2.9851 | 800 | 0.4298 | 0.5705 |
| 0.363 | 3.1716 | 850 | 0.4186 | 0.5806 |
| 0.3558 | 3.3582 | 900 | 0.4042 | 0.5722 |
| 0.364 | 3.5448 | 950 | 0.4911 | 0.5523 |
| 0.3495 | 3.7313 | 1000 | 0.4460 | 0.5805 |
| 0.344 | 3.9179 | 1050 | 0.4225 | 0.5843 |
| 0.3477 | 4.1045 | 1100 | 0.4326 | 0.5957 |
| 0.3346 | 4.2910 | 1150 | 0.4488 | 0.5804 |
| 0.3279 | 4.4776 | 1200 | 0.4383 | 0.5912 |
| 0.3518 | 4.6642 | 1250 | 0.4342 | 0.5885 |
| 0.3424 | 4.8507 | 1300 | 0.4534 | 0.5728 |
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