Downloads · 30 days
5
15% of all-time downloads
CoLA-Fisher-Standard_LoRA-Q_V-seed20
ekiprop/CoLA-Fisher-Standard_LoRA-Q_V-seed20
CoLA-Fisher-Standard_LoRA-Q_V-seed20 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
33
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
- f3eb3bf7
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-seed20
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4373
- Matthews Correlation: 0.5863
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 |
|---|---|---|---|---|
| 0.6394 | 0.1866 | 50 | 0.6055 | 0.0 |
| 0.5591 | 0.3731 | 100 | 0.4833 | 0.4354 |
| 0.4923 | 0.5597 | 150 | 0.5382 | 0.4187 |
| 0.4709 | 0.7463 | 200 | 0.4612 | 0.4830 |
| 0.4555 | 0.9328 | 250 | 0.5632 | 0.4348 |
| 0.4456 | 1.1194 | 300 | 0.4388 | 0.5370 |
| 0.4225 | 1.3060 | 350 | 0.4932 | 0.5128 |
| 0.4198 | 1.4925 | 400 | 0.4752 | 0.4753 |
| 0.44 | 1.6791 | 450 | 0.4090 | 0.5551 |
| 0.3995 | 1.8657 | 500 | 0.4833 | 0.5180 |
| 0.4021 | 2.0522 | 550 | 0.4117 | 0.5737 |
| 0.382 | 2.2388 | 600 | 0.4568 | 0.5575 |
| 0.3942 | 2.4254 | 650 | 0.4260 | 0.5420 |
| 0.3946 | 2.6119 | 700 | 0.4414 | 0.5497 |
| 0.3853 | 2.7985 | 750 | 0.4072 | 0.5694 |
| 0.3669 | 2.9851 | 800 | 0.4356 | 0.5548 |
| 0.3664 | 3.1716 | 850 | 0.4271 | 0.5576 |
| 0.3658 | 3.3582 | 900 | 0.4076 | 0.5737 |
| 0.372 | 3.5448 | 950 | 0.4994 | 0.5477 |
| 0.3524 | 3.7313 | 1000 | 0.4525 | 0.5650 |
| 0.3491 | 3.9179 | 1050 | 0.4229 | 0.5860 |
| 0.3589 | 4.1045 | 1100 | 0.4274 | 0.5729 |
| 0.3337 | 4.2910 | 1150 | 0.4415 | 0.5756 |
| 0.3328 | 4.4776 | 1200 | 0.4373 | 0.5863 |
| 0.3507 | 4.6642 | 1250 | 0.4395 | 0.5812 |
| 0.3414 | 4.8507 | 1300 | 0.4602 | 0.5729 |
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