Downloads · 30 days
5
22% of all-time downloads
CoLA-Fisher-GLoRA-p20-seed10
ekiprop/CoLA-Fisher-GLoRA-p20-seed10
CoLA-Fisher-GLoRA-p20-seed10 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
23
Public
Repo size
42.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 55%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 0f3ec656
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-GLoRA-p20-seed10
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4584
- Matthews Correlation: 0.4858
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 |
|---|---|---|---|---|
| 0.6382 | 0.1866 | 50 | 0.6108 | 0.0 |
| 0.6019 | 0.3731 | 100 | 0.6089 | 0.0 |
| 0.5961 | 0.5597 | 150 | 0.5962 | 0.0 |
| 0.5758 | 0.7463 | 200 | 0.5706 | 0.0 |
| 0.5611 | 0.9328 | 250 | 0.5212 | 0.2328 |
| 0.5301 | 1.1194 | 300 | 0.4927 | 0.3522 |
| 0.5091 | 1.3060 | 350 | 0.4883 | 0.3772 |
| 0.5064 | 1.4925 | 400 | 0.5502 | 0.2828 |
| 0.5162 | 1.6791 | 450 | 0.4561 | 0.4441 |
| 0.4874 | 1.8657 | 500 | 0.5154 | 0.3291 |
| 0.4997 | 2.0522 | 550 | 0.4667 | 0.4422 |
| 0.4843 | 2.2388 | 600 | 0.4679 | 0.4475 |
| 0.4574 | 2.4254 | 650 | 0.4746 | 0.4531 |
| 0.4495 | 2.6119 | 700 | 0.4977 | 0.4333 |
| 0.4365 | 2.7985 | 750 | 0.4914 | 0.4616 |
| 0.4537 | 2.9851 | 800 | 0.4584 | 0.4858 |
| 0.4565 | 3.1716 | 850 | 0.4732 | 0.4725 |
| 0.4406 | 3.3582 | 900 | 0.4876 | 0.4642 |
| 0.456 | 3.5448 | 950 | 0.5106 | 0.4307 |
| 0.4396 | 3.7313 | 1000 | 0.4818 | 0.4672 |
| 0.4592 | 3.9179 | 1050 | 0.4949 | 0.4517 |
| 0.4369 | 4.1045 | 1100 | 0.5072 | 0.4381 |
| 0.4332 | 4.2910 | 1150 | 0.4702 | 0.4672 |
| 0.4281 | 4.4776 | 1200 | 0.4799 | 0.4616 |
| 0.431 | 4.6642 | 1250 | 0.4749 | 0.4700 |
| 0.4269 | 4.8507 | 1300 | 0.4861 | 0.4648 |
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