Downloads · 30 days
9
16% of all-time downloads
CoLA-Fisher-GLoRA-p30-seed30
ekiprop/CoLA-Fisher-GLoRA-p30-seed30
CoLA-Fisher-GLoRA-p30-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
58
Public
Repo size
47.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 53%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- ed7941c0
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-p30-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: 0.4364
- Matthews Correlation: 0.5395
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 |
|---|---|---|---|---|
| 0.6309 | 0.1866 | 50 | 0.6066 | 0.0 |
| 0.6012 | 0.3731 | 100 | 0.5911 | 0.0 |
| 0.5587 | 0.5597 | 150 | 0.5374 | 0.1860 |
| 0.5135 | 0.7463 | 200 | 0.4900 | 0.4094 |
| 0.4607 | 0.9328 | 250 | 0.5696 | 0.3891 |
| 0.4715 | 1.1194 | 300 | 0.4906 | 0.4331 |
| 0.4555 | 1.3060 | 350 | 0.4826 | 0.4637 |
| 0.4689 | 1.4925 | 400 | 0.5486 | 0.4069 |
| 0.473 | 1.6791 | 450 | 0.4883 | 0.4412 |
| 0.438 | 1.8657 | 500 | 0.5060 | 0.4414 |
| 0.4445 | 2.0522 | 550 | 0.4668 | 0.4911 |
| 0.4167 | 2.2388 | 600 | 0.4763 | 0.4993 |
| 0.4259 | 2.4254 | 650 | 0.4671 | 0.5046 |
| 0.4147 | 2.6119 | 700 | 0.4848 | 0.5019 |
| 0.4067 | 2.7985 | 750 | 0.4742 | 0.5180 |
| 0.43 | 2.9851 | 800 | 0.4611 | 0.5126 |
| 0.4172 | 3.1716 | 850 | 0.4364 | 0.5395 |
| 0.3946 | 3.3582 | 900 | 0.4717 | 0.5285 |
| 0.4004 | 3.5448 | 950 | 0.5258 | 0.4610 |
| 0.3982 | 3.7313 | 1000 | 0.4692 | 0.5179 |
| 0.3929 | 3.9179 | 1050 | 0.4741 | 0.5100 |
| 0.3896 | 4.1045 | 1100 | 0.4713 | 0.5180 |
| 0.3769 | 4.2910 | 1150 | 0.4690 | 0.5206 |
| 0.376 | 4.4776 | 1200 | 0.4594 | 0.5339 |
| 0.3981 | 4.6642 | 1250 | 0.4695 | 0.5260 |
| 0.3765 | 4.8507 | 1300 | 0.4773 | 0.5180 |
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