Downloads · 30 days
7
28% of all-time downloads
CoLA-Fisher-GLoRA-p30-seed10
ekiprop/CoLA-Fisher-GLoRA-p30-seed10
CoLA-Fisher-GLoRA-p30-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
25
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
- dae38d6a
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-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: 0.4700
- Matthews Correlation: 0.5046
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 |
|---|---|---|---|---|
| 0.6295 | 0.1866 | 50 | 0.6079 | 0.0 |
| 0.6033 | 0.3731 | 100 | 0.5940 | 0.0 |
| 0.5605 | 0.5597 | 150 | 0.5347 | 0.2016 |
| 0.5161 | 0.7463 | 200 | 0.4723 | 0.4240 |
| 0.4792 | 0.9328 | 250 | 0.5230 | 0.3980 |
| 0.476 | 1.1194 | 300 | 0.4807 | 0.4440 |
| 0.4539 | 1.3060 | 350 | 0.4622 | 0.4831 |
| 0.468 | 1.4925 | 400 | 0.5184 | 0.4273 |
| 0.458 | 1.6791 | 450 | 0.4643 | 0.4692 |
| 0.4449 | 1.8657 | 500 | 0.5302 | 0.4248 |
| 0.4307 | 2.0522 | 550 | 0.4568 | 0.4887 |
| 0.4148 | 2.2388 | 600 | 0.4820 | 0.4804 |
| 0.4403 | 2.4254 | 650 | 0.4655 | 0.4938 |
| 0.4299 | 2.6119 | 700 | 0.4659 | 0.4914 |
| 0.4234 | 2.7985 | 750 | 0.4700 | 0.5046 |
| 0.4199 | 2.9851 | 800 | 0.4614 | 0.5019 |
| 0.4271 | 3.1716 | 850 | 0.4472 | 0.4923 |
| 0.4011 | 3.3582 | 900 | 0.4660 | 0.4867 |
| 0.4064 | 3.5448 | 950 | 0.5280 | 0.4777 |
| 0.4103 | 3.7313 | 1000 | 0.4777 | 0.4965 |
| 0.3927 | 3.9179 | 1050 | 0.4778 | 0.4965 |
| 0.4055 | 4.1045 | 1100 | 0.4760 | 0.4939 |
| 0.3924 | 4.2910 | 1150 | 0.4729 | 0.4965 |
| 0.3833 | 4.4776 | 1200 | 0.4614 | 0.4997 |
| 0.3896 | 4.6642 | 1250 | 0.4780 | 0.4992 |
| 0.3943 | 4.8507 | 1300 | 0.4776 | 0.4966 |
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