Downloads · 30 days
5
24% of all-time downloads
CoLA-GLoRA-p20-seed52
ekiprop/CoLA-GLoRA-p20-seed52
CoLA-GLoRA-p20-seed52 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
21
Public
Repo size
51.5 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
- 6d7aad8a
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-GLoRA-p20-seed52
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4258
- Matthews Correlation: 0.5746
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 |
|---|---|---|---|---|
| 0.6322 | 0.1866 | 50 | 0.5954 | 0.0 |
| 0.553 | 0.3731 | 100 | 0.5378 | 0.3092 |
| 0.4854 | 0.5597 | 150 | 0.5850 | 0.3832 |
| 0.4712 | 0.7463 | 200 | 0.4426 | 0.4979 |
| 0.4473 | 0.9328 | 250 | 0.5194 | 0.4332 |
| 0.449 | 1.1194 | 300 | 0.4309 | 0.5295 |
| 0.4328 | 1.3060 | 350 | 0.4827 | 0.4948 |
| 0.442 | 1.4925 | 400 | 0.4423 | 0.5289 |
| 0.4825 | 1.6791 | 450 | 0.4286 | 0.5186 |
| 0.422 | 1.8657 | 500 | 0.5695 | 0.4570 |
| 0.4175 | 2.0522 | 550 | 0.4530 | 0.5408 |
| 0.4074 | 2.2388 | 600 | 0.4618 | 0.5193 |
| 0.3998 | 2.4254 | 650 | 0.4290 | 0.5364 |
| 0.4127 | 2.6119 | 700 | 0.4386 | 0.5356 |
| 0.3915 | 2.7985 | 750 | 0.4258 | 0.5466 |
| 0.3973 | 2.9851 | 800 | 0.4711 | 0.5100 |
| 0.4002 | 3.1716 | 850 | 0.4082 | 0.5626 |
| 0.3899 | 3.3582 | 900 | 0.4167 | 0.5628 |
| 0.3746 | 3.5448 | 950 | 0.5847 | 0.4887 |
| 0.3767 | 3.7313 | 1000 | 0.4187 | 0.5648 |
| 0.3848 | 3.9179 | 1050 | 0.4268 | 0.5662 |
| 0.3744 | 4.1045 | 1100 | 0.4392 | 0.5499 |
| 0.3522 | 4.2910 | 1150 | 0.4408 | 0.5580 |
| 0.3622 | 4.4776 | 1200 | 0.4258 | 0.5746 |
| 0.3724 | 4.6642 | 1250 | 0.4430 | 0.5632 |
| 0.3557 | 4.8507 | 1300 | 0.4649 | 0.5522 |
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