Downloads · 30 days
4
16% of all-time downloads
CoLA-GLoRA-p10-seed20
ekiprop/CoLA-GLoRA-p10-seed20
CoLA-GLoRA-p10-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
25
Public
Repo size
42.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 56%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 5b554788
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-p10-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: 0.4676
- Matthews Correlation: 0.5261
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 |
|---|---|---|---|---|
| 0.633 | 0.1866 | 50 | 0.6111 | 0.0 |
| 0.5968 | 0.3731 | 100 | 0.5605 | 0.0 |
| 0.5274 | 0.5597 | 150 | 0.4606 | 0.4586 |
| 0.4781 | 0.7463 | 200 | 0.5145 | 0.4410 |
| 0.4608 | 0.9328 | 250 | 0.5761 | 0.4248 |
| 0.4679 | 1.1194 | 300 | 0.5076 | 0.4864 |
| 0.4607 | 1.3060 | 350 | 0.5077 | 0.4802 |
| 0.4597 | 1.4925 | 400 | 0.4880 | 0.4581 |
| 0.4856 | 1.6791 | 450 | 0.4551 | 0.4993 |
| 0.4471 | 1.8657 | 500 | 0.5421 | 0.4783 |
| 0.45 | 2.0522 | 550 | 0.4879 | 0.5159 |
| 0.4368 | 2.2388 | 600 | 0.5003 | 0.5155 |
| 0.4481 | 2.4254 | 650 | 0.4684 | 0.4939 |
| 0.4455 | 2.6119 | 700 | 0.4613 | 0.5164 |
| 0.4381 | 2.7985 | 750 | 0.4657 | 0.5047 |
| 0.4319 | 2.9851 | 800 | 0.4749 | 0.4857 |
| 0.4441 | 3.1716 | 850 | 0.4468 | 0.5214 |
| 0.4136 | 3.3582 | 900 | 0.4628 | 0.5150 |
| 0.4286 | 3.5448 | 950 | 0.5590 | 0.4630 |
| 0.4081 | 3.7313 | 1000 | 0.4891 | 0.4965 |
| 0.4346 | 3.9179 | 1050 | 0.4654 | 0.5100 |
| 0.4294 | 4.1045 | 1100 | 0.4627 | 0.5046 |
| 0.4016 | 4.2910 | 1150 | 0.4875 | 0.4938 |
| 0.4159 | 4.4776 | 1200 | 0.4676 | 0.5261 |
| 0.4119 | 4.6642 | 1250 | 0.4855 | 0.5046 |
| 0.4175 | 4.8507 | 1300 | 0.4861 | 0.4965 |
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