Downloads · 30 days
9
36% of all-time downloads
CoLA-GLoRA-p50-seed20
ekiprop/CoLA-GLoRA-p50-seed20
CoLA-GLoRA-p50-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
78.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.6 MB · 54%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 8353a9f7
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-p50-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: 0.4286
- Matthews Correlation: 0.5905
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 |
|---|---|---|---|---|
| 0.629 | 0.1866 | 50 | 0.5907 | 0.0 |
| 0.5199 | 0.3731 | 100 | 0.4536 | 0.5113 |
| 0.4742 | 0.5597 | 150 | 0.5143 | 0.4524 |
| 0.4584 | 0.7463 | 200 | 0.4634 | 0.4915 |
| 0.4464 | 0.9328 | 250 | 0.5301 | 0.4785 |
| 0.4126 | 1.1194 | 300 | 0.4129 | 0.5631 |
| 0.3929 | 1.3060 | 350 | 0.4787 | 0.5233 |
| 0.3895 | 1.4925 | 400 | 0.4322 | 0.5576 |
| 0.4138 | 1.6791 | 450 | 0.4113 | 0.5711 |
| 0.3519 | 1.8657 | 500 | 0.4815 | 0.5312 |
| 0.3673 | 2.0522 | 550 | 0.5444 | 0.5206 |
| 0.325 | 2.2388 | 600 | 0.4934 | 0.5369 |
| 0.3485 | 2.4254 | 650 | 0.4363 | 0.5576 |
| 0.3404 | 2.6119 | 700 | 0.4450 | 0.5634 |
| 0.3162 | 2.7985 | 750 | 0.4380 | 0.5812 |
| 0.3058 | 2.9851 | 800 | 0.4839 | 0.5547 |
| 0.2955 | 3.1716 | 850 | 0.4286 | 0.5905 |
| 0.2794 | 3.3582 | 900 | 0.4297 | 0.5890 |
| 0.2917 | 3.5448 | 950 | 0.5954 | 0.5130 |
| 0.2824 | 3.7313 | 1000 | 0.4573 | 0.5806 |
| 0.3024 | 3.9179 | 1050 | 0.4437 | 0.5809 |
| 0.2546 | 4.1045 | 1100 | 0.4969 | 0.5806 |
| 0.2248 | 4.2910 | 1150 | 0.5119 | 0.5833 |
| 0.2384 | 4.4776 | 1200 | 0.4921 | 0.5782 |
| 0.2548 | 4.6642 | 1250 | 0.5085 | 0.5754 |
| 0.2504 | 4.8507 | 1300 | 0.5144 | 0.5650 |
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