Downloads · 30 days
6
29% of all-time downloads
CoLA-GLoRA-p10-seed42
ekiprop/CoLA-GLoRA-p10-seed42
CoLA-GLoRA-p10-seed42 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
33.1 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
- 7590b16b
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-seed42
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4722
- Matthews Correlation: 0.5295
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 |
|---|---|---|---|---|
| 0.6378 | 0.1866 | 50 | 0.6126 | 0.0 |
| 0.6 | 0.3731 | 100 | 0.5667 | 0.0 |
| 0.5339 | 0.5597 | 150 | 0.4639 | 0.4563 |
| 0.48 | 0.7463 | 200 | 0.5376 | 0.4105 |
| 0.4585 | 0.9328 | 250 | 0.6096 | 0.4138 |
| 0.4703 | 1.1194 | 300 | 0.5163 | 0.4857 |
| 0.4642 | 1.3060 | 350 | 0.5108 | 0.4695 |
| 0.4605 | 1.4925 | 400 | 0.5185 | 0.4100 |
| 0.488 | 1.6791 | 450 | 0.4682 | 0.4966 |
| 0.4518 | 1.8657 | 500 | 0.5536 | 0.4667 |
| 0.4494 | 2.0522 | 550 | 0.5192 | 0.4966 |
| 0.437 | 2.2388 | 600 | 0.5388 | 0.4912 |
| 0.4492 | 2.4254 | 650 | 0.4719 | 0.4941 |
| 0.45 | 2.6119 | 700 | 0.4665 | 0.5136 |
| 0.439 | 2.7985 | 750 | 0.4706 | 0.5020 |
| 0.4357 | 2.9851 | 800 | 0.4841 | 0.4747 |
| 0.4466 | 3.1716 | 850 | 0.4600 | 0.5104 |
| 0.4111 | 3.3582 | 900 | 0.4722 | 0.5295 |
| 0.4294 | 3.5448 | 950 | 0.5569 | 0.4735 |
| 0.4101 | 3.7313 | 1000 | 0.4941 | 0.4938 |
| 0.437 | 3.9179 | 1050 | 0.4703 | 0.5019 |
| 0.4338 | 4.1045 | 1100 | 0.4634 | 0.5019 |
| 0.402 | 4.2910 | 1150 | 0.4964 | 0.5019 |
| 0.4182 | 4.4776 | 1200 | 0.4727 | 0.5021 |
| 0.4081 | 4.6642 | 1250 | 0.4952 | 0.4939 |
| 0.4188 | 4.8507 | 1300 | 0.4976 | 0.4911 |
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