Downloads · 30 days
7
29% of all-time downloads
CoLA-GLoRA-p30-seed42
ekiprop/CoLA-GLoRA-p30-seed42
CoLA-GLoRA-p30-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
24
Public
Repo size
61.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 49%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- c5002758
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-p30-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: 0.4515
- Matthews Correlation: 0.5804
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 |
|---|---|---|---|---|
| 0.6292 | 0.1866 | 50 | 0.5672 | 0.0 |
| 0.5114 | 0.3731 | 100 | 0.4736 | 0.4524 |
| 0.4772 | 0.5597 | 150 | 0.4626 | 0.4830 |
| 0.4575 | 0.7463 | 200 | 0.5015 | 0.5019 |
| 0.4445 | 0.9328 | 250 | 0.5993 | 0.3969 |
| 0.4483 | 1.1194 | 300 | 0.4312 | 0.5249 |
| 0.4082 | 1.3060 | 350 | 0.4965 | 0.5158 |
| 0.4194 | 1.4925 | 400 | 0.4595 | 0.4912 |
| 0.4449 | 1.6791 | 450 | 0.4480 | 0.5449 |
| 0.4026 | 1.8657 | 500 | 0.6127 | 0.4755 |
| 0.3945 | 2.0522 | 550 | 0.4924 | 0.5408 |
| 0.3525 | 2.2388 | 600 | 0.5247 | 0.5610 |
| 0.3768 | 2.4254 | 650 | 0.4592 | 0.5424 |
| 0.3546 | 2.6119 | 700 | 0.4882 | 0.5548 |
| 0.3669 | 2.7985 | 750 | 0.4179 | 0.5751 |
| 0.3689 | 2.9851 | 800 | 0.4627 | 0.5572 |
| 0.3423 | 3.1716 | 850 | 0.4110 | 0.5730 |
| 0.3316 | 3.3582 | 900 | 0.4188 | 0.5689 |
| 0.3532 | 3.5448 | 950 | 0.5419 | 0.5340 |
| 0.3351 | 3.7313 | 1000 | 0.4515 | 0.5804 |
| 0.3534 | 3.9179 | 1050 | 0.4386 | 0.5779 |
| 0.3345 | 4.1045 | 1100 | 0.4540 | 0.5624 |
| 0.3033 | 4.2910 | 1150 | 0.4533 | 0.5731 |
| 0.311 | 4.4776 | 1200 | 0.4619 | 0.5709 |
| 0.3016 | 4.6642 | 1250 | 0.4945 | 0.5754 |
| 0.31 | 4.8507 | 1300 | 0.5008 | 0.5575 |
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