Downloads · 30 days
9
30% of all-time downloads
CoLA-Fisher-GLoRA-p40-seed20
ekiprop/CoLA-Fisher-GLoRA-p40-seed20
CoLA-Fisher-GLoRA-p40-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
30
Public
Repo size
56.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.4 MB · 51%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 1166376b
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-Fisher-GLoRA-p40-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: 0.4289
- Matthews Correlation: 0.5756
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 |
|---|---|---|---|---|
| 0.6347 | 0.1866 | 50 | 0.6103 | 0.0 |
| 0.5838 | 0.3731 | 100 | 0.5515 | 0.0804 |
| 0.517 | 0.5597 | 150 | 0.4951 | 0.4185 |
| 0.4703 | 0.7463 | 200 | 0.4379 | 0.5083 |
| 0.4355 | 0.9328 | 250 | 0.5204 | 0.4556 |
| 0.4298 | 1.1194 | 300 | 0.4497 | 0.5242 |
| 0.4192 | 1.3060 | 350 | 0.4758 | 0.5046 |
| 0.4291 | 1.4925 | 400 | 0.5072 | 0.4824 |
| 0.4559 | 1.6791 | 450 | 0.4466 | 0.5233 |
| 0.4106 | 1.8657 | 500 | 0.5028 | 0.5196 |
| 0.3878 | 2.0522 | 550 | 0.4421 | 0.5354 |
| 0.3936 | 2.2388 | 600 | 0.4401 | 0.5319 |
| 0.3953 | 2.4254 | 650 | 0.4292 | 0.5349 |
| 0.376 | 2.6119 | 700 | 0.4507 | 0.5372 |
| 0.3789 | 2.7985 | 750 | 0.4239 | 0.5378 |
| 0.3749 | 2.9851 | 800 | 0.4286 | 0.5473 |
| 0.3866 | 3.1716 | 850 | 0.4150 | 0.5428 |
| 0.369 | 3.3582 | 900 | 0.4532 | 0.5286 |
| 0.3624 | 3.5448 | 950 | 0.5027 | 0.5243 |
| 0.3611 | 3.7313 | 1000 | 0.4737 | 0.5318 |
| 0.3562 | 3.9179 | 1050 | 0.4455 | 0.5417 |
| 0.3511 | 4.1045 | 1100 | 0.4257 | 0.5679 |
| 0.3423 | 4.2910 | 1150 | 0.4362 | 0.5601 |
| 0.3363 | 4.4776 | 1200 | 0.4289 | 0.5756 |
| 0.3426 | 4.6642 | 1250 | 0.4444 | 0.5627 |
| 0.3415 | 4.8507 | 1300 | 0.4536 | 0.5497 |
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