Downloads · 30 days
6
26% of all-time downloads
CoLA-GLoRA-p50-seed42
ekiprop/CoLA-GLoRA-p50-seed42
CoLA-GLoRA-p50-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
23
Public
Repo size
84.4 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
- 4d4de243
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-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: 0.5123
- Matthews Correlation: 0.5830
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 |
|---|---|---|---|---|
| 0.6348 | 0.1866 | 50 | 0.5943 | 0.0 |
| 0.5324 | 0.3731 | 100 | 0.4564 | 0.4782 |
| 0.4785 | 0.5597 | 150 | 0.4998 | 0.4747 |
| 0.4536 | 0.7463 | 200 | 0.4561 | 0.5113 |
| 0.4399 | 0.9328 | 250 | 0.5248 | 0.4786 |
| 0.4253 | 1.1194 | 300 | 0.4200 | 0.5455 |
| 0.397 | 1.3060 | 350 | 0.4786 | 0.5340 |
| 0.3858 | 1.4925 | 400 | 0.4291 | 0.5452 |
| 0.4116 | 1.6791 | 450 | 0.4200 | 0.5376 |
| 0.3594 | 1.8657 | 500 | 0.5154 | 0.5158 |
| 0.3604 | 2.0522 | 550 | 0.5287 | 0.5153 |
| 0.31 | 2.2388 | 600 | 0.4945 | 0.5432 |
| 0.3385 | 2.4254 | 650 | 0.4241 | 0.5556 |
| 0.3412 | 2.6119 | 700 | 0.4300 | 0.5733 |
| 0.3039 | 2.7985 | 750 | 0.4462 | 0.5790 |
| 0.3054 | 2.9851 | 800 | 0.4781 | 0.5650 |
| 0.2991 | 3.1716 | 850 | 0.4253 | 0.5682 |
| 0.275 | 3.3582 | 900 | 0.4179 | 0.5818 |
| 0.2912 | 3.5448 | 950 | 0.5640 | 0.5397 |
| 0.2723 | 3.7313 | 1000 | 0.4508 | 0.5614 |
| 0.2889 | 3.9179 | 1050 | 0.4525 | 0.5717 |
| 0.2396 | 4.1045 | 1100 | 0.4888 | 0.5735 |
| 0.2251 | 4.2910 | 1150 | 0.5140 | 0.5809 |
| 0.2249 | 4.4776 | 1200 | 0.5128 | 0.5809 |
| 0.2362 | 4.6642 | 1250 | 0.5253 | 0.5756 |
| 0.2443 | 4.8507 | 1300 | 0.5123 | 0.5830 |
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