Downloads · 30 days
7
28% of all-time downloads
CoLA-HEURISTIC-V_FFN-seed42
ekiprop/CoLA-HEURISTIC-V_FFN-seed42
CoLA-HEURISTIC-V_FFN-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
25
Public
Repo size
62.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.4 MB · 48%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- ba68a6f5
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-HEURISTIC-V_FFN-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: 0.4816
- Matthews Correlation: 0.5918
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 |
|---|---|---|---|---|
| 0.6431 | 0.1866 | 50 | 0.5961 | 0.0 |
| 0.5447 | 0.3731 | 100 | 0.4573 | 0.4773 |
| 0.4879 | 0.5597 | 150 | 0.5203 | 0.4384 |
| 0.4671 | 0.7463 | 200 | 0.4425 | 0.5227 |
| 0.4336 | 0.9328 | 250 | 0.5430 | 0.4517 |
| 0.4217 | 1.1194 | 300 | 0.4121 | 0.5530 |
| 0.3998 | 1.3060 | 350 | 0.4486 | 0.5414 |
| 0.3856 | 1.4925 | 400 | 0.4247 | 0.5390 |
| 0.4107 | 1.6791 | 450 | 0.4304 | 0.5501 |
| 0.376 | 1.8657 | 500 | 0.4805 | 0.5259 |
| 0.3606 | 2.0522 | 550 | 0.4610 | 0.5527 |
| 0.3268 | 2.2388 | 600 | 0.4994 | 0.5402 |
| 0.3377 | 2.4254 | 650 | 0.4367 | 0.5653 |
| 0.3453 | 2.6119 | 700 | 0.5045 | 0.5286 |
| 0.3148 | 2.7985 | 750 | 0.4705 | 0.5783 |
| 0.3254 | 2.9851 | 800 | 0.4697 | 0.5365 |
| 0.3066 | 3.1716 | 850 | 0.4332 | 0.5774 |
| 0.284 | 3.3582 | 900 | 0.4145 | 0.5741 |
| 0.295 | 3.5448 | 950 | 0.6046 | 0.5294 |
| 0.2868 | 3.7313 | 1000 | 0.4451 | 0.5792 |
| 0.2902 | 3.9179 | 1050 | 0.4463 | 0.5871 |
| 0.3021 | 4.1045 | 1100 | 0.4507 | 0.5779 |
| 0.2308 | 4.2910 | 1150 | 0.4818 | 0.5890 |
| 0.2472 | 4.4776 | 1200 | 0.4990 | 0.5860 |
| 0.2601 | 4.6642 | 1250 | 0.4816 | 0.5918 |
| 0.2522 | 4.8507 | 1300 | 0.5176 | 0.5729 |
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