Downloads · 30 days
5
22% of all-time downloads
CoLA-HEURISTIC-V_FFN-seed52
ekiprop/CoLA-HEURISTIC-V_FFN-seed52
CoLA-HEURISTIC-V_FFN-seed52 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
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
- b595488f
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-seed52
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4516
- Matthews Correlation: 0.6035
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 |
|---|---|---|---|---|
| 0.6427 | 0.1866 | 50 | 0.5945 | 0.0 |
| 0.5377 | 0.3731 | 100 | 0.4694 | 0.4589 |
| 0.4876 | 0.5597 | 150 | 0.5235 | 0.4496 |
| 0.4678 | 0.7463 | 200 | 0.4705 | 0.4747 |
| 0.4457 | 0.9328 | 250 | 0.5987 | 0.3583 |
| 0.4316 | 1.1194 | 300 | 0.4212 | 0.5585 |
| 0.3979 | 1.3060 | 350 | 0.4816 | 0.5233 |
| 0.3956 | 1.4925 | 400 | 0.4585 | 0.5290 |
| 0.4156 | 1.6791 | 450 | 0.4338 | 0.5677 |
| 0.3825 | 1.8657 | 500 | 0.5187 | 0.5100 |
| 0.3693 | 2.0522 | 550 | 0.4417 | 0.5606 |
| 0.3271 | 2.2388 | 600 | 0.5233 | 0.5364 |
| 0.3452 | 2.4254 | 650 | 0.4128 | 0.5725 |
| 0.3451 | 2.6119 | 700 | 0.4919 | 0.5420 |
| 0.3251 | 2.7985 | 750 | 0.4544 | 0.5701 |
| 0.3289 | 2.9851 | 800 | 0.4457 | 0.5548 |
| 0.3103 | 3.1716 | 850 | 0.4221 | 0.5940 |
| 0.2925 | 3.3582 | 900 | 0.4030 | 0.6022 |
| 0.298 | 3.5448 | 950 | 0.5842 | 0.5186 |
| 0.2973 | 3.7313 | 1000 | 0.4372 | 0.5935 |
| 0.2867 | 3.9179 | 1050 | 0.4520 | 0.5883 |
| 0.298 | 4.1045 | 1100 | 0.4621 | 0.5753 |
| 0.2533 | 4.2910 | 1150 | 0.4516 | 0.6035 |
| 0.2555 | 4.4776 | 1200 | 0.4762 | 0.5881 |
| 0.2579 | 4.6642 | 1250 | 0.4774 | 0.5958 |
| 0.2591 | 4.8507 | 1300 | 0.5174 | 0.5650 |
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