Downloads · 30 days
4
14% of all-time downloads
ekiprop/CoLA-HEURISTIC-LoRA-All-Attention-Q_K_V_O-seed30
CoLA-HEURISTIC-LoRA-All-Attention-Q_K_V_O-seed30 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. --
Downloads · 30 days
4
14% of all-time downloads
All-time downloads
29
Public
Repo size
61.7 MB
Likes
0
Public
Click a slice to open those files.
.safetensors4.7 MB · 50%
From the Hugging Face model README
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.63 | 0.1866 | 50 | 0.5720 | 0.0 |
| 0.5312 | 0.3731 | 100 | 0.4935 | 0.4037 |
| 0.4732 | 0.5597 | 150 | 0.4822 | 0.4727 |
| 0.4565 | 0.7463 | 200 | 0.4419 | 0.5179 |
| 0.4335 | 0.9328 | 250 | 0.5580 | 0.4498 |
| 0.4261 | 1.1194 | 300 | 0.4339 | 0.5136 |
| 0.3978 | 1.3060 | 350 | 0.4974 | 0.4889 |
| 0.3987 | 1.4925 | 400 | 0.4604 | 0.5002 |
| 0.4283 | 1.6791 | 450 | 0.4054 | 0.5396 |
| 0.3765 | 1.8657 | 500 | 0.5888 | 0.4804 |
| 0.3679 | 2.0522 | 550 | 0.5161 | 0.5220 |
| 0.3494 | 2.2388 | 600 | 0.4854 | 0.5364 |
| 0.3727 | 2.4254 | 650 | 0.4461 | 0.5506 |
| 0.3765 | 2.6119 | 700 | 0.4319 | 0.5528 |
| 0.3295 | 2.7985 | 750 | 0.4251 | 0.5848 |
| 0.3403 | 2.9851 | 800 | 0.4579 | 0.5445 |
| 0.3401 | 3.1716 | 850 | 0.4146 | 0.5648 |
| 0.3237 | 3.3582 | 900 | 0.4308 | 0.5713 |
| 0.3228 | 3.5448 | 950 | 0.5616 | 0.5443 |
| 0.3308 | 3.7313 | 1000 | 0.4390 | 0.5554 |
| 0.3239 | 3.9179 | 1050 | 0.4484 | 0.5634 |
| 0.3243 | 4.1045 | 1100 | 0.4403 | 0.5602 |
| 0.2887 | 4.2910 | 1150 | 0.4864 | 0.5753 |
| 0.2914 | 4.4776 | 1200 | 0.4808 | 0.5629 |
| 0.3089 | 4.6642 | 1250 | 0.4551 | 0.5638 |
| 0.3029 | 4.8507 | 1300 | 0.4804 | 0.5625 |