Downloads · 30 days
8
30% of all-time downloads
ekiprop/CoLA-Fisher-All-Attention-Q_K_V_O-seed30
CoLA-Fisher-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
8
30% of all-time downloads
All-time downloads
27
Public
Repo size
123 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 |
|---|---|---|---|---|
| 0.6313 | 0.1866 | 50 | 0.5814 | 0.0 |
| 0.5259 | 0.3731 | 100 | 0.4720 | 0.4531 |
| 0.478 | 0.5597 | 150 | 0.4844 | 0.4525 |
| 0.4601 | 0.7463 | 200 | 0.4399 | 0.5079 |
| 0.4253 | 0.9328 | 250 | 0.5527 | 0.4530 |
| 0.4308 | 1.1194 | 300 | 0.4239 | 0.5271 |
| 0.3956 | 1.3060 | 350 | 0.4998 | 0.4865 |
| 0.3959 | 1.4925 | 400 | 0.4725 | 0.4778 |
| 0.426 | 1.6791 | 450 | 0.4115 | 0.5573 |
| 0.3774 | 1.8657 | 500 | 0.5285 | 0.4996 |
| 0.3625 | 2.0522 | 550 | 0.5133 | 0.5430 |
| 0.3523 | 2.2388 | 600 | 0.5114 | 0.5426 |
| 0.3745 | 2.4254 | 650 | 0.4466 | 0.5335 |
| 0.3802 | 2.6119 | 700 | 0.4411 | 0.5554 |
| 0.3341 | 2.7985 | 750 | 0.4242 | 0.5925 |
| 0.3421 | 2.9851 | 800 | 0.4673 | 0.5495 |
| 0.3444 | 3.1716 | 850 | 0.4206 | 0.5751 |
| 0.3277 | 3.3582 | 900 | 0.4314 | 0.5708 |
| 0.3337 | 3.5448 | 950 | 0.5423 | 0.5339 |
| 0.3303 | 3.7313 | 1000 | 0.4399 | 0.5833 |
| 0.3219 | 3.9179 | 1050 | 0.4600 | 0.5858 |
| 0.322 | 4.1045 | 1100 | 0.4502 | 0.5881 |
| 0.2858 | 4.2910 | 1150 | 0.4870 | 0.5855 |
| 0.2938 | 4.4776 | 1200 | 0.4885 | 0.5856 |
| 0.3099 | 4.6642 | 1250 | 0.4640 | 0.5883 |
| 0.3057 | 4.8507 | 1300 | 0.4800 | 0.5779 |