Downloads · 30 days
7
26% of all-time downloads
ekiprop/CoLA-Fisher-All-Attention-Q_K_V_O-seed20
CoLA-Fisher-All-Attention-Q_K_V_O-seed20 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
7
26% of all-time downloads
All-time downloads
27
Public
Repo size
66.4 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 |
|---|---|---|---|---|
| 0.6316 | 0.1866 | 50 | 0.5929 | 0.0 |
| 0.5422 | 0.3731 | 100 | 0.4618 | 0.4539 |
| 0.4786 | 0.5597 | 150 | 0.4785 | 0.4802 |
| 0.4547 | 0.7463 | 200 | 0.4324 | 0.5171 |
| 0.4255 | 0.9328 | 250 | 0.5424 | 0.4584 |
| 0.4297 | 1.1194 | 300 | 0.4365 | 0.5351 |
| 0.395 | 1.3060 | 350 | 0.4659 | 0.5126 |
| 0.4056 | 1.4925 | 400 | 0.4436 | 0.4997 |
| 0.427 | 1.6791 | 450 | 0.4011 | 0.5673 |
| 0.3777 | 1.8657 | 500 | 0.5474 | 0.4965 |
| 0.3694 | 2.0522 | 550 | 0.5022 | 0.5325 |
| 0.3619 | 2.2388 | 600 | 0.4758 | 0.5596 |
| 0.3656 | 2.4254 | 650 | 0.4406 | 0.5699 |
| 0.3817 | 2.6119 | 700 | 0.4298 | 0.5466 |
| 0.3347 | 2.7985 | 750 | 0.4152 | 0.5770 |
| 0.3468 | 2.9851 | 800 | 0.4509 | 0.5417 |
| 0.3394 | 3.1716 | 850 | 0.4198 | 0.5599 |
| 0.3247 | 3.3582 | 900 | 0.4235 | 0.5725 |
| 0.3296 | 3.5448 | 950 | 0.5481 | 0.5445 |
| 0.3318 | 3.7313 | 1000 | 0.4357 | 0.5608 |
| 0.3168 | 3.9179 | 1050 | 0.4426 | 0.5711 |
| 0.3262 | 4.1045 | 1100 | 0.4283 | 0.5706 |
| 0.2877 | 4.2910 | 1150 | 0.4616 | 0.5554 |
| 0.3002 | 4.4776 | 1200 | 0.4683 | 0.5653 |
| 0.3093 | 4.6642 | 1250 | 0.4547 | 0.5534 |
| 0.3059 | 4.8507 | 1300 | 0.4739 | 0.5549 |