Downloads · 30 days
2
4% of all-time downloads
jialicheng/unlearn-so_cifar10_swin-base_bad_teaching_6_21
unlearn-so_cifar10_swin-base_bad_teaching_6_21 is a image classification model from jialicheng. Use it when you need a label for an image. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
2
4% of all-time downloads
All-time downloads
52
Public
Parameters
86.8M
350 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors348 MB · 99%
How the weights are stored.
F3286.8M · 100%
From the Hugging Face model README
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar10 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 | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 47 | 1.0900 | 0.965 | 0.2366 | 0.2366 | None |
| No log | 2.0 | 94 | 1.2204 | 0.96 | 0.2442 | 0.2442 | None |
| No log | 3.0 | 141 | 1.5806 | 0.9523 | 0.2554 | 0.2554 | None |
| No log | 4.0 | 188 | 1.2138 | 0.9673 | 0.2333 | 0.2333 | None |
| No log | 5.0 | 235 | 1.1211 | 0.971 | 0.2278 | 0.2278 | None |
| No log | 6.0 | 282 | 1.4198 | 0.9643 | 0.2380 | 0.2380 | None |
| No log | 7.0 | 329 | 1.0933 | 0.9647 | 0.2376 | 0.2376 | None |
| No log | 8.0 | 376 | 1.1065 | 0.9677 | 0.2330 | 0.2330 | None |
| No log | 9.0 | 423 | 0.9709 | 0.9677 | 0.2331 | 0.2331 | None |
| No log | 10.0 | 470 | 1.0030 | 0.9643 | 0.2382 | 0.2382 | None |