87
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: -30.4430
- Accuracy: 0.0139
- Dt Accuracy: 0.0139
- Df Accuracy: 0.0154
- Unlearn Overall Accuracy: 0
- Unlearn Time: None
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 87
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 40 | -0.8712 | 0.8158 | 0.3211 | 0.3211 | None |
| No log | 2.0 | 80 | -2.1491 | 0.6416 | 0.5009 | 0.5009 | None |
| No log | 3.0 | 120 | -5.6382 | 0.4252 | 0 | 0 | None |
| No log | 4.0 | 160 | -9.5851 | 0.2342 | 0 | 0 | None |
| No log | 5.0 | 200 | -12.9142 | 0.122 | 0 | 0 | None |
| No log | 6.0 | 240 | -15.9253 | 0.0724 | 0 | 0 | None |
| No log | 7.0 | 280 | -16.4527 | 0.0456 | 0 | 0 | None |
| No log | 8.0 | 320 | -21.4992 | 0.0362 | 0 | 0 | None |
| No log | 9.0 | 360 | -21.9941 | 0.0298 | 0 | 0 | None |
| No log | 10.0 | 400 | -25.7521 | 0.0264 | 0 | 0 | None |
| No log | 11.0 | 440 | -29.0888 | 0.0238 | 0 | 0 | None |
| No log | 12.0 | 480 | -29.4552 | 0.02 | 0 | 0 | None |
| -20.7172 | 13.0 | 520 | -28.0849 | 0.019 | 0 | 0 | None |
| -20.7172 | 14.0 | 560 | -33.1038 | 0.0162 | 0 | 0 | None |
| -20.7172 | 15.0 | 600 | -35.5528 | 0.0164 | 0 | 0 | None |
| -20.7172 | 16.0 | 640 | -34.3839 | 0.015 | 0 | 0 | None |
| -20.7172 | 17.0 | 680 | -31.2806 | 0.0156 | 0 | 0 | None |
| -20.7172 | 18.0 | 720 | -33.9595 | 0.0158 | 0 | 0 | None |
| -20.7172 | 19.0 | 760 | -34.7509 | 0.0154 | 0 | 0 | None |
| -20.7172 | 20.0 | 800 | -30.4430 | 0.0154 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2