13
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: -16.0461
- Accuracy: 0.0742
- Dt Accuracy: 0.0742
- Df Accuracy: 0.0714
- 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: 13
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 40 | -0.2241 | 0.9508 | 0.2585 | 0.2585 | None |
| No log | 2.0 | 80 | -1.7482 | 0.6996 | 0.5181 | 0.5181 | None |
| No log | 3.0 | 120 | -4.5269 | 0.428 | 0 | 0 | None |
| No log | 4.0 | 160 | -7.0117 | 0.2378 | 0 | 0 | None |
| No log | 5.0 | 200 | -9.8466 | 0.1428 | 0 | 0 | None |
| No log | 6.0 | 240 | -12.2087 | 0.1034 | 0 | 0 | None |
| No log | 7.0 | 280 | -13.8078 | 0.0818 | 0 | 0 | None |
| No log | 8.0 | 320 | -15.2491 | 0.075 | 0 | 0 | None |
| No log | 9.0 | 360 | -15.4137 | 0.0724 | 0 | 0 | None |
| No log | 10.0 | 400 | -16.0461 | 0.0714 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2