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: -3.0589
- Accuracy: 0.6234
- Dt Accuracy: 0.6234
- Df Accuracy: 0.6235
- Unlearn Overall Accuracy: 0.5520
- 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 | 16 | -0.1157 | 0.9805 | 0.2134 | 0.2134 | None |
| No log | 2.0 | 32 | -0.1686 | 0.962 | 0.2421 | 0.2421 | None |
| No log | 3.0 | 48 | -0.3309 | 0.913 | 0.3120 | 0.3120 | None |
| No log | 4.0 | 64 | -0.7153 | 0.836 | 0.4054 | 0.4054 | None |
| No log | 5.0 | 80 | -1.3874 | 0.7515 | 0.4836 | 0.4836 | None |
| No log | 6.0 | 96 | -1.9472 | 0.7035 | 0.5149 | 0.5149 | None |
| No log | 7.0 | 112 | -2.4520 | 0.66 | 0.5395 | 0.5395 | None |
| No log | 8.0 | 128 | -2.7804 | 0.641 | 0.5447 | 0.5447 | None |
| No log | 9.0 | 144 | -3.0317 | 0.628 | 0.5504 | 0.5504 | None |
| No log | 10.0 | 160 | -3.0589 | 0.6235 | 0.5520 | 0.5520 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2