42
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: -1.8776
- Accuracy: 0.6383
- Dt Accuracy: 0.6383
- Df Accuracy: 0.617
- Unlearn Overall Accuracy: 0.5617
- 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: 42
- 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 | -0.1324 | 0.9705 | 0.2290 | 0.2290 | None |
| No log | 2.0 | 32 | -0.1882 | 0.951 | 0.2585 | 0.2585 | None |
| No log | 3.0 | 48 | -0.3120 | 0.911 | 0.3150 | 0.3150 | None |
| No log | 4.0 | 64 | -0.5466 | 0.853 | 0.3868 | 0.3868 | None |
| No log | 5.0 | 80 | -0.8522 | 0.7885 | 0.4525 | 0.4525 | None |
| No log | 6.0 | 96 | -1.1810 | 0.7305 | 0.5005 | 0.5005 | None |
| No log | 7.0 | 112 | -1.5182 | 0.6755 | 0.5341 | 0.5341 | None |
| No log | 8.0 | 128 | -1.6919 | 0.648 | 0.5487 | 0.5487 | None |
| No log | 9.0 | 144 | -1.8480 | 0.626 | 0.5579 | 0.5579 | None |
| No log | 10.0 | 160 | -1.8776 | 0.617 | 0.5617 | 0.5617 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2