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: 0.9525
- Accuracy: 0.8914
- Dt Accuracy: 0.8914
- Df Accuracy: 0.897
- Unlearn Overall Accuracy: 0.3329
- 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: 0.0001
- 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 | 32 | 0.1667 | 0.972 | 0.2266 | 0.2266 | None |
| No log | 2.0 | 64 | 0.2031 | 0.9675 | 0.2336 | 0.2336 | None |
| No log | 3.0 | 96 | 0.2669 | 0.96 | 0.245 | 0.245 | None |
| No log | 4.0 | 128 | 0.3595 | 0.946 | 0.2658 | 0.2658 | None |
| No log | 5.0 | 160 | 0.5510 | 0.929 | 0.2899 | 0.2899 | None |
| No log | 6.0 | 192 | 0.6281 | 0.9235 | 0.2975 | 0.2975 | None |
| No log | 7.0 | 224 | 0.7606 | 0.9165 | 0.3069 | 0.3069 | None |
| No log | 8.0 | 256 | 0.8358 | 0.9035 | 0.3243 | 0.3243 | None |
| No log | 9.0 | 288 | 0.9320 | 0.8985 | 0.3309 | 0.3309 | None |
| No log | 10.0 | 320 | 0.9525 | 0.897 | 0.3329 | 0.3329 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2