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: 0.2368
- Accuracy: 0.9504
- Dt Accuracy: 0.9504
- Df Accuracy: 0.961
- Unlearn Overall Accuracy: 0.2436
- 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 | 16 | 0.1279 | 0.983 | 0.2094 | 0.2094 | None |
| No log | 2.0 | 32 | 0.1410 | 0.979 | 0.2157 | 0.2157 | None |
| No log | 3.0 | 48 | 0.1546 | 0.981 | 0.2125 | 0.2125 | None |
| No log | 4.0 | 64 | 0.1752 | 0.977 | 0.2188 | 0.2188 | None |
| No log | 5.0 | 80 | 0.1980 | 0.973 | 0.2251 | 0.2251 | None |
| No log | 6.0 | 96 | 0.2073 | 0.968 | 0.2328 | 0.2328 | None |
| No log | 7.0 | 112 | 0.2380 | 0.96 | 0.2451 | 0.2451 | None |
| No log | 8.0 | 128 | 0.2355 | 0.961 | 0.2436 | 0.2436 | None |
| No log | 9.0 | 144 | 0.2476 | 0.963 | 0.2404 | 0.2404 | None |
| No log | 10.0 | 160 | 0.2368 | 0.961 | 0.2436 | 0.2436 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2