87
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 3.1154
- Accuracy: 0.7581
- Dt Accuracy: 0.7581
- Df Accuracy: 0.758
- 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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 87
- 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 | 1.0680 | 0.896 | 0.3330 | 0.3330 | None |
| No log | 2.0 | 32 | 1.7999 | 0.817 | 0.4239 | 0.4239 | None |
| No log | 3.0 | 48 | 1.9001 | 0.808 | 0.4335 | 0.4335 | None |
| No log | 4.0 | 64 | 2.4956 | 0.788 | 0.4520 | 0.4520 | None |
| No log | 5.0 | 80 | 2.6975 | 0.783 | 0.4564 | 0.4564 | None |
| No log | 6.0 | 96 | 2.6041 | 0.766 | 0 | 0 | None |
| No log | 7.0 | 112 | 2.9651 | 0.759 | 0 | 0 | None |
| No log | 8.0 | 128 | 3.0466 | 0.758 | 0 | 0 | None |
| No log | 9.0 | 144 | 3.1867 | 0.745 | 0 | 0 | None |
| No log | 10.0 | 160 | 3.1154 | 0.758 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2