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: 4.6465
- Accuracy: 0.7241
- Dt Accuracy: 0.7241
- Df Accuracy: 0.7305
- 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 | 32 | 1.5473 | 0.8455 | 0.3933 | 0.3933 | None |
| No log | 2.0 | 64 | 2.8681 | 0.7835 | 0.4552 | 0.4552 | None |
| No log | 3.0 | 96 | 3.6692 | 0.7655 | 0 | 0 | None |
| No log | 4.0 | 128 | 4.2883 | 0.7575 | 0 | 0 | None |
| No log | 5.0 | 160 | 4.3924 | 0.747 | 0 | 0 | None |
| No log | 6.0 | 192 | 4.4375 | 0.724 | 0 | 0 | None |
| No log | 7.0 | 224 | 5.1765 | 0.7145 | 0 | 0 | None |
| No log | 8.0 | 256 | 4.2749 | 0.7355 | 0 | 0 | None |
| No log | 9.0 | 288 | 5.2545 | 0.7135 | 0 | 0 | None |
| No log | 10.0 | 320 | 4.6465 | 0.7305 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2