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: -5.3942
- Accuracy: 0.5338
- Dt Accuracy: 0.5338
- Df Accuracy: 0.5387
- 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: 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 | 24 | -0.1316 | 0.9787 | 0.2163 | 0.2163 | None |
| No log | 2.0 | 48 | -0.2809 | 0.9363 | 0.2796 | 0.2796 | None |
| No log | 3.0 | 72 | -0.9670 | 0.8253 | 0.4166 | 0.4166 | None |
| No log | 4.0 | 96 | -2.0953 | 0.7357 | 0.4946 | 0.4946 | None |
| No log | 5.0 | 120 | -3.1832 | 0.6693 | 0.5334 | 0.5334 | None |
| No log | 6.0 | 144 | -4.0033 | 0.6217 | 0.5528 | 0.5528 | None |
| No log | 7.0 | 168 | -4.7630 | 0.5853 | 0.5603 | 0.5603 | None |
| No log | 8.0 | 192 | -4.9921 | 0.5563 | 0 | 0 | None |
| No log | 9.0 | 216 | -5.3239 | 0.5447 | 0 | 0 | None |
| No log | 10.0 | 240 | -5.3942 | 0.5387 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2