87
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: 2.6588
- Accuracy: 0.8117
- Dt Accuracy: 0.8117
- Df Accuracy: 0.82
- Unlearn Overall Accuracy: 0.4205
- 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 | 47 | 0.1830 | 0.9733 | 0.2246 | 0.2246 | None |
| No log | 2.0 | 94 | 0.2905 | 0.9547 | 0.2530 | 0.2530 | None |
| No log | 3.0 | 141 | 0.4986 | 0.9363 | 0.2795 | 0.2795 | None |
| No log | 4.0 | 188 | 0.7269 | 0.9183 | 0.3046 | 0.3046 | None |
| No log | 5.0 | 235 | 1.1557 | 0.8923 | 0.3385 | 0.3385 | None |
| No log | 6.0 | 282 | 1.4587 | 0.8763 | 0.3581 | 0.3581 | None |
| No log | 7.0 | 329 | 2.1115 | 0.84 | 0.4001 | 0.4001 | None |
| No log | 8.0 | 376 | 2.4536 | 0.834 | 0.4056 | 0.4056 | None |
| No log | 9.0 | 423 | 2.5002 | 0.8287 | 0.4115 | 0.4115 | None |
| No log | 10.0 | 470 | 2.6588 | 0.82 | 0.4205 | 0.4205 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2