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: -5.1351
- Accuracy: 0.3293
- Dt Accuracy: 0.3293
- Df Accuracy: 0.334
- 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: 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 | 24 | -0.1340 | 0.978 | 0.2172 | 0.2172 | None |
| No log | 2.0 | 48 | -0.3315 | 0.9163 | 0.3074 | 0.3074 | None |
| No log | 3.0 | 72 | -1.0166 | 0.8127 | 0.4281 | 0.4281 | None |
| No log | 4.0 | 96 | -1.9409 | 0.692 | 0.5229 | 0.5229 | None |
| No log | 5.0 | 120 | -2.7606 | 0.5947 | 0.5629 | 0.5629 | None |
| No log | 6.0 | 144 | -3.7547 | 0.495 | 0 | 0 | None |
| No log | 7.0 | 168 | -4.4640 | 0.4177 | 0 | 0 | None |
| No log | 8.0 | 192 | -4.7580 | 0.3757 | 0 | 0 | None |
| No log | 9.0 | 216 | -5.1527 | 0.34 | 0 | 0 | None |
| No log | 10.0 | 240 | -5.1351 | 0.334 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2