42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: -11.6647
- Accuracy: 0.0518
- Dt Accuracy: 0.0518
- Df Accuracy: 0.0548
- 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 | 32 | -0.7864 | 0.8207 | 0.3149 | 0.3149 | None |
| No log | 2.0 | 64 | -1.7254 | 0.6075 | 0.5247 | 0.5247 | None |
| No log | 3.0 | 96 | -3.5493 | 0.3925 | 0 | 0 | None |
| -2.4439 | 4.0 | 128 | -5.8415 | 0.2325 | 0 | 0 | None |
| -2.4439 | 5.0 | 160 | -7.8720 | 0.1393 | 0 | 0 | None |
| -2.4439 | 6.0 | 192 | -9.3259 | 0.097 | 0 | 0 | None |
| -10.0885 | 7.0 | 224 | -10.1002 | 0.0725 | 0 | 0 | None |
| -10.0885 | 8.0 | 256 | -11.2496 | 0.0615 | 0 | 0 | None |
| -10.0885 | 9.0 | 288 | -11.6097 | 0.0558 | 0 | 0 | None |
| -16.1588 | 10.0 | 320 | -11.6647 | 0.0548 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2