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: 0.5627
- Accuracy: 0.8363
- Dt Accuracy: 0.8363
- Df Accuracy: 0.734
- Unlearn Overall Accuracy: 0.4323
- 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| 1.2716 | 1.0 | 391 | 0.5900 | 0.7525 | 0.4090 | 0.4090 | None |
| 1.2542 | 2.0 | 782 | 0.5805 | 0.7285 | 0.4390 | 0.4390 | None |
| 1.2022 | 3.0 | 1173 | 0.5819 | 0.7255 | 0.4426 | 0.4426 | None |
| 1.1697 | 4.0 | 1564 | 0.5784 | 0.7305 | 0.4367 | 0.4367 | None |
| 1.1514 | 5.0 | 1955 | 0.5715 | 0.7385 | 0.4270 | 0.4270 | None |
| 1.1302 | 6.0 | 2346 | 0.5700 | 0.74 | 0.4252 | 0.4252 | None |
| 1.1145 | 7.0 | 2737 | 0.5717 | 0.722 | 0.4472 | 0.4472 | None |
| 1.1044 | 8.0 | 3128 | 0.5694 | 0.7305 | 0.4368 | 0.4368 | None |
| 1.1058 | 9.0 | 3519 | 0.5634 | 0.7355 | 0.4305 | 0.4305 | None |
| 1.083 | 10.0 | 3910 | 0.5627 | 0.734 | 0.4323 | 0.4323 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0