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: 4.4409
- Accuracy: 0.2995
- Dt Accuracy: 0.2995
- Df Accuracy: 0.3113
- 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: 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 47 | 0.7529 | 0.862 | 0.2564 | 0.2564 | None |
| No log | 2.0 | 94 | 1.2009 | 0.7603 | 0.3879 | 0.3879 | None |
| 0.0 | 3.0 | 141 | 1.6691 | 0.662 | 0 | 0 | None |
| 0.0 | 4.0 | 188 | 2.3438 | 0.5537 | 0 | 0 | None |
| 0.0 | 5.0 | 235 | 2.6868 | 0.4997 | 0 | 0 | None |
| 0.0 | 6.0 | 282 | 3.4583 | 0.415 | 0 | 0 | None |
| 0.0 | 7.0 | 329 | 3.8090 | 0.374 | 0 | 0 | None |
| 0.0 | 8.0 | 376 | 4.0646 | 0.3437 | 0 | 0 | None |
| 0.0 | 9.0 | 423 | 4.7726 | 0.3033 | 0 | 0 | None |
| 0.0 | 10.0 | 470 | 4.4409 | 0.3113 | 0 | 0 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0