21
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: 13.4014
- Accuracy: 0.0116
- Dt Accuracy: 0.0116
- Df Accuracy: 0.0135
- 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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 21
- 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 | 63 | 1.6349 | 0.6707 | 0 | 0 | None |
| 0.0 | 2.0 | 126 | 3.8181 | 0.3593 | 0 | 0 | None |
| 0.0 | 3.0 | 189 | 7.1618 | 0.1343 | 0 | 0 | None |
| 0.0 | 4.0 | 252 | 8.6572 | 0.0385 | 0 | 0 | None |
| 0.0 | 5.0 | 315 | 11.9458 | 0.0227 | 0 | 0 | None |
| 0.0 | 6.0 | 378 | 11.8444 | 0.0158 | 0 | 0 | None |
| 0.0 | 7.0 | 441 | 12.8670 | 0.0143 | 0 | 0 | None |
| 0.0 | 8.0 | 504 | 13.4815 | 0.012 | 0 | 0 | None |
| 0.0 | 9.0 | 567 | 13.0402 | 0.0118 | 0 | 0 | None |
| 0.0 | 10.0 | 630 | 13.4014 | 0.0135 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2