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: 7.0630
- Accuracy: 0.1334
- Dt Accuracy: 0.1334
- Df Accuracy: 0.1335
- 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 | 32 | 0.9638 | 0.809 | 0.3298 | 0.3298 | None |
| No log | 2.0 | 64 | 1.5629 | 0.674 | 0 | 0 | None |
| No log | 3.0 | 96 | 2.5603 | 0.524 | 0 | 0 | None |
| 0.0 | 4.0 | 128 | 3.6729 | 0.395 | 0 | 0 | None |
| 0.0 | 5.0 | 160 | 4.3922 | 0.307 | 0 | 0 | None |
| 0.0 | 6.0 | 192 | 4.8566 | 0.2405 | 0 | 0 | None |
| 0.0 | 7.0 | 224 | 6.1736 | 0.183 | 0 | 0 | None |
| 0.0 | 8.0 | 256 | 6.3192 | 0.1575 | 0 | 0 | None |
| 0.0 | 9.0 | 288 | 6.9565 | 0.136 | 0 | 0 | None |
| 0.0 | 10.0 | 320 | 7.0630 | 0.1335 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2