42
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 7.2881
- Accuracy: 0.6471
- Dt Accuracy: 0.6471
- Df Accuracy: 0.646
- 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: 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 | 63 | 2.0543 | 0.8145 | 0.4257 | 0.4257 | None |
| No log | 2.0 | 126 | 3.8228 | 0.7465 | 0 | 0 | None |
| No log | 3.0 | 189 | 5.5986 | 0.7165 | 0 | 0 | None |
| No log | 4.0 | 252 | 6.0377 | 0.682 | 0 | 0 | None |
| No log | 5.0 | 315 | 5.7711 | 0.6695 | 0 | 0 | None |
| No log | 6.0 | 378 | 6.6544 | 0.67 | 0 | 0 | None |
| No log | 7.0 | 441 | 7.1566 | 0.6442 | 0 | 0 | None |
| 0.0 | 8.0 | 504 | 6.6774 | 0.6528 | 0 | 0 | None |
| 0.0 | 9.0 | 567 | 8.2420 | 0.632 | 0 | 0 | None |
| 0.0 | 10.0 | 630 | 7.2881 | 0.646 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2