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: 10.2877
- Accuracy: 0.5532
- Dt Accuracy: 0.5532
- Df Accuracy: 0.5602
- 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 | 79 | 3.9701 | 0.7518 | 0 | 0 | None |
| No log | 2.0 | 158 | 6.0782 | 0.6882 | 0 | 0 | None |
| No log | 3.0 | 237 | 5.8971 | 0.693 | 0 | 0 | None |
| No log | 4.0 | 316 | 7.4783 | 0.6388 | 0 | 0 | None |
| No log | 5.0 | 395 | 7.9576 | 0.588 | 0 | 0 | None |
| No log | 6.0 | 474 | 9.1742 | 0.5962 | 0 | 0 | None |
| 0.0 | 7.0 | 553 | 8.7191 | 0.5912 | 0 | 0 | None |
| 0.0 | 8.0 | 632 | 9.6104 | 0.559 | 0 | 0 | None |
| 0.0 | 9.0 | 711 | 9.2321 | 0.5802 | 0 | 0 | None |
| 0.0 | 10.0 | 790 | 10.2877 | 0.5602 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2