87
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: -8.7266
- Accuracy: 0.2127
- Dt Accuracy: 0.2127
- Df Accuracy: 0.2238
- 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: 87
- 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 | 40 | -0.2557 | 0.9418 | 0.2718 | 0.2718 | None |
| No log | 2.0 | 80 | -1.3323 | 0.7604 | 0.4743 | 0.4743 | None |
| No log | 3.0 | 120 | -3.0048 | 0.5552 | 0 | 0 | None |
| No log | 4.0 | 160 | -4.5930 | 0.406 | 0 | 0 | None |
| No log | 5.0 | 200 | -5.7110 | 0.315 | 0 | 0 | None |
| No log | 6.0 | 240 | -7.0668 | 0.262 | 0 | 0 | None |
| No log | 7.0 | 280 | -7.8676 | 0.2414 | 0 | 0 | None |
| No log | 8.0 | 320 | -8.4460 | 0.2298 | 0 | 0 | None |
| No log | 9.0 | 360 | -8.9921 | 0.226 | 0 | 0 | None |
| No log | 10.0 | 400 | -8.7266 | 0.2238 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2