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: 0.2967
- Accuracy: 0.9416
- Dt Accuracy: 0.9416
- Df Accuracy: 0.956
- Unlearn Overall Accuracy: 0.2509
- 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: 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 | 16 | 0.1276 | 0.981 | 0.2126 | 0.2126 | None |
| No log | 2.0 | 32 | 0.1524 | 0.978 | 0.2173 | 0.2173 | None |
| No log | 3.0 | 48 | 0.1731 | 0.974 | 0.2235 | 0.2235 | None |
| No log | 4.0 | 64 | 0.2054 | 0.969 | 0.2313 | 0.2313 | None |
| No log | 5.0 | 80 | 0.2144 | 0.969 | 0.2312 | 0.2312 | None |
| No log | 6.0 | 96 | 0.2425 | 0.966 | 0.2358 | 0.2358 | None |
| No log | 7.0 | 112 | 0.2626 | 0.962 | 0.2419 | 0.2419 | None |
| No log | 8.0 | 128 | 0.2643 | 0.963 | 0.2403 | 0.2403 | None |
| No log | 9.0 | 144 | 0.2703 | 0.958 | 0.2480 | 0.2480 | None |
| No log | 10.0 | 160 | 0.2967 | 0.956 | 0.2509 | 0.2509 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2