42
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: 3.0914
- Accuracy: 0.7888
- Dt Accuracy: 0.7888
- Df Accuracy: 0.7953
- Unlearn Overall Accuracy: 0.4445
- 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 | 47 | 0.1824 | 0.973 | 0.2251 | 0.2251 | None |
| No log | 2.0 | 94 | 0.3265 | 0.9543 | 0.2534 | 0.2534 | None |
| No log | 3.0 | 141 | 0.5218 | 0.9313 | 0.2866 | 0.2866 | None |
| No log | 4.0 | 188 | 0.8913 | 0.9087 | 0.3172 | 0.3172 | None |
| No log | 5.0 | 235 | 1.4137 | 0.8653 | 0.3716 | 0.3716 | None |
| No log | 6.0 | 282 | 1.6859 | 0.8523 | 0.3865 | 0.3865 | None |
| No log | 7.0 | 329 | 2.4252 | 0.8193 | 0.4215 | 0.4215 | None |
| No log | 8.0 | 376 | 3.0697 | 0.799 | 0.4407 | 0.4407 | None |
| No log | 9.0 | 423 | 2.8971 | 0.7977 | 0.4426 | 0.4426 | None |
| No log | 10.0 | 470 | 3.0914 | 0.7953 | 0.4445 | 0.4445 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2