87
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: -8.7543
- Accuracy: 0.3179
- Dt Accuracy: 0.3179
- Df Accuracy: 0.3234
- 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: 1e-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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 40 | -0.1896 | 0.9818 | 0.2110 | 0.2110 | None |
| No log | 2.0 | 80 | -0.7927 | 0.8626 | 0.3728 | 0.3728 | None |
| No log | 3.0 | 120 | -2.5928 | 0.6702 | 0.5282 | 0.5282 | None |
| No log | 4.0 | 160 | -4.2885 | 0.5462 | 0 | 0 | None |
| No log | 5.0 | 200 | -5.3869 | 0.473 | 0 | 0 | None |
| No log | 6.0 | 240 | -6.2143 | 0.444 | 0 | 0 | None |
| No log | 7.0 | 280 | -6.6037 | 0.4214 | 0 | 0 | None |
| No log | 8.0 | 320 | -7.8018 | 0.3912 | 0 | 0 | None |
| No log | 9.0 | 360 | -7.6152 | 0.3704 | 0 | 0 | None |
| No log | 10.0 | 400 | -8.4943 | 0.334 | 0 | 0 | None |
| No log | 11.0 | 440 | -8.5785 | 0.3242 | 0 | 0 | None |
| No log | 12.0 | 480 | -8.7543 | 0.3234 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2