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: -3.5888
- Accuracy: 0.559
- Dt Accuracy: 0.559
- Df Accuracy: 0.5643
- 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 | 24 | -0.1437 | 0.9897 | 0.1986 | 0.1986 | None |
| No log | 2.0 | 48 | -0.2039 | 0.9747 | 0.2222 | 0.2222 | None |
| No log | 3.0 | 72 | -0.6309 | 0.8987 | 0.3300 | 0.3300 | None |
| No log | 4.0 | 96 | -1.3061 | 0.8577 | 0.3785 | 0.3785 | None |
| No log | 5.0 | 120 | -1.7955 | 0.8027 | 0.4363 | 0.4363 | None |
| No log | 6.0 | 144 | -2.2647 | 0.7423 | 0.4859 | 0.4859 | None |
| No log | 7.0 | 168 | -2.6820 | 0.6757 | 0.5275 | 0.5275 | None |
| No log | 8.0 | 192 | -3.0834 | 0.619 | 0.5515 | 0.5515 | None |
| No log | 9.0 | 216 | -3.2852 | 0.5897 | 0.5594 | 0.5594 | None |
| No log | 10.0 | 240 | -3.4582 | 0.5743 | 0 | 0 | None |
| No log | 11.0 | 264 | -3.6993 | 0.566 | 0 | 0 | None |
| No log | 12.0 | 288 | -3.5888 | 0.5643 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2