100
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: -16.6742
- Accuracy: 0.0455
- Dt Accuracy: 0.0455
- Df Accuracy: 0.0452
- 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: 100
- 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 | 32 | -0.7298 | 0.835 | 0.2957 | 0.2957 | None |
| No log | 2.0 | 64 | -1.8559 | 0.6348 | 0.5072 | 0.5072 | None |
| No log | 3.0 | 96 | -4.4599 | 0.3832 | 0 | 0 | None |
| -2.4361 | 4.0 | 128 | -7.6550 | 0.2018 | 0 | 0 | None |
| -2.4361 | 5.0 | 160 | -10.6793 | 0.1128 | 0 | 0 | None |
| -2.4361 | 6.0 | 192 | -13.1186 | 0.0732 | 0 | 0 | None |
| -10.3352 | 7.0 | 224 | -14.8062 | 0.0568 | 0 | 0 | None |
| -10.3352 | 8.0 | 256 | -15.7218 | 0.05 | 0 | 0 | None |
| -10.3352 | 9.0 | 288 | -16.5016 | 0.046 | 0 | 0 | None |
| -16.1487 | 10.0 | 320 | -16.6742 | 0.0452 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2