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: -0.1339
- Accuracy: 0.9598
- Dt Accuracy: 0.9598
- Df Accuracy: 0.975
- Unlearn Overall Accuracy: 0.2220
- 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: 42
- 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 | 32 | -0.1086 | 0.987 | 0.2030 | 0.2030 | None |
| No log | 2.0 | 64 | -0.1094 | 0.986 | 0.2046 | 0.2046 | None |
| No log | 3.0 | 96 | -0.1083 | 0.9858 | 0.2050 | 0.2050 | None |
| No log | 4.0 | 128 | -0.1097 | 0.9868 | 0.2034 | 0.2034 | None |
| No log | 5.0 | 160 | -0.1118 | 0.9865 | 0.2038 | 0.2038 | None |
| No log | 6.0 | 192 | -0.1131 | 0.9852 | 0.2058 | 0.2058 | None |
| No log | 7.0 | 224 | -0.1175 | 0.9825 | 0.2102 | 0.2102 | None |
| No log | 8.0 | 256 | -0.1208 | 0.9802 | 0.2138 | 0.2138 | None |
| No log | 9.0 | 288 | -0.1232 | 0.9782 | 0.2169 | 0.2169 | None |
| No log | 10.0 | 320 | -0.1288 | 0.9762 | 0.2201 | 0.2201 | None |
| No log | 11.0 | 352 | -0.1324 | 0.9765 | 0.2197 | 0.2197 | None |
| No log | 12.0 | 384 | -0.1339 | 0.975 | 0.2220 | 0.2220 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2