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: -0.1110
- Accuracy: 0.9661
- Dt Accuracy: 0.9661
- Df Accuracy: 0.9853
- Unlearn Overall Accuracy: 0.2057
- 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 | 24 | -0.1086 | 0.9877 | 0.2020 | 0.2020 | None |
| No log | 2.0 | 48 | -0.1091 | 0.987 | 0.2030 | 0.2030 | None |
| No log | 3.0 | 72 | -0.1095 | 0.9867 | 0.2036 | 0.2036 | None |
| No log | 4.0 | 96 | -0.1097 | 0.9867 | 0.2036 | 0.2036 | None |
| No log | 5.0 | 120 | -0.1099 | 0.987 | 0.2030 | 0.2030 | None |
| No log | 6.0 | 144 | -0.1112 | 0.9847 | 0.2068 | 0.2068 | None |
| No log | 7.0 | 168 | -0.1107 | 0.9847 | 0.2068 | 0.2068 | None |
| No log | 8.0 | 192 | -0.1091 | 0.986 | 0.2047 | 0.2047 | None |
| No log | 9.0 | 216 | -0.1110 | 0.985 | 0.2063 | 0.2063 | None |
| No log | 10.0 | 240 | -0.1119 | 0.9847 | 0.2068 | 0.2068 | None |
| No log | 11.0 | 264 | -0.1110 | 0.9853 | 0.2057 | 0.2057 | None |
| No log | 12.0 | 288 | -0.1110 | 0.9853 | 0.2057 | 0.2057 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2