87
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: -0.1370
- Accuracy: 0.9572
- Dt Accuracy: 0.9572
- Df Accuracy: 0.9746
- Unlearn Overall Accuracy: 0.2226
- 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 | -0.1146 | 0.9854 | 0.2056 | 0.2056 | None |
| No log | 2.0 | 80 | -0.1093 | 0.9854 | 0.2056 | 0.2056 | None |
| No log | 3.0 | 120 | -0.1122 | 0.9852 | 0.2059 | 0.2059 | None |
| No log | 4.0 | 160 | -0.1165 | 0.9814 | 0.2119 | 0.2119 | None |
| No log | 5.0 | 200 | -0.1214 | 0.9802 | 0.2138 | 0.2138 | None |
| No log | 6.0 | 240 | -0.1211 | 0.9804 | 0.2135 | 0.2135 | None |
| No log | 7.0 | 280 | -0.1230 | 0.979 | 0.2157 | 0.2157 | None |
| No log | 8.0 | 320 | -0.1262 | 0.9778 | 0.2176 | 0.2176 | None |
| No log | 9.0 | 360 | -0.1289 | 0.977 | 0.2189 | 0.2189 | None |
| No log | 10.0 | 400 | -0.1403 | 0.974 | 0.2235 | 0.2235 | None |
| No log | 11.0 | 440 | -0.1360 | 0.975 | 0.2220 | 0.2220 | None |
| No log | 12.0 | 480 | -0.1370 | 0.9746 | 0.2226 | 0.2226 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2