87
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: 59.1734
- Accuracy: 0.0169
- Dt Accuracy: 0.0169
- Df Accuracy: 0.0184
- 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: 0.0002
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 79 | 3.6139 | 0.4246 | 0 | 0 | None |
| No log | 2.0 | 158 | 10.6952 | 0.0618 | 0 | 0 | None |
| No log | 3.0 | 237 | 17.4675 | 0.02 | 0 | 0 | None |
| No log | 4.0 | 316 | 24.7450 | 0.0176 | 0 | 0 | None |
| No log | 5.0 | 395 | 33.6965 | 0.0162 | 0 | 0 | None |
| No log | 6.0 | 474 | 39.7375 | 0.0152 | 0 | 0 | None |
| 0.0 | 7.0 | 553 | 50.0622 | 0.0166 | 0 | 0 | None |
| 0.0 | 8.0 | 632 | 41.3608 | 0.0162 | 0 | 0 | None |
| 0.0 | 9.0 | 711 | 51.3286 | 0.0156 | 0 | 0 | None |
| 0.0 | 10.0 | 790 | 47.9392 | 0.0156 | 0 | 0 | None |
| 0.0 | 11.0 | 869 | 47.2069 | 0.0168 | 0 | 0 | None |
| 0.0 | 12.0 | 948 | 45.5358 | 0.0164 | 0 | 0 | None |
| 0.0 | 13.0 | 1027 | 43.8302 | 0.0172 | 0 | 0 | None |
| 0.0 | 14.0 | 1106 | 57.6853 | 0.0176 | 0 | 0 | None |
| 0.0 | 15.0 | 1185 | 52.6795 | 0.0182 | 0 | 0 | None |
| 0.0 | 16.0 | 1264 | 71.4143 | 0.0176 | 0 | 0 | None |
| 0.0 | 17.0 | 1343 | 66.4316 | 0.019 | 0 | 0 | None |
| 0.0 | 18.0 | 1422 | 67.8244 | 0.0178 | 0 | 0 | None |
| 0.0 | 19.0 | 1501 | 61.4364 | 0.0182 | 0 | 0 | None |
| 0.0 | 20.0 | 1580 | 59.1734 | 0.0184 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2