42
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: -2.4222
- Accuracy: 0.5902
- Dt Accuracy: 0.5902
- Df Accuracy: 0.573
- Unlearn Overall Accuracy: 0.5542
- 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: 42
- 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 | 8 | -0.5876 | 0.905 | 0.1899 | 0.1899 | None |
| No log | 2.0 | 16 | -0.6369 | 0.871 | 0.2434 | 0.2434 | None |
| No log | 3.0 | 24 | -0.6889 | 0.85 | 0.2746 | 0.2746 | None |
| No log | 4.0 | 32 | -0.7405 | 0.837 | 0.2929 | 0.2929 | None |
| No log | 5.0 | 40 | -0.7999 | 0.821 | 0.3148 | 0.3148 | None |
| No log | 6.0 | 48 | -0.8907 | 0.793 | 0.3515 | 0.3515 | None |
| No log | 7.0 | 56 | -0.9839 | 0.767 | 0.3835 | 0.3835 | None |
| No log | 8.0 | 64 | -1.1172 | 0.743 | 0.4109 | 0.4109 | None |
| No log | 9.0 | 72 | -1.2552 | 0.712 | 0.4442 | 0.4442 | None |
| No log | 10.0 | 80 | -1.4104 | 0.69 | 0.4653 | 0.4653 | None |
| No log | 11.0 | 88 | -1.5454 | 0.665 | 0.4888 | 0.4888 | None |
| No log | 12.0 | 96 | -1.7092 | 0.646 | 0.5035 | 0.5035 | None |
| No log | 13.0 | 104 | -1.8727 | 0.623 | 0.5222 | 0.5222 | None |
| No log | 14.0 | 112 | -2.0095 | 0.607 | 0.5334 | 0.5334 | None |
| No log | 15.0 | 120 | -2.1280 | 0.597 | 0.5400 | 0.5400 | None |
| No log | 16.0 | 128 | -2.2337 | 0.589 | 0.5455 | 0.5455 | None |
| No log | 17.0 | 136 | -2.3178 | 0.582 | 0.5484 | 0.5484 | None |
| No log | 18.0 | 144 | -2.3705 | 0.577 | 0.5516 | 0.5516 | None |
| No log | 19.0 | 152 | -2.3891 | 0.576 | 0.5519 | 0.5519 | None |
| No log | 20.0 | 160 | -2.4222 | 0.573 | 0.5542 | 0.5542 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2