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: -21.0658
- Accuracy: 0.027
- Dt Accuracy: 0.027
- Df Accuracy: 0.0288
- 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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 40 | -1.2421 | 0.744 | 0.4074 | 0.4074 | None |
| No log | 2.0 | 80 | -4.2104 | 0.4494 | 0 | 0 | None |
| -3.0776 | 3.0 | 120 | -7.8109 | 0.2374 | 0 | 0 | None |
| -3.0776 | 4.0 | 160 | -10.7112 | 0.1116 | 0 | 0 | None |
| -12.3046 | 5.0 | 200 | -13.5279 | 0.0668 | 0 | 0 | None |
| -12.3046 | 6.0 | 240 | -16.0423 | 0.0472 | 0 | 0 | None |
| -12.3046 | 7.0 | 280 | -17.3981 | 0.039 | 0 | 0 | None |
| -20.2207 | 8.0 | 320 | -20.0833 | 0.0344 | 0 | 0 | None |
| -20.2207 | 9.0 | 360 | -20.2581 | 0.0292 | 0 | 0 | None |
| -24.2884 | 10.0 | 400 | -21.0658 | 0.0288 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2