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: -3.1830
- Accuracy: 0.439
- Dt Accuracy: 0.439
- Df Accuracy: 0.437
- 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 | 16 | -0.6100 | 0.88 | 0.2296 | 0.2296 | None |
| No log | 2.0 | 32 | -0.7246 | 0.827 | 0.3070 | 0.3070 | None |
| No log | 3.0 | 48 | -0.9540 | 0.7515 | 0.4018 | 0.4018 | None |
| No log | 4.0 | 64 | -1.3103 | 0.667 | 0.4855 | 0.4855 | None |
| No log | 5.0 | 80 | -1.7719 | 0.594 | 0.5370 | 0.5370 | None |
| No log | 6.0 | 96 | -2.2620 | 0.537 | 0.5627 | 0.5627 | None |
| -2.0705 | 7.0 | 112 | -2.6711 | 0.488 | 0 | 0 | None |
| -2.0705 | 8.0 | 128 | -2.9641 | 0.4535 | 0 | 0 | None |
| -2.0705 | 9.0 | 144 | -3.1426 | 0.4365 | 0 | 0 | None |
| -2.0705 | 10.0 | 160 | -3.1830 | 0.437 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2