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: -26.7713
- Accuracy: 0.0213
- Dt Accuracy: 0.0213
- Df Accuracy: 0.0217
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 32 | -0.7020 | 0.8555 | 0.2662 | 0.2662 | None |
| No log | 2.0 | 64 | -1.0831 | 0.763 | 0.3864 | 0.3864 | None |
| No log | 3.0 | 96 | -2.0345 | 0.6395 | 0.5026 | 0.5026 | None |
| No log | 4.0 | 128 | -3.9058 | 0.4895 | 0 | 0 | None |
| No log | 5.0 | 160 | -6.7776 | 0.3345 | 0 | 0 | None |
| No log | 6.0 | 192 | -9.4698 | 0.1872 | 0 | 0 | None |
| No log | 7.0 | 224 | -12.2079 | 0.1065 | 0 | 0 | None |
| No log | 8.0 | 256 | -13.2775 | 0.0673 | 0 | 0 | None |
| No log | 9.0 | 288 | -15.9643 | 0.0495 | 0 | 0 | None |
| No log | 10.0 | 320 | -18.5127 | 0.0377 | 0 | 0 | None |
| No log | 11.0 | 352 | -20.2035 | 0.031 | 0 | 0 | None |
| No log | 12.0 | 384 | -21.4233 | 0.0262 | 0 | 0 | None |
| No log | 13.0 | 416 | -23.6513 | 0.0238 | 0 | 0 | None |
| No log | 14.0 | 448 | -23.8714 | 0.0235 | 0 | 0 | None |
| No log | 15.0 | 480 | -25.9585 | 0.0243 | 0 | 0 | None |
| -16.7316 | 16.0 | 512 | -26.3497 | 0.0227 | 0 | 0 | None |
| -16.7316 | 17.0 | 544 | -25.2116 | 0.0227 | 0 | 0 | None |
| -16.7316 | 18.0 | 576 | -27.1010 | 0.0222 | 0 | 0 | None |
| -16.7316 | 19.0 | 608 | -26.0663 | 0.0213 | 0 | 0 | None |
| -16.7316 | 20.0 | 640 | -26.7713 | 0.0217 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2