42
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: -6.1734
- Accuracy: 0.4633
- Dt Accuracy: 0.4633
- Df Accuracy: 0.4718
- 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: 1e-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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 32 | -0.1475 | 0.9898 | 0.1985 | 0.1985 | None |
| No log | 2.0 | 64 | -0.3224 | 0.9503 | 0.2590 | 0.2590 | None |
| No log | 3.0 | 96 | -1.3843 | 0.8203 | 0.4182 | 0.4182 | None |
| No log | 4.0 | 128 | -2.7740 | 0.7192 | 0.5003 | 0.5003 | None |
| No log | 5.0 | 160 | -3.7965 | 0.6378 | 0.5409 | 0.5409 | None |
| No log | 6.0 | 192 | -4.6399 | 0.5607 | 0 | 0 | None |
| No log | 7.0 | 224 | -5.2912 | 0.5198 | 0 | 0 | None |
| No log | 8.0 | 256 | -5.6292 | 0.5075 | 0 | 0 | None |
| No log | 9.0 | 288 | -5.7188 | 0.4935 | 0 | 0 | None |
| No log | 10.0 | 320 | -5.8928 | 0.4843 | 0 | 0 | None |
| No log | 11.0 | 352 | -6.1721 | 0.4755 | 0 | 0 | None |
| No log | 12.0 | 384 | -6.1734 | 0.4718 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2