resnet50_jellyfish_classifier
This model is a fine-tuned version of microsoft/resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1954
- Accuracy: 0.9444
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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 23 | 1.2120 | 0.5611 |
| No log | 2.0 | 46 | 0.6042 | 0.7667 |
| No log | 3.0 | 69 | 0.3322 | 0.8667 |
| No log | 4.0 | 92 | 0.4372 | 0.8722 |
| No log | 5.0 | 115 | 0.2465 | 0.9167 |
| No log | 6.0 | 138 | 0.2132 | 0.9333 |
| No log | 7.0 | 161 | 0.1954 | 0.9444 |
| No log | 8.0 | 184 | 0.1981 | 0.9167 |
| No log | 9.0 | 207 | 0.1531 | 0.9389 |
| No log | 10.0 | 230 | 0.1495 | 0.9389 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2