resnet-50-0.007
This model is a fine-tuned version of microsoft/resnet-50 on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9735
- Accuracy: 0.6296
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: 0.007
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4221 | 1.0 | 224 | 1.2410 | 0.5274 |
| 1.2521 | 2.0 | 448 | 1.1716 | 0.5499 |
| 1.1609 | 3.0 | 672 | 1.0495 | 0.5968 |
| 1.1457 | 4.0 | 896 | 0.9735 | 0.6296 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1