metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: cat_dog_model
results: []
cat_dog_model
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0825
- Accuracy: 0.9705
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4162 | 1.0 | 586 | 0.1376 | 0.9562 |
| 0.1484 | 2.0 | 1172 | 0.0977 | 0.9645 |
| 0.1142 | 3.0 | 1758 | 0.0877 | 0.9665 |
| 0.1062 | 4.0 | 2344 | 0.0882 | 0.9695 |
| 0.1027 | 5.0 | 2930 | 0.0825 | 0.9705 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1