metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
model-index:
- name: ryan_model3272024
results: []
ryan_model3272024
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3657
- Na Accuracy: 0.625
- Ordinal Accuracy: 0.4762
- Ordinal Mae: 0.8694
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Na Accuracy | Ordinal Accuracy | Ordinal Mae |
|---|---|---|---|---|---|---|
| 0.412 | 0.78 | 25 | 0.3861 | 0.875 | 0.2143 | 1.0826 |
| 0.2394 | 1.56 | 50 | 0.4621 | 0.5 | 0.1905 | 1.0658 |
| 0.2287 | 2.34 | 75 | 0.5636 | 0.25 | 0.2857 | 0.9874 |
| 0.1518 | 3.12 | 100 | 0.3832 | 0.625 | 0.3810 | 0.9202 |
| 0.1448 | 3.91 | 125 | 0.3657 | 0.625 | 0.4762 | 0.8694 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2