metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21K
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetuned-cards-blackjack
results: []
finetuned-cards-blackjack
This model is a fine-tuned version of google/vit-base-patch16-224-in21K on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9121
- Accuracy: 0.7710
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 | Accuracy |
---|---|---|---|---|
3.1307 | 0.24 | 100 | 3.0180 | 0.2093 |
2.7372 | 0.48 | 200 | 2.5301 | 0.2762 |
2.4969 | 0.73 | 300 | 2.1760 | 0.3439 |
2.1973 | 0.97 | 400 | 2.0103 | 0.3756 |
1.8847 | 1.21 | 500 | 1.8402 | 0.4108 |
1.746 | 1.45 | 600 | 1.7051 | 0.4803 |
1.8698 | 1.69 | 700 | 1.5985 | 0.4889 |
1.7261 | 1.94 | 800 | 1.4312 | 0.5840 |
1.7385 | 2.18 | 900 | 1.3585 | 0.6286 |
1.5873 | 2.42 | 1000 | 1.2374 | 0.6758 |
1.4775 | 2.66 | 1100 | 1.1352 | 0.7024 |
1.2697 | 2.91 | 1200 | 1.1044 | 0.7093 |
1.2137 | 3.15 | 1300 | 1.0006 | 0.7616 |
1.423 | 3.39 | 1400 | 0.9589 | 0.7744 |
1.0098 | 3.63 | 1500 | 0.9360 | 0.7684 |
1.1325 | 3.87 | 1600 | 0.9121 | 0.7710 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2