metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- 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 beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.3037
- Na Accuracy: 0.7297
- Ordinal Accuracy: 0.5285
- Ordinal Mae: 0.6723
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 |
---|---|---|---|---|---|---|
0.4062 | 0.13 | 25 | 0.3799 | 0.6216 | 0.2395 | 0.9244 |
0.3536 | 0.27 | 50 | 0.3700 | 0.6757 | 0.3840 | 0.9067 |
0.4295 | 0.4 | 75 | 0.3405 | 0.7838 | 0.2966 | 0.8798 |
0.4114 | 0.53 | 100 | 0.3906 | 0.7297 | 0.3536 | 0.8806 |
0.3521 | 0.66 | 125 | 0.3530 | 0.8108 | 0.4259 | 0.8442 |
0.3349 | 0.8 | 150 | 0.3412 | 0.7297 | 0.4753 | 0.8016 |
0.4612 | 0.93 | 175 | 0.3639 | 0.5405 | 0.4677 | 0.7604 |
0.2424 | 1.06 | 200 | 0.3297 | 0.7027 | 0.4867 | 0.7117 |
0.2928 | 1.2 | 225 | 0.3494 | 0.6757 | 0.5285 | 0.6955 |
0.2436 | 1.33 | 250 | 0.3037 | 0.7297 | 0.5285 | 0.6723 |
0.2776 | 1.46 | 275 | 0.3366 | 0.5946 | 0.5171 | 0.6727 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2