finetuned-waste
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the BioNonbioWaste dataset. It achieves the following results on the evaluation set:
- Loss: 0.0048
- Accuracy: 1.0
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 |
---|---|---|---|---|
0.1044 | 0.5435 | 100 | 0.0418 | 0.9826 |
0.0517 | 1.0870 | 200 | 0.0545 | 0.9749 |
0.0168 | 1.6304 | 300 | 0.0099 | 0.9961 |
0.0526 | 2.1739 | 400 | 0.0048 | 1.0 |
0.062 | 2.7174 | 500 | 0.0196 | 0.9942 |
0.0088 | 3.2609 | 600 | 0.0155 | 0.9981 |
0.0239 | 3.8043 | 700 | 0.0106 | 0.9981 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 6