metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-large-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: plant-identification-vit
results: []
plant-identification-vit
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0315
- Accuracy: 0.8096
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: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0085 | 1.0 | 953 | 1.0659 | 0.7762 |
| 0.6805 | 2.0 | 1906 | 0.8413 | 0.8029 |
| 0.5039 | 3.0 | 2859 | 0.7920 | 0.8069 |
| 0.3847 | 4.0 | 3812 | 0.7760 | 0.8102 |
| 0.2826 | 5.0 | 4765 | 0.8024 | 0.8049 |
| 0.2229 | 6.0 | 5718 | 0.8382 | 0.8099 |
| 0.1064 | 7.0 | 6671 | 0.8983 | 0.8074 |
| 0.0676 | 8.0 | 7624 | 0.9672 | 0.8072 |
| 0.027 | 9.0 | 8577 | 1.0089 | 0.8099 |
| 0.0209 | 10.0 | 9530 | 1.0315 | 0.8096 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3