metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: lettuce-npk-vit
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8095238095238095
lettuce-npk-vit
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7449
- Accuracy: 0.8095
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.7273 | 2 | 1.3774 | 0.2143 |
| No log | 1.8182 | 5 | 1.2738 | 0.4524 |
| No log | 2.9091 | 8 | 1.1874 | 0.6190 |
| 1.2511 | 4.0 | 11 | 1.1162 | 0.7619 |
| 1.2511 | 4.7273 | 13 | 1.0780 | 0.7143 |
| 1.2511 | 5.8182 | 16 | 1.0037 | 0.7857 |
| 1.2511 | 6.9091 | 19 | 0.9342 | 0.8095 |
| 0.9308 | 8.0 | 22 | 0.8653 | 0.8095 |
| 0.9308 | 8.7273 | 24 | 0.8485 | 0.8095 |
| 0.9308 | 9.8182 | 27 | 0.8264 | 0.8333 |
| 0.7204 | 10.9091 | 30 | 0.8243 | 0.7857 |
| 0.7204 | 12.0 | 33 | 0.7299 | 0.8571 |
| 0.7204 | 12.7273 | 35 | 0.7376 | 0.8095 |
| 0.7204 | 13.8182 | 38 | 0.7358 | 0.8333 |
| 0.6101 | 14.5455 | 40 | 0.7449 | 0.8095 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1