metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: tsec_vit_model
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: 0.7689873417721519
tsec_vit_model
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: 0.4821
- Accuracy: 0.7690
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4963 | 0.9873 | 39 | 0.5699 | 0.6725 |
| 0.4959 | 2.0 | 79 | 0.5485 | 0.7152 |
| 0.4879 | 2.9873 | 118 | 0.4886 | 0.7690 |
| 0.5243 | 4.0 | 158 | 0.5133 | 0.7468 |
| 0.4654 | 4.9873 | 197 | 0.4927 | 0.7516 |
| 0.4776 | 6.0 | 237 | 0.4901 | 0.7642 |
| 0.4767 | 6.9873 | 276 | 0.4652 | 0.7816 |
| 0.4465 | 8.0 | 316 | 0.4795 | 0.7642 |
| 0.467 | 8.9873 | 355 | 0.4691 | 0.7484 |
| 0.4121 | 9.8734 | 390 | 0.4821 | 0.7690 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1