metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vogue-fashion-collection-15
results: []
vogue-fashion-collection-15
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4719
- Accuracy: 0.8380
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.1358 | 1.0 | 1094 | 6.1121 | 0.5762 |
| 4.5926 | 2.0 | 2189 | 4.5302 | 0.7306 |
| 3.386 | 3.0 | 3283 | 3.3786 | 0.7971 |
| 2.7142 | 4.0 | 4378 | 2.7066 | 0.8231 |
| 2.4032 | 5.0 | 5470 | 2.4719 | 0.8380 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0