metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: recomendation-system
results: []
recomendation-system
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: 2.3870
- Accuracy: 0.5658
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.7526 | 1.0 | 612 | 4.7474 | 0.2541 |
| 3.9574 | 2.0 | 1224 | 3.8794 | 0.4050 |
| 3.4665 | 3.0 | 1836 | 3.3852 | 0.4621 |
| 3.0017 | 4.0 | 2448 | 3.0551 | 0.4944 |
| 2.7217 | 5.0 | 3060 | 2.8251 | 0.5137 |
| 2.5752 | 6.0 | 3672 | 2.6569 | 0.5399 |
| 2.5064 | 7.0 | 4284 | 2.5447 | 0.5501 |
| 2.3956 | 8.0 | 4896 | 2.4493 | 0.5631 |
| 2.1768 | 9.0 | 5508 | 2.4040 | 0.5631 |
| 2.2168 | 10.0 | 6120 | 2.3870 | 0.5658 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1