metadata
base_model: microsoft/beit-large-patch16-224-pt22k-ft22k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Augmentation-beit-large
results: []
Train-Augmentation-beit-large
This model is a fine-tuned version of microsoft/beit-large-patch16-224-pt22k-ft22k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8592
- Accuracy: 0.8182
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 |
|---|---|---|---|---|
| 0.0993 | 0.99 | 93 | 0.6675 | 0.8340 |
| 0.0492 | 2.0 | 187 | 0.8597 | 0.8379 |
| 0.0134 | 2.99 | 280 | 0.7961 | 0.8024 |
| 0.0016 | 4.0 | 374 | 0.7594 | 0.8340 |
| 0.0004 | 4.97 | 465 | 0.8592 | 0.8182 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2