bus-deit / README.md
as-cle-bert's picture
End of training
aee778b verified
---
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bus-deit
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bus-deit
This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4103
- Accuracy: 0.8154
## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.84 | 4 | 0.5423 | 0.6769 |
| No log | 1.89 | 9 | 0.4281 | 0.8308 |
| 0.5835 | 2.53 | 12 | 0.4103 | 0.8154 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2