vit-base / README.md
aningddd's picture
End of training
dbbadd2 verified
---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base
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. -->
# vit-base
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3177
- Accuracy: 0.4987
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.6698 | 1.0 | 48 | 1.5900 | 0.2539 |
| 1.4981 | 2.0 | 96 | 1.4551 | 0.3835 |
| 1.2747 | 3.0 | 144 | 1.3591 | 0.4408 |
| 1.0701 | 4.0 | 192 | 1.3058 | 0.4902 |
| 0.7885 | 5.0 | 240 | 1.3177 | 0.4987 |
| 0.6023 | 6.0 | 288 | 1.3985 | 0.4870 |
| 0.4814 | 7.0 | 336 | 1.4607 | 0.4824 |
| 0.3708 | 8.0 | 384 | 1.5195 | 0.4720 |
| 0.2755 | 9.0 | 432 | 1.5524 | 0.4798 |
| 0.2476 | 10.0 | 480 | 1.5632 | 0.4792 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1