metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: donut-base-beans
results: []
donut-base-beans
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:
- F1: 0.9705
- Loss: 0.0429
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | F1 | Validation Loss |
|---|---|---|---|---|
| 0.0796 | 1.0 | 3367 | 0.4973 | 0.0687 |
| 0.0611 | 2.0 | 6734 | 0.4973 | 0.0585 |
| 0.0581 | 3.0 | 10101 | 0.4973 | 0.0591 |
| 0.059 | 4.0 | 13468 | 0.4973 | 0.0550 |
| 0.0563 | 5.0 | 16835 | 0.4973 | 0.0540 |
| 0.0532 | 5.0 | 19805 | 0.9705 | 0.0429 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1