metadata
base_model: squantumengine/donut-stnk-v3_5_left
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-stnk-v5_4-left
results: []
donut-stnk-v5_4-left
This model is a fine-tuned version of squantumengine/donut-stnk-v3_5_left on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1063
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.2035 | 1.0 | 206 | 0.1063 |
0.0864 | 2.0 | 412 | 0.1248 |
0.0667 | 3.0 | 618 | 0.1137 |
0.0366 | 4.0 | 824 | 0.1237 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1