metadata
library_name: transformers
license: apache-2.0
base_model: google/pix2struct-docvqa-base
tags:
- generated_from_trainer
model-index:
- name: Pix2StructCzechInvoice
results: []
Pix2StructCzechInvoice
This model is a fine-tuned version of google/pix2struct-docvqa-base on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2568
- eval_runtime: 37.2601
- eval_samples_per_second: 1.61
- eval_steps_per_second: 1.61
- epoch: 8.0
- step: 2400
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.57.6
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2