Donut_ocr_chart_10k
This model is a fine-tuned version of aravind-selvam/donut_finetuned_chart on the imagefolder dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2031
- eval_cer: 0.8316
- eval_runtime: 222.4582
- eval_samples_per_second: 4.495
- eval_steps_per_second: 0.283
- epoch: 4.0
- step: 1257
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: 2.5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3