metadata
tags:
- generated_from_trainer
model-index:
- name: 20231102-20_epochs_layoutlmv2-base-uncased_finetuned_docvqa
results: []
20231102-20_epochs_layoutlmv2-base-uncased_finetuned_docvqa
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9087
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3689 | 3.51 | 100 | 3.7775 |
| 3.2761 | 7.02 | 200 | 3.3707 |
| 2.6415 | 10.53 | 300 | 3.0807 |
| 2.2233 | 14.04 | 400 | 3.0120 |
| 1.9586 | 17.54 | 500 | 2.9087 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.10.1
- Tokenizers 0.14.1