metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: layoutlmv2_docvqa_first
results: []
layoutlmv2_docvqa_first
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4333
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: 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: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5047 | 0.1106 | 50 | 3.7546 |
0.6441 | 0.2212 | 100 | 4.1337 |
0.7907 | 0.3319 | 150 | 3.9319 |
0.7647 | 0.4425 | 200 | 3.5061 |
0.5767 | 0.5531 | 250 | 3.4685 |
0.8027 | 0.6637 | 300 | 3.5278 |
0.5282 | 0.7743 | 350 | 4.1561 |
0.9692 | 0.8850 | 400 | 3.5156 |
0.9379 | 0.9956 | 450 | 3.4333 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1