metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
model-index:
- name: layoutlmv2-large-uncased-finetuned-vi-infovqa
results: []
layoutlmv2-large-uncased-finetuned-vi-infovqa
This model is a fine-tuned version of microsoft/layoutlmv2-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.2383
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: 2
- seed: 250500
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.9983 | 0.83 | 500 | 6.2383 |
| 6.2621 | 1.65 | 1000 | 6.2383 |
| 6.2492 | 2.48 | 1500 | 6.2383 |
| 6.2548 | 3.3 | 2000 | 6.2383 |
| 6.2515 | 4.13 | 2500 | 6.2383 |
| 6.2543 | 4.95 | 3000 | 6.2383 |
| 6.2545 | 5.78 | 3500 | 6.2383 |
| 6.247 | 6.6 | 4000 | 6.2383 |
| 6.2499 | 7.43 | 4500 | 6.2383 |
| 6.2434 | 8.25 | 5000 | 6.2383 |
| 6.2416 | 9.08 | 5500 | 6.2383 |
| 6.2425 | 9.9 | 6000 | 6.2383 |
Framework versions
- Transformers 4.14.1
- Pytorch 1.8.0+cu101
- Datasets 1.16.1
- Tokenizers 0.10.3