layoutlmv2-base-uncased_finetuned_docvqa_v2
This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.1294
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.0605 | 1.25 | 5 | 5.7157 |
| 5.657 | 2.5 | 10 | 5.2955 |
| 5.3186 | 3.75 | 15 | 4.9105 |
| 5.0131 | 5.0 | 20 | 4.6027 |
| 4.7982 | 6.25 | 25 | 4.4191 |
| 4.5996 | 7.5 | 30 | 4.2716 |
| 4.5649 | 8.75 | 35 | 4.1632 |
| 4.3776 | 10.0 | 40 | 4.1294 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for apriliantono/layoutlmv2-base-uncased_finetuned_docvqa_v2
Base model
microsoft/layoutlmv2-base-uncased