complete-prova
This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4074
- Precision: 0.5533
- Recall: 0.3424
- F1: 0.4230
- Accuracy: 0.9092
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0.76 | 100 | 0.6181 | 0.0 | 0.0 | 0.0 | 0.8733 |
| No log | 1.52 | 200 | 0.5377 | 0.4167 | 0.0485 | 0.0869 | 0.8792 |
| No log | 2.27 | 300 | 0.4737 | 0.4286 | 0.1222 | 0.1902 | 0.8870 |
| No log | 3.03 | 400 | 0.4254 | 0.5152 | 0.3278 | 0.4007 | 0.9063 |
| 0.5393 | 3.79 | 500 | 0.4074 | 0.5533 | 0.3424 | 0.4230 | 0.9092 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.6.1
- Tokenizers 0.13.2