<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
SOCIEDADES3.0
This model is a fine-tuned version of microsoft/layoutlmv3-large on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.0009
- Precision: 0.9555
- Recall: 0.9621
- F1: 0.9588
- Accuracy: 0.9998
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: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.28 | 100 | 0.0024 | 0.8819 | 0.8759 | 0.8789 | 0.9993 |
No log | 0.56 | 200 | 0.0017 | 0.9354 | 0.9483 | 0.9418 | 0.9997 |
No log | 0.84 | 300 | 0.0017 | 0.9514 | 0.9448 | 0.9481 | 0.9997 |
No log | 1.12 | 400 | 0.0010 | 0.9517 | 0.9517 | 0.9517 | 0.9998 |
0.0049 | 1.4 | 500 | 0.0010 | 0.9586 | 0.9586 | 0.9586 | 0.9998 |
0.0049 | 1.69 | 600 | 0.0014 | 0.9583 | 0.9517 | 0.9550 | 0.9997 |
0.0049 | 1.97 | 700 | 0.0015 | 0.9414 | 0.9414 | 0.9414 | 0.9997 |
0.0049 | 2.25 | 800 | 0.0024 | 0.9452 | 0.9517 | 0.9485 | 0.9995 |
0.0049 | 2.53 | 900 | 0.0016 | 0.9444 | 0.9379 | 0.9412 | 0.9997 |
0.0005 | 2.81 | 1000 | 0.0025 | 0.8947 | 0.9379 | 0.9158 | 0.9994 |
0.0005 | 3.09 | 1100 | 0.0011 | 0.9392 | 0.9586 | 0.9488 | 0.9996 |
0.0005 | 3.37 | 1200 | 0.0008 | 0.9655 | 0.9655 | 0.9655 | 0.9998 |
0.0005 | 3.65 | 1300 | 0.0017 | 0.9375 | 0.9310 | 0.9343 | 0.9996 |
0.0005 | 3.93 | 1400 | 0.0009 | 0.9615 | 0.9483 | 0.9549 | 0.9998 |
0.0004 | 4.21 | 1500 | 0.0008 | 0.9655 | 0.9655 | 0.9655 | 0.9998 |
0.0004 | 4.49 | 1600 | 0.0009 | 0.9655 | 0.9655 | 0.9655 | 0.9998 |
0.0004 | 4.78 | 1700 | 0.0009 | 0.9655 | 0.9655 | 0.9655 | 0.9998 |
0.0004 | 5.06 | 1800 | 0.0009 | 0.9530 | 0.9793 | 0.9660 | 0.9998 |
0.0004 | 5.34 | 1900 | 0.0009 | 0.9555 | 0.9621 | 0.9588 | 0.9998 |
0.0002 | 5.62 | 2000 | 0.0009 | 0.9555 | 0.9621 | 0.9588 | 0.9998 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2