<!-- 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. -->
REPROCESO4.0
This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.0282
- Precision: 0.9527
- Recall: 0.9951
- F1: 0.9734
- Accuracy: 0.9976
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 | 0.79 | 100 | 0.0191 | 0.9482 | 0.9951 | 0.9711 | 0.9973 |
No log | 1.57 | 200 | 0.0213 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
No log | 2.36 | 300 | 0.0222 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
No log | 3.15 | 400 | 0.0216 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0336 | 3.94 | 500 | 0.0231 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0336 | 4.72 | 600 | 0.0245 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0336 | 5.51 | 700 | 0.0246 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0336 | 6.3 | 800 | 0.0220 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0336 | 7.09 | 900 | 0.0248 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0011 | 7.87 | 1000 | 0.0259 | 0.9502 | 0.9901 | 0.9698 | 0.9973 |
0.0011 | 8.66 | 1100 | 0.0257 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0011 | 9.45 | 1200 | 0.0264 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0011 | 10.24 | 1300 | 0.0272 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0011 | 11.02 | 1400 | 0.0273 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0002 | 11.81 | 1500 | 0.0276 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0002 | 12.6 | 1600 | 0.0278 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0002 | 13.39 | 1700 | 0.0280 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0002 | 14.17 | 1800 | 0.0281 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0002 | 14.96 | 1900 | 0.0282 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0001 | 15.75 | 2000 | 0.0282 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3