<!-- 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. -->
REPROCESO5.0
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: 0.0180
- 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 | 0.55 | 100 | 0.0157 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
No log | 1.09 | 200 | 0.0208 | 0.9258 | 0.9852 | 0.9545 | 0.9965 |
No log | 1.64 | 300 | 0.0184 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
No log | 2.19 | 400 | 0.0162 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0268 | 2.73 | 500 | 0.0128 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0268 | 3.28 | 600 | 0.0178 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0268 | 3.83 | 700 | 0.0142 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0268 | 4.37 | 800 | 0.0176 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0268 | 4.92 | 900 | 0.0170 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0028 | 5.46 | 1000 | 0.0165 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0028 | 6.01 | 1100 | 0.0166 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0028 | 6.56 | 1200 | 0.0152 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0028 | 7.1 | 1300 | 0.0162 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0028 | 7.65 | 1400 | 0.0196 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0016 | 8.2 | 1500 | 0.0173 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0016 | 8.74 | 1600 | 0.0169 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0016 | 9.29 | 1700 | 0.0162 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0016 | 9.84 | 1800 | 0.0154 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0016 | 10.38 | 1900 | 0.0180 | 0.9527 | 0.9951 | 0.9734 | 0.9976 |
0.0011 | 10.93 | 2000 | 0.0180 | 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