LayoutLM_Invoice6
This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0219
- Ax Amount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}
- Endor Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}
- Nvoice Number: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}
- Otal Amount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}
- Ustomer Address: {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11}
- Ustomer Name: {'precision': 1.0, 'recall': 0.9090909090909091, 'f1': 0.9523809523809523, 'number': 11}
- Overall Precision: 0.9846
- Overall Recall: 0.9697
- Overall F1: 0.9771
- Overall Accuracy: 0.9939
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: 6
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 300
Training results
Training Loss | Epoch | Step | Validation Loss | Ax Amount | Endor Name | Nvoice Number | Otal Amount | Ustomer Address | Ustomer Name | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.8763 | 6.25 | 50 | 0.2290 | {'precision': 1.0, 'recall': 0.5454545454545454, 'f1': 0.7058823529411764, 'number': 11} | {'precision': 0.8181818181818182, 'recall': 0.8181818181818182, 'f1': 0.8181818181818182, 'number': 11} | {'precision': 1.0, 'recall': 0.8181818181818182, 'f1': 0.9, 'number': 11} | {'precision': 0.5454545454545454, 'recall': 0.5454545454545454, 'f1': 0.5454545454545454, 'number': 11} | {'precision': 0.7692307692307693, 'recall': 0.9090909090909091, 'f1': 0.8333333333333333, 'number': 11} | {'precision': 0.75, 'recall': 0.8181818181818182, 'f1': 0.7826086956521738, 'number': 11} | 0.7903 | 0.7424 | 0.7656 | 0.9666 |
0.1315 | 12.5 | 100 | 0.0312 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9166666666666666, 'recall': 1.0, 'f1': 0.9565217391304348, 'number': 11} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | 0.9701 | 0.9848 | 0.9774 | 0.9970 |
0.0239 | 18.75 | 150 | 0.0371 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | {'precision': 1.0, 'recall': 0.9090909090909091, 'f1': 0.9523809523809523, 'number': 11} | 0.9846 | 0.9697 | 0.9771 | 0.9939 |
0.0098 | 25.0 | 200 | 0.0450 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | {'precision': 1.0, 'recall': 0.9090909090909091, 'f1': 0.9523809523809523, 'number': 11} | 0.9846 | 0.9697 | 0.9771 | 0.9939 |
0.0085 | 31.25 | 250 | 0.0360 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | {'precision': 1.0, 'recall': 0.9090909090909091, 'f1': 0.9523809523809523, 'number': 11} | 0.9846 | 0.9697 | 0.9771 | 0.9939 |
0.0065 | 37.5 | 300 | 0.0219 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11} | {'precision': 0.9090909090909091, 'recall': 0.9090909090909091, 'f1': 0.9090909090909091, 'number': 11} | {'precision': 1.0, 'recall': 0.9090909090909091, 'f1': 0.9523809523809523, 'number': 11} | 0.9846 | 0.9697 | 0.9771 | 0.9939 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.2.0+cpu
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Szczotar93/LayoutLM_Invoice6
Base model
microsoft/layoutlm-base-uncased
Finetuned
this model