<!-- 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. -->
perioli_manifesti_v5.8
This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:
- F1: 0.9952
- Loss: 0.0315
- Overall Precision: 0.9623
- Overall Recall: 0.9713
- Overall F1: 0.9668
- Overall Accuracy: 0.9952
- Container id: {'precision': 0.9936708860759493, 'recall': 0.98125, 'f1': 0.9874213836477987, 'number': 160}
- Seal number: {'precision': 0.9820359281437125, 'recall': 0.9879518072289156, 'f1': 0.984984984984985, 'number': 166}
- Container quantity: {'precision': 0.978021978021978, 'recall': 0.9888888888888889, 'f1': 0.9834254143646408, 'number': 90}
- Container type: {'precision': 0.974025974025974, 'recall': 0.9803921568627451, 'f1': 0.977198697068404, 'number': 153}
- Tare: {'precision': 0.967741935483871, 'recall': 0.9917355371900827, 'f1': 0.979591836734694, 'number': 121}
- Package quantity: {'precision': 0.9195402298850575, 'recall': 0.9696969696969697, 'f1': 0.943952802359882, 'number': 165}
- Weight: {'precision': 0.96875, 'recall': 0.9763779527559056, 'f1': 0.9725490196078432, 'number': 127}
- Others: {'precision': 0.9547945205479452, 'recall': 0.9574175824175825, 'f1': 0.9561042524005487, 'number': 728}
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: 4000
Training results
| Training Loss | Epoch | Step | F1 | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Container id | Seal number | Container quantity | Container type | Tare | Package quantity | Weight | Others |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1271 | 2.34 | 500 | 0.9951 | 0.0246 | 0.9605 | 0.9667 | 0.9636 | 0.9951 | {'precision': 0.98125, 'recall': 0.98125, 'f1': 0.98125, 'number': 160} | {'precision': 0.9939024390243902, 'recall': 0.9819277108433735, 'f1': 0.9878787878787879, 'number': 166} | {'precision': 1.0, 'recall': 0.9888888888888889, 'f1': 0.9944134078212291, 'number': 90} | {'precision': 0.9738562091503268, 'recall': 0.9738562091503268, 'f1': 0.9738562091503268, 'number': 153} | {'precision': 0.9516129032258065, 'recall': 0.9752066115702479, 'f1': 0.963265306122449, 'number': 121} | {'precision': 0.930635838150289, 'recall': 0.9757575757575757, 'f1': 0.9526627218934911, 'number': 165} | {'precision': 0.952755905511811, 'recall': 0.952755905511811, 'f1': 0.952755905511811, 'number': 127} | {'precision': 0.9507523939808481, 'recall': 0.9546703296703297, 'f1': 0.9527073337902673, 'number': 728} |
| 0.016 | 4.67 | 1000 | 0.9953 | 0.0255 | 0.9604 | 0.9643 | 0.9624 | 0.9953 | {'precision': 0.9874213836477987, 'recall': 0.98125, 'f1': 0.9843260188087775, 'number': 160} | {'precision': 0.9939393939393939, 'recall': 0.9879518072289156, 'f1': 0.9909365558912386, 'number': 166} | {'precision': 0.9888888888888889, 'recall': 0.9888888888888889, 'f1': 0.9888888888888889, 'number': 90} | {'precision': 0.9671052631578947, 'recall': 0.9607843137254902, 'f1': 0.9639344262295081, 'number': 153} | {'precision': 0.9669421487603306, 'recall': 0.9669421487603306, 'f1': 0.9669421487603306, 'number': 121} | {'precision': 0.9137931034482759, 'recall': 0.9636363636363636, 'f1': 0.9380530973451328, 'number': 165} | {'precision': 0.976, 'recall': 0.9606299212598425, 'f1': 0.9682539682539683, 'number': 127} | {'precision': 0.9493844049247606, 'recall': 0.9532967032967034, 'f1': 0.9513365318711446, 'number': 728} |
| 0.0093 | 7.01 | 1500 | 0.9960 | 0.0232 | 0.9668 | 0.9708 | 0.9688 | 0.9960 | {'precision': 0.9874213836477987, 'recall': 0.98125, 'f1': 0.9843260188087775, 'number': 160} | {'precision': 0.9939393939393939, 'recall': 0.9879518072289156, 'f1': 0.9909365558912386, 'number': 166} | {'precision': 1.0, 'recall': 0.9888888888888889, 'f1': 0.9944134078212291, 'number': 90} | {'precision': 0.9803921568627451, 'recall': 0.9803921568627451, 'f1': 0.9803921568627451, 'number': 153} | {'precision': 0.9596774193548387, 'recall': 0.9834710743801653, 'f1': 0.9714285714285714, 'number': 121} | {'precision': 0.9352941176470588, 'recall': 0.9636363636363636, 'f1': 0.9492537313432835, 'number': 165} | {'precision': 0.9612403100775194, 'recall': 0.9763779527559056, 'f1': 0.9687500000000001, 'number': 127} | {'precision': 0.9587912087912088, 'recall': 0.9587912087912088, 'f1': 0.9587912087912088, 'number': 728} |
| 0.0053 | 9.35 | 2000 | 0.9950 | 0.0296 | 0.9578 | 0.9696 | 0.9637 | 0.9950 | {'precision': 0.96875, 'recall': 0.96875, 'f1': 0.96875, 'number': 160} | {'precision': 0.9939759036144579, 'recall': 0.9939759036144579, 'f1': 0.9939759036144579, 'number': 166} | {'precision': 1.0, 'recall': 0.9888888888888889, 'f1': 0.9944134078212291, 'number': 90} | {'precision': 0.9803921568627451, 'recall': 0.9803921568627451, 'f1': 0.9803921568627451, 'number': 153} | {'precision': 0.967741935483871, 'recall': 0.9917355371900827, 'f1': 0.979591836734694, 'number': 121} | {'precision': 0.9090909090909091, 'recall': 0.9696969696969697, 'f1': 0.93841642228739, 'number': 165} | {'precision': 0.96875, 'recall': 0.9763779527559056, 'f1': 0.9725490196078432, 'number': 127} | {'precision': 0.9455782312925171, 'recall': 0.9546703296703297, 'f1': 0.9501025290498976, 'number': 728} |
| 0.0046 | 11.68 | 2500 | 0.9955 | 0.0291 | 0.9668 | 0.9719 | 0.9694 | 0.9955 | {'precision': 0.9874213836477987, 'recall': 0.98125, 'f1': 0.9843260188087775, 'number': 160} | {'precision': 0.9939393939393939, 'recall': 0.9879518072289156, 'f1': 0.9909365558912386, 'number': 166} | {'precision': 1.0, 'recall': 0.9888888888888889, 'f1': 0.9944134078212291, 'number': 90} | {'precision': 0.9803921568627451, 'recall': 0.9803921568627451, 'f1': 0.9803921568627451, 'number': 153} | {'precision': 0.9758064516129032, 'recall': 1.0, 'f1': 0.9877551020408163, 'number': 121} | {'precision': 0.9190751445086706, 'recall': 0.9636363636363636, 'f1': 0.9408284023668639, 'number': 165} | {'precision': 0.9763779527559056, 'recall': 0.9763779527559056, 'f1': 0.9763779527559056, 'number': 127} | {'precision': 0.9574759945130316, 'recall': 0.9587912087912088, 'f1': 0.9581331503088538, 'number': 728} |
| 0.0028 | 14.02 | 3000 | 0.9948 | 0.0322 | 0.9578 | 0.9678 | 0.9628 | 0.9948 | {'precision': 0.9936708860759493, 'recall': 0.98125, 'f1': 0.9874213836477987, 'number': 160} | {'precision': 0.9879518072289156, 'recall': 0.9879518072289156, 'f1': 0.9879518072289156, 'number': 166} | {'precision': 0.978021978021978, 'recall': 0.9888888888888889, 'f1': 0.9834254143646408, 'number': 90} | {'precision': 0.974025974025974, 'recall': 0.9803921568627451, 'f1': 0.977198697068404, 'number': 153} | {'precision': 0.975609756097561, 'recall': 0.9917355371900827, 'f1': 0.9836065573770492, 'number': 121} | {'precision': 0.8977272727272727, 'recall': 0.9575757575757575, 'f1': 0.9266862170087976, 'number': 165} | {'precision': 0.9609375, 'recall': 0.968503937007874, 'f1': 0.9647058823529412, 'number': 127} | {'precision': 0.9480874316939891, 'recall': 0.9532967032967034, 'f1': 0.9506849315068493, 'number': 728} |
| 0.0017 | 16.36 | 3500 | 0.9955 | 0.0296 | 0.9652 | 0.9719 | 0.9685 | 0.9955 | {'precision': 0.9936708860759493, 'recall': 0.98125, 'f1': 0.9874213836477987, 'number': 160} | {'precision': 0.9820359281437125, 'recall': 0.9879518072289156, 'f1': 0.984984984984985, 'number': 166} | {'precision': 0.978021978021978, 'recall': 0.9888888888888889, 'f1': 0.9834254143646408, 'number': 90} | {'precision': 0.974025974025974, 'recall': 0.9803921568627451, 'f1': 0.977198697068404, 'number': 153} | {'precision': 0.9836065573770492, 'recall': 0.9917355371900827, 'f1': 0.9876543209876544, 'number': 121} | {'precision': 0.930635838150289, 'recall': 0.9757575757575757, 'f1': 0.9526627218934911, 'number': 165} | {'precision': 0.9682539682539683, 'recall': 0.9606299212598425, 'f1': 0.9644268774703557, 'number': 127} | {'precision': 0.9562243502051984, 'recall': 0.9601648351648352, 'f1': 0.9581905414667581, 'number': 728} |
| 0.0011 | 18.69 | 4000 | 0.9952 | 0.0315 | 0.9623 | 0.9713 | 0.9668 | 0.9952 | {'precision': 0.9936708860759493, 'recall': 0.98125, 'f1': 0.9874213836477987, 'number': 160} | {'precision': 0.9820359281437125, 'recall': 0.9879518072289156, 'f1': 0.984984984984985, 'number': 166} | {'precision': 0.978021978021978, 'recall': 0.9888888888888889, 'f1': 0.9834254143646408, 'number': 90} | {'precision': 0.974025974025974, 'recall': 0.9803921568627451, 'f1': 0.977198697068404, 'number': 153} | {'precision': 0.967741935483871, 'recall': 0.9917355371900827, 'f1': 0.979591836734694, 'number': 121} | {'precision': 0.9195402298850575, 'recall': 0.9696969696969697, 'f1': 0.943952802359882, 'number': 165} | {'precision': 0.96875, 'recall': 0.9763779527559056, 'f1': 0.9725490196078432, 'number': 127} | {'precision': 0.9547945205479452, 'recall': 0.9574175824175825, 'f1': 0.9561042524005487, 'number': 728} |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3
