<!-- 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_vgm_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: 0.9962
- Loss: 0.0286
- Overall Precision: 0.9224
- Overall Recall: 0.9421
- Overall F1: 0.9321
- Overall Accuracy: 0.9962
- Authorized person: {'precision': 0.8148148148148148, 'recall': 0.9166666666666666, 'f1': 0.8627450980392156, 'number': 24}
- Container type: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5}
- Container id: {'precision': 0.9333333333333333, 'recall': 1.0, 'f1': 0.9655172413793104, 'number': 28}
- Booking number: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22}
- Vgm: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 26}
- Signer name: {'precision': 0.9285714285714286, 'recall': 0.8125, 'f1': 0.8666666666666666, 'number': 16}
- Shipper: {'precision': 0.76, 'recall': 0.8260869565217391, 'f1': 0.7916666666666667, 'number': 23}
- Others: {'precision': 0.9354838709677419, 'recall': 0.9456521739130435, 'f1': 0.9405405405405404, 'number': 184}
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: 5000
Training results
| Training Loss | Epoch | Step | F1 | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Authorized person | Container type | Container id | Booking number | Vgm | Signer name | Shipper | Others |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0888 | 2.22 | 500 | 0.9929 | 0.0246 | 0.8349 | 0.8171 | 0.8259 | 0.9929 | {'precision': 0.76, 'recall': 0.7916666666666666, 'f1': 0.7755102040816326, 'number': 24} | {'precision': 0.5714285714285714, 'recall': 0.8, 'f1': 0.6666666666666666, 'number': 5} | {'precision': 0.9032258064516129, 'recall': 1.0, 'f1': 0.9491525423728813, 'number': 28} | {'precision': 1.0, 'recall': 0.9545454545454546, 'f1': 0.9767441860465117, 'number': 22} | {'precision': 0.7916666666666666, 'recall': 0.7307692307692307, 'f1': 0.76, 'number': 26} | {'precision': 0.8333333333333334, 'recall': 0.625, 'f1': 0.7142857142857143, 'number': 16} | {'precision': 0.75, 'recall': 0.782608695652174, 'f1': 0.7659574468085107, 'number': 23} | {'precision': 0.8418079096045198, 'recall': 0.8097826086956522, 'f1': 0.8254847645429363, 'number': 184} |
| 0.0141 | 4.44 | 1000 | 0.9945 | 0.0267 | 0.8813 | 0.9055 | 0.8932 | 0.9945 | {'precision': 0.65625, 'recall': 0.875, 'f1': 0.75, 'number': 24} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 5} | {'precision': 0.875, 'recall': 1.0, 'f1': 0.9333333333333333, 'number': 28} | {'precision': 0.9545454545454546, 'recall': 0.9545454545454546, 'f1': 0.9545454545454546, 'number': 22} | {'precision': 0.8620689655172413, 'recall': 0.9615384615384616, 'f1': 0.9090909090909091, 'number': 26} | {'precision': 1.0, 'recall': 0.8125, 'f1': 0.896551724137931, 'number': 16} | {'precision': 0.8947368421052632, 'recall': 0.7391304347826086, 'f1': 0.8095238095238095, 'number': 23} | {'precision': 0.9081081081081082, 'recall': 0.9130434782608695, 'f1': 0.9105691056910569, 'number': 184} |
| 0.004 | 6.67 | 1500 | 0.9953 | 0.0211 | 0.9069 | 0.9207 | 0.9138 | 0.9953 | {'precision': 0.8148148148148148, 'recall': 0.9166666666666666, 'f1': 0.8627450980392156, 'number': 24} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 5} | {'precision': 0.9032258064516129, 'recall': 1.0, 'f1': 0.9491525423728813, 'number': 28} | {'precision': 1.0, 'recall': 0.9545454545454546, 'f1': 0.9767441860465117, 'number': 22} | {'precision': 0.9259259259259259, 'recall': 0.9615384615384616, 'f1': 0.9433962264150944, 'number': 26} | {'precision': 0.9230769230769231, 'recall': 0.75, 'f1': 0.8275862068965517, 'number': 16} | {'precision': 0.8260869565217391, 'recall': 0.8260869565217391, 'f1': 0.8260869565217391, 'number': 23} | {'precision': 0.9193548387096774, 'recall': 0.9293478260869565, 'f1': 0.9243243243243242, 'number': 184} |
| 0.0023 | 8.89 | 2000 | 0.9953 | 0.0244 | 0.9055 | 0.9055 | 0.9055 | 0.9953 | {'precision': 0.8148148148148148, 'recall': 0.9166666666666666, 'f1': 0.8627450980392156, 'number': 24} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 5} | {'precision': 0.9333333333333333, 'recall': 1.0, 'f1': 0.9655172413793104, 'number': 28} | {'precision': 1.0, 'recall': 0.9545454545454546, 'f1': 0.9767441860465117, 'number': 22} | {'precision': 0.8518518518518519, 'recall': 0.8846153846153846, 'f1': 0.8679245283018868, 'number': 26} | {'precision': 0.9230769230769231, 'recall': 0.75, 'f1': 0.8275862068965517, 'number': 16} | {'precision': 0.8571428571428571, 'recall': 0.782608695652174, 'f1': 0.8181818181818182, 'number': 23} | {'precision': 0.9184782608695652, 'recall': 0.9184782608695652, 'f1': 0.9184782608695652, 'number': 184} |
| 0.0016 | 11.11 | 2500 | 0.9964 | 0.0261 | 0.9247 | 0.9360 | 0.9303 | 0.9964 | {'precision': 0.7586206896551724, 'recall': 0.9166666666666666, 'f1': 0.830188679245283, 'number': 24} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 0.9032258064516129, 'recall': 1.0, 'f1': 0.9491525423728813, 'number': 28} | {'precision': 1.0, 'recall': 0.9545454545454546, 'f1': 0.9767441860465117, 'number': 22} | {'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001, 'number': 26} | {'precision': 0.9285714285714286, 'recall': 0.8125, 'f1': 0.8666666666666666, 'number': 16} | {'precision': 0.8333333333333334, 'recall': 0.8695652173913043, 'f1': 0.851063829787234, 'number': 23} | {'precision': 0.9456521739130435, 'recall': 0.9456521739130435, 'f1': 0.9456521739130435, 'number': 184} |
| 0.0009 | 13.33 | 3000 | 0.9959 | 0.0257 | 0.9157 | 0.9268 | 0.9212 | 0.9959 | {'precision': 0.8076923076923077, 'recall': 0.875, 'f1': 0.8400000000000001, 'number': 24} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 5} | {'precision': 0.9032258064516129, 'recall': 1.0, 'f1': 0.9491525423728813, 'number': 28} | {'precision': 1.0, 'recall': 0.9545454545454546, 'f1': 0.9767441860465117, 'number': 22} | {'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001, 'number': 26} | {'precision': 0.9285714285714286, 'recall': 0.8125, 'f1': 0.8666666666666666, 'number': 16} | {'precision': 0.7777777777777778, 'recall': 0.9130434782608695, 'f1': 0.84, 'number': 23} | {'precision': 0.9347826086956522, 'recall': 0.9347826086956522, 'f1': 0.9347826086956522, 'number': 184} |
| 0.0008 | 15.56 | 3500 | 0.9957 | 0.0286 | 0.9290 | 0.9177 | 0.9233 | 0.9957 | {'precision': 0.84, 'recall': 0.875, 'f1': 0.8571428571428572, 'number': 24} | {'precision': 0.8, 'recall': 0.8, 'f1': 0.8000000000000002, 'number': 5} | {'precision': 0.9333333333333333, 'recall': 1.0, 'f1': 0.9655172413793104, 'number': 28} | {'precision': 0.9565217391304348, 'recall': 1.0, 'f1': 0.9777777777777777, 'number': 22} | {'precision': 0.9615384615384616, 'recall': 0.9615384615384616, 'f1': 0.9615384615384616, 'number': 26} | {'precision': 0.9230769230769231, 'recall': 0.75, 'f1': 0.8275862068965517, 'number': 16} | {'precision': 0.9047619047619048, 'recall': 0.8260869565217391, 'f1': 0.8636363636363636, 'number': 23} | {'precision': 0.9392265193370166, 'recall': 0.9239130434782609, 'f1': 0.9315068493150687, 'number': 184} |
| 0.0002 | 17.78 | 4000 | 0.9962 | 0.0292 | 0.9286 | 0.9512 | 0.9398 | 0.9962 | {'precision': 0.7857142857142857, 'recall': 0.9166666666666666, 'f1': 0.8461538461538461, 'number': 24} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 0.9333333333333333, 'recall': 1.0, 'f1': 0.9655172413793104, 'number': 28} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 26} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 16} | {'precision': 0.8333333333333334, 'recall': 0.8695652173913043, 'f1': 0.851063829787234, 'number': 23} | {'precision': 0.946524064171123, 'recall': 0.9619565217391305, 'f1': 0.954177897574124, 'number': 184} |
| 0.0002 | 20.0 | 4500 | 0.9963 | 0.0294 | 0.9174 | 0.9482 | 0.9325 | 0.9963 | {'precision': 0.8461538461538461, 'recall': 0.9166666666666666, 'f1': 0.8799999999999999, 'number': 24} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 0.9333333333333333, 'recall': 1.0, 'f1': 0.9655172413793104, 'number': 28} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.9629629629629629, 'recall': 1.0, 'f1': 0.9811320754716981, 'number': 26} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 16} | {'precision': 0.8076923076923077, 'recall': 0.9130434782608695, 'f1': 0.8571428571428572, 'number': 23} | {'precision': 0.9259259259259259, 'recall': 0.9510869565217391, 'f1': 0.9383378016085792, 'number': 184} |
| 0.0002 | 22.22 | 5000 | 0.9962 | 0.0286 | 0.9224 | 0.9421 | 0.9321 | 0.9962 | {'precision': 0.8148148148148148, 'recall': 0.9166666666666666, 'f1': 0.8627450980392156, 'number': 24} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 0.9333333333333333, 'recall': 1.0, 'f1': 0.9655172413793104, 'number': 28} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 26} | {'precision': 0.9285714285714286, 'recall': 0.8125, 'f1': 0.8666666666666666, 'number': 16} | {'precision': 0.76, 'recall': 0.8260869565217391, 'f1': 0.7916666666666667, 'number': 23} | {'precision': 0.9354838709677419, 'recall': 0.9456521739130435, 'f1': 0.9405405405405404, 'number': 184} |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3
