<!-- 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_v5.8.3
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: 0.9584
- Recall: 0.9690
- F1: 0.9637
- Accuracy: 0.9953
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 | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.4 | 100 | 0.1382 | 0.7597 | 0.7766 | 0.7681 | 0.9681 |
No log | 0.81 | 200 | 0.0622 | 0.8825 | 0.9088 | 0.8954 | 0.9861 |
No log | 1.21 | 300 | 0.0430 | 0.9173 | 0.9409 | 0.9290 | 0.9910 |
No log | 1.62 | 400 | 0.0379 | 0.9178 | 0.9468 | 0.9321 | 0.9916 |
0.1487 | 2.02 | 500 | 0.0273 | 0.9509 | 0.9626 | 0.9567 | 0.9942 |
0.1487 | 2.43 | 600 | 0.0353 | 0.9274 | 0.9567 | 0.9419 | 0.9925 |
0.1487 | 2.83 | 700 | 0.0272 | 0.9573 | 0.9690 | 0.9631 | 0.9950 |
0.1487 | 3.24 | 800 | 0.0264 | 0.9531 | 0.9632 | 0.9581 | 0.9939 |
0.1487 | 3.64 | 900 | 0.0230 | 0.9547 | 0.9608 | 0.9577 | 0.9945 |
0.0186 | 4.05 | 1000 | 0.0284 | 0.9443 | 0.9614 | 0.9528 | 0.9938 |
0.0186 | 4.45 | 1100 | 0.0341 | 0.9263 | 0.9561 | 0.9410 | 0.9920 |
0.0186 | 4.86 | 1200 | 0.0320 | 0.9477 | 0.9649 | 0.9562 | 0.9944 |
0.0186 | 5.26 | 1300 | 0.0267 | 0.9566 | 0.9661 | 0.9613 | 0.9949 |
0.0186 | 5.67 | 1400 | 0.0279 | 0.9548 | 0.9643 | 0.9596 | 0.9947 |
0.0106 | 6.07 | 1500 | 0.0262 | 0.9560 | 0.9667 | 0.9613 | 0.9947 |
0.0106 | 6.48 | 1600 | 0.0269 | 0.9526 | 0.9643 | 0.9584 | 0.9947 |
0.0106 | 6.88 | 1700 | 0.0249 | 0.9611 | 0.9678 | 0.9645 | 0.9955 |
0.0106 | 7.29 | 1800 | 0.0314 | 0.9509 | 0.9620 | 0.9564 | 0.9940 |
0.0106 | 7.69 | 1900 | 0.0311 | 0.9493 | 0.9643 | 0.9568 | 0.9944 |
0.0068 | 8.1 | 2000 | 0.0211 | 0.9616 | 0.9667 | 0.9641 | 0.9956 |
0.0068 | 8.5 | 2100 | 0.0272 | 0.9548 | 0.9626 | 0.9586 | 0.9948 |
0.0068 | 8.91 | 2200 | 0.0246 | 0.9667 | 0.9673 | 0.9670 | 0.9957 |
0.0068 | 9.31 | 2300 | 0.0267 | 0.9567 | 0.9696 | 0.9631 | 0.9951 |
0.0068 | 9.72 | 2400 | 0.0236 | 0.9605 | 0.9673 | 0.9639 | 0.9955 |
0.0056 | 10.12 | 2500 | 0.0259 | 0.9555 | 0.9667 | 0.9610 | 0.9949 |
0.0056 | 10.53 | 2600 | 0.0269 | 0.9578 | 0.9678 | 0.9628 | 0.9951 |
0.0056 | 10.93 | 2700 | 0.0268 | 0.9581 | 0.9637 | 0.9609 | 0.9946 |
0.0056 | 11.34 | 2800 | 0.0275 | 0.9572 | 0.9673 | 0.9622 | 0.9950 |
0.0056 | 11.74 | 2900 | 0.0273 | 0.9555 | 0.9661 | 0.9607 | 0.9947 |
0.0038 | 12.15 | 3000 | 0.0252 | 0.9644 | 0.9661 | 0.9652 | 0.9956 |
0.0038 | 12.55 | 3100 | 0.0260 | 0.9593 | 0.9661 | 0.9627 | 0.9952 |
0.0038 | 12.96 | 3200 | 0.0260 | 0.9577 | 0.9673 | 0.9625 | 0.9950 |
0.0038 | 13.36 | 3300 | 0.0285 | 0.9550 | 0.9678 | 0.9614 | 0.9949 |
0.0038 | 13.77 | 3400 | 0.0291 | 0.9533 | 0.9673 | 0.9602 | 0.9948 |
0.0029 | 14.17 | 3500 | 0.0294 | 0.9499 | 0.9655 | 0.9577 | 0.9946 |
0.0029 | 14.57 | 3600 | 0.0292 | 0.9561 | 0.9678 | 0.9619 | 0.9949 |
0.0029 | 14.98 | 3700 | 0.0301 | 0.9510 | 0.9643 | 0.9576 | 0.9943 |
0.0029 | 15.38 | 3800 | 0.0277 | 0.9578 | 0.9684 | 0.9631 | 0.9954 |
0.0029 | 15.79 | 3900 | 0.0279 | 0.9584 | 0.9690 | 0.9637 | 0.9953 |
0.0023 | 16.19 | 4000 | 0.0282 | 0.9584 | 0.9690 | 0.9637 | 0.9953 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3