<!-- 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_v8.0
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: 0.0299
- Precision: 0.9566
- Recall: 0.9746
- F1: 0.9655
- Accuracy: 0.9955
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: 6000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.39 | 100 | 0.1908 | 0.6353 | 0.7029 | 0.6674 | 0.9427 |
No log | 0.78 | 200 | 0.0525 | 0.8934 | 0.9269 | 0.9098 | 0.9869 |
No log | 1.17 | 300 | 0.0416 | 0.9066 | 0.9332 | 0.9197 | 0.9886 |
No log | 1.56 | 400 | 0.0330 | 0.9287 | 0.9523 | 0.9404 | 0.9917 |
0.1696 | 1.95 | 500 | 0.0280 | 0.9368 | 0.9500 | 0.9433 | 0.9922 |
0.1696 | 2.34 | 600 | 0.0336 | 0.9276 | 0.9566 | 0.9419 | 0.9918 |
0.1696 | 2.73 | 700 | 0.0287 | 0.9381 | 0.9597 | 0.9488 | 0.9928 |
0.1696 | 3.12 | 800 | 0.0231 | 0.9522 | 0.9664 | 0.9593 | 0.9945 |
0.1696 | 3.52 | 900 | 0.0239 | 0.9369 | 0.9640 | 0.9503 | 0.9934 |
0.026 | 3.91 | 1000 | 0.0203 | 0.9605 | 0.9703 | 0.9654 | 0.9953 |
0.026 | 4.3 | 1100 | 0.0234 | 0.9553 | 0.9699 | 0.9626 | 0.9950 |
0.026 | 4.69 | 1200 | 0.0230 | 0.9477 | 0.9703 | 0.9589 | 0.9944 |
0.026 | 5.08 | 1300 | 0.0253 | 0.9540 | 0.9722 | 0.9630 | 0.9952 |
0.026 | 5.47 | 1400 | 0.0222 | 0.9517 | 0.9695 | 0.9605 | 0.9947 |
0.0152 | 5.86 | 1500 | 0.0263 | 0.9474 | 0.9711 | 0.9591 | 0.9947 |
0.0152 | 6.25 | 1600 | 0.0252 | 0.9519 | 0.9672 | 0.9595 | 0.9946 |
0.0152 | 6.64 | 1700 | 0.0235 | 0.9553 | 0.9695 | 0.9624 | 0.9948 |
0.0152 | 7.03 | 1800 | 0.0207 | 0.9571 | 0.9676 | 0.9623 | 0.9949 |
0.0152 | 7.42 | 1900 | 0.0272 | 0.9526 | 0.9734 | 0.9629 | 0.9951 |
0.0098 | 7.81 | 2000 | 0.0240 | 0.9527 | 0.9691 | 0.9609 | 0.9949 |
0.0098 | 8.2 | 2100 | 0.0253 | 0.9505 | 0.9687 | 0.9595 | 0.9947 |
0.0098 | 8.59 | 2200 | 0.0267 | 0.9444 | 0.9695 | 0.9568 | 0.9945 |
0.0098 | 8.98 | 2300 | 0.0217 | 0.9562 | 0.9726 | 0.9643 | 0.9953 |
0.0098 | 9.38 | 2400 | 0.0223 | 0.9591 | 0.9722 | 0.9656 | 0.9953 |
0.0072 | 9.77 | 2500 | 0.0243 | 0.9569 | 0.9726 | 0.9647 | 0.9954 |
0.0072 | 10.16 | 2600 | 0.0252 | 0.9520 | 0.9699 | 0.9609 | 0.9948 |
0.0072 | 10.55 | 2700 | 0.0233 | 0.9591 | 0.9726 | 0.9658 | 0.9954 |
0.0072 | 10.94 | 2800 | 0.0268 | 0.9458 | 0.9695 | 0.9575 | 0.9944 |
0.0072 | 11.33 | 2900 | 0.0266 | 0.9533 | 0.9746 | 0.9639 | 0.9952 |
0.0053 | 11.72 | 3000 | 0.0257 | 0.9536 | 0.9722 | 0.9628 | 0.9953 |
0.0053 | 12.11 | 3100 | 0.0215 | 0.9618 | 0.9738 | 0.9678 | 0.9958 |
0.0053 | 12.5 | 3200 | 0.0236 | 0.9544 | 0.9734 | 0.9638 | 0.9953 |
0.0053 | 12.89 | 3300 | 0.0229 | 0.9617 | 0.9726 | 0.9672 | 0.9957 |
0.0053 | 13.28 | 3400 | 0.0257 | 0.9581 | 0.9738 | 0.9659 | 0.9956 |
0.004 | 13.67 | 3500 | 0.0233 | 0.9651 | 0.9734 | 0.9692 | 0.9959 |
0.004 | 14.06 | 3600 | 0.0268 | 0.9513 | 0.9695 | 0.9603 | 0.9948 |
0.004 | 14.45 | 3700 | 0.0290 | 0.9532 | 0.9707 | 0.9618 | 0.9950 |
0.004 | 14.84 | 3800 | 0.0279 | 0.9558 | 0.9722 | 0.9640 | 0.9953 |
0.004 | 15.23 | 3900 | 0.0308 | 0.9524 | 0.9707 | 0.9615 | 0.9948 |
0.0031 | 15.62 | 4000 | 0.0272 | 0.9580 | 0.9730 | 0.9655 | 0.9955 |
0.0031 | 16.02 | 4100 | 0.0272 | 0.9569 | 0.9711 | 0.9639 | 0.9953 |
0.0031 | 16.41 | 4200 | 0.0279 | 0.9577 | 0.9726 | 0.9651 | 0.9954 |
0.0031 | 16.8 | 4300 | 0.0290 | 0.9517 | 0.9707 | 0.9611 | 0.9949 |
0.0031 | 17.19 | 4400 | 0.0274 | 0.9584 | 0.9719 | 0.9651 | 0.9954 |
0.0022 | 17.58 | 4500 | 0.0326 | 0.9521 | 0.9711 | 0.9615 | 0.9949 |
0.0022 | 17.97 | 4600 | 0.0310 | 0.9554 | 0.9719 | 0.9636 | 0.9952 |
0.0022 | 18.36 | 4700 | 0.0285 | 0.9558 | 0.9715 | 0.9636 | 0.9953 |
0.0022 | 18.75 | 4800 | 0.0295 | 0.9566 | 0.9746 | 0.9655 | 0.9956 |
0.0022 | 19.14 | 4900 | 0.0280 | 0.9580 | 0.9730 | 0.9655 | 0.9955 |
0.0015 | 19.53 | 5000 | 0.0320 | 0.9499 | 0.9719 | 0.9608 | 0.9950 |
0.0015 | 19.92 | 5100 | 0.0271 | 0.9641 | 0.9762 | 0.9701 | 0.9961 |
0.0015 | 20.31 | 5200 | 0.0276 | 0.9618 | 0.9754 | 0.9686 | 0.9959 |
0.0015 | 20.7 | 5300 | 0.0322 | 0.9537 | 0.9734 | 0.9634 | 0.9953 |
0.0015 | 21.09 | 5400 | 0.0282 | 0.9570 | 0.9746 | 0.9657 | 0.9955 |
0.0012 | 21.48 | 5500 | 0.0318 | 0.9533 | 0.9742 | 0.9637 | 0.9953 |
0.0012 | 21.88 | 5600 | 0.0286 | 0.9577 | 0.9742 | 0.9659 | 0.9955 |
0.0012 | 22.27 | 5700 | 0.0304 | 0.9570 | 0.9746 | 0.9657 | 0.9955 |
0.0012 | 22.66 | 5800 | 0.0299 | 0.9566 | 0.9738 | 0.9651 | 0.9954 |
0.0012 | 23.05 | 5900 | 0.0300 | 0.9566 | 0.9746 | 0.9655 | 0.9955 |
0.0011 | 23.44 | 6000 | 0.0299 | 0.9566 | 0.9746 | 0.9655 | 0.9955 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3