<!-- 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_v9.0
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: 0.0224
- Precision: 0.9455
- Recall: 0.9697
- F1: 0.9575
- Accuracy: 0.9951
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: 3000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.36 | 100 | 0.1518 | 0.6899 | 0.7246 | 0.7068 | 0.9525 |
No log | 0.71 | 200 | 0.0630 | 0.8527 | 0.9059 | 0.8785 | 0.9824 |
No log | 1.07 | 300 | 0.0404 | 0.8838 | 0.9173 | 0.9002 | 0.9857 |
No log | 1.43 | 400 | 0.0317 | 0.9107 | 0.9462 | 0.9281 | 0.9908 |
0.1621 | 1.79 | 500 | 0.0455 | 0.8690 | 0.9397 | 0.9029 | 0.9876 |
0.1621 | 2.14 | 600 | 0.0298 | 0.9239 | 0.9586 | 0.9410 | 0.9926 |
0.1621 | 2.5 | 700 | 0.0241 | 0.9423 | 0.9514 | 0.9468 | 0.9937 |
0.1621 | 2.86 | 800 | 0.0227 | 0.9474 | 0.9624 | 0.9549 | 0.9944 |
0.1621 | 3.21 | 900 | 0.0239 | 0.9406 | 0.9662 | 0.9532 | 0.9943 |
0.0264 | 3.57 | 1000 | 0.0260 | 0.9263 | 0.9617 | 0.9437 | 0.9933 |
0.0264 | 3.93 | 1100 | 0.0210 | 0.9470 | 0.9666 | 0.9567 | 0.9948 |
0.0264 | 4.29 | 1200 | 0.0228 | 0.9423 | 0.9676 | 0.9548 | 0.9946 |
0.0264 | 4.64 | 1300 | 0.0216 | 0.9471 | 0.9690 | 0.9579 | 0.9948 |
0.0264 | 5.0 | 1400 | 0.0274 | 0.9296 | 0.9652 | 0.9471 | 0.9937 |
0.0162 | 5.36 | 1500 | 0.0260 | 0.9414 | 0.9683 | 0.9546 | 0.9947 |
0.0162 | 5.71 | 1600 | 0.0239 | 0.9407 | 0.9683 | 0.9543 | 0.9946 |
0.0162 | 6.07 | 1700 | 0.0240 | 0.9408 | 0.9697 | 0.9550 | 0.9947 |
0.0162 | 6.43 | 1800 | 0.0220 | 0.9429 | 0.9673 | 0.9549 | 0.9948 |
0.0162 | 6.79 | 1900 | 0.0211 | 0.9490 | 0.9686 | 0.9587 | 0.9951 |
0.0105 | 7.14 | 2000 | 0.0210 | 0.9492 | 0.9717 | 0.9603 | 0.9954 |
0.0105 | 7.5 | 2100 | 0.0206 | 0.9478 | 0.9700 | 0.9588 | 0.9952 |
0.0105 | 7.86 | 2200 | 0.0218 | 0.9481 | 0.9700 | 0.9589 | 0.9952 |
0.0105 | 8.21 | 2300 | 0.0238 | 0.9430 | 0.9690 | 0.9558 | 0.9948 |
0.0105 | 8.57 | 2400 | 0.0222 | 0.9455 | 0.9697 | 0.9575 | 0.9951 |
0.0082 | 8.93 | 2500 | 0.0199 | 0.9521 | 0.9728 | 0.9623 | 0.9956 |
0.0082 | 9.29 | 2600 | 0.0221 | 0.9418 | 0.9700 | 0.9557 | 0.9949 |
0.0082 | 9.64 | 2700 | 0.0210 | 0.9494 | 0.9697 | 0.9594 | 0.9952 |
0.0082 | 10.0 | 2800 | 0.0213 | 0.9478 | 0.9710 | 0.9593 | 0.9953 |
0.0082 | 10.36 | 2900 | 0.0215 | 0.9495 | 0.9717 | 0.9605 | 0.9954 |
0.0061 | 10.71 | 3000 | 0.0224 | 0.9455 | 0.9697 | 0.9575 | 0.9951 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3