<!-- 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_v9.1
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: 0.0209
- Precision: 0.9475
- Recall: 0.9700
- F1: 0.9586
- Accuracy: 0.9952
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 | 0.1628 | 0.6631 | 0.7373 | 0.6982 | 0.9515 |
No log | 0.71 | 200 | 0.0651 | 0.8361 | 0.8983 | 0.8661 | 0.9813 |
No log | 1.07 | 300 | 0.0553 | 0.8383 | 0.9114 | 0.8733 | 0.9833 |
No log | 1.43 | 400 | 0.0288 | 0.9227 | 0.9421 | 0.9323 | 0.9914 |
0.1596 | 1.79 | 500 | 0.0289 | 0.9263 | 0.9538 | 0.9399 | 0.9927 |
0.1596 | 2.14 | 600 | 0.0244 | 0.9393 | 0.9607 | 0.9499 | 0.9939 |
0.1596 | 2.5 | 700 | 0.0234 | 0.9402 | 0.9648 | 0.9524 | 0.9943 |
0.1596 | 2.86 | 800 | 0.0222 | 0.9484 | 0.9631 | 0.9557 | 0.9948 |
0.1596 | 3.21 | 900 | 0.0239 | 0.9494 | 0.9642 | 0.9567 | 0.9948 |
0.0252 | 3.57 | 1000 | 0.0233 | 0.9536 | 0.9645 | 0.9590 | 0.9951 |
0.0252 | 3.93 | 1100 | 0.0217 | 0.9480 | 0.9624 | 0.9552 | 0.9946 |
0.0252 | 4.29 | 1200 | 0.0245 | 0.9298 | 0.9593 | 0.9444 | 0.9935 |
0.0252 | 4.64 | 1300 | 0.0231 | 0.9437 | 0.9648 | 0.9542 | 0.9946 |
0.0252 | 5.0 | 1400 | 0.0220 | 0.9503 | 0.9690 | 0.9595 | 0.9954 |
0.0173 | 5.36 | 1500 | 0.0244 | 0.9357 | 0.9635 | 0.9494 | 0.9942 |
0.0173 | 5.71 | 1600 | 0.0240 | 0.9425 | 0.9666 | 0.9544 | 0.9947 |
0.0173 | 6.07 | 1700 | 0.0229 | 0.9412 | 0.9662 | 0.9536 | 0.9945 |
0.0173 | 6.43 | 1800 | 0.0238 | 0.9415 | 0.9652 | 0.9532 | 0.9944 |
0.0173 | 6.79 | 1900 | 0.0236 | 0.9418 | 0.9642 | 0.9528 | 0.9944 |
0.0116 | 7.14 | 2000 | 0.0223 | 0.9454 | 0.9673 | 0.9562 | 0.9949 |
0.0116 | 7.5 | 2100 | 0.0220 | 0.9509 | 0.9673 | 0.9590 | 0.9951 |
0.0116 | 7.86 | 2200 | 0.0263 | 0.9326 | 0.9638 | 0.9480 | 0.9939 |
0.0116 | 8.21 | 2300 | 0.0217 | 0.9484 | 0.9693 | 0.9587 | 0.9951 |
0.0116 | 8.57 | 2400 | 0.0217 | 0.9491 | 0.9697 | 0.9592 | 0.9952 |
0.0074 | 8.93 | 2500 | 0.0216 | 0.9490 | 0.9683 | 0.9585 | 0.9952 |
0.0074 | 9.29 | 2600 | 0.0217 | 0.95 | 0.9693 | 0.9596 | 0.9952 |
0.0074 | 9.64 | 2700 | 0.0220 | 0.9455 | 0.9693 | 0.9573 | 0.9950 |
0.0074 | 10.0 | 2800 | 0.0216 | 0.9439 | 0.9690 | 0.9563 | 0.9950 |
0.0074 | 10.36 | 2900 | 0.0216 | 0.9449 | 0.9693 | 0.9570 | 0.9950 |
0.0059 | 10.71 | 3000 | 0.0209 | 0.9475 | 0.9700 | 0.9586 | 0.9952 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3