generated_from_trainer

<!-- 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_v8.1

This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:

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:

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 0.4 100 0.1287 0.7656 0.8050 0.7848 0.9662
No log 0.79 200 0.0595 0.8683 0.912 0.8896 0.9843
No log 1.19 300 0.0529 0.8628 0.9250 0.8928 0.9850
No log 1.58 400 0.0325 0.9271 0.9501 0.9385 0.9917
0.1448 1.98 500 0.0338 0.9144 0.9482 0.9310 0.9905
0.1448 2.37 600 0.0270 0.9445 0.9592 0.9518 0.9932
0.1448 2.77 700 0.0270 0.9367 0.9589 0.9477 0.9929
0.1448 3.16 800 0.0235 0.9536 0.9638 0.9587 0.9945
0.1448 3.56 900 0.0251 0.9423 0.9650 0.9535 0.9940
0.0246 3.95 1000 0.0257 0.9382 0.9665 0.9521 0.9939
0.0246 4.35 1100 0.0245 0.9425 0.9684 0.9553 0.9943
0.0246 4.74 1200 0.0245 0.9468 0.9691 0.9578 0.9947
0.0246 5.14 1300 0.0256 0.9450 0.9688 0.9567 0.9946
0.0246 5.53 1400 0.0204 0.9501 0.9657 0.9579 0.9947
0.0148 5.93 1500 0.0210 0.9568 0.9707 0.9637 0.9953
0.0148 6.32 1600 0.0242 0.9507 0.9703 0.9604 0.9948
0.0148 6.72 1700 0.0237 0.9541 0.9661 0.9601 0.9948
0.0148 7.11 1800 0.0246 0.9449 0.9661 0.9554 0.9941
0.0148 7.51 1900 0.0227 0.9571 0.9699 0.9635 0.9955
0.0092 7.91 2000 0.0242 0.9507 0.9703 0.9604 0.9949
0.0092 8.3 2100 0.0258 0.9476 0.9710 0.9592 0.9947
0.0092 8.7 2200 0.0214 0.9551 0.9726 0.9638 0.9953
0.0092 9.09 2300 0.0232 0.9523 0.9730 0.9625 0.9953
0.0092 9.49 2400 0.0212 0.9515 0.9714 0.9614 0.9951
0.0064 9.88 2500 0.0219 0.9572 0.9722 0.9647 0.9955
0.0064 10.28 2600 0.0239 0.9566 0.9730 0.9647 0.9955
0.0064 10.67 2700 0.0221 0.9601 0.9726 0.9663 0.9958
0.0064 11.07 2800 0.0210 0.9572 0.9710 0.9641 0.9954
0.0064 11.46 2900 0.0267 0.9554 0.9722 0.9637 0.9952
0.0047 11.86 3000 0.0247 0.9533 0.9714 0.9623 0.9951
0.0047 12.25 3100 0.0254 0.9572 0.9718 0.9645 0.9954
0.0047 12.65 3200 0.0239 0.9533 0.9722 0.9627 0.9954
0.0047 13.04 3300 0.0233 0.9552 0.9737 0.9643 0.9956
0.0047 13.44 3400 0.0226 0.9569 0.9733 0.9651 0.9956
0.0037 13.83 3500 0.0241 0.9552 0.9741 0.9645 0.9956
0.0037 14.23 3600 0.0240 0.9565 0.9726 0.9645 0.9954
0.0037 14.62 3700 0.0218 0.9577 0.9737 0.9656 0.9958
0.0037 15.02 3800 0.0213 0.9595 0.9737 0.9665 0.9958
0.0037 15.42 3900 0.0237 0.9540 0.9726 0.9632 0.9953
0.0026 15.81 4000 0.0237 0.9576 0.9726 0.9650 0.9956
0.0026 16.21 4100 0.0253 0.9551 0.9733 0.9642 0.9955
0.0026 16.6 4200 0.0249 0.9558 0.9722 0.9639 0.9953
0.0026 17.0 4300 0.0239 0.9562 0.9722 0.9641 0.9955
0.0026 17.39 4400 0.0245 0.9577 0.9741 0.9658 0.9957
0.002 17.79 4500 0.0248 0.9588 0.9745 0.9666 0.9959
0.002 18.18 4600 0.0260 0.9569 0.9718 0.9643 0.9955
0.002 18.58 4700 0.0251 0.9581 0.9745 0.9662 0.9958
0.002 18.97 4800 0.0260 0.9581 0.9745 0.9662 0.9958
0.002 19.37 4900 0.0260 0.9569 0.9737 0.9653 0.9956
0.0015 19.76 5000 0.0261 0.9569 0.9737 0.9653 0.9956

Framework versions