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_v5.8.2

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 0.1197 0.8324 0.7696 0.7998 0.9748
No log 0.81 200 0.0613 0.8586 0.9123 0.8846 0.9858
No log 1.21 300 0.0387 0.9068 0.9450 0.9255 0.9907
No log 1.62 400 0.0238 0.9459 0.9602 0.9530 0.9942
0.1421 2.02 500 0.0224 0.9622 0.9673 0.9647 0.9953
0.1421 2.43 600 0.0235 0.9617 0.9684 0.9650 0.9952
0.1421 2.83 700 0.0222 0.9644 0.9673 0.9658 0.9950
0.1421 3.24 800 0.0271 0.9506 0.9673 0.9588 0.9945
0.1421 3.64 900 0.0273 0.9420 0.9591 0.9504 0.9936
0.0199 4.05 1000 0.0264 0.9511 0.9667 0.9588 0.9945
0.0199 4.45 1100 0.0219 0.9617 0.9684 0.9650 0.9953
0.0199 4.86 1200 0.0238 0.9572 0.9684 0.9628 0.9951
0.0199 5.26 1300 0.0259 0.9632 0.9655 0.9644 0.9953
0.0199 5.67 1400 0.0226 0.9554 0.9649 0.9601 0.9948
0.0116 6.07 1500 0.0205 0.9632 0.9655 0.9644 0.9952
0.0116 6.48 1600 0.0239 0.9674 0.9731 0.9703 0.9957
0.0116 6.88 1700 0.0250 0.96 0.9684 0.9642 0.9953
0.0116 7.29 1800 0.0236 0.9651 0.9713 0.9682 0.9957
0.0116 7.69 1900 0.0264 0.9589 0.9696 0.9642 0.9954
0.0089 8.1 2000 0.0274 0.9623 0.9702 0.9662 0.9950
0.0089 8.5 2100 0.0255 0.9685 0.9702 0.9693 0.9957
0.0089 8.91 2200 0.0295 0.9667 0.9690 0.9679 0.9953
0.0089 9.31 2300 0.0235 0.9703 0.9754 0.9729 0.9963
0.0089 9.72 2400 0.0255 0.9640 0.9719 0.9680 0.9955
0.0062 10.12 2500 0.0250 0.9630 0.9731 0.9680 0.9956
0.0062 10.53 2600 0.0276 0.9601 0.9708 0.9654 0.9955
0.0062 10.93 2700 0.0272 0.9680 0.9743 0.9711 0.9960
0.0062 11.34 2800 0.0291 0.9674 0.9713 0.9694 0.9955
0.0062 11.74 2900 0.0259 0.9697 0.9743 0.9720 0.9960
0.0041 12.15 3000 0.0248 0.9680 0.9725 0.9702 0.9960
0.0041 12.55 3100 0.0287 0.9640 0.9696 0.9668 0.9951
0.0041 12.96 3200 0.0300 0.9703 0.9731 0.9717 0.9957
0.0041 13.36 3300 0.0262 0.9679 0.9708 0.9693 0.9955
0.0041 13.77 3400 0.0265 0.9692 0.9749 0.9720 0.9957
0.0033 14.17 3500 0.0295 0.9662 0.9696 0.9679 0.9955
0.0033 14.57 3600 0.0301 0.9680 0.9743 0.9711 0.9958
0.0033 14.98 3700 0.0280 0.9686 0.9743 0.9714 0.9957
0.0033 15.38 3800 0.0300 0.9669 0.9749 0.9709 0.9958
0.0033 15.79 3900 0.0319 0.9617 0.9696 0.9656 0.9954
0.0018 16.19 4000 0.0263 0.9658 0.9737 0.9697 0.9958
0.0018 16.6 4100 0.0273 0.9692 0.9754 0.9723 0.9958
0.0018 17.0 4200 0.0273 0.9675 0.9749 0.9712 0.9962
0.0018 17.41 4300 0.0298 0.9669 0.9749 0.9709 0.9956
0.0018 17.81 4400 0.0318 0.9646 0.9725 0.9685 0.9956
0.0015 18.22 4500 0.0301 0.9669 0.9737 0.9703 0.9956
0.0015 18.62 4600 0.0302 0.9680 0.9737 0.9708 0.9956
0.0015 19.03 4700 0.0298 0.9664 0.9743 0.9703 0.9956
0.0015 19.43 4800 0.0286 0.9664 0.9749 0.9706 0.9958
0.0015 19.84 4900 0.0297 0.9658 0.9754 0.9706 0.9958
0.0009 20.24 5000 0.0261 0.9681 0.9754 0.9717 0.9962
0.0009 20.65 5100 0.0283 0.9653 0.9766 0.9709 0.9958
0.0009 21.05 5200 0.0302 0.9653 0.9766 0.9709 0.9958
0.0009 21.46 5300 0.0316 0.9642 0.9754 0.9698 0.9957
0.0009 21.86 5400 0.0297 0.9652 0.9737 0.9694 0.9957
0.0007 22.27 5500 0.0298 0.9652 0.9737 0.9694 0.9957
0.0007 22.67 5600 0.0297 0.9652 0.9737 0.9694 0.9955
0.0007 23.08 5700 0.0299 0.9647 0.9743 0.9695 0.9956
0.0007 23.48 5800 0.0300 0.9647 0.9749 0.9697 0.9957
0.0007 23.89 5900 0.0300 0.9647 0.9749 0.9697 0.9957
0.0006 24.29 6000 0.0300 0.9647 0.9743 0.9695 0.9956

Framework versions