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_v8.2

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 0.37 100 0.1368 0.7334 0.6575 0.6934 0.9545
No log 0.74 200 0.0733 0.8189 0.8899 0.8529 0.9775
No log 1.11 300 0.0420 0.8868 0.9296 0.9077 0.9872
No log 1.48 400 0.0315 0.9338 0.9466 0.9402 0.9915
0.1641 1.85 500 0.0306 0.9294 0.9470 0.9381 0.9917
0.1641 2.22 600 0.0268 0.9452 0.9526 0.9489 0.9934
0.1641 2.59 700 0.0250 0.9478 0.9492 0.9485 0.9935
0.1641 2.96 800 0.0254 0.9352 0.9622 0.9485 0.9936
0.1641 3.33 900 0.0250 0.9384 0.9648 0.9514 0.9938
0.0266 3.7 1000 0.0265 0.9247 0.9600 0.9420 0.9927
0.0266 4.07 1100 0.0231 0.9450 0.9681 0.9564 0.9944
0.0266 4.44 1200 0.0210 0.9527 0.9700 0.9612 0.9952
0.0266 4.81 1300 0.0204 0.9609 0.9648 0.9628 0.9952
0.0266 5.19 1400 0.0240 0.9509 0.9685 0.9596 0.9950
0.0151 5.56 1500 0.0214 0.9558 0.9703 0.9630 0.9952
0.0151 5.93 1600 0.0212 0.9485 0.9700 0.9591 0.9950
0.0151 6.3 1700 0.0204 0.9520 0.9711 0.9615 0.9953
0.0151 6.67 1800 0.0238 0.9436 0.9681 0.9557 0.9944
0.0151 7.04 1900 0.0266 0.9356 0.9696 0.9523 0.9937
0.0105 7.41 2000 0.0186 0.9616 0.9748 0.9682 0.9962
0.0105 7.78 2100 0.0188 0.9634 0.9759 0.9696 0.9964
0.0105 8.15 2200 0.0229 0.9566 0.9726 0.9645 0.9955
0.0105 8.52 2300 0.0198 0.9663 0.9774 0.9718 0.9966
0.0105 8.89 2400 0.0195 0.9598 0.9737 0.9667 0.9961
0.0067 9.26 2500 0.0203 0.9623 0.9755 0.9689 0.9962
0.0067 9.63 2600 0.0211 0.9537 0.9692 0.9614 0.9953
0.0067 10.0 2700 0.0210 0.9553 0.9733 0.9642 0.9958
0.0067 10.37 2800 0.0204 0.9577 0.9733 0.9654 0.9960
0.0067 10.74 2900 0.0206 0.9566 0.9729 0.9647 0.9958
0.0054 11.11 3000 0.0203 0.9627 0.9770 0.9698 0.9964
0.0054 11.48 3100 0.0211 0.9546 0.9744 0.9644 0.9956
0.0054 11.85 3200 0.0187 0.9620 0.9748 0.9683 0.9962
0.0054 12.22 3300 0.0188 0.9627 0.9766 0.9696 0.9962
0.0054 12.59 3400 0.0206 0.9578 0.9752 0.9664 0.9960
0.0037 12.96 3500 0.0233 0.9588 0.9748 0.9667 0.9960
0.0037 13.33 3600 0.0234 0.9574 0.9748 0.9660 0.9958
0.0037 13.7 3700 0.0195 0.9652 0.9759 0.9705 0.9964
0.0037 14.07 3800 0.0224 0.9616 0.9733 0.9674 0.9961
0.0037 14.44 3900 0.0224 0.9620 0.9752 0.9685 0.9962
0.0025 14.81 4000 0.0262 0.9595 0.9755 0.9675 0.9960
0.0025 15.19 4100 0.0220 0.9627 0.9755 0.9691 0.9962
0.0025 15.56 4200 0.0231 0.9631 0.9770 0.9700 0.9964
0.0025 15.93 4300 0.0239 0.9606 0.9755 0.9680 0.9962
0.0025 16.3 4400 0.0235 0.9617 0.9759 0.9687 0.9962
0.002 16.67 4500 0.0246 0.9599 0.9748 0.9673 0.9959
0.002 17.04 4600 0.0231 0.9631 0.9763 0.9696 0.9964
0.002 17.41 4700 0.0245 0.9592 0.9752 0.9671 0.9960
0.002 17.78 4800 0.0239 0.9620 0.9766 0.9693 0.9963
0.002 18.15 4900 0.0242 0.9631 0.9770 0.9700 0.9964
0.0016 18.52 5000 0.0241 0.9631 0.9770 0.9700 0.9964

Framework versions