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_v5.8.7

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 0.1526 0.7156 0.7662 0.7400 0.9540
No log 0.81 200 0.0693 0.8493 0.9013 0.8745 0.9796
No log 1.21 300 0.0490 0.8860 0.9297 0.9073 0.9864
No log 1.62 400 0.0510 0.8810 0.9356 0.9075 0.9863
0.1511 2.02 500 0.0377 0.9174 0.9479 0.9324 0.9900
0.1511 2.43 600 0.0396 0.8996 0.9447 0.9216 0.9887
0.1511 2.83 700 0.0363 0.9142 0.9463 0.9299 0.9897
0.1511 3.24 800 0.0261 0.9503 0.9506 0.9504 0.9930
0.1511 3.64 900 0.0272 0.9489 0.9605 0.9547 0.9936
0.0289 4.05 1000 0.0283 0.9436 0.9641 0.9537 0.9935
0.0289 4.45 1100 0.0261 0.9500 0.9684 0.9591 0.9943
0.0289 4.86 1200 0.0250 0.9615 0.9656 0.9635 0.9949
0.0289 5.26 1300 0.0296 0.9437 0.9664 0.9549 0.9938
0.0289 5.67 1400 0.0268 0.9539 0.9648 0.9594 0.9942
0.0173 6.07 1500 0.0253 0.9526 0.9684 0.9604 0.9945
0.0173 6.48 1600 0.0257 0.9537 0.9688 0.9612 0.9948
0.0173 6.88 1700 0.0228 0.9566 0.9672 0.9619 0.9947
0.0173 7.29 1800 0.0273 0.9537 0.9688 0.9612 0.9946
0.0173 7.69 1900 0.0257 0.9548 0.9668 0.9608 0.9947
0.0117 8.1 2000 0.0256 0.9590 0.9688 0.9639 0.9949
0.0117 8.5 2100 0.0244 0.9591 0.9724 0.9657 0.9953
0.0117 8.91 2200 0.0257 0.9592 0.9743 0.9667 0.9954
0.0117 9.31 2300 0.0244 0.9613 0.9716 0.9664 0.9954
0.0117 9.72 2400 0.0240 0.9550 0.9641 0.9595 0.9945
0.0088 10.12 2500 0.0230 0.9628 0.9712 0.9670 0.9955
0.0088 10.53 2600 0.0231 0.9607 0.9739 0.9672 0.9955
0.0088 10.93 2700 0.0230 0.9625 0.9735 0.9680 0.9957
0.0088 11.34 2800 0.0253 0.9602 0.9731 0.9667 0.9954
0.0088 11.74 2900 0.0258 0.9618 0.9739 0.9678 0.9956
0.006 12.15 3000 0.0215 0.9656 0.9743 0.9699 0.9959
0.006 12.55 3100 0.0264 0.9509 0.9704 0.9605 0.9946
0.006 12.96 3200 0.0234 0.9564 0.9704 0.9633 0.9950
0.006 13.36 3300 0.0248 0.9569 0.9724 0.9645 0.9951
0.006 13.77 3400 0.0218 0.9637 0.9739 0.9688 0.9957
0.0052 14.17 3500 0.0204 0.9659 0.9743 0.9701 0.9959
0.0052 14.57 3600 0.0271 0.9565 0.9727 0.9646 0.9952
0.0052 14.98 3700 0.0274 0.9551 0.9735 0.9642 0.9953
0.0052 15.38 3800 0.0239 0.9603 0.9747 0.9675 0.9958
0.0052 15.79 3900 0.0251 0.9622 0.9759 0.9690 0.9959
0.0036 16.19 4000 0.0246 0.9565 0.9727 0.9646 0.9953
0.0036 16.6 4100 0.0263 0.9606 0.9735 0.9670 0.9956
0.0036 17.0 4200 0.0260 0.9607 0.9759 0.9683 0.9958
0.0036 17.41 4300 0.0258 0.9618 0.9751 0.9684 0.9958
0.0036 17.81 4400 0.0257 0.9606 0.9727 0.9666 0.9955
0.0031 18.22 4500 0.0252 0.9652 0.9743 0.9697 0.9959
0.0031 18.62 4600 0.0232 0.9679 0.9751 0.9715 0.9961
0.0031 19.03 4700 0.0268 0.9569 0.9731 0.9650 0.9952
0.0031 19.43 4800 0.0255 0.9606 0.9727 0.9666 0.9955
0.0031 19.84 4900 0.0263 0.9590 0.9708 0.9649 0.9954
0.0023 20.24 5000 0.0274 0.9591 0.9720 0.9655 0.9954
0.0023 20.65 5100 0.0251 0.9659 0.9735 0.9697 0.9959
0.0023 21.05 5200 0.0255 0.9670 0.9731 0.9701 0.9959
0.0023 21.46 5300 0.0251 0.9625 0.9727 0.9676 0.9956
0.0023 21.86 5400 0.0270 0.9610 0.9720 0.9664 0.9954
0.0018 22.27 5500 0.0270 0.9598 0.9724 0.9661 0.9954
0.0018 22.67 5600 0.0249 0.9651 0.9731 0.9691 0.9959
0.0018 23.08 5700 0.0260 0.9633 0.9731 0.9682 0.9956
0.0018 23.48 5800 0.0261 0.9610 0.9731 0.9670 0.9955
0.0018 23.89 5900 0.0259 0.9621 0.9724 0.9672 0.9955
0.0015 24.29 6000 0.0258 0.9632 0.9727 0.9680 0.9956

Framework versions