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. -->

rhenus_v3.4

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 0.43 100 0.1573 0.7621 0.8332 0.7960 0.9633
No log 0.85 200 0.1619 0.8087 0.8280 0.8182 0.9682
No log 1.28 300 0.1650 0.7720 0.8280 0.799 0.9652
No log 1.7 400 0.1498 0.7973 0.8518 0.8236 0.9693
0.0484 2.13 500 0.1508 0.8059 0.8518 0.8282 0.9690
0.0484 2.55 600 0.1542 0.8006 0.8487 0.8239 0.9679
0.0484 2.98 700 0.1660 0.7750 0.8528 0.8120 0.9657
0.0484 3.4 800 0.1644 0.7644 0.8642 0.8113 0.9649
0.0484 3.83 900 0.1723 0.7577 0.8394 0.7965 0.9630
0.0322 4.26 1000 0.1759 0.8153 0.8373 0.8262 0.9692
0.0322 4.68 1100 0.1610 0.7893 0.8539 0.8203 0.9689
0.0322 5.11 1200 0.1680 0.8107 0.8301 0.8203 0.9690
0.0322 5.53 1300 0.1512 0.7955 0.8425 0.8183 0.9692
0.0322 5.96 1400 0.1699 0.7597 0.8549 0.8045 0.9639
0.024 6.38 1500 0.1574 0.8165 0.8622 0.8387 0.9701
0.024 6.81 1600 0.1466 0.8236 0.8518 0.8375 0.9735
0.024 7.23 1700 0.1487 0.8 0.8539 0.8261 0.9709
0.024 7.66 1800 0.1453 0.8213 0.8570 0.8387 0.9709
0.024 8.09 1900 0.1538 0.8186 0.8653 0.8413 0.9720
0.0177 8.51 2000 0.1562 0.8035 0.8642 0.8328 0.9709
0.0177 8.94 2100 0.1645 0.8099 0.8518 0.8303 0.9695
0.0177 9.36 2200 0.1467 0.8148 0.8663 0.8398 0.9719
0.0177 9.79 2300 0.1504 0.8418 0.8601 0.8508 0.9754
0.0177 10.21 2400 0.1622 0.8402 0.8394 0.8398 0.9719
0.0118 10.64 2500 0.1343 0.8465 0.8746 0.8603 0.9757
0.0118 11.06 2600 0.1540 0.8328 0.8570 0.8447 0.9724
0.0118 11.49 2700 0.1592 0.8206 0.8487 0.8344 0.9714
0.0118 11.91 2800 0.1479 0.8365 0.8746 0.8551 0.9743
0.0118 12.34 2900 0.1682 0.8087 0.8715 0.8389 0.9714
0.0097 12.77 3000 0.1519 0.8046 0.8663 0.8343 0.9724
0.0097 13.19 3100 0.1486 0.8427 0.8715 0.8569 0.9744
0.0097 13.62 3200 0.1535 0.8240 0.8684 0.8456 0.9735
0.0097 14.04 3300 0.1463 0.8302 0.8715 0.8504 0.9743
0.0097 14.47 3400 0.1541 0.8162 0.8653 0.8400 0.9714
0.0074 14.89 3500 0.1668 0.8126 0.8674 0.8391 0.9719
0.0074 15.32 3600 0.1652 0.8291 0.8549 0.8418 0.9720
0.0074 15.74 3700 0.1698 0.8234 0.8601 0.8414 0.9720
0.0074 16.17 3800 0.1620 0.8193 0.8788 0.848 0.9735
0.0074 16.6 3900 0.1608 0.8459 0.8591 0.8524 0.9743
0.0063 17.02 4000 0.1619 0.8227 0.8653 0.8434 0.9740
0.0063 17.45 4100 0.1530 0.8229 0.8715 0.8465 0.9743
0.0063 17.87 4200 0.1563 0.8287 0.8725 0.8501 0.9738
0.0063 18.3 4300 0.1594 0.8091 0.8694 0.8382 0.9730
0.0063 18.72 4400 0.1569 0.8251 0.8705 0.8472 0.9746
0.0049 19.15 4500 0.1473 0.8664 0.8736 0.8700 0.9781
0.0049 19.57 4600 0.1597 0.8167 0.8725 0.8437 0.9725
0.0049 20.0 4700 0.1552 0.8223 0.8725 0.8467 0.9740
0.0049 20.43 4800 0.1614 0.8400 0.8756 0.8574 0.9749
0.0049 20.85 4900 0.1519 0.8386 0.8725 0.8553 0.9759
0.0039 21.28 5000 0.1582 0.8273 0.8736 0.8498 0.9738
0.0039 21.7 5100 0.1618 0.8200 0.8736 0.8460 0.9744
0.0039 22.13 5200 0.1504 0.8309 0.8756 0.8527 0.9752
0.0039 22.55 5300 0.1512 0.8358 0.8756 0.8553 0.9755
0.0039 22.98 5400 0.1525 0.8231 0.8777 0.8495 0.9749
0.0029 23.4 5500 0.1568 0.8328 0.8777 0.8547 0.9746
0.0029 23.83 5600 0.1495 0.8408 0.8808 0.8603 0.9767
0.0029 24.26 5700 0.1510 0.8371 0.8788 0.8574 0.9763
0.0029 24.68 5800 0.1548 0.8278 0.8767 0.8515 0.9754
0.0029 25.11 5900 0.1524 0.8319 0.8767 0.8537 0.9759
0.0027 25.53 6000 0.1510 0.8351 0.8767 0.8554 0.9763

Framework versions