perioli_vgm_v5.4

作者 DataIntelligenceTeam · 下载 0 · 点赞 0 · 更新 2023-11-02

generated_from_trainer

perioli_vgm_v5.4

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 0.52 100 0.0894 0.5174 0.4351 0.4727 0.9782
No log 1.04 200 0.0414 0.6754 0.6444 0.6595 0.9883
No log 1.55 300 0.0413 0.6481 0.7782 0.7072 0.9874
No log 2.07 400 0.0187 0.7757 0.8536 0.8127 0.9940
0.0743 2.59 500 0.0121 0.8427 0.8745 0.8583 0.9963
0.0743 3.11 600 0.0178 0.8192 0.8912 0.8537 0.9951
0.0743 3.63 700 0.0166 0.8353 0.8912 0.8623 0.9954
0.0743 4.15 800 0.0119 0.8051 0.9163 0.8571 0.9954
0.0743 4.66 900 0.0122 0.9224 0.9456 0.9339 0.9972
0.0095 5.18 1000 0.0149 0.9313 0.9079 0.9195 0.9971
0.0095 5.7 1100 0.0146 0.9578 0.9498 0.9538 0.9979
0.0095 6.22 1200 0.0164 0.9309 0.9582 0.9443 0.9969
0.0095 6.74 1300 0.0183 0.8814 0.9331 0.9065 0.9964
0.0095 7.25 1400 0.0132 0.9540 0.9540 0.9540 0.9979
0.0025 7.77 1500 0.0142 0.9456 0.9456 0.9456 0.9977
0.0025 8.29 1600 0.0136 0.9617 0.9456 0.9536 0.9979
0.0025 8.81 1700 0.0143 0.9494 0.9414 0.9454 0.9977
0.0025 9.33 1800 0.0144 0.9388 0.9623 0.9504 0.9977
0.0025 9.84 1900 0.0121 0.9540 0.9540 0.9540 0.9979
0.0012 10.36 2000 0.0127 0.9707 0.9707 0.9707 0.9982
0.0012 10.88 2100 0.0140 0.9465 0.9623 0.9544 0.9979
0.0012 11.4 2200 0.0129 0.9506 0.9665 0.9585 0.9982
0.0012 11.92 2300 0.0126 0.9506 0.9665 0.9585 0.9982
0.0012 12.44 2400 0.0140 0.9585 0.9665 0.9625 0.9980
0.0007 12.95 2500 0.0135 0.9585 0.9665 0.9625 0.9980

Framework versions