perioli_manifesti_v5.1

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

generated_from_trainer

perioli_manifesti_v5.1

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 0.48 100 0.1283 0.7806 0.8086 0.7944 0.9734
No log 0.96 200 0.0539 0.8832 0.9102 0.8965 0.9865
No log 1.44 300 0.0451 0.9001 0.9389 0.9191 0.9893
No log 1.92 400 0.0395 0.9058 0.9326 0.9190 0.9890
0.1374 2.4 500 0.0312 0.9269 0.9461 0.9364 0.9926
0.1374 2.88 600 0.0306 0.9230 0.9587 0.9405 0.9925
0.1374 3.37 700 0.0260 0.9356 0.9659 0.9505 0.9939
0.1374 3.85 800 0.0331 0.9244 0.9668 0.9451 0.9928
0.1374 4.33 900 0.0296 0.9099 0.9524 0.9306 0.9909
0.0233 4.81 1000 0.0235 0.9379 0.9632 0.9504 0.9943
0.0233 5.29 1100 0.0200 0.9407 0.9695 0.9549 0.9948
0.0233 5.77 1200 0.0263 0.9233 0.9632 0.9428 0.9929
0.0233 6.25 1300 0.0267 0.9291 0.9650 0.9467 0.9933
0.0233 6.73 1400 0.0243 0.9348 0.9668 0.9505 0.9941
0.0147 7.21 1500 0.0260 0.9280 0.9614 0.9444 0.9934
0.0147 7.69 1600 0.0256 0.9311 0.9596 0.9451 0.9934
0.0147 8.17 1700 0.0246 0.9291 0.9542 0.9415 0.9930
0.0147 8.65 1800 0.0242 0.9364 0.9650 0.9504 0.9941
0.0147 9.13 1900 0.0266 0.9268 0.9560 0.9412 0.9928
0.0107 9.62 2000 0.0300 0.9296 0.9605 0.9448 0.9932
0.0107 10.1 2100 0.0277 0.9365 0.9677 0.9518 0.9941
0.0107 10.58 2200 0.0292 0.9324 0.9668 0.9493 0.9937
0.0107 11.06 2300 0.0247 0.9284 0.9560 0.9420 0.9930
0.0107 11.54 2400 0.0298 0.9191 0.9488 0.9337 0.9921
0.0067 12.02 2500 0.0303 0.9215 0.9497 0.9354 0.9922
0.0067 12.5 2600 0.0305 0.9234 0.9533 0.9381 0.9925
0.0067 12.98 2700 0.0301 0.9215 0.9497 0.9354 0.9922

Framework versions