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. -->

Sinergy-Question-Answering

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 4.55 100 0.3686 0.5748 0.7179 0.6384 0.8881
No log 9.09 200 0.3057 0.6799 0.7546 0.7153 0.9189
No log 13.64 300 0.3287 0.7491 0.7875 0.7679 0.9354
No log 18.18 400 0.3452 0.7414 0.7875 0.7638 0.9307
0.2603 22.73 500 0.3365 0.7313 0.7875 0.7584 0.9415
0.2603 27.27 600 0.5244 0.7745 0.7802 0.7774 0.9097
0.2603 31.82 700 0.4429 0.7737 0.7766 0.7751 0.9338
0.2603 36.36 800 0.4776 0.7657 0.8022 0.7835 0.9266
0.2603 40.91 900 0.5305 0.7855 0.7912 0.7883 0.9236
0.051 45.45 1000 0.5867 0.7949 0.7949 0.7949 0.9261
0.051 50.0 1100 0.5569 0.7774 0.7802 0.7788 0.9323
0.051 54.55 1200 0.6154 0.7509 0.7509 0.7509 0.9200
0.051 59.09 1300 0.5406 0.7305 0.7546 0.7423 0.9297
0.051 63.64 1400 0.6069 0.7544 0.7875 0.7706 0.9287
0.0127 68.18 1500 0.6142 0.7603 0.7436 0.7519 0.9210
0.0127 72.73 1600 0.5822 0.7399 0.7399 0.7399 0.9297
0.0127 77.27 1700 0.5584 0.75 0.7582 0.7541 0.9297
0.0127 81.82 1800 0.5962 0.7509 0.7729 0.7617 0.9241
0.0127 86.36 1900 0.6891 0.7580 0.7802 0.7690 0.9236
0.0013 90.91 2000 0.6205 0.75 0.7582 0.7541 0.9266
0.0013 95.45 2100 0.6235 0.7745 0.7802 0.7774 0.9292
0.0013 100.0 2200 0.6329 0.7656 0.7656 0.7656 0.9292
0.0013 104.55 2300 0.6482 0.7739 0.7399 0.7566 0.9241
0.0013 109.09 2400 0.6440 0.7675 0.7619 0.7647 0.9292
0.0008 113.64 2500 0.6388 0.7630 0.7546 0.7587 0.9343
0.0008 118.18 2600 0.7076 0.7774 0.7546 0.7658 0.9225
0.0008 122.73 2700 0.6698 0.7721 0.7692 0.7706 0.9297
0.0008 127.27 2800 0.6898 0.76 0.7656 0.7628 0.9220
0.0008 131.82 2900 0.6800 0.7482 0.7619 0.7550 0.9282
0.0006 136.36 3000 0.6911 0.7393 0.7582 0.7486 0.9215
0.0006 140.91 3100 0.6818 0.7446 0.7582 0.7514 0.9220
0.0006 145.45 3200 0.7043 0.7473 0.7692 0.7581 0.9210
0.0006 150.0 3300 0.6935 0.7482 0.7729 0.7604 0.9246
0.0006 154.55 3400 0.7163 0.7482 0.7729 0.7604 0.9230
0.0001 159.09 3500 0.7329 0.7590 0.7729 0.7659 0.9205
0.0001 163.64 3600 0.7570 0.7737 0.7766 0.7751 0.9215
0.0001 168.18 3700 0.7552 0.7664 0.7692 0.7678 0.9225
0.0001 172.73 3800 0.7226 0.7831 0.7802 0.7817 0.9246
0.0001 177.27 3900 0.6868 0.7844 0.7729 0.7786 0.9297
0.0003 181.82 4000 0.6916 0.7757 0.7729 0.7743 0.9256
0.0003 186.36 4100 0.6862 0.7749 0.7692 0.7721 0.9292
0.0003 190.91 4200 0.7067 0.7749 0.7692 0.7721 0.9225
0.0003 195.45 4300 0.7059 0.7628 0.7656 0.7642 0.9210
0.0003 200.0 4400 0.7300 0.7609 0.7692 0.7650 0.9210
0.0002 204.55 4500 0.7299 0.7572 0.7656 0.7614 0.9215
0.0002 209.09 4600 0.7168 0.7527 0.7692 0.7609 0.9210
0.0002 213.64 4700 0.7177 0.7545 0.7656 0.76 0.9210
0.0002 218.18 4800 0.7182 0.7545 0.7656 0.76 0.9210
0.0002 222.73 4900 0.7190 0.7628 0.7656 0.7642 0.9205
0.0001 227.27 5000 0.7168 0.7572 0.7656 0.7614 0.9215

Framework versions