README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - nielsr/funsd-layoutlmv3
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-funsd
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: nielsr/funsd-layoutlmv3
          type: nielsr/funsd-layoutlmv3
          args: funsd
        metrics:
          - name: Precision
            type: precision
            value: 0.9026198714780029
          - name: Recall
            type: recall
            value: 0.913
          - name: F1
            type: f1
            value: 0.9077802634849614
          - name: Accuracy
            type: accuracy
            value: 0.8330271015158475

layoutlmv3-finetuned-funsd

This model is a fine-tuned version of microsoft/layoutlmv3-base on the nielsr/funsd-layoutlmv3 dataset. It achieves the following results on the evaluation set:

• Loss: 1.1164
• Precision: 0.9026
• Recall: 0.913
• F1: 0.9078
• Accuracy: 0.8330

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:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	10.0	100	0.5238	0.8366	0.886	0.8606	0.8410
No log	20.0	200	0.6930	0.8751	0.8965	0.8857	0.8322
No log	30.0	300	0.7784	0.8902	0.908	0.8990	0.8414
No log	40.0	400	0.9056	0.8916	0.905	0.8983	0.8364
0.2429	50.0	500	1.0016	0.8954	0.9075	0.9014	0.8298
0.2429	60.0	600	1.0097	0.8899	0.897	0.8934	0.8294
0.2429	70.0	700	1.0722	0.9035	0.9085	0.9060	0.8315
0.2429	80.0	800	1.0884	0.8905	0.9105	0.9004	0.8269
0.2429	90.0	900	1.1292	0.8938	0.909	0.9013	0.8279
0.0098	100.0	1000	1.1164	0.9026	0.913	0.9078	0.8330
No log	10.0	100	0.5238	0.8366	0.886	0.8606	0.8410
No log	20.0	200	0.6930	0.8751	0.8965	0.8857	0.8322
No log	30.0	300	0.7784	0.8902	0.908	0.8990	0.8414
No log	40.0	400	0.9056	0.8916	0.905	0.8983	0.8364
0.2429	50.0	500	1.0016	0.8954	0.9075	0.9014	0.8298
0.2429	60.0	600	1.0097	0.8899	0.897	0.8934	0.8294
0.2429	70.0	700	1.0722	0.9035	0.9085	0.9060	0.8315
0.2429	80.0	800	1.0884	0.8905	0.9105	0.9004	0.8269
0.2429	90.0	900	1.1292	0.8938	0.909	0.9013	0.8279
0.0098	100.0	1000	1.1164	0.9026	0.913	0.9078	0.8330

[4000/4000 20:34, Epoch 53/54] Step Training Loss Validation Loss Precision Recall F1 Accuracy 250 No log 0.435449 0.854588 0.902136 0.877719 0.835968 500 0.505800 0.611310 0.869822 0.876304 0.873051 0.839177 750 0.505800 0.635022 0.879886 0.917039 0.898078 0.853085 1000 0.097000 0.765935 0.900818 0.929459 0.914914 0.860097 1250 0.097000 0.887739 0.885533 0.903130 0.894245 0.842625 1500 0.029900 0.948754 0.898018 0.923000 0.910338 0.843575 1750 0.029900 1.102811 0.900433 0.929955 0.914956 0.840128 2000 0.009700 1.039040 0.901415 0.917536 0.909404 0.852728 2250 0.009700 1.044235 0.904716 0.924491 0.914496 0.849519 2500 0.002500 1.013194 0.913086 0.918530 0.915800 0.849637 2750 0.002500 1.017520 0.908605 0.928465 0.918428 0.854986 3000 0.000900 1.029559 0.914216 0.926478 0.920306 0.859384 3250 0.000900 1.038318 0.918177 0.930949 0.924519 0.859979 3500 0.000800 1.045578 0.914216 0.926478 0.920306 0.858552 3750 0.000800 1.040568 0.913894 0.927968 0.920877 0.858433 4000 0.000700 1.041146 0.913894 0.927968 0.920877 0.8585528552

Framework versions

• Transformers 4.19.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.0.0
• Tokenizers 0.11.6