lilt-en-funsd / README.md
LaFeeSalomette's picture
End of training
d5cd02b verified
metadata
license: mit
base_model: SCUT-DLVCLab/lilt-roberta-en-base
tags:
  - generated_from_trainer
model-index:
  - name: lilt-en-funsd
    results: []

lilt-en-funsd

This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6171
  • Answer: {'precision': 0.8831168831168831, 'recall': 0.9155446756425949, 'f1': 0.8990384615384616, 'number': 817}
  • Header: {'precision': 0.6153846153846154, 'recall': 0.47058823529411764, 'f1': 0.5333333333333333, 'number': 119}
  • Question: {'precision': 0.8849557522123894, 'recall': 0.9285051067780873, 'f1': 0.9062075215224287, 'number': 1077}
  • Overall Precision: 0.8723
  • Overall Recall: 0.8962
  • Overall F1: 0.8841
  • Overall Accuracy: 0.8029

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 2500

Training results

Training Loss Epoch Step Validation Loss Answer Header Question Overall Precision Overall Recall Overall F1 Overall Accuracy
0.2349 10.53 200 1.1246 {'precision': 0.8461538461538461, 'recall': 0.8616891064871481, 'f1': 0.8538508186779866, 'number': 817} {'precision': 0.5871559633027523, 'recall': 0.5378151260504201, 'f1': 0.5614035087719299, 'number': 119} {'precision': 0.8546861564918314, 'recall': 0.9229340761374187, 'f1': 0.8875, 'number': 1077} 0.8375 0.8753 0.8560 0.7887
0.0404 21.05 400 1.4684 {'precision': 0.8298109010011123, 'recall': 0.9130966952264382, 'f1': 0.8694638694638694, 'number': 817} {'precision': 0.5688073394495413, 'recall': 0.5210084033613446, 'f1': 0.543859649122807, 'number': 119} {'precision': 0.879231473010064, 'recall': 0.8922934076137419, 'f1': 0.8857142857142858, 'number': 1077} 0.8420 0.8788 0.8600 0.7863
0.0121 31.58 600 1.6187 {'precision': 0.852112676056338, 'recall': 0.8886168910648715, 'f1': 0.8699820251647693, 'number': 817} {'precision': 0.5775862068965517, 'recall': 0.5630252100840336, 'f1': 0.5702127659574467, 'number': 119} {'precision': 0.8789237668161435, 'recall': 0.9099350046425255, 'f1': 0.8941605839416058, 'number': 1077} 0.8512 0.8808 0.8657 0.7944
0.0071 42.11 800 1.6262 {'precision': 0.8503480278422274, 'recall': 0.8971848225214198, 'f1': 0.8731387730792138, 'number': 817} {'precision': 0.5714285714285714, 'recall': 0.47058823529411764, 'f1': 0.5161290322580646, 'number': 119} {'precision': 0.895117540687161, 'recall': 0.9192200557103064, 'f1': 0.9070087036188731, 'number': 1077} 0.8611 0.8838 0.8723 0.7929
0.0052 52.63 1000 1.6864 {'precision': 0.8615751789976134, 'recall': 0.8837209302325582, 'f1': 0.8725075528700906, 'number': 817} {'precision': 0.52, 'recall': 0.5462184873949579, 'f1': 0.5327868852459017, 'number': 119} {'precision': 0.8842297174111212, 'recall': 0.9006499535747446, 'f1': 0.8923643054277829, 'number': 1077} 0.8529 0.8728 0.8628 0.7844
0.0022 63.16 1200 1.5608 {'precision': 0.8601895734597157, 'recall': 0.8886168910648715, 'f1': 0.8741721854304636, 'number': 817} {'precision': 0.6896551724137931, 'recall': 0.5042016806722689, 'f1': 0.5825242718446602, 'number': 119} {'precision': 0.8609215017064846, 'recall': 0.9368616527390901, 'f1': 0.897287683414851, 'number': 1077} 0.8535 0.8917 0.8722 0.7973
0.0018 73.68 1400 1.6781 {'precision': 0.8458904109589042, 'recall': 0.9069767441860465, 'f1': 0.8753691671588896, 'number': 817} {'precision': 0.6129032258064516, 'recall': 0.4789915966386555, 'f1': 0.5377358490566039, 'number': 119} {'precision': 0.874447391688771, 'recall': 0.9182915506035283, 'f1': 0.8958333333333334, 'number': 1077} 0.8510 0.8877 0.8690 0.7922
0.0014 84.21 1600 1.7078 {'precision': 0.8706293706293706, 'recall': 0.9143206854345165, 'f1': 0.8919402985074627, 'number': 817} {'precision': 0.6421052631578947, 'recall': 0.5126050420168067, 'f1': 0.5700934579439252, 'number': 119} {'precision': 0.8945454545454545, 'recall': 0.9136490250696379, 'f1': 0.9039963252181902, 'number': 1077} 0.8729 0.8902 0.8815 0.8051
0.0006 94.74 1800 1.6171 {'precision': 0.8831168831168831, 'recall': 0.9155446756425949, 'f1': 0.8990384615384616, 'number': 817} {'precision': 0.6153846153846154, 'recall': 0.47058823529411764, 'f1': 0.5333333333333333, 'number': 119} {'precision': 0.8849557522123894, 'recall': 0.9285051067780873, 'f1': 0.9062075215224287, 'number': 1077} 0.8723 0.8962 0.8841 0.8029
0.0003 105.26 2000 1.7091 {'precision': 0.8490990990990991, 'recall': 0.9228886168910648, 'f1': 0.8844574780058652, 'number': 817} {'precision': 0.5959595959595959, 'recall': 0.4957983193277311, 'f1': 0.5412844036697246, 'number': 119} {'precision': 0.8993536472760849, 'recall': 0.904363974001857, 'f1': 0.9018518518518519, 'number': 1077} 0.8633 0.8877 0.8753 0.8047
0.0003 115.79 2200 1.6547 {'precision': 0.8760233918128655, 'recall': 0.9167686658506732, 'f1': 0.8959330143540669, 'number': 817} {'precision': 0.6170212765957447, 'recall': 0.48739495798319327, 'f1': 0.5446009389671361, 'number': 119} {'precision': 0.8952122854561879, 'recall': 0.9201485608170845, 'f1': 0.9075091575091575, 'number': 1077} 0.8745 0.8932 0.8838 0.8080
0.0002 126.32 2400 1.6868 {'precision': 0.8633754305396096, 'recall': 0.9204406364749081, 'f1': 0.8909952606635071, 'number': 817} {'precision': 0.6020408163265306, 'recall': 0.4957983193277311, 'f1': 0.543778801843318, 'number': 119} {'precision': 0.8884924174843889, 'recall': 0.924791086350975, 'f1': 0.9062784349408554, 'number': 1077} 0.8646 0.8977 0.8808 0.8059

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cpu
  • Datasets 2.18.0
  • Tokenizers 0.15.2