moska's picture
Model save
c18a5f5
metadata
license: cc-by-4.0
base_model: allegro/plt5-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - recall
  - f1
  - precision
model-index:
  - name: plt5-seq-clf-with-entities-updated-finetuned
    results: []

plt5-seq-clf-with-entities-updated-finetuned

This model is a fine-tuned version of allegro/plt5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9863
  • Accuracy: {'accuracy': 0.6016129032258064}
  • Recall: {'recall': 0.6016129032258064}
  • F1: {'f1': 0.6090459454706235}
  • Precision: {'precision': 0.6487538544674235}

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: 5.6e-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
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy Recall F1 Precision
1.7248 1.0 718 1.6722 {'accuracy': 0.47258064516129034} {'recall': 0.47258064516129034} {'f1': 0.30332120269936047} {'precision': 0.2233324661810614}
1.6984 2.0 1436 1.6216 {'accuracy': 0.47258064516129034} {'recall': 0.47258064516129034} {'f1': 0.30332120269936047} {'precision': 0.2233324661810614}
1.6839 3.0 2154 1.6344 {'accuracy': 0.47258064516129034} {'recall': 0.47258064516129034} {'f1': 0.30332120269936047} {'precision': 0.2233324661810614}
1.6882 4.0 2872 1.6261 {'accuracy': 0.47258064516129034} {'recall': 0.47258064516129034} {'f1': 0.30332120269936047} {'precision': 0.2233324661810614}
1.68 5.0 3590 1.6223 {'accuracy': 0.47258064516129034} {'recall': 0.47258064516129034} {'f1': 0.30332120269936047} {'precision': 0.2233324661810614}
1.6777 6.0 4308 1.6521 {'accuracy': 0.4854838709677419} {'recall': 0.4854838709677419} {'f1': 0.36285141031634727} {'precision': 0.30095036265938396}
1.6681 7.0 5026 1.6165 {'accuracy': 0.47096774193548385} {'recall': 0.47096774193548385} {'f1': 0.3142909197822259} {'precision': 0.27758817356390014}
1.6585 8.0 5744 1.5583 {'accuracy': 0.47580645161290325} {'recall': 0.47580645161290325} {'f1': 0.3179514906044033} {'precision': 0.274054689168981}
1.6399 9.0 6462 1.6084 {'accuracy': 0.3564516129032258} {'recall': 0.3564516129032258} {'f1': 0.30977675417942074} {'precision': 0.3086887092441926}
1.6158 10.0 7180 1.6613 {'accuracy': 0.3225806451612903} {'recall': 0.3225806451612903} {'f1': 0.2777093706693196} {'precision': 0.5070305497722745}
1.5835 11.0 7898 1.6525 {'accuracy': 0.3370967741935484} {'recall': 0.3370967741935484} {'f1': 0.2946753320835634} {'precision': 0.4987499213117131}
1.5443 12.0 8616 1.5433 {'accuracy': 0.39838709677419354} {'recall': 0.39838709677419354} {'f1': 0.37257538542456536} {'precision': 0.5472359482869795}
1.4792 13.0 9334 1.4685 {'accuracy': 0.4290322580645161} {'recall': 0.4290322580645161} {'f1': 0.3843028777529311} {'precision': 0.5497170294652844}
1.419 14.0 10052 1.5534 {'accuracy': 0.4032258064516129} {'recall': 0.4032258064516129} {'f1': 0.35189485350144095} {'precision': 0.5701307405449848}
1.3881 15.0 10770 1.3641 {'accuracy': 0.4790322580645161} {'recall': 0.4790322580645161} {'f1': 0.4461803399889066} {'precision': 0.5258731490942117}
1.3582 16.0 11488 1.3837 {'accuracy': 0.43870967741935485} {'recall': 0.43870967741935485} {'f1': 0.3975785817347331} {'precision': 0.5481481481481482}
1.3074 17.0 12206 1.2409 {'accuracy': 0.5177419354838709} {'recall': 0.5177419354838709} {'f1': 0.49737440159156987} {'precision': 0.5439755251062998}
1.2529 18.0 12924 1.2490 {'accuracy': 0.5241935483870968} {'recall': 0.5241935483870968} {'f1': 0.5075488601971412} {'precision': 0.5801964826379877}
1.2223 19.0 13642 1.1680 {'accuracy': 0.5435483870967742} {'recall': 0.5435483870967742} {'f1': 0.5172098120467532} {'precision': 0.5483692723442298}
1.1881 20.0 14360 1.1325 {'accuracy': 0.5467741935483871} {'recall': 0.5467741935483871} {'f1': 0.528976565119481} {'precision': 0.5918362760770626}
1.1524 21.0 15078 1.1075 {'accuracy': 0.5338709677419354} {'recall': 0.5338709677419354} {'f1': 0.5363641334830415} {'precision': 0.6113524377471905}
1.1307 22.0 15796 1.0685 {'accuracy': 0.5612903225806452} {'recall': 0.5612903225806452} {'f1': 0.567131293394492} {'precision': 0.6230821316117012}
1.1198 23.0 16514 1.0978 {'accuracy': 0.5564516129032258} {'recall': 0.5564516129032258} {'f1': 0.5596055517552543} {'precision': 0.6285694241881432}
1.0856 24.0 17232 1.0779 {'accuracy': 0.5532258064516129} {'recall': 0.5532258064516129} {'f1': 0.5591833153283243} {'precision': 0.6338935526492327}
1.0829 25.0 17950 1.0175 {'accuracy': 0.5903225806451613} {'recall': 0.5903225806451613} {'f1': 0.5964860501094582} {'precision': 0.6422535611112073}
1.0613 26.0 18668 1.0426 {'accuracy': 0.567741935483871} {'recall': 0.567741935483871} {'f1': 0.5748961882147833} {'precision': 0.6378855920377489}
1.0363 27.0 19386 0.9920 {'accuracy': 0.5935483870967742} {'recall': 0.5935483870967742} {'f1': 0.6001368374403852} {'precision': 0.6385480642288512}
1.0412 28.0 20104 1.0210 {'accuracy': 0.5758064516129032} {'recall': 0.5758064516129032} {'f1': 0.5836230006413563} {'precision': 0.6487093843541626}
1.0256 29.0 20822 0.9992 {'accuracy': 0.5870967741935483} {'recall': 0.5870967741935483} {'f1': 0.5944960724933464} {'precision': 0.6439234847872369}
1.0354 30.0 21540 0.9863 {'accuracy': 0.6016129032258064} {'recall': 0.6016129032258064} {'f1': 0.6090459454706235} {'precision': 0.6487538544674235}

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3