xlnet-base-cased-finetuned-WikiNeural-PoS

This model is a fine-tuned version of xlnet-base-cased.

It achieves the following results on the evaluation set:

  • Loss: 0.0949
  • Loc
    • Precision: 0.9289891395154553
    • Recall: 0.9336691855583543
    • F1: 0.931323283082077
    • Number: 5955
  • Misc
    • Precision: 0.8191960332920134
    • Recall: 0.9140486069946651
    • F1: 0.8640268957788569
    • Number: 5061
  • Org
    • Precision: 0.9199886104783599
    • Recall: 0.9367932734125833
    • F1: 0.9283148972848728
    • Number: 3449
  • Per
    • Precision: 0.9687377113645301
    • Recall: 0.9456813819577735
    • F1: 0.9570707070707071
    • Number: 5210
  • Overall
    • Precision: 0.9068
    • Recall: 0.9324
    • F1: 0.9194
    • Accuracy: 0.9904

Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Token%20Classification/Monolingual/WikiNeural%20-%20Transformer%20Comparison/POS%20Project%20with%20Wikineural%20Dataset%20-%20XLNet%20Transformer.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: https://huggingface.co/datasets/Babelscape/wikineural

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-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
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Loc Precision Loc Recall Loc F1 Loc Number Misc Precision Misc Recall Misc F1 Misc Number Org Precision Org Recall Org F1 Org Number Per Precision Per Recall Per F1 Per Number Overall Precision Overall Recall Overall F1 Overall Accuracy
0.1119 1.0 5795 0.1067 0.9054 0.9382 0.9215 5955 0.7967 0.8884 0.8401 5061 0.9112 0.9226 0.9169 3449 0.9585 0.9524 0.9554 5210 0.8899 0.9264 0.9078 0.9887
0.0724 2.0 11590 0.0949 0.9290 0.9337 0.9313 5955 0.8192 0.9140 0.8640 5061 0.9200 0.9368 0.9283 3449 0.9687 0.9457 0.9571 5210 0.9068 0.9324 0.9194 0.9904
  • All values in the above chart are rounded to the nearest ten-thousandths.

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train DunnBC22/xlnet-base-cased-finetuned-WikiNeural-PoS

Collection including DunnBC22/xlnet-base-cased-finetuned-WikiNeural-PoS