README.md

metadata

license: mit
tags:
  - generated_from_trainer
model-index:
  - name: xlnet-base-cased-finetuned-WikiCorpus-PoS
    results: []
datasets:
  - Babelscape/wikineural
language:
  - en
metrics:
  - accuracy
  - f1
  - recall
  - precision
  - seqeval
pipeline_tag: token-classification

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