PII_detection_Finetuned_ai4bharat_naamapadam_bert_uncased

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

tmp_trainer

This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset.

Model description

More information needed This repository contains code and instructions for fine-tuning a token classification model (BERT/DeBERTa) on the Ai4Bharat Naamapadam dataset for multilingual Named Entity Recognition (NER) across Indian languages. This work was done for the GE Hackathon PII detection challenge.

https://github.com/kaushiksaravanan/PII-Deberta-finetuning-Ai4Bharat-naamapadam

Intended uses & limitations

More information needed

Training and evaluation data

More information needed https://github.com/kaushiksaravanan/PII-Deberta-finetuning-Ai4Bharat-naamapadam Dataset: Ai4Bharat Naamapadam Model: Google BERT https://huggingface.co/datasets/ai4bharat/naamapadam

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
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1