bert-finetuned-ner-word-embedding-model

This model is a fine-tuned version of bert-base-cased on the the combined training dataset(tweetner7(train_2021)+augmented dataset(train_2021) using word embedding technique).

Training Dataset: lsoni/combined_tweetner7_word_embedding_augmented_dataset

Evaluation Dataset: lsoni/combined_tweetner7_word_embedding_augmented_dataset_eval

It achieves the following results on the evaluation set:

• Loss: 0.5411
• Precision: 0.6710
• Recall: 0.5062
• F1: 0.5771
• Accuracy: 0.8650

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: 2e-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

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.7157	1.0	624	0.5842	0.6958	0.4498	0.5464	0.8608
0.5299	2.0	1248	0.5449	0.6662	0.4897	0.5645	0.8635
0.4648	3.0	1872	0.5411	0.6710	0.5062	0.5771	0.8650

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.1
• Datasets 2.10.1
• Tokenizers 0.12.1