Article_250v5_NER_Model_3Epochs_UNAUGMENTED

This model is a fine-tuned version of bert-base-cased on the article250v5_wikigold_split dataset. It achieves the following results on the evaluation set:

• Loss: 0.3250
• Precision: 0.3979
• Recall: 0.4221
• F1: 0.4097
• Accuracy: 0.8779

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
No log	1.0	31	0.5229	0.1336	0.0344	0.0547	0.8008
No log	2.0	62	0.3701	0.3628	0.3357	0.3487	0.8596
No log	3.0	93	0.3250	0.3979	0.4221	0.4097	0.8779

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0+cu113
• Datasets 2.4.0
• Tokenizers 0.11.6