Article_50v8_NER_Model_3Epochs_UNAUGMENTED

This model is a fine-tuned version of bert-base-cased on the article50v8_wikigold_split dataset. It achieves the following results on the evaluation set:

• Loss: 0.7555
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.7786

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	6	0.9789	0.1	0.0047	0.0089	0.7776
No log	2.0	12	0.7892	0.0	0.0	0.0	0.7786
No log	3.0	18	0.7555	0.0	0.0	0.0	0.7786

Framework versions

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