Products_NER

This model is a fine-tuned version of dslim/bert-base-NER on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0022
• Precision: 0.9991
• Recall: 0.9992
• F1: 0.9992
• Accuracy: 0.9996

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: 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	Precision	Recall	F1	Accuracy
0.0051	1.0	2470	0.0035	0.9981	0.9986	0.9984	0.9992
0.0016	2.0	4940	0.0022	0.9991	0.9992	0.9992	0.9996

Framework versions

• Transformers 4.33.2
• Pytorch 1.13.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3