distilbert-NER-finetuned

This model is a fine-tuned version of dslim/distilbert-NER on the conll2012_ontonotesv5 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4666
• Accuracy: 0.8738
• F1: 0.4990

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: 5e-05
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.8992	1.0	61	0.6227	0.8404	0.4295
0.5484	2.0	122	0.5143	0.8631	0.4784
0.4243	3.0	183	0.4757	0.8710	0.4985
0.3599	4.0	244	0.4666	0.8738	0.4990

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1