few_nerd

This model is a fine-tuned version of distilbert-base-uncased on the eight coarse-grained classes of few-nerd using BIO tagging schema It achieves the following results on the evaluation set:

• Loss: 0.1731
• Precision: 0.7490
• Recall: 0.7884
• F1: 0.7682
• Accuracy: 0.9458

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
0.1849	1.0	8236	0.1771	0.7490	0.7736	0.7611	0.9442
0.1541	2.0	16472	0.1731	0.7490	0.7884	0.7682	0.9458

Framework versions

• Transformers 4.27.3
• Pytorch 2.0.0+cu117
• Datasets 2.10.1
• Tokenizers 0.13.2