klue-roberta-large-klue-2016klp-crime-2-ner

This model is a fine-tuned version of soddokayo/klue-roberta-large-klue-2016klp-ner on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4442
• Precision: 0.1538
• Recall: 0.1124
• F1: 0.1299
• Accuracy: 0.9005

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	7	0.6609	0.0	0.0	0.0	0.8536
No log	2.0	14	0.4892	0.02	0.0112	0.0144	0.8817
No log	3.0	21	0.4442	0.1538	0.1124	0.1299	0.9005

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cpu
• Datasets 2.12.0
• Tokenizers 0.11.0