crabz / FERNET-CC_sk-ner

Named Entity Recognition based on FERNET-CC_sk

This model is a fine-tuned version of fav-kky/FERNET-CC_sk on the Slovak wikiann dataset. It achieves the following results on the evaluation set:

• Loss: 0.1763
• Precision: 0.9360
• Recall: 0.9472
• F1: 0.9416
• Accuracy: 0.9789

Intended uses & limitation

Supported classes: LOCATION, PERSON, ORGANIZATION

from transformers import pipeline

ner_pipeline = pipeline(task='ner', model='crabz/slovakbert-ner')
input_sentence = "Minister financií a líder mandátovo najsilnejšieho hnutia OĽaNO Igor Matovič upozorňuje, že následky tretej vlny budú na Slovensku veľmi veľké."
classifications = ner_pipeline(input_sentence)

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: 10.0

Training results

Framework versions

• Transformers 4.14.0.dev0
• Pytorch 1.10.0
• Datasets 1.16.1
• Tokenizers 0.10.3