tags: - generated_from_trainer datasets: - ner-tr metrics: - precision - recall - f1 - accuracy model-index: - name: named-entity-tr results: - task: name: Token Classification type: token-classification dataset: name: ner-tr type: ner-tr config: NERTR split: train args: NERTR metrics: - name: Precision type: precision value: 0.0 - name: Recall type: recall value: 0.0 - name: F1 type: f1 value: 0.0 - name: Accuracy type: accuracy value: 0.45027322404371584

named-entity-tr

This model is a fine-tuned version of dbmdz/electra-base-turkish-cased-discriminator on the ner-tr dataset. It achieves the following results on the evaluation set:

• Loss: 2.2782
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.4503

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	9	2.7645	0.0537	0.0777	0.0635	0.3191
No log	2.0	18	2.3464	0.0	0.0	0.0	0.4503
No log	3.0	27	2.2782	0.0	0.0	0.0	0.4503

Framework versions

• Transformers 4.22.0
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1