pnr-svc's picture
update model card README.md
e487b8c
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - ner-tr
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilbert-turkish-ner
    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: 1
          - name: Recall
            type: recall
            value: 1
          - name: F1
            type: f1
            value: 1
          - name: Accuracy
            type: accuracy
            value: 1

distilbert-turkish-ner

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

  • Loss: 0.0013
  • Precision: 1.0
  • Recall: 1.0
  • F1: 1.0
  • Accuracy: 1.0

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
0.5744 1.0 529 0.0058 1.0 1.0 1.0 1.0
0.0094 2.0 1058 0.0017 1.0 1.0 1.0 1.0
0.0047 3.0 1587 0.0013 1.0 1.0 1.0 1.0

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1