Edit model card

mobilebert-uncased-finetuned-ner

This model is a fine-tuned version of google/mobilebert-uncased on the id_nergrit_corpus dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3800
  • Precision: 0.6700
  • Recall: 0.6136
  • F1: 0.6406
  • Accuracy: 0.8974

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
0.6239 1.0 1567 0.4989 0.5842 0.4877 0.5316 0.8688
0.5356 2.0 3134 0.4003 0.6368 0.5879 0.6113 0.8905
0.4035 3.0 4701 0.3800 0.6700 0.6136 0.6406 0.8974

Framework versions

  • Transformers 4.29.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
10

Dataset used to train kstn/mobilebert-uncased-finetuned-ner

Evaluation results