Edit model card

bert-base-uncased-finetuned-ner

This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0615
  • Precision: 0.9222
  • Recall: 0.9372
  • F1: 0.9297
  • Accuracy: 0.9838

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: IPU
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • total_eval_batch_size: 5
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • training precision: Mixed Precision

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.051 1.0 877 0.0667 0.9090 0.9190 0.9139 0.9811
0.2483 2.0 1754 0.0600 0.9295 0.9344 0.9320 0.9839
0.0153 3.0 2631 0.0615 0.9222 0.9372 0.9297 0.9838

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.10.0+cpu
  • Datasets 2.7.1
  • Tokenizers 0.12.1
Downloads last month
3

Dataset used to train nmb-paperspace-hf/bert-base-uncased-finetuned-ner