Edit model card

ner

This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2942
  • Precision: 0.5553
  • Recall: 0.3772
  • F1: 0.4492
  • Accuracy: 0.9469

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: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 213 0.2666 0.6024 0.2808 0.3831 0.9405
No log 2.0 426 0.2605 0.5708 0.3364 0.4233 0.9456
0.1299 3.0 639 0.2827 0.5658 0.3346 0.4205 0.9452
0.1299 4.0 852 0.2836 0.5503 0.3753 0.4463 0.9469
0.051 5.0 1065 0.2942 0.5553 0.3772 0.4492 0.9469

Framework versions

  • Transformers 4.27.4
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
2
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train phi0108/ner

Evaluation results