metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mit_restaurant
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilbert-finetuned-mit-restaurant-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: mit_restaurant
          type: mit_restaurant
          config: mit_restaurant
          split: validation
          args: mit_restaurant
        metrics:
          - name: Precision
            type: precision
            value: 0.776800439802089
          - name: Recall
            type: recall
            value: 0.7983050847457627
          - name: F1
            type: f1
            value: 0.7874059626636947
          - name: Accuracy
            type: accuracy
            value: 0.9116093286947559

distilbert-finetuned-mit-restaurant-ner

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

Loss: 0.3210
Precision: 0.7768
Recall: 0.7983
F1: 0.7874
Accuracy: 0.9116

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.6991	1.0	863	0.3478	0.7113	0.7684	0.7387	0.8994
0.2773	2.0	1726	0.3264	0.7533	0.7989	0.7754	0.9063
0.2164	3.0	2589	0.3137	0.7644	0.8045	0.7839	0.9121
0.1789	4.0	3452	0.3163	0.7755	0.7983	0.7867	0.9115
0.1573	5.0	4315	0.3210	0.7768	0.7983	0.7874	0.9116

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2