metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
base_model: distilbert-base-cased
model-index:
  - name: distilbert-base-cased-ner
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: validation
          args: conll2003
        metrics:
          - type: precision
            value: 0.932077342588002
            name: Precision
          - type: recall
            value: 0.9491753618310333
            name: Recall
          - type: f1
            value: 0.940548653381139
            name: F1
          - type: accuracy
            value: 0.984782480720551
            name: Accuracy
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: test
        metrics:
          - type: accuracy
            value: 0.8975276153858275
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjA4OTdkZGZhOGVjNzUxMTExZTIxOTBhN2ExYmU0ZGE3MmFmZGYwZjhhMzExYjgwYjljMTg1YzJkMjk2NzVmYyIsInZlcnNpb24iOjF9.4QqmAwmUTNJlRnQiukdI23SNjKa6ZC9K6GBuuVuELeUueYI5R1tP58WYtNglr9BHWqhj1NuqeRNJSa7VFP0dDg
          - type: precision
            value: 0.9258126323573902
            name: Precision
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2ZmZTAwZTBmZGNkODM2NTk3NjkyMTZmOGVhOGM0MDY1YzVlMTdkYjkwMTU3YzI4ODNhZDMyMTM5N2M4YjhjNCIsInZlcnNpb24iOjF9.ybM6lA3dtYn6sFT70ocFeAxLGoMUcXedGx2YeVz58VQt0g2WqhCsHm6MOeTH1W33zgaYF7thcEoT6zOEr8PzBw
          - type: recall
            value: 0.9132871306827602
            name: Recall
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjM0ZTY5NTQzYWI2ZGQzOWU1YjQ1MjhjYjVjNzllYzE5MjE3MTI2ODY2NzQzOWIwMjJiODIxNTJiYWI3MDg0YyIsInZlcnNpb24iOjF9.8nEFuGWTjzFButONIeft0c9pSrdxkNTNxwlyr76tqu3B9VSRdSCswauC2d5ccTXqrNBljmMa8CixqwlVwEj2CQ
          - type: auc
            value: NaN
            name: AUC
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWMwY2Q2MGY4ODM2NTdlYjQ0OTI3ZmYyYjYyYTk3ZmNjMTRmYTZjYWFjOTg2NGI2NGZkNGQxZmRiNGU0N2VhYyIsInZlcnNpb24iOjF9.15J6CBL2SyWfraaDRfA80qptuANH89eQzrpnYKoNLyysmblllMwJxJWzQdMEHRveLOXgpNYjdurAZSFy7p0KCA
          - type: f1
            value: 0.9195072279905185
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTZmMTgwZDc2M2ZhMWE5MjMxZDVmOWViNjI3MTM0MTJjMWE5ZTU1NDJhNjRmMTE1NmVlZGY1NmVkODBlNGZiYSIsInZlcnNpb24iOjF9.OoKpemZwjZKioOj4fTNAnJHHBBdOlTHyNIEKWTLfuHcIiqJwYZ_VQ9LyEGPrN9YsgDkM-NiIWaEKkdi4Ww15Dw
          - type: loss
            value: 0.8574212193489075
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGVhYzFhMzEzOWM4NDJmN2QwZjRmMjYxNjY1MjczNzEzZTZhYzY1YzhjMzg1MjdjODgyNjE2YTRhMzcyMzhiMiIsInZlcnNpb24iOjF9.jfXLq-DE6HVYMC43QoxmTFKmCS7uSKxJYr0lJMu8Z7dKOfv9P4Py1cJG1GWcsdlGjlfVPvGq3pZ1Ofu8uao5BA

distilbert-base-cased-ner

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

Loss: 0.1088
Precision: 0.9321
Recall: 0.9492
F1: 0.9405
Accuracy: 0.9848

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: 2147483647
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1015	1.0	1756	0.1001	0.8858	0.9167	0.9010	0.9740
0.049	2.0	3512	0.0803	0.8993	0.9273	0.9131	0.9798
0.0327	3.0	5268	0.0794	0.9199	0.9350	0.9274	0.9821
0.0237	4.0	7024	0.0880	0.9050	0.9344	0.9194	0.9813
0.0131	5.0	8780	0.0849	0.9178	0.9446	0.9310	0.9837
0.0073	6.0	10536	0.0975	0.9166	0.9446	0.9304	0.9838
0.0044	7.0	12292	0.0965	0.9267	0.9475	0.9370	0.9842
0.0015	8.0	14048	0.1075	0.9273	0.9463	0.9367	0.9843
0.0011	9.0	15804	0.1089	0.9317	0.9480	0.9398	0.9847
0.0006	10.0	17560	0.1088	0.9321	0.9492	0.9405	0.9848

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3