README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - conll2003
  - autoevaluate/conll2003-sample
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: entity-extraction
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          args: conll2003
        metrics:
          - type: precision
            value: 0.8862817854414493
            name: Precision
          - type: recall
            value: 0.9084908826490659
            name: Recall
          - type: f1
            value: 0.8972489227709645
            name: F1
          - type: accuracy
            value: 0.9774889986814304
            name: Accuracy
          - type: accuracy
            value: 0.9703231821006837
            name: Accuracy
            verified: true
          - type: precision
            value: 0.9758137392136365
            name: Precision
            verified: true
          - type: recall
            value: 0.9764192759122017
            name: Recall
            verified: true
          - type: f1
            value: 0.9761164136513085
            name: F1 Score
            verified: true
          - type: accuracy
            value: 0.9703231821006837
            name: Accuracy
            verified: true
          - type: precision
            value: 0.9758137392136365
            name: Precision
            verified: true
          - type: recall
            value: 0.9764192759122017
            name: Recall
            verified: true
          - type: f1
            value: 0.9761164136513085
            name: F1 Score
            verified: true
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: autoevaluate/conll2003-sample
          type: autoevaluate/conll2003-sample
          config: autoevaluate--conll2003-sample
          split: test
        metrics:
          - type: accuracy
            value: 0.9680247550283652
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTgzYzIwNTcyNzgxN2JiNGU0Y2RhMmY2YzRhMzUyNGY5NGE2MDA0NTVmYTFjYzdjMWQ2M2UxOTY4YmJkNWI2OCIsInZlcnNpb24iOjF9.TXZVtZoAvkUw_iXjmVwAdPtzhimwv33pA0BqxbKLGP3QSpJAsFbAbDwh2kUaKH4mTtgmcGgmtsywIgV5_ZEFAA
          - type: precision
            value: 0.9708377518557795
            name: Precision
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWJkYzQ0MzhmNGE4Y2UyMmIzNThmMTdlZjMzODdlOWMzMTg1NTEwNWQ3NDMyNTYxODZiMzZhYTQ5NDU2ZGZlMSIsInZlcnNpb24iOjF9.rFvd0bxUagfktMsv-Q0NJr2WN2MuZ74dR0Opq9_MqjXnhi1wPxRcfbjw2RYUKnRM9PVVkBrb3WyTGYljcJYMCA
          - type: recall
            value: 0.9754928076718167
            name: Recall
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjkzMGExNzU3NWY4Y2E0ODgyZTU5MzY1NTYxMDU3M2E3N2RkMmEwNzRmNWRmZDA1N2Y3MDQ5OGE3ZWQ3ZDA0NyIsInZlcnNpb24iOjF9.yAlh4o8i2o4GG6TES8-IoYlvqCh8NS09OeQ8yILRiRo8Uk9u6CdaZAklstD60jyMlanP7c_IP-SQsqokJ41tCg
          - type: f1
            value: 0.9731597129949509
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmFiNDdjODdjNGJhYjNiZGUwNzc2OTQ0NDhhMjk5ZTFlMjM4NTE5MTViYTBlYzI2ZTE4MzQ5MmE3MTBiZWU0ZiIsInZlcnNpb24iOjF9.amNItmETm5mBYgwTYkYEO7L7mlO6xxPJhHfy8X8LidtLir8euAUxoj4gLro9-NETDGaZOLLvvjx7SRyODMwrAg
          - type: loss
            value: 0.1187286302447319
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWFlYThiZGFhYzI4ZjZiNDUyMmQ3ZDVhMGIzZDJhNmU3ZjEwNTU1NTE2YjA3ZjM2NGNlNTA1MmYwNWY4NTdjMiIsInZlcnNpb24iOjF9.qBgBdwqISdVvRHyJQ-8JgqeGGG6J1wrNEcoJiqUgZ8OQIn8FKi6I0xmdBukkoYMapegWqwIGjNVNF4WAsjoyAg

entity-extraction

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

• Loss: 0.0808
• Precision: 0.8863
• Recall: 0.9085
• F1: 0.8972
• Accuracy: 0.9775

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2552	1.0	878	0.0808	0.8863	0.9085	0.8972	0.9775

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1