lewtun's picture
lewtun HF staff
Add evaluation results on acronym_identification dataset
7f7fd47
|
raw
history blame
2.86 kB
metadata
tags: autotrain
language: en
widget:
  - text: I love AutoTrain 🤗
datasets:
  - lewtun/autotrain-data-acronym-identification
  - acronym_identification
co2_eq_emissions: 10.435358044493652
model-index:
  - name: autotrain-demo
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: acronym_identification
          type: acronym_identification
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9708090976211485
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: acronym_identification
          type: acronym_identification
          config: default
          split: train
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9790777669399117
            verified: true
          - name: Precision
            type: precision
            value: 0.9197835301644851
            verified: true
          - name: Recall
            type: recall
            value: 0.946479027789208
            verified: true
          - name: F1
            type: f1
            value: 0.9329403493591477
            verified: true
          - name: loss
            type: loss
            value: 0.06360606849193573
            verified: true
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: acronym_identification
          type: acronym_identification
          config: default
          split: validation
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9758354452761242
            verified: true
          - name: Precision
            type: precision
            value: 0.9339674814732883
            verified: true
          - name: Recall
            type: recall
            value: 0.9159344831326608
            verified: true
          - name: F1
            type: f1
            value: 0.9248630887185104
            verified: true
          - name: loss
            type: loss
            value: 0.07593930512666702
            verified: true

Model Trained Using AutoTrain

  • Problem type: Entity Extraction
  • Model ID: 7324788
  • CO2 Emissions (in grams): 10.435358044493652

Validation Metrics

  • Loss: 0.08991389721632004
  • Accuracy: 0.9708090976211485
  • Precision: 0.8998421675654347
  • Recall: 0.9309429854401959
  • F1: 0.9151284109149278

Usage

You can use cURL to access this model:

$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/lewtun/autotrain-acronym-identification-7324788

Or Python API:

from transformers import AutoModelForTokenClassification, AutoTokenizer

model = AutoModelForTokenClassification.from_pretrained("lewtun/autotrain-acronym-identification-7324788", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("lewtun/autotrain-acronym-identification-7324788", use_auth_token=True)

inputs = tokenizer("I love AutoTrain", return_tensors="pt")

outputs = model(**inputs)