README.md

metadata

license: apache-2.0
base_model: albert/albert-base-v2
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: startup-score
    results: []
language:
  - en
widget:
  - text: >-
      Company Name : Dropbox Inc. ,Gender: FEMALE, Company Description: Dropbox
      lets you save and access all your files and photos in one place for easy
      sharing. Easily share files & access team content from your computer,
      mobile or any web browser, Company Website: https://www.dropbox.com/, Job
      Titles: Chief Operating Officer (COO)/ Head of Operations, Business Model:
      nan, Revenue: $50,001 - $250,000 (USD), Profit: Not generating profit yet
      ,Total External Funding: 4000000, Notable Investors: Y Combinator, Sequioa
      Capital, Competition Region: North America, Team Size: Complementary team
      with some founders having significant work experience Market Opportunity ,
      Problem to be solved: Product solves a problem and has an attractive niche
      in a large market. Very strong value proposition to customers. Clear
      customer identification with unique positioning in mostly untapped market
      (more than or equals to USD 1 billion)., Innovation: Some unique IP,
      patents or data (pending patent) ,Business Model: Good revenue model /
      business model is defined and has been validated with large number of
      customers ,Scalability: Solution has no issues to scale globally or within
      home country but scaling has not started ,Traction: Prototype testing with
      initial customers (Beta testing)

startup-score

This model is a fine-tuned version of albert/albert-base-v2 on Startup Score Dataset. It achieves the following results on the evaluation set:

• Loss: 0.7827
• Accuracy: 0.25
• F1: 0.3000
• Precision: 0.375
• Recall: 0.25
• Accuracy Label Eligible: 0.0
• Accuracy Label Not eligible: 0.3333

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1