pszemraj's picture
Update README.md
638e08e
metadata
license: mit
base_model: roberta-large-mnli
tags:
  - book
  - genre
  - book title
metrics:
  - f1
widget:
  - text: The Quantum Chip
    example_title: Science Fiction & Fantasy
  - text: One Dollar's Journey
    example_title: Business & Finance
  - text: Timmy The Talking Tree
    example_title: idk fiction
  - text: The Cursed Canvas
    example_title: Arts & Design
  - text: Hoops and Hegel
    example_title: Philosophy & Religion
  - text: Overview of Streams in North Dakota
    example_title: Nature
  - text: Advanced Topology
    example_title: Non-fiction/Math
  - text: Cooking Up Love
    example_title: Food & Cooking
  - text: Dr. Doolittle's Extraplanatary Commute
    example_title: Science & Technology
pipeline_tag: text-classification

roberta-large-mnli for title-genre classification

This model is a fine-tuned version of roberta-large-mnli on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2758
  • F1: 0.5464

Model description

This classifies one or more genre labels in a multi-label setting for a given book title.

The 'standard' way of interpreting the predictions is that the predicted labels for a given example are only the ones with a greater than 50% probability.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 6e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-10
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss F1
0.3096 1.0 62 0.2862 0.3707
0.2863 2.0 124 0.2804 0.4422
0.2618 3.0 186 0.2773 0.4989
0.2432 4.0 248 0.2764 0.5223
0.2241 5.0 310 0.2758 0.5464

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.2.0.dev20231001+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3