README.md

metadata

license: apache-2.0
base_model: google/flan-t5-base
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: flan-t5-base-intent
    results: []

flan-t5-base-intent

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• F1: 100.0
• Gen Len: 2.3333

Model description

Use double quotation for any tweet. 0: Anti-tobacco 1: Neutral 2: Pro-tobacco

Intended uses & limitations

The fine tuned model by STOP is intended for Anti-tobacco/ Pro-tobacco monitoring for social media.

Training and evaluation data

The model was developed and fine tuned in STOP, University of Bath, UK

Data used is sherif1311/intend which was collected, augmented and trained by STOP.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Framework versions

• Transformers 4.31.0
• Pytorch 1.12.1+cu116
• Datasets 2.14.4
• Tokenizers 0.12.1