README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: Nato-chat
    results: []
language:
  - en
widget:
  - text: What is the Full form of NATO?
    example_title: Full Form
  - text: Name the NATO member countries.
    example_title: NATO Members
  - text: What kind of support did Ukraine offer to NATO?
    example_title: Example 1
  - text: >-
      Which country withdrew from the integrated military command of NATO in
      1966?
    example_title: Example 2
  - text: Who were the original members of NATO
    example_title: OG Members
  - text: When was NATO established?
    example_title: Example 3
  - text: How many NATO members are there currently?
    example_title: Example 4
  - text: Who are the representatives of NATO member countries?
    example_title: Example 5
  - text: 'Question: What is the aim of the Mediterranean Dialogue?'
    example_title: Example 6
inference:
  parameters:
    max_length: 600

Nato-chat

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1764
• Rouge1: 0.6435
• Rouge2: 0.5596
• Rougel: 0.6287
• Rougelsum: 0.6312

Model description

Flan-t5 Base

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0