README.md

metadata

license: mit
base_model: gpt2
tags:
  - generated_from_trainer
datasets:
  - wiki_qa
metrics:
  - accuracy
  - f1
model-index:
  - name: GPT2QA_wikiqa
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: wiki_qa
          type: wiki_qa
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9578606158833063
          - name: F1
            type: f1
            value: 0

GPT2QA_wikiqa

This model is a fine-tuned version of gpt2 on the wiki_qa dataset. It achieves the following results on the evaluation set:

• Loss: 0.2413
• Accuracy: 0.9579
• F1: 0.0

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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.1963	1.0	1387	0.2651	0.9579	0.0
0.2095	2.0	2774	0.2413	0.9579	0.0

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1