README.md

metadata

language:
  - en
license: mit
tags:
  - generated_from_trainer
datasets:
  - OpenTable
metrics:
  - accuracy
model-index:
  - name: gpt2.CEBaB_confounding.price_food_ambiance_negative.absa.5-class.seed_42
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: OpenTable OPENTABLE-ABSA
          type: OpenTable
          args: opentable-absa
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8310893512851897

gpt2.CEBaB_confounding.price_food_ambiance_negative.absa.5-class.seed_42

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

• Loss: 0.4726
• Accuracy: 0.8311
• Macro-f1: 0.8295
• Weighted-macro-f1: 0.8313

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.2+cu102
• Datasets 2.5.2
• Tokenizers 0.12.1