varun-v-rao's picture
End of training
32de796 verified
metadata
license: mit
base_model: openai-community/gpt2
tags:
  - generated_from_trainer
datasets:
  - stanfordnlp/snli
metrics:
  - accuracy
model-index:
  - name: gpt2-bn-adapter-895K-snli-model1
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: snli
          type: stanfordnlp/snli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8274740906319854

gpt2-bn-adapter-895K-snli-model1

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

  • Loss: 0.4353
  • Accuracy: 0.8275

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: 64
  • eval_batch_size: 32
  • seed: 10
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5633 1.0 8584 0.4692 0.8149
0.5225 2.0 17168 0.4438 0.8248
0.5205 3.0 25752 0.4353 0.8275

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0