varun-v-rao's picture
End of training
480c47a verified
metadata
license: mit
base_model: openai-community/gpt2-large
tags:
  - generated_from_trainer
datasets:
  - stanfordnlp/snli
metrics:
  - accuracy
model-index:
  - name: gpt2-large-bn-adapter-7.42M-snli-model2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: snli
          type: stanfordnlp/snli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9006299532615322

gpt2-large-bn-adapter-7.42M-snli-model2

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

  • Loss: 0.2734
  • Accuracy: 0.9006

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: 100
  • 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
0.374 1.0 17168 0.2993 0.8888
0.334 2.0 34336 0.2791 0.8989
0.307 3.0 51504 0.2734 0.9006

Framework versions

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