yuhuizhang's picture
update model card README.md
98d6ac6
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - sst2
model-index:
  - name: finetuned_gpt2_sst2_negation0.05
    results: []

finetuned_gpt2_sst2_negation0.05

This model is a fine-tuned version of gpt2 on the sst2 dataset. It achieves the following results on the evaluation set:

  • Loss: 3.5271

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: 8
  • eval_batch_size: 8
  • seed: 42
  • 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
3.1134 1.0 1062 3.5060
2.926 2.0 2124 3.5158
2.8331 3.0 3186 3.5271

Framework versions

  • Transformers 4.22.2
  • Pytorch 1.12.1+cu113
  • Datasets 2.5.2
  • Tokenizers 0.12.1