Tristan Thrush
update model card README.md
2a0f457
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: gpt2_summarization_reward_model
    results: []

gpt2_summarization_reward_model

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7376
  • Accuracy: 0.6020

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
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6521 1.0 1451 0.6670 0.6037
0.6101 2.0 2902 0.6763 0.6022
0.5772 3.0 4353 0.7034 0.6026
0.5503 4.0 5804 0.7215 0.6024
0.5347 5.0 7255 0.7376 0.6020

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2