Hugging Face's logo

bachephysicdun
/
HW2-dpo

Text Generation
Transformers
Safetensors
gpt2
trl
dpo
Generated from Trainer
orpo
text-generation-inference
Inference Endpoints
Model card Files Community
HW2-dpo / README.md
bachephysicdun's picture
bachephysicdun
End of training
663bf5a verified
preview code
|
raw
history blame contribute delete
1.12 kB
metadata
library_name: transformers
license: mit
base_model: bachephysicdun/HW2-supervised
tags:
  - trl
  - dpo
  - generated_from_trainer
  - orpo
datasets:
  - piqa
model-index:
  - name: HW2-dpo
    results: []

HW2-dpo

This model is a fine-tuned version of bachephysicdun/HW2-supervised on the piqa dataset.

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: 5e-05
  • train_batch_size: 4
  • 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

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1