metadata

library_name: peft
tags:
  - trl
  - dpo
  - generated_from_trainer
base_model: NousResearch/Llama-2-13b-hf
model-index:
  - name: Llama-2-13b-summarization_uk_dpo
    results: []

Llama-2-13b-summarization_uk_dpo

This model is a fine-tuned version of NousResearch/Llama-2-13b-hf on the None 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: 2e-06
train_batch_size: 1
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 5

Training results

Framework versions

PEFT 0.9.0
Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.15.2