metadata

library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:
  - trl
  - online-dpo
  - generated_from_trainer
model-index:
  - name: online-dpo-qwen2-2
    results: []
datasets: trl-lib/ultrafeedback-prompt

online-dpo-qwen2-2

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the https://huggingface.co/datasets/trl-lib/ultrafeedback-prompt 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-07
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: 3.0

Training results

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1