metadata

library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2-Math-7B-Instruct
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - xinlai/Math-Step-DPO-10K
model-index:
  - name: qwen2-math-7b-step-dpo
    results: []

qwen2-math-7b-step-dpo

This model is a fine-tuned version of Qwen/Qwen2-Math-7B-Instruct on the xinlai/Math-Step-DPO-10K 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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 8.0

Training results

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1