metadata

license: mit
base_model: HuggingFaceH4/mistral-7b-sft-beta
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: DPO-Zephyr-7B-baseline
    results: []

DPO-Zephyr-7B-baseline

This model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized 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: 3
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 3
total_train_batch_size: 9
total_eval_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1