metadata

license: other
base_model: Qwen/Qwen1.5-7B-Chat
tags:
  - alignment-handbook
  - trl
  - orpo
  - generated_from_trainer
  - trl
  - orpo
  - generated_from_trainer
datasets:
  - mlabonne/orpo-dpo-mix-40k
model-index:
  - name: qwen1.5-7b-chat-orpo-v2
    results: []

qwen1.5-7b-chat-orpo-v2

This model is a fine-tuned version of Qwen/Qwen1.5-7B-Chat on the mlabonne/orpo-dpo-mix-40k 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-06
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 16
total_eval_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: inverse_sqrt
lr_scheduler_warmup_steps: 100
num_epochs: 1

Training results

Framework versions

Transformers 4.41.2
Pytorch 2.2.2
Datasets 2.19.2
Tokenizers 0.19.1