Hugging Face's logo

DUAL-GPO
/
zephyr-7b-ipo-40k-60k-0.001-i2

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
Model card Files
xet
 Metrics Community

zephyr-7b-ipo-40k-60k-0.001-i2

This model is a fine-tuned version of DUAL-GPO/zephyr-7b-ipo-10k-40k-0.001-i1-merged 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-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 3
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 12
  • total_eval_batch_size: 6
  • 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

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.1.2
  • Datasets 2.14.6
  • Tokenizers 0.15.2
Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DUAL-GPO/zephyr-7b-ipo-40k-60k-0.001-i2

Base model

DUAL-GPO/zephyr-7b-ipo-10k-40k-0.001-i1-merged
Adapter
(1)
this model

Dataset used to train DUAL-GPO/zephyr-7b-ipo-40k-60k-0.001-i2