lole25's picture
End of training
203b1c9 verified
metadata
license: mit
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
base_model: microsoft/phi-2
model-index:
  - name: phi-2-gpo-lora-ultrafeedback-test
    results: []

phi-2-gpo-lora-ultrafeedback-test

This model is a fine-tuned version of lole25/phi-2-gpo-lora-ultrafeedback-test 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: 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: 2

Training results

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.14.6
  • Tokenizers 0.15.2