phi-2-role-play / README.md
kingabzpro's picture
Update README.md
075ac01 verified
metadata
license: apache-2.0
library_name: peft
tags:
  - pretrained
  - lora
  - qlora
  - 4bit
  - phi-2
  - generated_from_trainer
base_model: microsoft/phi-2
model-index:
  - name: phi-2-role-play
    results: []
datasets:
  - hieunguyenminh/roleplay
language:
  - en
pipeline_tag: text-generation

phi-2-role-play

This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

image/png

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.1
  • Pytorch 2.0.0
  • Datasets 2.16.1
  • Tokenizers 0.15.0