README.md

metadata

license: gemma
library_name: peft
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - alignment-handbook
  - generated_from_trainer
base_model: google/gemma-2b
datasets:
  - HuggingFaceH4/deita-10k-v0-sft
  - hon9kon9ize/yue-alpaca-chat
model-index:
  - name: cantonese-gemma-sft-lora
    results: []

cantonese-gemma-sft-lora

This model is a fine-tuned version of google/gemma-2b on the HuggingFaceH4/deita-10k-v0-sft and the hon9kon9ize/yue-alpaca-chat datasets.

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: 0.0001
• train_batch_size: 1
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1

Training results

Framework versions

• PEFT 0.7.1
• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2