Edit model card


This model is a fine-tuned version of 01-ai/Yi-1.5-6B undergone layers freezeing learning on the 300m tokens Cantonese dataset, in order to train a new words embedding in the expanded vocab. This model has not been continued pre-trainined, therefore it is not recommended to be used for further pre-training.

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1.0

Training results

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.19.1
Downloads last month
Model size
6.07B params
Tensor type

Finetuned from