hon9kon9ize/yi-1.5-6b-yue-vocab-expanded

yi-1.5-6b-yub-vocab-expanded

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