Chinese-Llama-2-7B / README.md
seeledu's picture
Update README.md
04a4314
metadata
tags:
  - generated_from_trainer
model-index:
  - name: Chinese-Llama-2-7B
    results: []

llama2-7b-llama2_coig_dt_ca-all

This model is a fine-tuned version of llama2-7B-HF on an Chinese instruction dataset.

More information can be found in this Github Homepage.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1
  • distributed_type: multi-GPU
  • num_devices: 16
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 256
  • total_eval_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 3.0

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.11.0
  • Tokenizers 0.13.2