REILX's picture
Update README.md
957eab8 verified
metadata
license: llama3
datasets:
  - silk-road/alpaca-data-gpt4-chinese
  - TigerResearch/sft_zh
  - LooksJuicy/ruozhiba
  - leo009/alpaca-cleaned-zh-cn
  - REILX/extracted_tagengo_gpt4
language:
  - en
  - zh
pipeline_tag: text-generation
tags:
  - text-generation-inference
  - llama
  - chat
  - sft
  - llama-factory

模型:

数据集:

(使用langid清理以上数据集,删除其中非中文资料)

训练工具

https://github.com/hiyouga/LLaMA-Factory

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0