search

shibing624 / textgen

TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。
Apache License 2.0
938 stars 109 forks source link

gpt2训练学不到东西 #56

Open Lxhnnn opened 1 year ago

Lxhnnn commented 1 year ago

training_zh_gpt2_demo.py训练时损失值一直很大

shibing624 commented 1 year ago
  1. loss降不下来，一般数据集质量不够；
  2. 可以试试chinese-llama等大模型。
stale[bot] commented 11 months ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.(由于长期不活动，机器人自动关闭此问题，如果需要欢迎提问)