Giter Club home page Giter Club logo

Comments (9)

hiyouga avatar hiyouga commented on May 10, 2024 1

您好,我们写了一份关于加载自定义内容的教程文档,请移步:https://github.com/hiyouga/ChatGLM-Efficient-Tuning/blob/main/examples/alter_self_cognition.md

from chatglm-efficient-tuning.

hiyouga avatar hiyouga commented on May 10, 2024

没有看到详细的报错信息,请问你微调模型了吗。把微调日志发一下。

from chatglm-efficient-tuning.

poppysix avatar poppysix commented on May 10, 2024

没有报错,看起来一切正常啊
CUDA_VISIBLE_DEVICES=0 python finetune_chatglm.py
--do_train
--dataset example
--finetuning_type lora
--output_dir output
--per_device_train_batch_size 16
--gradient_accumulation_steps 1
--lr_scheduler_type cosine
--logging_steps 10
--save_steps 1000
--max_train_samples 3000
--learning_rate 5e-5
--num_train_epochs 1.0
--fp16
169

from chatglm-efficient-tuning.

hiyouga avatar hiyouga commented on May 10, 2024

这个只是做个例子。具体微调要准备其他大型数据集,这个示例数据集数据量太小了。

from chatglm-efficient-tuning.

poppysix avatar poppysix commented on May 10, 2024

这个只是做个例子。具体微调要准备其他大型数据集,这个示例数据集数据量太小了。

用了自己的数据集900条也不出结果,用官方Tuning是可以出来的

from chatglm-efficient-tuning.

hiyouga avatar hiyouga commented on May 10, 2024

可以试着增大Lora的r值,或者使用和官方一样的pre_seq_len=128的P-Tuning方法。同时增大learning_rate=1e-3

默认参数中为了避免模型发生灾难性遗忘并过拟合到新数据集上,采用的都是较为保守的参数。

from chatglm-efficient-tuning.

LainNetWork avatar LainNetWork commented on May 10, 2024

可以试着增大Lora的r值,或者使用和官方一样的pre_seq_len=128的P-Tuning方法。同时增大learning_rate=1e-3

默认参数中为了避免模型发生灾难性遗忘并过拟合到新数据集上,采用的都是较为保守的参数。

你好,小白想请教一个问题,这个增大lora的r值具体要怎么做呢?需要加什么参数么?

from chatglm-efficient-tuning.

hiyouga avatar hiyouga commented on May 10, 2024

你好,小白想请教一个问题,这个增大lora的r值具体要怎么做呢?需要加什么参数么?

@LainNetWork 加入参数--lora_rank=16

from chatglm-efficient-tuning.

LainNetWork avatar LainNetWork commented on May 10, 2024

你好,小白想请教一个问题,这个增大lora的r值具体要怎么做呢?需要加什么参数么?

@LainNetWork 加入参数--lora_rank=16

明白了,感谢回答~

from chatglm-efficient-tuning.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.