We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
我参考文档docs/Yuan2_fastchat.md,进行训练,我的数据格式如下: [{"id": "identity_0", "conversations": [ {"from": "human", "value": "嘿,Bob,你最近看过什么好看的电影吗?"}, {"from": "gpt", "value": "嗯,我上周刚看了《流浪地球2》,简直太棒了!..."}, {"from": "human", "value": "流浪地球是一部很看好的电影,你一定会喜欢的"}, {"from": "gpt", "value": "我一定会喜欢的"} ] }]
当我输出process中的input_ids和target 生成的input_ids是: (human)嘿,Bob,你最近看过什么好看的电影吗? (gpt)嗯,我上周刚看了《流浪地球2》,简直太棒了!... (human)流浪地球是一部很看好的电影,你一定会喜欢的 (gpt)我一定会喜欢的 生成的target是: (human)嘿,Bob,你最近看过什么好看的电影吗? (gpt)嗯,我上周刚看了《流浪地球2》,简直太棒了!... (human)流浪地球是一部很看好的电影,你一定会喜欢的
我的问题是,target不应该是学习gpt的回复吗,为什么我生成的target像是在学习用户的提问
The text was updated successfully, but these errors were encountered:
是以下参数的影响吗? --efficient_loss False --split_example_loss True --last_response_loss False \
Sorry, something went wrong.
No branches or pull requests
我参考文档docs/Yuan2_fastchat.md,进行训练,我的数据格式如下:
[{"id": "identity_0",
"conversations": [
{"from": "human", "value": "嘿,Bob,你最近看过什么好看的电影吗?"},
{"from": "gpt", "value": "嗯,我上周刚看了《流浪地球2》,简直太棒了!..."},
{"from": "human", "value": "流浪地球是一部很看好的电影,你一定会喜欢的"},
{"from": "gpt", "value": "我一定会喜欢的"}
]
}]
当我输出process中的input_ids和target
生成的input_ids是:
(human)嘿,Bob,你最近看过什么好看的电影吗?
(gpt)嗯,我上周刚看了《流浪地球2》,简直太棒了!...
(human)流浪地球是一部很看好的电影,你一定会喜欢的
(gpt)我一定会喜欢的
生成的target是:
(human)嘿,Bob,你最近看过什么好看的电影吗?
(gpt)嗯,我上周刚看了《流浪地球2》,简直太棒了!...
(human)流浪地球是一部很看好的电影,你一定会喜欢的
我的问题是,target不应该是学习gpt的回复吗,为什么我生成的target像是在学习用户的提问
The text was updated successfully, but these errors were encountered: