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
请教一下,关于train_llava的代码。为什么[final_inputs_ids] (https://github.com/yuanzhoulvpi2017/zero_nlp/blob/main/train_llava/train_llava/data.py#L128) 使用pad_token_id进行填充,而final_label_ids 使用 ignore_idx进行填充? 为啥不是都用pad_token_id填充呢?
还有为啥ignore_idx 等于-100,模型是怎么知道-100是ignore_idx的呢?每个llm都知道-100是要忽略的值吗?比如llama,qwen之类的。
感谢!
The text was updated successfully, but these errors were encountered:
ignore_idx到时候应该算loss之类的需要被遮住。特别是stf的时候。
llava原版代码会把ignore_idx传入数据构建的时候。例如
def _mask_targets(target, tokenized_lens, speakers): # cur_idx = 0 cur_idx = tokenized_lens[0] tokenized_lens = tokenized_lens[1:] target[:cur_idx] = IGNORE_INDEX for tokenized_len, speaker in zip(tokenized_lens, speakers): if speaker == "human": target[cur_idx+2:cur_idx + tokenized_len] = IGNORE_INDEX cur_idx += tokenized_len
但是llm是怎么知道-100要被mask掉这个我还不太清楚。 不知道大佬是否有啥高见。 @yuanzhoulvpi2017
Sorry, something went wrong.
No branches or pull requests
请教一下,关于train_llava的代码。为什么[final_inputs_ids] (https://github.com/yuanzhoulvpi2017/zero_nlp/blob/main/train_llava/train_llava/data.py#L128) 使用pad_token_id进行填充,而final_label_ids 使用 ignore_idx进行填充? 为啥不是都用pad_token_id填充呢?
还有为啥ignore_idx 等于-100,模型是怎么知道-100是ignore_idx的呢?每个llm都知道-100是要忽略的值吗?比如llama,qwen之类的。
感谢!
The text was updated successfully, but these errors were encountered: