Dataset validation

[1145523635]

Dear author:

I am currently conducting mathematical reasoning experiments using two basic models, qwen2.5-math-1.5b/7b. I did not see any data on ACM23 AIME24 in the official technical report. Was the data used in your paper in January this year the result of your own testing?

[love-cfall]

Dear author:

I am currently conducting mathematical reasoning experiments using two basic models, qwen2.5-math-1.5b/7b. I did not see any data on ACM23 AIME24 in the official technical report. Was the data used in your paper in January this year the result of your own testing?

Hello, I’d like to ask for some clarification.

I’m training Qwen3-14B-base on 8×H100, and during the early stage of training I encounter a large number of errors like:

Failed to decode tool call: Expecting property name enclosed in double quotes
Failed to decode tool call: Expecting ',' delimiter
Failed to decode tool call: Extra data
Error when executing tool: 'str' object has no attribute 'get'
Error when executing tool: 'WolframAlpha'
Error when executing tool: 'math'

I’m wondering whether this behavior is normal during the initial phase of training.