ModelQwen2.5-Math-1.5B

Qwen2.5-Math-1.5B

A math-reasoning-specialized model in the Qwen series with 1.5B parameters, designed for mathematical problem solving and reasoning tasks.

Timeline (last 90 days)

Oct 14

In controlled GRPO experiments conducted on Qwen2.5-Math-1.5B with a batch size span of 16x, the results supported both predictions: slower progress and an approximately invariant failure clock.

Unverified50%

All Facts (1)

Unverified

In controlled GRPO experiments conducted on Qwen2.5-Math-1.5B with a batch size span of 16x, the results supported both predictions: slower progress and an approximately invariant failure clock.

50%

Source Articles

Does a Larger Batch Actually Learn Slower? The RLVR "Two-Clock" Framework Reveals the Truth About Batch Size and Learning Rate ScalingOct 14