chengq1001

Results 4 comments of chengq1001

Why does the loss suddenly drop to zero and the grad_norm stabilize at 1 at specific training steps when fine-tuning Llama3.2-vision-11B?

请问解决了吗？求解决方案

未来会支持混合图文数据的多模态增量预训练吗？

+1

Watchdog caught collective operation timeout: WorkNCCL(SeqNum=1580, OpType=ALLREDUCE, NumelIn=466119168, NumelOut=466119168, Timeout(ms)=600000) ran for 600004 milliseconds before timing out.

some issue

verl是否支持使用LLM作为交互式环境进行multi-turn rl? | Does verl support multi-turn rl using LLM as an interactive environment?

same question