8 lines
181 B
YAML
8 lines
181 B
YAML
|
- mode=train
|
||
|
|
- task=math
|
||
|
|
- algorithm=grpo
|
||
|
|
- algorithm.training.curriculum_schedule=cosine
|
||
|
|
- model=qwen15
|
||
|
|
- algorithm.training.max_steps=1600
|
||
|
|
- algorithm.training.vllm_mode=colocate
|