Skip to content

Fix doc/config issues about prompt/response/sequence lengths #370

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Merged
pan-x-c merged 2 commits into from
Nov 7, 2025
Merged

Fix doc/config issues about prompt/response/sequence lengths #370

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b3f4b0
Fix doc/config issues about prompt/response/sequence lengths
yanxi-chen Nov 7, 2025
dea6ccd
Resolve comment
yanxi-chen Nov 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docs/sphinx_doc/source/tutorial/example_async_mode.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@ algorithm:
repeat_times: 8
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 4
Expand Down Expand Up @@ -69,6 +71,8 @@ algorithm:
lr: 1e-6
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 4
Expand Down Expand Up @@ -128,6 +132,8 @@ algorithm:
repeat_times: 8
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster: # important
node_num: 1
gpu_per_node: 8
Expand Down
4 changes: 4 additions & 0 deletions docs/sphinx_doc/source/tutorial/example_dpo.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,8 @@ algorithm:
checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1536
cluster:
node_num: 1
gpu_per_node: 8
Expand Down Expand Up @@ -114,6 +116,8 @@ algorithm:
checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 10240
max_model_len: 10752
cluster:
node_num: 1
gpu_per_node: 2
Expand Down
2 changes: 2 additions & 0 deletions docs/sphinx_doc/source/tutorial/example_reasoning_basic.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,8 @@ algorithm:
lr: 1e-5
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 2
Expand Down
6 changes: 6 additions & 0 deletions docs/sphinx_doc/source_zh/tutorial/example_async_mode.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@ algorithm:
repeat_times: 8
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 4
Expand Down Expand Up @@ -69,6 +71,8 @@ algorithm:
lr: 1e-6
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 4
Expand Down Expand Up @@ -128,6 +132,8 @@ algorithm:
repeat_times: 8
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster: # important
node_num: 1
gpu_per_node: 8
Expand Down
4 changes: 4 additions & 0 deletions docs/sphinx_doc/source_zh/tutorial/example_dpo.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,8 @@ algorithm:
checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1536
cluster:
node_num: 1
gpu_per_node: 8
Expand Down Expand Up @@ -116,6 +118,8 @@ algorithm:
checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 10240
max_model_len: 10752
cluster:
node_num: 1
gpu_per_node: 2
Expand Down
2 changes: 2 additions & 0 deletions docs/sphinx_doc/source_zh/tutorial/example_reasoning_basic.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,8 @@ algorithm:
lr: 1e-5
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 2
Expand Down
2 changes: 1 addition & 1 deletion examples/asymre_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
algorithm:
algorithm_type: asymre
repeat_times: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/asymre_math/math.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-3B-Instruct} # the path to your model
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
algorithm:
algorithm_type: asymre
repeat_times: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/async_gsm8k/explorer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 4
Expand Down
2 changes: 1 addition & 1 deletion examples/async_gsm8k/trainer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 4
Expand Down
2 changes: 1 addition & 1 deletion examples/cispo_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/grpo_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/grpo_gsm8k_experience_pipeline/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/grpo_gsm8k_ruler/gsm8k_ruler.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/grpo_gsm8k_task_pipeline/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ data_processor:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/grpo_lora_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
lora_configs:
- name: lora
lora_rank: 32
Expand Down
2 changes: 1 addition & 1 deletion examples/ppo_countdown/countdown.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/ppo_countdown_megatron/countdown.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/rec_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ mode: both
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-3B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
algorithm:
algorithm_type: rec
repeat_times: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/sppo_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ checkpoint_root_dir: ${oc.env:TRINITY_CHECKPOINT_ROOT_DIR,./checkpoints}
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
algorithm:
algorithm_type: sppo
repeat_times: 8
Expand Down
2 changes: 1 addition & 1 deletion examples/topr_gsm8k/gsm8k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ algorithm:
model:
model_path: ${oc.env:TRINITY_MODEL_PATH,Qwen/Qwen2.5-1.5B-Instruct}
max_response_tokens: 1024
max_model_len: 1280
max_model_len: 2048
cluster:
node_num: 1
gpu_per_node: 8
Expand Down