Make rollout completion tokens configurable

configs/_base_/default.yaml

@@ -79,7 +79,6 @@ env:
   name: ""
   skill_init: ""
   split_mode: ratio       # ratio = build deterministic split from data_path; split_dir = use pre-split train/val/test
-  split_ratio: "2:1:7"    # explicit default for dataset-backed benchmarks: train:val:test
   split_seed: 42
   split_dir: ""
   data_path: ""

configs/alfworld/default.yaml

@@ -19,11 +19,11 @@ env:
   name: alfworld
   skill_init: skillopt/envs/alfworld/skills/initial.md
   split_mode: split_dir
-  split_ratio: "2:1:7"
   split_dir: data/ablation_splits/alfworld/2-1-7_seed42
   data_path: ""
   split_output_dir: ""
   max_steps: 50
+  max_completion_tokens: 16384
   workers: 8
   max_api_workers: 8
   limit: 0

configs/docvqa/default.yaml

@@ -18,11 +18,11 @@ env:
   name: docvqa
   skill_init: skillopt/envs/docvqa/skills/initial.md
   split_mode: split_dir
-  split_ratio: "2:1:7"
   split_dir: data/docvqa/splits
   data_path: ""
   split_output_dir: ""
   max_turns: 1
+  max_completion_tokens: 16384
   workers: 16
   image_detail: auto
   limit: 0

configs/livemathematicianbench/default.yaml

@@ -9,11 +9,11 @@ env:
   name: livemathematicianbench
   skill_init: skillopt/envs/livemathematicianbench/skills/initial.md
   split_mode: split_dir
-  split_ratio: "2:1:7"
   split_dir: data/ablation_splits/livemathematicianbench/2-1-7_seed42
   data_path: ""
   split_output_dir: ""
   max_turns: 1
+  max_completion_tokens: 16384
   exec_timeout: 300
   workers: 64
   limit: 0

configs/officeqa/default.yaml

@@ -23,7 +23,7 @@ env:
     - data/officeqa_docs_official
   workers: 4
   max_tool_turns: 24
-  max_completion_tokens: 10000
+  max_completion_tokens: 16384
   search_mode: offline
   max_queries_per_turn: 4
   search_api_url: http://apisix.westus2.cloudapp.azure.com/search_tool/search

configs/searchqa/default.yaml

@@ -23,10 +23,10 @@ env:
   name: searchqa
   skill_init: skillopt/envs/searchqa/skills/initial.md
   split_mode: split_dir
-  split_ratio: "2:1:7"
   split_dir: data/searchqa_split
   data_path: ""
   split_output_dir: ""
   max_turns: 1
+  max_completion_tokens: 16384
   workers: 24
   limit: 0

configs/spreadsheetbench/default.yaml

@@ -23,12 +23,12 @@ env:
   name: spreadsheetbench
   skill_init: skillopt/envs/spreadsheetbench/skills/initial.md
   split_mode: split_dir
-  split_ratio: "2:1:7"
   split_dir: data/spreadsheetbench_split
   data_path: ""
   split_output_dir: ""
   data_root: data/spreadsheetbench_verified_400
   mode: multi
   max_turns: 30
+  max_completion_tokens: 16384
   exec_timeout: 600
   workers: 24