cleanup: remove unused benchmarks, deep_probe, meta_reflect

Remove sealqa, babyvision, mathverse, mmrb, swebench envs and configs. Remove deep_probe, deep_reflect, meta_reflect modules and prompts. Remove download_babyvision script. These are not part of the core released benchmarks. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-05-24 19:36:27 +00:00
parent 2df2542aec
commit f55a26414e
71 changed files with 0 additions and 11199 deletions
@@ -1,21 +0,0 @@
-_base_: ../_base_/default.yaml
-
-train:
-  batch_size: 64
-  accumulation: 1
-
-env:
-  name: babyvision
-  skill_init: skillopt/envs/babyvision/skills/initial.md
-  split_mode: ratio
-  split_ratio: "2:1:7"
-  split_dir: ""
-  data_path: ""
-  split_output_dir: ""
-  max_turns: 1
-  workers: 16
-  limit: 0
-  image_detail: auto
-  judge_model: gpt-5.4
-  judge_max_completion_tokens: 256
-  judge_retries: 5
@@ -1,23 +0,0 @@
-_base_: ../_base_/default.yaml
-
-model:
-  codex_exec_sandbox: danger-full-access
-
-train:
-  batch_size: 64
-  accumulation: 1
-
-env:
-  name: mathverse
-  skill_init: skillopt/envs/mathverse/skills/initial.md
-  split_dir: ""
-  data_root: data/MathVerse
-  problem_version: Text Lite
-  use_text_dominant_reference: false
-  max_turns: 1
-  workers: 16
-  limit: 0
-  image_detail: auto
-  judge_model: gpt-5.4
-  judge_max_completion_tokens: 256
-  judge_retries: 5
@@ -1,18 +0,0 @@
-_base_: ../_base_/default.yaml
-
-train:
-  batch_size: 128
-  accumulation: 1
-
-env:
-  name: mmrb
-  skill_init: skillopt/envs/mmrb/skills/initial.md
-  split_mode: ratio
-  split_ratio: "2:1:7"
-  split_dir: ""
-  data_path: ""
-  split_output_dir: ""
-  max_turns: 1
-  workers: 16
-  limit: 0
-  image_detail: auto
@@ -1,23 +0,0 @@
-_base_: ../_base_/default.yaml
-
-model:
-  reasoning_effort: medium
-
-train:
-  batch_size: 10
-  accumulation: 1
-
-gradient:
-  minibatch_size: 8
-  merge_batch_size: 8
-
-optimizer:
-  learning_rate: 4
-
-env:
-  name: sealqa
-  skill_init: skillopt/envs/sealqa/skills/initial.md
-  split_dir: data/sealqa_split
-  workers: 4
-  max_tool_turns: 12
-  limit: 0
@@ -1,36 +0,0 @@
-_base_: ../_base_/default.yaml
-
-model:
-  reasoning_effort: medium
-
-train:
-  batch_size: 20
-  accumulation: 1
-
-gradient:
-  minibatch_size: 4
-  merge_batch_size: 8
-
-optimizer:
-  learning_rate: 4
-
-evaluation:
-  sel_env_num: 0
-  test_env_num: 0
-
-env:
-  name: swebench
-  skill_init: skillopt/envs/swebench/skills/initial.md
-  split_mode: ratio
-  split_ratio: "2:1:7"
-  split_dir: ""
-  data_path: ""
-  split_output_dir: ""
-  dataset_name: lite
-  hf_split: test
-  workers: 8
-  eval_workers: 8
-  step_limit: 50
-  cost_limit: 3.0
-  timeout_per_instance: 600
-  limit: 0