FengdiFlo commited on
Commit
e4e729d
·
verified ·
1 Parent(s): 4d26bf6

upload lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1 checkpoints

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +12 -0
  2. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_0.pt +3 -0
  3. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_1.pt +3 -0
  4. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_2.pt +3 -0
  5. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_3.pt +3 -0
  6. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/fsdp_config.json +4 -0
  7. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/added_tokens.json +28 -0
  8. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/chat_template.jinja +89 -0
  9. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/config.json +60 -0
  10. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/generation_config.json +13 -0
  11. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/merges.txt +0 -0
  12. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/special_tokens_map.json +31 -0
  13. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/tokenizer.json +3 -0
  14. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/tokenizer_config.json +239 -0
  15. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/vocab.json +0 -0
  16. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_0.pt +3 -0
  17. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_1.pt +3 -0
  18. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_2.pt +3 -0
  19. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_3.pt +3 -0
  20. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_0.pt +3 -0
  21. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_1.pt +3 -0
  22. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_2.pt +3 -0
  23. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_3.pt +3 -0
  24. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_0.pt +3 -0
  25. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_1.pt +3 -0
  26. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_2.pt +3 -0
  27. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_3.pt +3 -0
  28. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/fsdp_config.json +4 -0
  29. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/added_tokens.json +28 -0
  30. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/chat_template.jinja +89 -0
  31. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/config.json +60 -0
  32. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/generation_config.json +13 -0
  33. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/merges.txt +0 -0
  34. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/special_tokens_map.json +31 -0
  35. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/tokenizer.json +3 -0
  36. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/tokenizer_config.json +239 -0
  37. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/vocab.json +0 -0
  38. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_0.pt +3 -0
  39. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_1.pt +3 -0
  40. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_2.pt +3 -0
  41. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_3.pt +3 -0
  42. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_0.pt +3 -0
  43. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_1.pt +3 -0
  44. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_2.pt +3 -0
  45. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_3.pt +3 -0
  46. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/data.pt +3 -0
  47. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_0.pt +3 -0
  48. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_1.pt +3 -0
  49. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_2.pt +3 -0
  50. lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_3.pt +3 -0
.gitattributes CHANGED
@@ -204,3 +204,15 @@ lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_60/actor/huggingf
204
  lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
205
  lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
206
  lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
204
  lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
205
  lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
206
  lambda_0_no_use_Y_pass_at_4.0_p-diff-adv-pass-at-k/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
207
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
208
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
209
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
210
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
211
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_180/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
212
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_180/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
213
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
214
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
215
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
216
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
217
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
218
+ lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114a9b7be6a9ee99bfe4e651ad1e7428b81c9d7a3ed7cbbe11bb37dac9ffca83
3
+ size 15141
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265861750580817a5a58812f4bc032134d548289890e2ab89361eea3aff2b207
3
+ size 15205
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7306744ac53067cd957873687339659b7b8a60815afe309a3242bb0dacc10b5a
3
+ size 15141
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9744e79cbf5483fe2488d7c0266dd62015b3511c6c1f8c1b93fc1b1cf3e5a7
3
+ size 15205
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/fsdp_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "FSDP_version": 1,
3
+ "world_size": 4
4
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 6144,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 40960,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen3",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 151643,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.57.6",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.6"
13
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998f598220154624fcc2310bf88de0f92a3307eff7d50fbfccaf5862f8406a89
3
+ size 2031920747
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ef0db7b8ff7355b81efbba8b745762bb972f6899126cbdaad20be3d60c70d2
3
+ size 2031920747
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2794dd06215029b91f7796c440f07467d55205e521df77083317f37169d9434
3
+ size 2031920747
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7906e2669131f3c0f60348c3a9bf24f958498b2277e4da979422362e6422cf4
3
+ size 2031920747
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4707f6e3206677aa04f8f1d8507829d97320b01402ad838866849c8f5a042a5
3
+ size 3441176616
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a485eb24a625727ebe4cf3a2e2932798c6b08f136a14207b1ca0ab066e0fb0fd
3
+ size 3441176616
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ac2af3d44a317d1cc547ff3706a3b7a23681f1686d04a0e05557018b63332d
3
+ size 3441176616
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f372184dee7476a78855d1d65ab05a2eef78ec3804abb5cabb0814034fd21ec
3
+ size 3441176616
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe7c4385717c067c6a8b8ea640cec3ba8146caa62ac9cef9bc19702005351c2
3
+ size 15141
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad26b6abe322da57eadb1b0234ad41acd2baad3a11f23806ce77c492247463b
3
+ size 15205
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c49256ce0199d989053736d645830785960a84840ecb42f760e3af2bc5f4c44
3
+ size 15141
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fcd6064677ed81222c5cfeaddc32e8bfe6543626d45cd38000c858d7bd0068
3
+ size 15205
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/fsdp_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "FSDP_version": 1,
3
+ "world_size": 4
4
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 6144,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 40960,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen3",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 151643,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.57.6",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.6"
13
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5be1473cee156dcb67e448cd89f1dd3332c07b17fc816c77ec505a3960e26a
3
+ size 2031944043
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17cee5a2110ebde1306329a895d6e106adf91aa1fd91b21dcc94ea581cf5b82
3
+ size 2031935851
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f284fc19174d50396182bbedb4eecb9cec9d25d4d02dfcad3815082cb904bae
3
+ size 2031935851
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d9f3e77acf0f609fd3b4a8b042f588c637fdfc8d990ef0c659d7894e3b5e16
3
+ size 2031935851
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc5044b301f082f457062ba7d6af8cc05f08be60b7a573977185cf562350952
3
+ size 3441180712
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acd23f3aafcc606e7687e8f98142c01897e5415266843fc71a4a49e00a9f9f4
3
+ size 3441180712
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d93a379d26f76fe0e24060eb222e745f63b947ee65b357668ec6040eb64d73
3
+ size 3441180712
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/credit/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e868e4cd1b4da117a0268a5b23509855d670f1e58189422edc5585d93a8b03
3
+ size 3441180712
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_120/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281c5c2ed8153cdeda37e14691f1a570141d6201245a9c99eebca1dbe34ad5fc
3
+ size 21425
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c1917ce502cba901676b86ea068af3daa4a62508b28b2f06bd6924e72e2a61
3
+ size 15141
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7021b171989f44e831673154afcb642cd752826fd4856ea0f3af79014ed01780
3
+ size 15205
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345c410163a153b00ecbf206f97512ba78ae88a976e632f13bb9beb66cb61c31
3
+ size 15141
lambda_0_no_use_Y_direct_pass1_pass_at_4.0_p-diff-adv-pass-at-k-direct-p1/global_step_150/actor/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7596f6232a55f3ea0ed2696e8ae549685dd09f99936e94c9793825498df85cec
3
+ size 15205