Hugging Face's logo

max-rl
/
checkpoint-archives

Safetensors
Model card Files
xet
 Community
guanning commited on
Commit
7742d2e
·
verified ·
1 Parent(s): 0312045

Archive checkpoint folder MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo

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 +3 -0
  2. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/added_tokens.json +28 -0
  3. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/chat_template.jinja +85 -0
  4. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/config.json +60 -0
  5. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_0.pt +3 -0
  6. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_1.pt +3 -0
  7. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_2.pt +3 -0
  8. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_3.pt +3 -0
  9. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_4.pt +3 -0
  10. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_5.pt +3 -0
  11. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_6.pt +3 -0
  12. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_7.pt +3 -0
  13. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/generation_config.json +6 -0
  14. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/merges.txt +0 -0
  15. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_0.pt +3 -0
  16. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_1.pt +3 -0
  17. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_2.pt +3 -0
  18. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_3.pt +3 -0
  19. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_4.pt +3 -0
  20. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_5.pt +3 -0
  21. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_6.pt +3 -0
  22. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_7.pt +3 -0
  23. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_0.pt +3 -0
  24. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_1.pt +3 -0
  25. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_2.pt +3 -0
  26. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_3.pt +3 -0
  27. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_4.pt +3 -0
  28. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_5.pt +3 -0
  29. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_6.pt +3 -0
  30. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_7.pt +3 -0
  31. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/special_tokens_map.json +31 -0
  32. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/tokenizer.json +3 -0
  33. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/tokenizer_config.json +239 -0
  34. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/vocab.json +0 -0
  35. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/data.pt +3 -0
  36. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/added_tokens.json +28 -0
  37. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/chat_template.jinja +85 -0
  38. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/config.json +60 -0
  39. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_0.pt +3 -0
  40. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_1.pt +3 -0
  41. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_2.pt +3 -0
  42. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_3.pt +3 -0
  43. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_4.pt +3 -0
  44. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_5.pt +3 -0
  45. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_6.pt +3 -0
  46. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_7.pt +3 -0
  47. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/generation_config.json +6 -0
  48. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/merges.txt +0 -0
  49. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/model_world_size_8_rank_0.pt +3 -0
  50. MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/model_world_size_8_rank_1.pt +3 -0
.gitattributes CHANGED
@@ -35,3 +35,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  MaxRL_Qwen3-0.6B-Base_IDK/normal_1e-6_grpo/global_step_200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  MaxRL_Qwen3-0.6B-Base_IDK/normal_1e-6_grpo/global_step_400/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  MaxRL_Qwen3-0.6B-Base_IDK/normal_1e-6_grpo/global_step_200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  MaxRL_Qwen3-0.6B-Base_IDK/normal_1e-6_grpo/global_step_400/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_600/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/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
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 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.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/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": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
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": 32768,
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
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6ec91eee812edc4b7d6ef8aaaea126a098beedd13350e6ddbb256c7bff9fbd
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674b3317f8a06c018e821df87985d096fbb7add0019d8ee24ec3390ed5d437e4
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132540cbcd46a34ea1e1e53e2fe8cfe8b875d829db7848733bc9841a3700aaf7
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb9f723620a0fa461f445c3c01402b89f23489a9e109411a8140dc1963c8594
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f79f2eb2536f5f327cc43d19278e422e715044d07bed2faff365bbe7c23ec2
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d796320702d902b85703e81b19b280ca49620b214cee128923a7375759127b
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70dc07ead07a451764d100b0543a240a809d73fb8a3917ba42d3e7efcf907b38
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b5ba15161c29ef50b6157cbf2191c7473c5c9ae770757744f8bbbe7747a2be
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.57.6"
6
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d8b80569bde3754ad12a1ee215834f9762732b9d73d92e710bfff167da3bb3
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0decc1d4b486ee18601e4c3cf8284a5d45f31677f6c5170baf56fe9ad2b0ed06
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d06b34b8dac7801ddf4e042547ebbb419c44d43d810297ecf9851d2c33e6be
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e489167da4703ea33279a3fd95850f089f54286545af1eada74685393a9593d1
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83fff6c2ea5e23ecfac9effb99c9e83be3dc9b68390b7f6026778cb943b0efd
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b307e177dc548ae6a85162f71d7da5c09b4557454ae7e79f1483517c65b68ad
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96aa7b00748c9c3a2d2f16ea6447efe191dffcb0600da20e13ccf61966c1b0c0
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2779565a58d0696e420b18a8fb291c5bc8719dbd9e2dbbb1681e30f5ba8eb8cc
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e052885fe8b239c6a44a9cfdc4dd495bda7b41aee003f06fe1c860bb594393
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9d72c884d2002c42a6967d55b085a8bb88429dd1cd680f2915275e509c19c1
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c7a9e61cb5698b76c46be426efc5a96d755e6867767669f3d6fc22b8d4b5c8
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cdf789f03e4986fa7bff8e514ad0efc14ca3f30022244a121be941d56bc904
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aade482336154b83e7507f3c1d8de99e6db5a6af3d74c38533ca66268a6460f4
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23643b16b973aba4ce2bd94179604a3c45816128d6dacbeea9f15f8d8326b152
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31ae54825f6688ad941a5fe68f186b86255c86f44e577dd2ad0ea7a5f8f74af
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3961f5f7eef73d80996198f4b85be79d3bba0a4d54ce2f2284048470c0999b4f
3
+ size 596076087
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/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": "<|endoftext|>",
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
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/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": "<|endoftext|>",
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
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/actor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_200/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8844ee43bab3d6efc97b2964c4ec1dedf5dd9ad61892becd7b9b384ced2a08fa
3
+ size 1492
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/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
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 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.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/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": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
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": 32768,
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
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd45b0008c98319a55b0674561aadadb8372043dae7a94ebf7f61879727a92f
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd9b400239886e8c9eff36b205fae77bc281d44a64760cdfd1873302b3540b0
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d796dae858fdd293600473ec705d5a802220aca95d47431d012bbd23b925fc2
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908663b29be51abdfb651dbda54f5ac2ceab26b3b0135e903cb544260b23ee00
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:982e82a1bec4dc06d568de04475840577910d66bf7abd4cc7128bfccbda2b9a1
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1211056a0600b8ca6559849a6a2c161f90e2812bd4dac9a1df989f123c645b
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5641bf9114ff646d21f5a666a17fee202de79a0b54e0fc8d7f1740fd90c579
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:310dff529c90a26a153999a2f2ca8bb2f9fe253bf285db973c6b5cbb4d5093cc
3
+ size 14632
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.57.6"
6
+ }
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ef491c5dadeb5b38768939a87162e6586f223ccc2555a11a8c4a7b3dee5246
3
+ size 376037626
MaxRL_Qwen3-0.6B-Base_IDK/normal_3e-6_grpo/global_step_400/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561a04b5528e7ca8d72f7a70a5fa7da161694b87f9622d0c4180c5237d3d3d22
3
+ size 376037626