Hugging Face's logo

zenlm
/
zen-nano

Text Generation
Transformers
Safetensors
GGUF
English
qwen3
zen
nano
0.6B
edge-computing
conversational
text-generation-inference
Model card Files
xet
Community
1
zeekay commited on
Commit
2f1d9cd
·
verified ·
1 Parent(s): 284f710

Upload finetuned zen-nano model with Zen identity

Browse files
Files changed (46) hide show
  1. .gitattributes +3 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +89 -0
  4. checkpoint-216/added_tokens.json +28 -0
  5. checkpoint-216/chat_template.jinja +89 -0
  6. checkpoint-216/config.json +60 -0
  7. checkpoint-216/generation_config.json +12 -0
  8. checkpoint-216/merges.txt +0 -0
  9. checkpoint-216/model.safetensors +3 -0
  10. checkpoint-216/optimizer.pt +3 -0
  11. checkpoint-216/rng_state.pth +3 -0
  12. checkpoint-216/scheduler.pt +3 -0
  13. checkpoint-216/special_tokens_map.json +25 -0
  14. checkpoint-216/tokenizer.json +3 -0
  15. checkpoint-216/tokenizer_config.json +239 -0
  16. checkpoint-216/trainer_state.json +342 -0
  17. checkpoint-216/training_args.bin +3 -0
  18. checkpoint-216/vocab.json +0 -0
  19. checkpoint-240/added_tokens.json +28 -0
  20. checkpoint-240/chat_template.jinja +89 -0
  21. checkpoint-240/config.json +60 -0
  22. checkpoint-240/generation_config.json +12 -0
  23. checkpoint-240/merges.txt +0 -0
  24. checkpoint-240/model.safetensors +3 -0
  25. checkpoint-240/optimizer.pt +3 -0
  26. checkpoint-240/rng_state.pth +3 -0
  27. checkpoint-240/scheduler.pt +3 -0
  28. checkpoint-240/special_tokens_map.json +25 -0
  29. checkpoint-240/tokenizer.json +3 -0
  30. checkpoint-240/tokenizer_config.json +239 -0
  31. checkpoint-240/trainer_state.json +377 -0
  32. checkpoint-240/training_args.bin +3 -0
  33. checkpoint-240/vocab.json +0 -0
  34. config.json +60 -0
  35. generation_config.json +12 -0
  36. merges.txt +0 -0
  37. model.safetensors +3 -0
  38. optimizer.pt +3 -0
  39. rng_state.pth +3 -0
  40. scheduler.pt +3 -0
  41. special_tokens_map.json +25 -0
  42. tokenizer.json +3 -0
  43. tokenizer_config.json +239 -0
  44. trainer_state.json +69 -0
  45. training_args.bin +3 -0
  46. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-216/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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
+ }
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 %}
checkpoint-216/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
+ }
checkpoint-216/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 %}
checkpoint-216/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
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": 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": 151645,
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": "4.56.1",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
checkpoint-216/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151645,
8
+ "temperature": 0.6,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.56.1"
12
+ }
checkpoint-216/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5278d9620372202c3d7ca82cd6595179ecc7f1bbc21c03bf1590c6081323339b
3
+ size 1192135096
checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d223b54bfff67c9fb77480d6f6b37ca746249b0baab4ccbdf59f49614cec27ec
3
+ size 2384451723
checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817374c79694074958ac2537b4ffcf4ae1bd7defb8d81f48363bb8622b3fef00
3
+ size 14391
checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c165805c6ec023b291231674f4f38def913f38b5d09d9d0edf165026ae6b595
3
+ size 1465
checkpoint-216/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
checkpoint-216/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
checkpoint-216/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": "<|im_end|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
checkpoint-216/trainer_state.json ADDED
@@ -0,0 +1,342 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 9.0,
6
+ "eval_steps": 500,
7
+ "global_step": 216,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.041666666666666664,
14
+ "grad_norm": 73.5,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.9287,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.20833333333333334,
21
+ "grad_norm": 80.5,
22
+ "learning_rate": 4.000000000000001e-06,
23
+ "loss": 3.994,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.4166666666666667,
28
+ "grad_norm": 63.75,
29
+ "learning_rate": 9e-06,
30
+ "loss": 3.6819,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.625,
35
+ "grad_norm": 49.25,
36
+ "learning_rate": 1.4000000000000001e-05,
37
+ "loss": 2.5702,
38
+ "step": 15
39
+ },
40
+ {
41
+ "epoch": 0.8333333333333334,
42
+ "grad_norm": 48.75,
43
+ "learning_rate": 1.9e-05,
44
+ "loss": 1.4286,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 1.0416666666666667,
49
+ "grad_norm": 11.3125,
50
+ "learning_rate": 2.4e-05,
51
+ "loss": 0.7957,
52
+ "step": 25
53
+ },
54
+ {
55
+ "epoch": 1.25,
56
+ "grad_norm": 9.0625,
57
+ "learning_rate": 2.9e-05,
58
+ "loss": 0.7432,
59
+ "step": 30
60
+ },
61
+ {
62
+ "epoch": 1.4583333333333333,
63
+ "grad_norm": 16.5,
64
+ "learning_rate": 3.4000000000000007e-05,
65
+ "loss": 0.6508,
66
+ "step": 35
67
+ },
68
+ {
69
+ "epoch": 1.6666666666666665,
70
+ "grad_norm": 12.75,
71
+ "learning_rate": 3.9000000000000006e-05,
72
+ "loss": 0.591,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 1.875,
77
+ "grad_norm": 6.59375,
78
+ "learning_rate": 4.4000000000000006e-05,
79
+ "loss": 0.6682,
80
+ "step": 45
81
+ },
82
+ {
83
+ "epoch": 2.0833333333333335,
84
+ "grad_norm": 11.1875,
85
+ "learning_rate": 4.9e-05,
86
+ "loss": 0.4391,
87
+ "step": 50
88
+ },
89
+ {
90
+ "epoch": 2.2916666666666665,
91
+ "grad_norm": 9.5,
92
+ "learning_rate": 4.8947368421052635e-05,
93
+ "loss": 0.3461,
94
+ "step": 55
95
+ },
96
+ {
97
+ "epoch": 2.5,
98
+ "grad_norm": 15.5,
99
+ "learning_rate": 4.7631578947368424e-05,
100
+ "loss": 0.4083,
101
+ "step": 60
102
+ },
103
+ {
104
+ "epoch": 2.7083333333333335,
105
+ "grad_norm": 12.0,
106
+ "learning_rate": 4.6315789473684214e-05,
107
+ "loss": 0.377,
108
+ "step": 65
109
+ },
110
+ {
111
+ "epoch": 2.9166666666666665,
112
+ "grad_norm": 10.0625,
113
+ "learning_rate": 4.5e-05,
114
+ "loss": 0.3861,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 3.125,
119
+ "grad_norm": 6.78125,
120
+ "learning_rate": 4.368421052631579e-05,
121
+ "loss": 0.3271,
122
+ "step": 75
123
+ },
124
+ {
125
+ "epoch": 3.3333333333333335,
126
+ "grad_norm": 5.125,
127
+ "learning_rate": 4.236842105263158e-05,
128
+ "loss": 0.2295,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 3.5416666666666665,
133
+ "grad_norm": 5.75,
134
+ "learning_rate": 4.105263157894737e-05,
135
+ "loss": 0.2661,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 3.75,
140
+ "grad_norm": 10.9375,
141
+ "learning_rate": 3.973684210526316e-05,
142
+ "loss": 0.2583,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 3.9583333333333335,
147
+ "grad_norm": 10.0625,
148
+ "learning_rate": 3.842105263157895e-05,
149
+ "loss": 0.2631,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 4.166666666666667,
154
+ "grad_norm": 6.4375,
155
+ "learning_rate": 3.710526315789474e-05,
156
+ "loss": 0.1991,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 4.375,
161
+ "grad_norm": 6.71875,
162
+ "learning_rate": 3.578947368421053e-05,
163
+ "loss": 0.1937,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 4.583333333333333,
168
+ "grad_norm": 5.0,
169
+ "learning_rate": 3.447368421052632e-05,
170
+ "loss": 0.1894,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 4.791666666666667,
175
+ "grad_norm": 10.8125,
176
+ "learning_rate": 3.3157894736842106e-05,
177
+ "loss": 0.2233,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 5.0,
182
+ "grad_norm": 6.53125,
183
+ "learning_rate": 3.1842105263157895e-05,
184
+ "loss": 0.2006,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 5.208333333333333,
189
+ "grad_norm": 4.59375,
190
+ "learning_rate": 3.0526315789473684e-05,
191
+ "loss": 0.1657,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 5.416666666666667,
196
+ "grad_norm": 4.65625,
197
+ "learning_rate": 2.9210526315789477e-05,
198
+ "loss": 0.1937,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 5.625,
203
+ "grad_norm": 7.90625,
204
+ "learning_rate": 2.7894736842105263e-05,
205
+ "loss": 0.1801,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 5.833333333333333,
210
+ "grad_norm": 3.984375,
211
+ "learning_rate": 2.6578947368421052e-05,
212
+ "loss": 0.1704,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 6.041666666666667,
217
+ "grad_norm": 3.8125,
218
+ "learning_rate": 2.5263157894736845e-05,
219
+ "loss": 0.168,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 6.25,
224
+ "grad_norm": 5.15625,
225
+ "learning_rate": 2.394736842105263e-05,
226
+ "loss": 0.1395,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 6.458333333333333,
231
+ "grad_norm": 4.25,
232
+ "learning_rate": 2.2631578947368423e-05,
233
+ "loss": 0.1426,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 6.666666666666667,
238
+ "grad_norm": 4.8125,
239
+ "learning_rate": 2.1315789473684212e-05,
240
+ "loss": 0.1591,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 6.875,
245
+ "grad_norm": 5.3125,
246
+ "learning_rate": 2e-05,
247
+ "loss": 0.1656,
248
+ "step": 165
249
+ },
250
+ {
251
+ "epoch": 7.083333333333333,
252
+ "grad_norm": 3.53125,
253
+ "learning_rate": 1.868421052631579e-05,
254
+ "loss": 0.1505,
255
+ "step": 170
256
+ },
257
+ {
258
+ "epoch": 7.291666666666667,
259
+ "grad_norm": 4.875,
260
+ "learning_rate": 1.736842105263158e-05,
261
+ "loss": 0.1356,
262
+ "step": 175
263
+ },
264
+ {
265
+ "epoch": 7.5,
266
+ "grad_norm": 3.890625,
267
+ "learning_rate": 1.605263157894737e-05,
268
+ "loss": 0.1359,
269
+ "step": 180
270
+ },
271
+ {
272
+ "epoch": 7.708333333333333,
273
+ "grad_norm": 3.59375,
274
+ "learning_rate": 1.4736842105263157e-05,
275
+ "loss": 0.1444,
276
+ "step": 185
277
+ },
278
+ {
279
+ "epoch": 7.916666666666667,
280
+ "grad_norm": 4.5,
281
+ "learning_rate": 1.3421052631578948e-05,
282
+ "loss": 0.1446,
283
+ "step": 190
284
+ },
285
+ {
286
+ "epoch": 8.125,
287
+ "grad_norm": 3.375,
288
+ "learning_rate": 1.2105263157894737e-05,
289
+ "loss": 0.1381,
290
+ "step": 195
291
+ },
292
+ {
293
+ "epoch": 8.333333333333334,
294
+ "grad_norm": 4.03125,
295
+ "learning_rate": 1.0789473684210526e-05,
296
+ "loss": 0.1372,
297
+ "step": 200
298
+ },
299
+ {
300
+ "epoch": 8.541666666666666,
301
+ "grad_norm": 3.921875,
302
+ "learning_rate": 9.473684210526317e-06,
303
+ "loss": 0.1354,
304
+ "step": 205
305
+ },
306
+ {
307
+ "epoch": 8.75,
308
+ "grad_norm": 4.03125,
309
+ "learning_rate": 8.157894736842106e-06,
310
+ "loss": 0.1321,
311
+ "step": 210
312
+ },
313
+ {
314
+ "epoch": 8.958333333333334,
315
+ "grad_norm": 3.390625,
316
+ "learning_rate": 6.842105263157896e-06,
317
+ "loss": 0.1351,
318
+ "step": 215
319
+ }
320
+ ],
321
+ "logging_steps": 5,
322
+ "max_steps": 240,
323
+ "num_input_tokens_seen": 0,
324
+ "num_train_epochs": 10,
325
+ "save_steps": 500,
326
+ "stateful_callbacks": {
327
+ "TrainerControl": {
328
+ "args": {
329
+ "should_epoch_stop": false,
330
+ "should_evaluate": false,
331
+ "should_log": false,
332
+ "should_save": true,
333
+ "should_training_stop": false
334
+ },
335
+ "attributes": {}
336
+ }
337
+ },
338
+ "total_flos": 572368078503936.0,
339
+ "train_batch_size": 4,
340
+ "trial_name": null,
341
+ "trial_params": null
342
+ }
checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57dd6ee21e08885a384c25251b744c7c77828bafa879ca11b2116f30c68c8c3
3
+ size 5713
checkpoint-216/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/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
+ }
checkpoint-240/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 %}
checkpoint-240/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
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": 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": 151645,
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": "4.56.1",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
checkpoint-240/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151645,
8
+ "temperature": 0.6,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.56.1"
12
+ }
checkpoint-240/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a9ae479f1f4509d12d547b8b5eb3c5b6b031dd7ee66f9d0ac74552dec87032
3
+ size 1192135096
checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fbf37852ca0d8ce03c282d4e8fcf78b26926841dcc48c3663eb133a6ca4ad3
3
+ size 2384451723
checkpoint-240/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527276764335e03ea915d0573a9ad59eeff630ed1d94d41b99d98ba5a5610338
3
+ size 14391
checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb018bb4914c132e9aa57195da03a5a6ab62a5c65ffe18011d8098bbd5e83f7
3
+ size 1465
checkpoint-240/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
checkpoint-240/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
checkpoint-240/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": "<|im_end|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 240,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.041666666666666664,
14
+ "grad_norm": 73.5,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.9287,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.20833333333333334,
21
+ "grad_norm": 80.5,
22
+ "learning_rate": 4.000000000000001e-06,
23
+ "loss": 3.994,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.4166666666666667,
28
+ "grad_norm": 63.75,
29
+ "learning_rate": 9e-06,
30
+ "loss": 3.6819,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.625,
35
+ "grad_norm": 49.25,
36
+ "learning_rate": 1.4000000000000001e-05,
37
+ "loss": 2.5702,
38
+ "step": 15
39
+ },
40
+ {
41
+ "epoch": 0.8333333333333334,
42
+ "grad_norm": 48.75,
43
+ "learning_rate": 1.9e-05,
44
+ "loss": 1.4286,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 1.0416666666666667,
49
+ "grad_norm": 11.3125,
50
+ "learning_rate": 2.4e-05,
51
+ "loss": 0.7957,
52
+ "step": 25
53
+ },
54
+ {
55
+ "epoch": 1.25,
56
+ "grad_norm": 9.0625,
57
+ "learning_rate": 2.9e-05,
58
+ "loss": 0.7432,
59
+ "step": 30
60
+ },
61
+ {
62
+ "epoch": 1.4583333333333333,
63
+ "grad_norm": 16.5,
64
+ "learning_rate": 3.4000000000000007e-05,
65
+ "loss": 0.6508,
66
+ "step": 35
67
+ },
68
+ {
69
+ "epoch": 1.6666666666666665,
70
+ "grad_norm": 12.75,
71
+ "learning_rate": 3.9000000000000006e-05,
72
+ "loss": 0.591,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 1.875,
77
+ "grad_norm": 6.59375,
78
+ "learning_rate": 4.4000000000000006e-05,
79
+ "loss": 0.6682,
80
+ "step": 45
81
+ },
82
+ {
83
+ "epoch": 2.0833333333333335,
84
+ "grad_norm": 11.1875,
85
+ "learning_rate": 4.9e-05,
86
+ "loss": 0.4391,
87
+ "step": 50
88
+ },
89
+ {
90
+ "epoch": 2.2916666666666665,
91
+ "grad_norm": 9.5,
92
+ "learning_rate": 4.8947368421052635e-05,
93
+ "loss": 0.3461,
94
+ "step": 55
95
+ },
96
+ {
97
+ "epoch": 2.5,
98
+ "grad_norm": 15.5,
99
+ "learning_rate": 4.7631578947368424e-05,
100
+ "loss": 0.4083,
101
+ "step": 60
102
+ },
103
+ {
104
+ "epoch": 2.7083333333333335,
105
+ "grad_norm": 12.0,
106
+ "learning_rate": 4.6315789473684214e-05,
107
+ "loss": 0.377,
108
+ "step": 65
109
+ },
110
+ {
111
+ "epoch": 2.9166666666666665,
112
+ "grad_norm": 10.0625,
113
+ "learning_rate": 4.5e-05,
114
+ "loss": 0.3861,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 3.125,
119
+ "grad_norm": 6.78125,
120
+ "learning_rate": 4.368421052631579e-05,
121
+ "loss": 0.3271,
122
+ "step": 75
123
+ },
124
+ {
125
+ "epoch": 3.3333333333333335,
126
+ "grad_norm": 5.125,
127
+ "learning_rate": 4.236842105263158e-05,
128
+ "loss": 0.2295,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 3.5416666666666665,
133
+ "grad_norm": 5.75,
134
+ "learning_rate": 4.105263157894737e-05,
135
+ "loss": 0.2661,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 3.75,
140
+ "grad_norm": 10.9375,
141
+ "learning_rate": 3.973684210526316e-05,
142
+ "loss": 0.2583,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 3.9583333333333335,
147
+ "grad_norm": 10.0625,
148
+ "learning_rate": 3.842105263157895e-05,
149
+ "loss": 0.2631,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 4.166666666666667,
154
+ "grad_norm": 6.4375,
155
+ "learning_rate": 3.710526315789474e-05,
156
+ "loss": 0.1991,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 4.375,
161
+ "grad_norm": 6.71875,
162
+ "learning_rate": 3.578947368421053e-05,
163
+ "loss": 0.1937,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 4.583333333333333,
168
+ "grad_norm": 5.0,
169
+ "learning_rate": 3.447368421052632e-05,
170
+ "loss": 0.1894,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 4.791666666666667,
175
+ "grad_norm": 10.8125,
176
+ "learning_rate": 3.3157894736842106e-05,
177
+ "loss": 0.2233,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 5.0,
182
+ "grad_norm": 6.53125,
183
+ "learning_rate": 3.1842105263157895e-05,
184
+ "loss": 0.2006,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 5.208333333333333,
189
+ "grad_norm": 4.59375,
190
+ "learning_rate": 3.0526315789473684e-05,
191
+ "loss": 0.1657,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 5.416666666666667,
196
+ "grad_norm": 4.65625,
197
+ "learning_rate": 2.9210526315789477e-05,
198
+ "loss": 0.1937,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 5.625,
203
+ "grad_norm": 7.90625,
204
+ "learning_rate": 2.7894736842105263e-05,
205
+ "loss": 0.1801,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 5.833333333333333,
210
+ "grad_norm": 3.984375,
211
+ "learning_rate": 2.6578947368421052e-05,
212
+ "loss": 0.1704,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 6.041666666666667,
217
+ "grad_norm": 3.8125,
218
+ "learning_rate": 2.5263157894736845e-05,
219
+ "loss": 0.168,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 6.25,
224
+ "grad_norm": 5.15625,
225
+ "learning_rate": 2.394736842105263e-05,
226
+ "loss": 0.1395,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 6.458333333333333,
231
+ "grad_norm": 4.25,
232
+ "learning_rate": 2.2631578947368423e-05,
233
+ "loss": 0.1426,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 6.666666666666667,
238
+ "grad_norm": 4.8125,
239
+ "learning_rate": 2.1315789473684212e-05,
240
+ "loss": 0.1591,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 6.875,
245
+ "grad_norm": 5.3125,
246
+ "learning_rate": 2e-05,
247
+ "loss": 0.1656,
248
+ "step": 165
249
+ },
250
+ {
251
+ "epoch": 7.083333333333333,
252
+ "grad_norm": 3.53125,
253
+ "learning_rate": 1.868421052631579e-05,
254
+ "loss": 0.1505,
255
+ "step": 170
256
+ },
257
+ {
258
+ "epoch": 7.291666666666667,
259
+ "grad_norm": 4.875,
260
+ "learning_rate": 1.736842105263158e-05,
261
+ "loss": 0.1356,
262
+ "step": 175
263
+ },
264
+ {
265
+ "epoch": 7.5,
266
+ "grad_norm": 3.890625,
267
+ "learning_rate": 1.605263157894737e-05,
268
+ "loss": 0.1359,
269
+ "step": 180
270
+ },
271
+ {
272
+ "epoch": 7.708333333333333,
273
+ "grad_norm": 3.59375,
274
+ "learning_rate": 1.4736842105263157e-05,
275
+ "loss": 0.1444,
276
+ "step": 185
277
+ },
278
+ {
279
+ "epoch": 7.916666666666667,
280
+ "grad_norm": 4.5,
281
+ "learning_rate": 1.3421052631578948e-05,
282
+ "loss": 0.1446,
283
+ "step": 190
284
+ },
285
+ {
286
+ "epoch": 8.125,
287
+ "grad_norm": 3.375,
288
+ "learning_rate": 1.2105263157894737e-05,
289
+ "loss": 0.1381,
290
+ "step": 195
291
+ },
292
+ {
293
+ "epoch": 8.333333333333334,
294
+ "grad_norm": 4.03125,
295
+ "learning_rate": 1.0789473684210526e-05,
296
+ "loss": 0.1372,
297
+ "step": 200
298
+ },
299
+ {
300
+ "epoch": 8.541666666666666,
301
+ "grad_norm": 3.921875,
302
+ "learning_rate": 9.473684210526317e-06,
303
+ "loss": 0.1354,
304
+ "step": 205
305
+ },
306
+ {
307
+ "epoch": 8.75,
308
+ "grad_norm": 4.03125,
309
+ "learning_rate": 8.157894736842106e-06,
310
+ "loss": 0.1321,
311
+ "step": 210
312
+ },
313
+ {
314
+ "epoch": 8.958333333333334,
315
+ "grad_norm": 3.390625,
316
+ "learning_rate": 6.842105263157896e-06,
317
+ "loss": 0.1351,
318
+ "step": 215
319
+ },
320
+ {
321
+ "epoch": 9.166666666666666,
322
+ "grad_norm": 3.96875,
323
+ "learning_rate": 5.526315789473684e-06,
324
+ "loss": 0.1331,
325
+ "step": 220
326
+ },
327
+ {
328
+ "epoch": 9.375,
329
+ "grad_norm": 3.84375,
330
+ "learning_rate": 4.210526315789474e-06,
331
+ "loss": 0.129,
332
+ "step": 225
333
+ },
334
+ {
335
+ "epoch": 9.583333333333334,
336
+ "grad_norm": 3.953125,
337
+ "learning_rate": 2.8947368421052634e-06,
338
+ "loss": 0.1285,
339
+ "step": 230
340
+ },
341
+ {
342
+ "epoch": 9.791666666666666,
343
+ "grad_norm": 3.828125,
344
+ "learning_rate": 1.5789473684210528e-06,
345
+ "loss": 0.1367,
346
+ "step": 235
347
+ },
348
+ {
349
+ "epoch": 10.0,
350
+ "grad_norm": 6.5,
351
+ "learning_rate": 2.6315789473684213e-07,
352
+ "loss": 0.1335,
353
+ "step": 240
354
+ }
355
+ ],
356
+ "logging_steps": 5,
357
+ "max_steps": 240,
358
+ "num_input_tokens_seen": 0,
359
+ "num_train_epochs": 10,
360
+ "save_steps": 500,
361
+ "stateful_callbacks": {
362
+ "TrainerControl": {
363
+ "args": {
364
+ "should_epoch_stop": false,
365
+ "should_evaluate": false,
366
+ "should_log": false,
367
+ "should_save": true,
368
+ "should_training_stop": true
369
+ },
370
+ "attributes": {}
371
+ }
372
+ },
373
+ "total_flos": 635964531671040.0,
374
+ "train_batch_size": 4,
375
+ "trial_name": null,
376
+ "trial_params": null
377
+ }
checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57dd6ee21e08885a384c25251b744c7c77828bafa879ca11b2116f30c68c8c3
3
+ size 5713
checkpoint-240/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
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": 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": 151645,
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": "4.56.1",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151645,
8
+ "temperature": 0.6,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.56.1"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a9ae479f1f4509d12d547b8b5eb3c5b6b031dd7ee66f9d0ac74552dec87032
3
+ size 1192135096
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba91f17480d811dcf8acac44c6def8c1268c45461d6f7d99d16779f661226c08
3
+ size 2384451723
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e0be4f448bb33f8b4fa29459a8f8b0c1fba61268187c625e170a5ba0fb9710
3
+ size 14391
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b187bc43043d53c20c13dc7755f997532cdf7f3cb24243135ca8fbbbca7d55
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
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": "<|im_end|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 24,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.041666666666666664,
14
+ "grad_norm": 73.5,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.9287,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.20833333333333334,
21
+ "grad_norm": 80.5,
22
+ "learning_rate": 4.000000000000001e-06,
23
+ "loss": 3.994,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.4166666666666667,
28
+ "grad_norm": 63.75,
29
+ "learning_rate": 9e-06,
30
+ "loss": 3.6819,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.625,
35
+ "grad_norm": 49.25,
36
+ "learning_rate": 1.4000000000000001e-05,
37
+ "loss": 2.5702,
38
+ "step": 15
39
+ },
40
+ {
41
+ "epoch": 0.8333333333333334,
42
+ "grad_norm": 48.75,
43
+ "learning_rate": 1.9e-05,
44
+ "loss": 1.4286,
45
+ "step": 20
46
+ }
47
+ ],
48
+ "logging_steps": 5,
49
+ "max_steps": 240,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 10,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": false
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 63596453167104.0,
66
+ "train_batch_size": 4,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57dd6ee21e08885a384c25251b744c7c77828bafa879ca11b2116f30c68c8c3
3
+ size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff