nililba commited on
Commit
562cd8c
·
verified ·
1 Parent(s): 6d80c69

Upload folder using huggingface_hub

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 +4 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +85 -0
  4. checkpoint-1000/added_tokens.json +28 -0
  5. checkpoint-1000/chat_template.jinja +85 -0
  6. checkpoint-1000/config.json +30 -0
  7. checkpoint-1000/generation_config.json +6 -0
  8. checkpoint-1000/merges.txt +0 -0
  9. checkpoint-1000/optimizer.pt +3 -0
  10. checkpoint-1000/pytorch_model.bin +3 -0
  11. checkpoint-1000/rng_state.pth +3 -0
  12. checkpoint-1000/scheduler.pt +3 -0
  13. checkpoint-1000/special_tokens_map.json +31 -0
  14. checkpoint-1000/tokenizer.json +3 -0
  15. checkpoint-1000/tokenizer_config.json +255 -0
  16. checkpoint-1000/trainer_state.json +734 -0
  17. checkpoint-1000/training_args.bin +3 -0
  18. checkpoint-1000/vocab.json +0 -0
  19. checkpoint-1500/added_tokens.json +28 -0
  20. checkpoint-1500/chat_template.jinja +85 -0
  21. checkpoint-1500/config.json +30 -0
  22. checkpoint-1500/generation_config.json +6 -0
  23. checkpoint-1500/merges.txt +0 -0
  24. checkpoint-1500/optimizer.pt +3 -0
  25. checkpoint-1500/pytorch_model.bin +3 -0
  26. checkpoint-1500/rng_state.pth +3 -0
  27. checkpoint-1500/scheduler.pt +3 -0
  28. checkpoint-1500/special_tokens_map.json +31 -0
  29. checkpoint-1500/tokenizer.json +3 -0
  30. checkpoint-1500/tokenizer_config.json +255 -0
  31. checkpoint-1500/trainer_state.json +1084 -0
  32. checkpoint-1500/training_args.bin +3 -0
  33. checkpoint-1500/vocab.json +0 -0
  34. checkpoint-500/added_tokens.json +28 -0
  35. checkpoint-500/chat_template.jinja +85 -0
  36. checkpoint-500/config.json +30 -0
  37. checkpoint-500/generation_config.json +6 -0
  38. checkpoint-500/merges.txt +0 -0
  39. checkpoint-500/optimizer.pt +3 -0
  40. checkpoint-500/pytorch_model.bin +3 -0
  41. checkpoint-500/rng_state.pth +3 -0
  42. checkpoint-500/scheduler.pt +3 -0
  43. checkpoint-500/special_tokens_map.json +31 -0
  44. checkpoint-500/tokenizer.json +3 -0
  45. checkpoint-500/tokenizer_config.json +255 -0
  46. checkpoint-500/trainer_state.json +384 -0
  47. checkpoint-500/training_args.bin +3 -0
  48. checkpoint-500/vocab.json +0 -0
  49. config.json +30 -0
  50. generation_config.json +6 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ 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 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 %}
checkpoint-1000/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-1000/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 %}
checkpoint-1000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
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
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151669
30
+ }
checkpoint-1000/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": "4.52.3"
6
+ }
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f376e9388dffa8ac3c7eb19a835465d5a4adaa829d02c4fb856b2d23abf337f
3
+ size 4766475646
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36096580cf7f6eaf5715c37ef024b566fc5fe1f813651af2510f6595dc9d7c69
3
+ size 2383210594
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634ee359c8cab3a97758b2a85a761bf0dccbaf59b6eb47e708e07aca4dbf63dc
3
+ size 1064
checkpoint-1000/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
+ }
checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61978ef1e7f4221e8ec52fc8be51c4b8e244de9ded89dd78cba92402ef6d14b2
3
+ size 11423287
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "4689": {
6
+ "content": "END",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "14374": {
14
+ "content": "###",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "151643": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151644": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151645": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151646": {
46
+ "content": "<|object_ref_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151647": {
54
+ "content": "<|object_ref_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151648": {
62
+ "content": "<|box_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151649": {
70
+ "content": "<|box_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151650": {
78
+ "content": "<|quad_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151651": {
86
+ "content": "<|quad_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151652": {
94
+ "content": "<|vision_start|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151653": {
102
+ "content": "<|vision_end|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151654": {
110
+ "content": "<|vision_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151655": {
118
+ "content": "<|image_pad|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151656": {
126
+ "content": "<|video_pad|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "151657": {
134
+ "content": "<tool_call>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151658": {
142
+ "content": "</tool_call>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151659": {
150
+ "content": "<|fim_prefix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151660": {
158
+ "content": "<|fim_middle|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151661": {
166
+ "content": "<|fim_suffix|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151662": {
174
+ "content": "<|fim_pad|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151663": {
182
+ "content": "<|repo_name|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151664": {
190
+ "content": "<|file_sep|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151665": {
198
+ "content": "<tool_response>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151666": {
206
+ "content": "</tool_response>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151667": {
214
+ "content": "<think>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "151668": {
222
+ "content": "</think>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|im_start|>",
232
+ "<|im_end|>",
233
+ "<|object_ref_start|>",
234
+ "<|object_ref_end|>",
235
+ "<|box_start|>",
236
+ "<|box_end|>",
237
+ "<|quad_start|>",
238
+ "<|quad_end|>",
239
+ "<|vision_start|>",
240
+ "<|vision_end|>",
241
+ "<|vision_pad|>",
242
+ "<|image_pad|>",
243
+ "<|video_pad|>"
244
+ ],
245
+ "bos_token": null,
246
+ "clean_up_tokenization_spaces": false,
247
+ "eos_token": "<|endoftext|>",
248
+ "errors": "replace",
249
+ "extra_special_tokens": {},
250
+ "model_max_length": 131072,
251
+ "pad_token": "<|endoftext|>",
252
+ "split_special_tokens": false,
253
+ "tokenizer_class": "Qwen2Tokenizer",
254
+ "unk_token": null
255
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02,
14
+ "grad_norm": 70.61351013183594,
15
+ "learning_rate": 4.97e-05,
16
+ "loss": 4.2158,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04,
21
+ "grad_norm": 73.62928009033203,
22
+ "learning_rate": 4.936666666666667e-05,
23
+ "loss": 1.6566,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.06,
28
+ "grad_norm": 108.96935272216797,
29
+ "learning_rate": 4.903333333333334e-05,
30
+ "loss": 1.7678,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.08,
35
+ "grad_norm": 61.242454528808594,
36
+ "learning_rate": 4.87e-05,
37
+ "loss": 1.5158,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "grad_norm": 131.24546813964844,
43
+ "learning_rate": 4.836666666666667e-05,
44
+ "loss": 2.0604,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "grad_norm": 40.62075424194336,
50
+ "learning_rate": 4.803333333333333e-05,
51
+ "loss": 1.4759,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.14,
56
+ "grad_norm": 68.39600372314453,
57
+ "learning_rate": 4.77e-05,
58
+ "loss": 1.6714,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.16,
63
+ "grad_norm": 65.06390380859375,
64
+ "learning_rate": 4.736666666666667e-05,
65
+ "loss": 1.3931,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.18,
70
+ "grad_norm": 91.259765625,
71
+ "learning_rate": 4.7033333333333336e-05,
72
+ "loss": 1.4381,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.2,
77
+ "grad_norm": 114.90811920166016,
78
+ "learning_rate": 4.6700000000000003e-05,
79
+ "loss": 1.5654,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "grad_norm": 54.1782341003418,
85
+ "learning_rate": 4.636666666666667e-05,
86
+ "loss": 2.0443,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.24,
91
+ "grad_norm": 71.6166763305664,
92
+ "learning_rate": 4.603333333333333e-05,
93
+ "loss": 1.6087,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.26,
98
+ "grad_norm": 74.20275115966797,
99
+ "learning_rate": 4.5700000000000006e-05,
100
+ "loss": 1.6605,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.28,
105
+ "grad_norm": 77.95655059814453,
106
+ "learning_rate": 4.536666666666667e-05,
107
+ "loss": 1.5884,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.3,
112
+ "grad_norm": 47.96751403808594,
113
+ "learning_rate": 4.5033333333333335e-05,
114
+ "loss": 2.4234,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.32,
119
+ "grad_norm": 114.87418365478516,
120
+ "learning_rate": 4.47e-05,
121
+ "loss": 1.8465,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.34,
126
+ "grad_norm": 64.47191619873047,
127
+ "learning_rate": 4.436666666666667e-05,
128
+ "loss": 1.6719,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.36,
133
+ "grad_norm": 63.627681732177734,
134
+ "learning_rate": 4.403333333333334e-05,
135
+ "loss": 1.7967,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.38,
140
+ "grad_norm": 30.865203857421875,
141
+ "learning_rate": 4.3700000000000005e-05,
142
+ "loss": 1.5015,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4,
147
+ "grad_norm": 12.00632095336914,
148
+ "learning_rate": 4.3366666666666666e-05,
149
+ "loss": 1.6298,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.42,
154
+ "grad_norm": 83.26287841796875,
155
+ "learning_rate": 4.3033333333333334e-05,
156
+ "loss": 1.9531,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.44,
161
+ "grad_norm": 43.74462127685547,
162
+ "learning_rate": 4.27e-05,
163
+ "loss": 1.4834,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.46,
168
+ "grad_norm": 41.31574249267578,
169
+ "learning_rate": 4.236666666666667e-05,
170
+ "loss": 1.8548,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.48,
175
+ "grad_norm": 66.2603759765625,
176
+ "learning_rate": 4.2033333333333336e-05,
177
+ "loss": 1.4464,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5,
182
+ "grad_norm": 18.777666091918945,
183
+ "learning_rate": 4.17e-05,
184
+ "loss": 1.3379,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.52,
189
+ "grad_norm": 40.735050201416016,
190
+ "learning_rate": 4.136666666666667e-05,
191
+ "loss": 1.4589,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.54,
196
+ "grad_norm": 89.99899291992188,
197
+ "learning_rate": 4.103333333333333e-05,
198
+ "loss": 1.6462,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.56,
203
+ "grad_norm": 26.000844955444336,
204
+ "learning_rate": 4.07e-05,
205
+ "loss": 1.5459,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.58,
210
+ "grad_norm": 72.94963836669922,
211
+ "learning_rate": 4.036666666666667e-05,
212
+ "loss": 1.3914,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.6,
217
+ "grad_norm": 36.23366928100586,
218
+ "learning_rate": 4.0033333333333335e-05,
219
+ "loss": 1.7466,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.62,
224
+ "grad_norm": 37.300697326660156,
225
+ "learning_rate": 3.97e-05,
226
+ "loss": 1.6585,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.64,
231
+ "grad_norm": 48.120933532714844,
232
+ "learning_rate": 3.936666666666667e-05,
233
+ "loss": 1.7376,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.66,
238
+ "grad_norm": 41.503997802734375,
239
+ "learning_rate": 3.903333333333333e-05,
240
+ "loss": 1.4676,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.68,
245
+ "grad_norm": 13.966187477111816,
246
+ "learning_rate": 3.8700000000000006e-05,
247
+ "loss": 1.4801,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7,
252
+ "grad_norm": 55.511837005615234,
253
+ "learning_rate": 3.8366666666666666e-05,
254
+ "loss": 1.9258,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.72,
259
+ "grad_norm": 46.56684494018555,
260
+ "learning_rate": 3.803333333333334e-05,
261
+ "loss": 1.4785,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.74,
266
+ "grad_norm": 51.37467575073242,
267
+ "learning_rate": 3.77e-05,
268
+ "loss": 1.3089,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.76,
273
+ "grad_norm": 63.84782409667969,
274
+ "learning_rate": 3.736666666666667e-05,
275
+ "loss": 2.0258,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.78,
280
+ "grad_norm": 54.59080123901367,
281
+ "learning_rate": 3.703333333333334e-05,
282
+ "loss": 1.4266,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.8,
287
+ "grad_norm": 27.919336318969727,
288
+ "learning_rate": 3.6700000000000004e-05,
289
+ "loss": 1.8133,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.82,
294
+ "grad_norm": 43.32358169555664,
295
+ "learning_rate": 3.636666666666667e-05,
296
+ "loss": 1.4812,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.84,
301
+ "grad_norm": 33.77085494995117,
302
+ "learning_rate": 3.603333333333333e-05,
303
+ "loss": 1.4177,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.86,
308
+ "grad_norm": 53.14788055419922,
309
+ "learning_rate": 3.57e-05,
310
+ "loss": 1.4277,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.88,
315
+ "grad_norm": 43.82292175292969,
316
+ "learning_rate": 3.536666666666667e-05,
317
+ "loss": 1.3996,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.9,
322
+ "grad_norm": 74.1073989868164,
323
+ "learning_rate": 3.5033333333333336e-05,
324
+ "loss": 1.4942,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.92,
329
+ "grad_norm": 67.50479888916016,
330
+ "learning_rate": 3.4699999999999996e-05,
331
+ "loss": 1.4433,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.94,
336
+ "grad_norm": 44.51863479614258,
337
+ "learning_rate": 3.436666666666667e-05,
338
+ "loss": 1.3934,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.96,
343
+ "grad_norm": 42.15129470825195,
344
+ "learning_rate": 3.403333333333333e-05,
345
+ "loss": 1.4448,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.98,
350
+ "grad_norm": 59.780059814453125,
351
+ "learning_rate": 3.3700000000000006e-05,
352
+ "loss": 1.25,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.0,
357
+ "grad_norm": 56.6463623046875,
358
+ "learning_rate": 3.336666666666667e-05,
359
+ "loss": 1.3204,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.02,
364
+ "grad_norm": 42.17279815673828,
365
+ "learning_rate": 3.3033333333333334e-05,
366
+ "loss": 1.875,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.04,
371
+ "grad_norm": 53.357017517089844,
372
+ "learning_rate": 3.27e-05,
373
+ "loss": 1.3936,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.06,
378
+ "grad_norm": 33.11314392089844,
379
+ "learning_rate": 3.236666666666667e-05,
380
+ "loss": 1.5159,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.08,
385
+ "grad_norm": 39.53742980957031,
386
+ "learning_rate": 3.203333333333334e-05,
387
+ "loss": 1.3661,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.1,
392
+ "grad_norm": 37.94576644897461,
393
+ "learning_rate": 3.1700000000000005e-05,
394
+ "loss": 1.3893,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.12,
399
+ "grad_norm": 40.539207458496094,
400
+ "learning_rate": 3.1366666666666666e-05,
401
+ "loss": 1.4794,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.1400000000000001,
406
+ "grad_norm": 34.75075912475586,
407
+ "learning_rate": 3.103333333333333e-05,
408
+ "loss": 1.0972,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.16,
413
+ "grad_norm": 52.29777526855469,
414
+ "learning_rate": 3.07e-05,
415
+ "loss": 1.9438,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.18,
420
+ "grad_norm": 63.562442779541016,
421
+ "learning_rate": 3.0366666666666665e-05,
422
+ "loss": 1.4552,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.2,
427
+ "grad_norm": 36.03409194946289,
428
+ "learning_rate": 3.0033333333333336e-05,
429
+ "loss": 1.4451,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.22,
434
+ "grad_norm": 35.75303268432617,
435
+ "learning_rate": 2.97e-05,
436
+ "loss": 1.3203,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.24,
441
+ "grad_norm": 41.28643798828125,
442
+ "learning_rate": 2.936666666666667e-05,
443
+ "loss": 1.3898,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.26,
448
+ "grad_norm": 42.44171905517578,
449
+ "learning_rate": 2.9033333333333335e-05,
450
+ "loss": 1.4461,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.28,
455
+ "grad_norm": 33.191993713378906,
456
+ "learning_rate": 2.87e-05,
457
+ "loss": 1.5485,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.3,
462
+ "grad_norm": 35.58934020996094,
463
+ "learning_rate": 2.836666666666667e-05,
464
+ "loss": 1.4225,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.32,
469
+ "grad_norm": 38.515438079833984,
470
+ "learning_rate": 2.8033333333333335e-05,
471
+ "loss": 1.4034,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.34,
476
+ "grad_norm": 42.85960006713867,
477
+ "learning_rate": 2.7700000000000002e-05,
478
+ "loss": 1.3505,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.3599999999999999,
483
+ "grad_norm": 83.25682067871094,
484
+ "learning_rate": 2.7366666666666667e-05,
485
+ "loss": 1.35,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.38,
490
+ "grad_norm": 49.6702880859375,
491
+ "learning_rate": 2.7033333333333334e-05,
492
+ "loss": 1.8784,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.4,
497
+ "grad_norm": 51.177093505859375,
498
+ "learning_rate": 2.6700000000000002e-05,
499
+ "loss": 1.3637,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.42,
504
+ "grad_norm": 40.318206787109375,
505
+ "learning_rate": 2.6366666666666666e-05,
506
+ "loss": 1.3539,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.44,
511
+ "grad_norm": 45.05327224731445,
512
+ "learning_rate": 2.6033333333333337e-05,
513
+ "loss": 1.5676,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.46,
518
+ "grad_norm": 28.770118713378906,
519
+ "learning_rate": 2.57e-05,
520
+ "loss": 1.342,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.48,
525
+ "grad_norm": 29.81730842590332,
526
+ "learning_rate": 2.5366666666666665e-05,
527
+ "loss": 1.3532,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.5,
532
+ "grad_norm": 48.3309440612793,
533
+ "learning_rate": 2.5033333333333336e-05,
534
+ "loss": 1.4733,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.52,
539
+ "grad_norm": 70.29447937011719,
540
+ "learning_rate": 2.47e-05,
541
+ "loss": 1.457,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.54,
546
+ "grad_norm": 37.76487350463867,
547
+ "learning_rate": 2.4366666666666668e-05,
548
+ "loss": 1.4183,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.56,
553
+ "grad_norm": 33.34684753417969,
554
+ "learning_rate": 2.4033333333333336e-05,
555
+ "loss": 1.4226,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.58,
560
+ "grad_norm": 32.89299392700195,
561
+ "learning_rate": 2.37e-05,
562
+ "loss": 1.3785,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.6,
567
+ "grad_norm": 56.79878616333008,
568
+ "learning_rate": 2.3366666666666668e-05,
569
+ "loss": 1.4579,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.62,
574
+ "grad_norm": 32.62324523925781,
575
+ "learning_rate": 2.3033333333333335e-05,
576
+ "loss": 1.4094,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.6400000000000001,
581
+ "grad_norm": 39.20806121826172,
582
+ "learning_rate": 2.2700000000000003e-05,
583
+ "loss": 1.4686,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.6600000000000001,
588
+ "grad_norm": 31.847000122070312,
589
+ "learning_rate": 2.236666666666667e-05,
590
+ "loss": 1.3953,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.6800000000000002,
595
+ "grad_norm": 40.128971099853516,
596
+ "learning_rate": 2.2033333333333335e-05,
597
+ "loss": 1.4658,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.7,
602
+ "grad_norm": 36.050846099853516,
603
+ "learning_rate": 2.1700000000000002e-05,
604
+ "loss": 1.6216,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.72,
609
+ "grad_norm": 64.60285186767578,
610
+ "learning_rate": 2.1366666666666667e-05,
611
+ "loss": 1.4508,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.74,
616
+ "grad_norm": 65.16170501708984,
617
+ "learning_rate": 2.1033333333333334e-05,
618
+ "loss": 1.4214,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.76,
623
+ "grad_norm": 35.84981155395508,
624
+ "learning_rate": 2.07e-05,
625
+ "loss": 1.3662,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.78,
630
+ "grad_norm": 40.32749557495117,
631
+ "learning_rate": 2.0366666666666666e-05,
632
+ "loss": 1.4159,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.8,
637
+ "grad_norm": 37.723114013671875,
638
+ "learning_rate": 2.0033333333333334e-05,
639
+ "loss": 1.3919,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.8199999999999998,
644
+ "grad_norm": 35.627803802490234,
645
+ "learning_rate": 1.97e-05,
646
+ "loss": 1.4407,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.8399999999999999,
651
+ "grad_norm": 34.74470138549805,
652
+ "learning_rate": 1.9366666666666665e-05,
653
+ "loss": 1.3455,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.8599999999999999,
658
+ "grad_norm": 30.108226776123047,
659
+ "learning_rate": 1.9033333333333333e-05,
660
+ "loss": 1.4827,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.88,
665
+ "grad_norm": 72.5284652709961,
666
+ "learning_rate": 1.87e-05,
667
+ "loss": 1.38,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.9,
672
+ "grad_norm": 40.3804817199707,
673
+ "learning_rate": 1.8366666666666668e-05,
674
+ "loss": 1.3436,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.92,
679
+ "grad_norm": 48.87946701049805,
680
+ "learning_rate": 1.8033333333333336e-05,
681
+ "loss": 1.369,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.94,
686
+ "grad_norm": 50.297794342041016,
687
+ "learning_rate": 1.77e-05,
688
+ "loss": 1.3892,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.96,
693
+ "grad_norm": 43.455909729003906,
694
+ "learning_rate": 1.7366666666666668e-05,
695
+ "loss": 1.5923,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.98,
700
+ "grad_norm": 26.250675201416016,
701
+ "learning_rate": 1.7033333333333335e-05,
702
+ "loss": 1.4009,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 2.0,
707
+ "grad_norm": 30.42631721496582,
708
+ "learning_rate": 1.6700000000000003e-05,
709
+ "loss": 1.3333,
710
+ "step": 1000
711
+ }
712
+ ],
713
+ "logging_steps": 10,
714
+ "max_steps": 1500,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 3,
717
+ "save_steps": 500,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 5412464099328000.0,
731
+ "train_batch_size": 2,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2ae8ab9de045c8c8f69e621a036f39a4c6b3ea196155bf70db96ba8d5df4d0
3
+ size 5304
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/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-1500/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 %}
checkpoint-1500/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
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
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151669
30
+ }
checkpoint-1500/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": "4.52.3"
6
+ }
checkpoint-1500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cacce21305fc014c2d14f70b85bfa7087173884109464296b03a9a92b4cbfeaf
3
+ size 4766475646
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978c717113824b1a54f07fae169b4c1574db38c7c0a41811fc3aa416f322524e
3
+ size 2383210594
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7592e941fa77449d9f7015724b6a3901e596c11e155596880b96def1f284283
3
+ size 1064
checkpoint-1500/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
+ }
checkpoint-1500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61978ef1e7f4221e8ec52fc8be51c4b8e244de9ded89dd78cba92402ef6d14b2
3
+ size 11423287
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "4689": {
6
+ "content": "END",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "14374": {
14
+ "content": "###",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "151643": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151644": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151645": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151646": {
46
+ "content": "<|object_ref_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151647": {
54
+ "content": "<|object_ref_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151648": {
62
+ "content": "<|box_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151649": {
70
+ "content": "<|box_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151650": {
78
+ "content": "<|quad_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151651": {
86
+ "content": "<|quad_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151652": {
94
+ "content": "<|vision_start|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151653": {
102
+ "content": "<|vision_end|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151654": {
110
+ "content": "<|vision_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151655": {
118
+ "content": "<|image_pad|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151656": {
126
+ "content": "<|video_pad|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "151657": {
134
+ "content": "<tool_call>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151658": {
142
+ "content": "</tool_call>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151659": {
150
+ "content": "<|fim_prefix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151660": {
158
+ "content": "<|fim_middle|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151661": {
166
+ "content": "<|fim_suffix|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151662": {
174
+ "content": "<|fim_pad|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151663": {
182
+ "content": "<|repo_name|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151664": {
190
+ "content": "<|file_sep|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151665": {
198
+ "content": "<tool_response>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151666": {
206
+ "content": "</tool_response>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151667": {
214
+ "content": "<think>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "151668": {
222
+ "content": "</think>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|im_start|>",
232
+ "<|im_end|>",
233
+ "<|object_ref_start|>",
234
+ "<|object_ref_end|>",
235
+ "<|box_start|>",
236
+ "<|box_end|>",
237
+ "<|quad_start|>",
238
+ "<|quad_end|>",
239
+ "<|vision_start|>",
240
+ "<|vision_end|>",
241
+ "<|vision_pad|>",
242
+ "<|image_pad|>",
243
+ "<|video_pad|>"
244
+ ],
245
+ "bos_token": null,
246
+ "clean_up_tokenization_spaces": false,
247
+ "eos_token": "<|endoftext|>",
248
+ "errors": "replace",
249
+ "extra_special_tokens": {},
250
+ "model_max_length": 131072,
251
+ "pad_token": "<|endoftext|>",
252
+ "split_special_tokens": false,
253
+ "tokenizer_class": "Qwen2Tokenizer",
254
+ "unk_token": null
255
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,1084 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02,
14
+ "grad_norm": 70.61351013183594,
15
+ "learning_rate": 4.97e-05,
16
+ "loss": 4.2158,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04,
21
+ "grad_norm": 73.62928009033203,
22
+ "learning_rate": 4.936666666666667e-05,
23
+ "loss": 1.6566,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.06,
28
+ "grad_norm": 108.96935272216797,
29
+ "learning_rate": 4.903333333333334e-05,
30
+ "loss": 1.7678,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.08,
35
+ "grad_norm": 61.242454528808594,
36
+ "learning_rate": 4.87e-05,
37
+ "loss": 1.5158,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "grad_norm": 131.24546813964844,
43
+ "learning_rate": 4.836666666666667e-05,
44
+ "loss": 2.0604,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "grad_norm": 40.62075424194336,
50
+ "learning_rate": 4.803333333333333e-05,
51
+ "loss": 1.4759,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.14,
56
+ "grad_norm": 68.39600372314453,
57
+ "learning_rate": 4.77e-05,
58
+ "loss": 1.6714,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.16,
63
+ "grad_norm": 65.06390380859375,
64
+ "learning_rate": 4.736666666666667e-05,
65
+ "loss": 1.3931,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.18,
70
+ "grad_norm": 91.259765625,
71
+ "learning_rate": 4.7033333333333336e-05,
72
+ "loss": 1.4381,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.2,
77
+ "grad_norm": 114.90811920166016,
78
+ "learning_rate": 4.6700000000000003e-05,
79
+ "loss": 1.5654,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "grad_norm": 54.1782341003418,
85
+ "learning_rate": 4.636666666666667e-05,
86
+ "loss": 2.0443,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.24,
91
+ "grad_norm": 71.6166763305664,
92
+ "learning_rate": 4.603333333333333e-05,
93
+ "loss": 1.6087,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.26,
98
+ "grad_norm": 74.20275115966797,
99
+ "learning_rate": 4.5700000000000006e-05,
100
+ "loss": 1.6605,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.28,
105
+ "grad_norm": 77.95655059814453,
106
+ "learning_rate": 4.536666666666667e-05,
107
+ "loss": 1.5884,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.3,
112
+ "grad_norm": 47.96751403808594,
113
+ "learning_rate": 4.5033333333333335e-05,
114
+ "loss": 2.4234,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.32,
119
+ "grad_norm": 114.87418365478516,
120
+ "learning_rate": 4.47e-05,
121
+ "loss": 1.8465,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.34,
126
+ "grad_norm": 64.47191619873047,
127
+ "learning_rate": 4.436666666666667e-05,
128
+ "loss": 1.6719,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.36,
133
+ "grad_norm": 63.627681732177734,
134
+ "learning_rate": 4.403333333333334e-05,
135
+ "loss": 1.7967,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.38,
140
+ "grad_norm": 30.865203857421875,
141
+ "learning_rate": 4.3700000000000005e-05,
142
+ "loss": 1.5015,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4,
147
+ "grad_norm": 12.00632095336914,
148
+ "learning_rate": 4.3366666666666666e-05,
149
+ "loss": 1.6298,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.42,
154
+ "grad_norm": 83.26287841796875,
155
+ "learning_rate": 4.3033333333333334e-05,
156
+ "loss": 1.9531,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.44,
161
+ "grad_norm": 43.74462127685547,
162
+ "learning_rate": 4.27e-05,
163
+ "loss": 1.4834,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.46,
168
+ "grad_norm": 41.31574249267578,
169
+ "learning_rate": 4.236666666666667e-05,
170
+ "loss": 1.8548,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.48,
175
+ "grad_norm": 66.2603759765625,
176
+ "learning_rate": 4.2033333333333336e-05,
177
+ "loss": 1.4464,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5,
182
+ "grad_norm": 18.777666091918945,
183
+ "learning_rate": 4.17e-05,
184
+ "loss": 1.3379,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.52,
189
+ "grad_norm": 40.735050201416016,
190
+ "learning_rate": 4.136666666666667e-05,
191
+ "loss": 1.4589,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.54,
196
+ "grad_norm": 89.99899291992188,
197
+ "learning_rate": 4.103333333333333e-05,
198
+ "loss": 1.6462,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.56,
203
+ "grad_norm": 26.000844955444336,
204
+ "learning_rate": 4.07e-05,
205
+ "loss": 1.5459,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.58,
210
+ "grad_norm": 72.94963836669922,
211
+ "learning_rate": 4.036666666666667e-05,
212
+ "loss": 1.3914,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.6,
217
+ "grad_norm": 36.23366928100586,
218
+ "learning_rate": 4.0033333333333335e-05,
219
+ "loss": 1.7466,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.62,
224
+ "grad_norm": 37.300697326660156,
225
+ "learning_rate": 3.97e-05,
226
+ "loss": 1.6585,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.64,
231
+ "grad_norm": 48.120933532714844,
232
+ "learning_rate": 3.936666666666667e-05,
233
+ "loss": 1.7376,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.66,
238
+ "grad_norm": 41.503997802734375,
239
+ "learning_rate": 3.903333333333333e-05,
240
+ "loss": 1.4676,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.68,
245
+ "grad_norm": 13.966187477111816,
246
+ "learning_rate": 3.8700000000000006e-05,
247
+ "loss": 1.4801,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7,
252
+ "grad_norm": 55.511837005615234,
253
+ "learning_rate": 3.8366666666666666e-05,
254
+ "loss": 1.9258,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.72,
259
+ "grad_norm": 46.56684494018555,
260
+ "learning_rate": 3.803333333333334e-05,
261
+ "loss": 1.4785,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.74,
266
+ "grad_norm": 51.37467575073242,
267
+ "learning_rate": 3.77e-05,
268
+ "loss": 1.3089,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.76,
273
+ "grad_norm": 63.84782409667969,
274
+ "learning_rate": 3.736666666666667e-05,
275
+ "loss": 2.0258,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.78,
280
+ "grad_norm": 54.59080123901367,
281
+ "learning_rate": 3.703333333333334e-05,
282
+ "loss": 1.4266,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.8,
287
+ "grad_norm": 27.919336318969727,
288
+ "learning_rate": 3.6700000000000004e-05,
289
+ "loss": 1.8133,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.82,
294
+ "grad_norm": 43.32358169555664,
295
+ "learning_rate": 3.636666666666667e-05,
296
+ "loss": 1.4812,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.84,
301
+ "grad_norm": 33.77085494995117,
302
+ "learning_rate": 3.603333333333333e-05,
303
+ "loss": 1.4177,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.86,
308
+ "grad_norm": 53.14788055419922,
309
+ "learning_rate": 3.57e-05,
310
+ "loss": 1.4277,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.88,
315
+ "grad_norm": 43.82292175292969,
316
+ "learning_rate": 3.536666666666667e-05,
317
+ "loss": 1.3996,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.9,
322
+ "grad_norm": 74.1073989868164,
323
+ "learning_rate": 3.5033333333333336e-05,
324
+ "loss": 1.4942,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.92,
329
+ "grad_norm": 67.50479888916016,
330
+ "learning_rate": 3.4699999999999996e-05,
331
+ "loss": 1.4433,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.94,
336
+ "grad_norm": 44.51863479614258,
337
+ "learning_rate": 3.436666666666667e-05,
338
+ "loss": 1.3934,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.96,
343
+ "grad_norm": 42.15129470825195,
344
+ "learning_rate": 3.403333333333333e-05,
345
+ "loss": 1.4448,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.98,
350
+ "grad_norm": 59.780059814453125,
351
+ "learning_rate": 3.3700000000000006e-05,
352
+ "loss": 1.25,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.0,
357
+ "grad_norm": 56.6463623046875,
358
+ "learning_rate": 3.336666666666667e-05,
359
+ "loss": 1.3204,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.02,
364
+ "grad_norm": 42.17279815673828,
365
+ "learning_rate": 3.3033333333333334e-05,
366
+ "loss": 1.875,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.04,
371
+ "grad_norm": 53.357017517089844,
372
+ "learning_rate": 3.27e-05,
373
+ "loss": 1.3936,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.06,
378
+ "grad_norm": 33.11314392089844,
379
+ "learning_rate": 3.236666666666667e-05,
380
+ "loss": 1.5159,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.08,
385
+ "grad_norm": 39.53742980957031,
386
+ "learning_rate": 3.203333333333334e-05,
387
+ "loss": 1.3661,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.1,
392
+ "grad_norm": 37.94576644897461,
393
+ "learning_rate": 3.1700000000000005e-05,
394
+ "loss": 1.3893,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.12,
399
+ "grad_norm": 40.539207458496094,
400
+ "learning_rate": 3.1366666666666666e-05,
401
+ "loss": 1.4794,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.1400000000000001,
406
+ "grad_norm": 34.75075912475586,
407
+ "learning_rate": 3.103333333333333e-05,
408
+ "loss": 1.0972,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.16,
413
+ "grad_norm": 52.29777526855469,
414
+ "learning_rate": 3.07e-05,
415
+ "loss": 1.9438,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.18,
420
+ "grad_norm": 63.562442779541016,
421
+ "learning_rate": 3.0366666666666665e-05,
422
+ "loss": 1.4552,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.2,
427
+ "grad_norm": 36.03409194946289,
428
+ "learning_rate": 3.0033333333333336e-05,
429
+ "loss": 1.4451,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.22,
434
+ "grad_norm": 35.75303268432617,
435
+ "learning_rate": 2.97e-05,
436
+ "loss": 1.3203,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.24,
441
+ "grad_norm": 41.28643798828125,
442
+ "learning_rate": 2.936666666666667e-05,
443
+ "loss": 1.3898,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.26,
448
+ "grad_norm": 42.44171905517578,
449
+ "learning_rate": 2.9033333333333335e-05,
450
+ "loss": 1.4461,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.28,
455
+ "grad_norm": 33.191993713378906,
456
+ "learning_rate": 2.87e-05,
457
+ "loss": 1.5485,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.3,
462
+ "grad_norm": 35.58934020996094,
463
+ "learning_rate": 2.836666666666667e-05,
464
+ "loss": 1.4225,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.32,
469
+ "grad_norm": 38.515438079833984,
470
+ "learning_rate": 2.8033333333333335e-05,
471
+ "loss": 1.4034,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.34,
476
+ "grad_norm": 42.85960006713867,
477
+ "learning_rate": 2.7700000000000002e-05,
478
+ "loss": 1.3505,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.3599999999999999,
483
+ "grad_norm": 83.25682067871094,
484
+ "learning_rate": 2.7366666666666667e-05,
485
+ "loss": 1.35,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.38,
490
+ "grad_norm": 49.6702880859375,
491
+ "learning_rate": 2.7033333333333334e-05,
492
+ "loss": 1.8784,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.4,
497
+ "grad_norm": 51.177093505859375,
498
+ "learning_rate": 2.6700000000000002e-05,
499
+ "loss": 1.3637,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.42,
504
+ "grad_norm": 40.318206787109375,
505
+ "learning_rate": 2.6366666666666666e-05,
506
+ "loss": 1.3539,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.44,
511
+ "grad_norm": 45.05327224731445,
512
+ "learning_rate": 2.6033333333333337e-05,
513
+ "loss": 1.5676,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.46,
518
+ "grad_norm": 28.770118713378906,
519
+ "learning_rate": 2.57e-05,
520
+ "loss": 1.342,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.48,
525
+ "grad_norm": 29.81730842590332,
526
+ "learning_rate": 2.5366666666666665e-05,
527
+ "loss": 1.3532,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.5,
532
+ "grad_norm": 48.3309440612793,
533
+ "learning_rate": 2.5033333333333336e-05,
534
+ "loss": 1.4733,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.52,
539
+ "grad_norm": 70.29447937011719,
540
+ "learning_rate": 2.47e-05,
541
+ "loss": 1.457,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.54,
546
+ "grad_norm": 37.76487350463867,
547
+ "learning_rate": 2.4366666666666668e-05,
548
+ "loss": 1.4183,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.56,
553
+ "grad_norm": 33.34684753417969,
554
+ "learning_rate": 2.4033333333333336e-05,
555
+ "loss": 1.4226,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.58,
560
+ "grad_norm": 32.89299392700195,
561
+ "learning_rate": 2.37e-05,
562
+ "loss": 1.3785,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.6,
567
+ "grad_norm": 56.79878616333008,
568
+ "learning_rate": 2.3366666666666668e-05,
569
+ "loss": 1.4579,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.62,
574
+ "grad_norm": 32.62324523925781,
575
+ "learning_rate": 2.3033333333333335e-05,
576
+ "loss": 1.4094,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.6400000000000001,
581
+ "grad_norm": 39.20806121826172,
582
+ "learning_rate": 2.2700000000000003e-05,
583
+ "loss": 1.4686,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.6600000000000001,
588
+ "grad_norm": 31.847000122070312,
589
+ "learning_rate": 2.236666666666667e-05,
590
+ "loss": 1.3953,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.6800000000000002,
595
+ "grad_norm": 40.128971099853516,
596
+ "learning_rate": 2.2033333333333335e-05,
597
+ "loss": 1.4658,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.7,
602
+ "grad_norm": 36.050846099853516,
603
+ "learning_rate": 2.1700000000000002e-05,
604
+ "loss": 1.6216,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.72,
609
+ "grad_norm": 64.60285186767578,
610
+ "learning_rate": 2.1366666666666667e-05,
611
+ "loss": 1.4508,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.74,
616
+ "grad_norm": 65.16170501708984,
617
+ "learning_rate": 2.1033333333333334e-05,
618
+ "loss": 1.4214,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.76,
623
+ "grad_norm": 35.84981155395508,
624
+ "learning_rate": 2.07e-05,
625
+ "loss": 1.3662,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.78,
630
+ "grad_norm": 40.32749557495117,
631
+ "learning_rate": 2.0366666666666666e-05,
632
+ "loss": 1.4159,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.8,
637
+ "grad_norm": 37.723114013671875,
638
+ "learning_rate": 2.0033333333333334e-05,
639
+ "loss": 1.3919,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.8199999999999998,
644
+ "grad_norm": 35.627803802490234,
645
+ "learning_rate": 1.97e-05,
646
+ "loss": 1.4407,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.8399999999999999,
651
+ "grad_norm": 34.74470138549805,
652
+ "learning_rate": 1.9366666666666665e-05,
653
+ "loss": 1.3455,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.8599999999999999,
658
+ "grad_norm": 30.108226776123047,
659
+ "learning_rate": 1.9033333333333333e-05,
660
+ "loss": 1.4827,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.88,
665
+ "grad_norm": 72.5284652709961,
666
+ "learning_rate": 1.87e-05,
667
+ "loss": 1.38,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.9,
672
+ "grad_norm": 40.3804817199707,
673
+ "learning_rate": 1.8366666666666668e-05,
674
+ "loss": 1.3436,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.92,
679
+ "grad_norm": 48.87946701049805,
680
+ "learning_rate": 1.8033333333333336e-05,
681
+ "loss": 1.369,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.94,
686
+ "grad_norm": 50.297794342041016,
687
+ "learning_rate": 1.77e-05,
688
+ "loss": 1.3892,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.96,
693
+ "grad_norm": 43.455909729003906,
694
+ "learning_rate": 1.7366666666666668e-05,
695
+ "loss": 1.5923,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.98,
700
+ "grad_norm": 26.250675201416016,
701
+ "learning_rate": 1.7033333333333335e-05,
702
+ "loss": 1.4009,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 2.0,
707
+ "grad_norm": 30.42631721496582,
708
+ "learning_rate": 1.6700000000000003e-05,
709
+ "loss": 1.3333,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 2.02,
714
+ "grad_norm": 53.33681869506836,
715
+ "learning_rate": 1.6366666666666667e-05,
716
+ "loss": 1.4114,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 2.04,
721
+ "grad_norm": 40.35858917236328,
722
+ "learning_rate": 1.6033333333333335e-05,
723
+ "loss": 1.3778,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 2.06,
728
+ "grad_norm": 34.881256103515625,
729
+ "learning_rate": 1.5700000000000002e-05,
730
+ "loss": 1.2281,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 2.08,
735
+ "grad_norm": 53.44401550292969,
736
+ "learning_rate": 1.536666666666667e-05,
737
+ "loss": 1.4416,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 2.1,
742
+ "grad_norm": 33.54370880126953,
743
+ "learning_rate": 1.5033333333333336e-05,
744
+ "loss": 1.3953,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 2.12,
749
+ "grad_norm": 16.53406524658203,
750
+ "learning_rate": 1.47e-05,
751
+ "loss": 1.1336,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 2.14,
756
+ "grad_norm": 22.269121170043945,
757
+ "learning_rate": 1.4366666666666667e-05,
758
+ "loss": 1.5907,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 2.16,
763
+ "grad_norm": 23.64450454711914,
764
+ "learning_rate": 1.4033333333333335e-05,
765
+ "loss": 1.5443,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 2.18,
770
+ "grad_norm": 183.4439239501953,
771
+ "learning_rate": 1.3700000000000001e-05,
772
+ "loss": 4.4497,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 2.2,
777
+ "grad_norm": 40.55182647705078,
778
+ "learning_rate": 1.3366666666666667e-05,
779
+ "loss": 7.1512,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 2.22,
784
+ "grad_norm": 40.742427825927734,
785
+ "learning_rate": 1.3033333333333333e-05,
786
+ "loss": 1.3964,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 2.24,
791
+ "grad_norm": 58.78276443481445,
792
+ "learning_rate": 1.27e-05,
793
+ "loss": 1.3682,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 2.26,
798
+ "grad_norm": 27.762662887573242,
799
+ "learning_rate": 1.2366666666666666e-05,
800
+ "loss": 1.3149,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 2.2800000000000002,
805
+ "grad_norm": 60.419437408447266,
806
+ "learning_rate": 1.2033333333333334e-05,
807
+ "loss": 1.4831,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 2.3,
812
+ "grad_norm": 62.96380615234375,
813
+ "learning_rate": 1.1700000000000001e-05,
814
+ "loss": 1.4638,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 2.32,
819
+ "grad_norm": 32.46728515625,
820
+ "learning_rate": 1.1366666666666667e-05,
821
+ "loss": 1.4317,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 2.34,
826
+ "grad_norm": 36.206382751464844,
827
+ "learning_rate": 1.1033333333333335e-05,
828
+ "loss": 1.3965,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 2.36,
833
+ "grad_norm": 27.393978118896484,
834
+ "learning_rate": 1.0700000000000001e-05,
835
+ "loss": 1.4052,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 2.38,
840
+ "grad_norm": 34.69779968261719,
841
+ "learning_rate": 1.0366666666666667e-05,
842
+ "loss": 1.438,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 2.4,
847
+ "grad_norm": 35.44539260864258,
848
+ "learning_rate": 1.0033333333333333e-05,
849
+ "loss": 1.3184,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 2.42,
854
+ "grad_norm": 35.62276077270508,
855
+ "learning_rate": 9.7e-06,
856
+ "loss": 1.3745,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 2.44,
861
+ "grad_norm": 39.036869049072266,
862
+ "learning_rate": 9.366666666666666e-06,
863
+ "loss": 1.4504,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 2.46,
868
+ "grad_norm": 43.82394790649414,
869
+ "learning_rate": 9.033333333333334e-06,
870
+ "loss": 1.3977,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 2.48,
875
+ "grad_norm": 35.87830352783203,
876
+ "learning_rate": 8.7e-06,
877
+ "loss": 1.349,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 2.5,
882
+ "grad_norm": 37.99837112426758,
883
+ "learning_rate": 8.366666666666667e-06,
884
+ "loss": 1.4141,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 2.52,
889
+ "grad_norm": 31.749996185302734,
890
+ "learning_rate": 8.033333333333335e-06,
891
+ "loss": 1.3457,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 2.54,
896
+ "grad_norm": 41.74779510498047,
897
+ "learning_rate": 7.7e-06,
898
+ "loss": 1.5417,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 2.56,
903
+ "grad_norm": 35.62648010253906,
904
+ "learning_rate": 7.3666666666666676e-06,
905
+ "loss": 1.3816,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 2.58,
910
+ "grad_norm": 40.89716720581055,
911
+ "learning_rate": 7.0333333333333335e-06,
912
+ "loss": 1.3847,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 2.6,
917
+ "grad_norm": 32.391666412353516,
918
+ "learning_rate": 6.700000000000001e-06,
919
+ "loss": 1.431,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 2.62,
924
+ "grad_norm": 62.34846115112305,
925
+ "learning_rate": 6.366666666666667e-06,
926
+ "loss": 1.3736,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 2.64,
931
+ "grad_norm": 29.50358772277832,
932
+ "learning_rate": 6.033333333333334e-06,
933
+ "loss": 1.3388,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 2.66,
938
+ "grad_norm": 62.63405990600586,
939
+ "learning_rate": 5.7000000000000005e-06,
940
+ "loss": 1.4557,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 2.68,
945
+ "grad_norm": 61.824378967285156,
946
+ "learning_rate": 5.366666666666667e-06,
947
+ "loss": 1.3909,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 2.7,
952
+ "grad_norm": 63.94225311279297,
953
+ "learning_rate": 5.033333333333334e-06,
954
+ "loss": 1.4039,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 2.7199999999999998,
959
+ "grad_norm": 32.076011657714844,
960
+ "learning_rate": 4.7e-06,
961
+ "loss": 1.2879,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 2.74,
966
+ "grad_norm": 68.8197021484375,
967
+ "learning_rate": 4.366666666666667e-06,
968
+ "loss": 1.4695,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 2.76,
973
+ "grad_norm": 59.826053619384766,
974
+ "learning_rate": 4.033333333333333e-06,
975
+ "loss": 1.4535,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 2.7800000000000002,
980
+ "grad_norm": 32.45442581176758,
981
+ "learning_rate": 3.7e-06,
982
+ "loss": 1.4156,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 2.8,
987
+ "grad_norm": 36.638893127441406,
988
+ "learning_rate": 3.3666666666666665e-06,
989
+ "loss": 1.3712,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 2.82,
994
+ "grad_norm": 61.558937072753906,
995
+ "learning_rate": 3.0333333333333337e-06,
996
+ "loss": 1.4228,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 2.84,
1001
+ "grad_norm": 32.557228088378906,
1002
+ "learning_rate": 2.7e-06,
1003
+ "loss": 1.3725,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 2.86,
1008
+ "grad_norm": 37.94230651855469,
1009
+ "learning_rate": 2.3666666666666667e-06,
1010
+ "loss": 1.3427,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 2.88,
1015
+ "grad_norm": 41.18326187133789,
1016
+ "learning_rate": 2.033333333333333e-06,
1017
+ "loss": 1.3908,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 2.9,
1022
+ "grad_norm": 38.61515426635742,
1023
+ "learning_rate": 1.7000000000000002e-06,
1024
+ "loss": 1.3995,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 2.92,
1029
+ "grad_norm": 33.568912506103516,
1030
+ "learning_rate": 1.3666666666666668e-06,
1031
+ "loss": 1.3433,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 2.94,
1036
+ "grad_norm": 32.206260681152344,
1037
+ "learning_rate": 1.0333333333333333e-06,
1038
+ "loss": 1.3067,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 2.96,
1043
+ "grad_norm": 36.90066146850586,
1044
+ "learning_rate": 7.000000000000001e-07,
1045
+ "loss": 1.4349,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 2.98,
1050
+ "grad_norm": 42.08134841918945,
1051
+ "learning_rate": 3.6666666666666667e-07,
1052
+ "loss": 1.3735,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 3.0,
1057
+ "grad_norm": 31.836576461791992,
1058
+ "learning_rate": 3.3333333333333334e-08,
1059
+ "loss": 1.4106,
1060
+ "step": 1500
1061
+ }
1062
+ ],
1063
+ "logging_steps": 10,
1064
+ "max_steps": 1500,
1065
+ "num_input_tokens_seen": 0,
1066
+ "num_train_epochs": 3,
1067
+ "save_steps": 500,
1068
+ "stateful_callbacks": {
1069
+ "TrainerControl": {
1070
+ "args": {
1071
+ "should_epoch_stop": false,
1072
+ "should_evaluate": false,
1073
+ "should_log": false,
1074
+ "should_save": true,
1075
+ "should_training_stop": true
1076
+ },
1077
+ "attributes": {}
1078
+ }
1079
+ },
1080
+ "total_flos": 8118696148992000.0,
1081
+ "train_batch_size": 2,
1082
+ "trial_name": null,
1083
+ "trial_params": null
1084
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2ae8ab9de045c8c8f69e621a036f39a4c6b3ea196155bf70db96ba8d5df4d0
3
+ size 5304
checkpoint-1500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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-500/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 %}
checkpoint-500/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
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
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151669
30
+ }
checkpoint-500/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": "4.52.3"
6
+ }
checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43108dc74a1fb71982cf758beb897edec4a7b37b49dfb35af52200807f7c065
3
+ size 4766475646
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c049a62c750b1124753d1fdd940be3bb51e06d2791516246047d3270427fa01
3
+ size 2383210594
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441fe55200e88247d0cb84c3a5d41f73058895b59e0666b89da76a37ed964576
3
+ size 1064
checkpoint-500/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
+ }
checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61978ef1e7f4221e8ec52fc8be51c4b8e244de9ded89dd78cba92402ef6d14b2
3
+ size 11423287
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "4689": {
6
+ "content": "END",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "14374": {
14
+ "content": "###",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "151643": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151644": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151645": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151646": {
46
+ "content": "<|object_ref_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151647": {
54
+ "content": "<|object_ref_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151648": {
62
+ "content": "<|box_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151649": {
70
+ "content": "<|box_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151650": {
78
+ "content": "<|quad_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151651": {
86
+ "content": "<|quad_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151652": {
94
+ "content": "<|vision_start|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151653": {
102
+ "content": "<|vision_end|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151654": {
110
+ "content": "<|vision_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151655": {
118
+ "content": "<|image_pad|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151656": {
126
+ "content": "<|video_pad|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "151657": {
134
+ "content": "<tool_call>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151658": {
142
+ "content": "</tool_call>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151659": {
150
+ "content": "<|fim_prefix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151660": {
158
+ "content": "<|fim_middle|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151661": {
166
+ "content": "<|fim_suffix|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151662": {
174
+ "content": "<|fim_pad|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151663": {
182
+ "content": "<|repo_name|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151664": {
190
+ "content": "<|file_sep|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151665": {
198
+ "content": "<tool_response>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151666": {
206
+ "content": "</tool_response>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151667": {
214
+ "content": "<think>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "151668": {
222
+ "content": "</think>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|im_start|>",
232
+ "<|im_end|>",
233
+ "<|object_ref_start|>",
234
+ "<|object_ref_end|>",
235
+ "<|box_start|>",
236
+ "<|box_end|>",
237
+ "<|quad_start|>",
238
+ "<|quad_end|>",
239
+ "<|vision_start|>",
240
+ "<|vision_end|>",
241
+ "<|vision_pad|>",
242
+ "<|image_pad|>",
243
+ "<|video_pad|>"
244
+ ],
245
+ "bos_token": null,
246
+ "clean_up_tokenization_spaces": false,
247
+ "eos_token": "<|endoftext|>",
248
+ "errors": "replace",
249
+ "extra_special_tokens": {},
250
+ "model_max_length": 131072,
251
+ "pad_token": "<|endoftext|>",
252
+ "split_special_tokens": false,
253
+ "tokenizer_class": "Qwen2Tokenizer",
254
+ "unk_token": null
255
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02,
14
+ "grad_norm": 70.61351013183594,
15
+ "learning_rate": 4.97e-05,
16
+ "loss": 4.2158,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04,
21
+ "grad_norm": 73.62928009033203,
22
+ "learning_rate": 4.936666666666667e-05,
23
+ "loss": 1.6566,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.06,
28
+ "grad_norm": 108.96935272216797,
29
+ "learning_rate": 4.903333333333334e-05,
30
+ "loss": 1.7678,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.08,
35
+ "grad_norm": 61.242454528808594,
36
+ "learning_rate": 4.87e-05,
37
+ "loss": 1.5158,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "grad_norm": 131.24546813964844,
43
+ "learning_rate": 4.836666666666667e-05,
44
+ "loss": 2.0604,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "grad_norm": 40.62075424194336,
50
+ "learning_rate": 4.803333333333333e-05,
51
+ "loss": 1.4759,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.14,
56
+ "grad_norm": 68.39600372314453,
57
+ "learning_rate": 4.77e-05,
58
+ "loss": 1.6714,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.16,
63
+ "grad_norm": 65.06390380859375,
64
+ "learning_rate": 4.736666666666667e-05,
65
+ "loss": 1.3931,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.18,
70
+ "grad_norm": 91.259765625,
71
+ "learning_rate": 4.7033333333333336e-05,
72
+ "loss": 1.4381,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.2,
77
+ "grad_norm": 114.90811920166016,
78
+ "learning_rate": 4.6700000000000003e-05,
79
+ "loss": 1.5654,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "grad_norm": 54.1782341003418,
85
+ "learning_rate": 4.636666666666667e-05,
86
+ "loss": 2.0443,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.24,
91
+ "grad_norm": 71.6166763305664,
92
+ "learning_rate": 4.603333333333333e-05,
93
+ "loss": 1.6087,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.26,
98
+ "grad_norm": 74.20275115966797,
99
+ "learning_rate": 4.5700000000000006e-05,
100
+ "loss": 1.6605,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.28,
105
+ "grad_norm": 77.95655059814453,
106
+ "learning_rate": 4.536666666666667e-05,
107
+ "loss": 1.5884,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.3,
112
+ "grad_norm": 47.96751403808594,
113
+ "learning_rate": 4.5033333333333335e-05,
114
+ "loss": 2.4234,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.32,
119
+ "grad_norm": 114.87418365478516,
120
+ "learning_rate": 4.47e-05,
121
+ "loss": 1.8465,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.34,
126
+ "grad_norm": 64.47191619873047,
127
+ "learning_rate": 4.436666666666667e-05,
128
+ "loss": 1.6719,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.36,
133
+ "grad_norm": 63.627681732177734,
134
+ "learning_rate": 4.403333333333334e-05,
135
+ "loss": 1.7967,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.38,
140
+ "grad_norm": 30.865203857421875,
141
+ "learning_rate": 4.3700000000000005e-05,
142
+ "loss": 1.5015,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4,
147
+ "grad_norm": 12.00632095336914,
148
+ "learning_rate": 4.3366666666666666e-05,
149
+ "loss": 1.6298,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.42,
154
+ "grad_norm": 83.26287841796875,
155
+ "learning_rate": 4.3033333333333334e-05,
156
+ "loss": 1.9531,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.44,
161
+ "grad_norm": 43.74462127685547,
162
+ "learning_rate": 4.27e-05,
163
+ "loss": 1.4834,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.46,
168
+ "grad_norm": 41.31574249267578,
169
+ "learning_rate": 4.236666666666667e-05,
170
+ "loss": 1.8548,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.48,
175
+ "grad_norm": 66.2603759765625,
176
+ "learning_rate": 4.2033333333333336e-05,
177
+ "loss": 1.4464,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5,
182
+ "grad_norm": 18.777666091918945,
183
+ "learning_rate": 4.17e-05,
184
+ "loss": 1.3379,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.52,
189
+ "grad_norm": 40.735050201416016,
190
+ "learning_rate": 4.136666666666667e-05,
191
+ "loss": 1.4589,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.54,
196
+ "grad_norm": 89.99899291992188,
197
+ "learning_rate": 4.103333333333333e-05,
198
+ "loss": 1.6462,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.56,
203
+ "grad_norm": 26.000844955444336,
204
+ "learning_rate": 4.07e-05,
205
+ "loss": 1.5459,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.58,
210
+ "grad_norm": 72.94963836669922,
211
+ "learning_rate": 4.036666666666667e-05,
212
+ "loss": 1.3914,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.6,
217
+ "grad_norm": 36.23366928100586,
218
+ "learning_rate": 4.0033333333333335e-05,
219
+ "loss": 1.7466,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.62,
224
+ "grad_norm": 37.300697326660156,
225
+ "learning_rate": 3.97e-05,
226
+ "loss": 1.6585,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.64,
231
+ "grad_norm": 48.120933532714844,
232
+ "learning_rate": 3.936666666666667e-05,
233
+ "loss": 1.7376,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.66,
238
+ "grad_norm": 41.503997802734375,
239
+ "learning_rate": 3.903333333333333e-05,
240
+ "loss": 1.4676,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.68,
245
+ "grad_norm": 13.966187477111816,
246
+ "learning_rate": 3.8700000000000006e-05,
247
+ "loss": 1.4801,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7,
252
+ "grad_norm": 55.511837005615234,
253
+ "learning_rate": 3.8366666666666666e-05,
254
+ "loss": 1.9258,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.72,
259
+ "grad_norm": 46.56684494018555,
260
+ "learning_rate": 3.803333333333334e-05,
261
+ "loss": 1.4785,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.74,
266
+ "grad_norm": 51.37467575073242,
267
+ "learning_rate": 3.77e-05,
268
+ "loss": 1.3089,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.76,
273
+ "grad_norm": 63.84782409667969,
274
+ "learning_rate": 3.736666666666667e-05,
275
+ "loss": 2.0258,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.78,
280
+ "grad_norm": 54.59080123901367,
281
+ "learning_rate": 3.703333333333334e-05,
282
+ "loss": 1.4266,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.8,
287
+ "grad_norm": 27.919336318969727,
288
+ "learning_rate": 3.6700000000000004e-05,
289
+ "loss": 1.8133,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.82,
294
+ "grad_norm": 43.32358169555664,
295
+ "learning_rate": 3.636666666666667e-05,
296
+ "loss": 1.4812,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.84,
301
+ "grad_norm": 33.77085494995117,
302
+ "learning_rate": 3.603333333333333e-05,
303
+ "loss": 1.4177,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.86,
308
+ "grad_norm": 53.14788055419922,
309
+ "learning_rate": 3.57e-05,
310
+ "loss": 1.4277,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.88,
315
+ "grad_norm": 43.82292175292969,
316
+ "learning_rate": 3.536666666666667e-05,
317
+ "loss": 1.3996,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.9,
322
+ "grad_norm": 74.1073989868164,
323
+ "learning_rate": 3.5033333333333336e-05,
324
+ "loss": 1.4942,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.92,
329
+ "grad_norm": 67.50479888916016,
330
+ "learning_rate": 3.4699999999999996e-05,
331
+ "loss": 1.4433,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.94,
336
+ "grad_norm": 44.51863479614258,
337
+ "learning_rate": 3.436666666666667e-05,
338
+ "loss": 1.3934,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.96,
343
+ "grad_norm": 42.15129470825195,
344
+ "learning_rate": 3.403333333333333e-05,
345
+ "loss": 1.4448,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.98,
350
+ "grad_norm": 59.780059814453125,
351
+ "learning_rate": 3.3700000000000006e-05,
352
+ "loss": 1.25,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.0,
357
+ "grad_norm": 56.6463623046875,
358
+ "learning_rate": 3.336666666666667e-05,
359
+ "loss": 1.3204,
360
+ "step": 500
361
+ }
362
+ ],
363
+ "logging_steps": 10,
364
+ "max_steps": 1500,
365
+ "num_input_tokens_seen": 0,
366
+ "num_train_epochs": 3,
367
+ "save_steps": 500,
368
+ "stateful_callbacks": {
369
+ "TrainerControl": {
370
+ "args": {
371
+ "should_epoch_stop": false,
372
+ "should_evaluate": false,
373
+ "should_log": false,
374
+ "should_save": true,
375
+ "should_training_stop": false
376
+ },
377
+ "attributes": {}
378
+ }
379
+ },
380
+ "total_flos": 2706232049664000.0,
381
+ "train_batch_size": 2,
382
+ "trial_name": null,
383
+ "trial_params": null
384
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2ae8ab9de045c8c8f69e621a036f39a4c6b3ea196155bf70db96ba8d5df4d0
3
+ size 5304
checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
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
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151669
30
+ }
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": "4.52.3"
6
+ }