joe-xhedi commited on
Commit
e3467e3
·
verified ·
1 Parent(s): adcd389

Upload GRPO-trained geological model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
4
+ tags:
5
+ - geology
6
+ - earth-science
7
+ - qwen
8
+ - grpo
9
+ - instruction-tuned
10
+ language:
11
+ - en
12
+ pipeline_tag: text-generation
13
+ library_name: transformers
14
+ ---
15
+
16
+ # Qwen-GRPO-geological-training
17
+
18
+ GRPO-trained Qwen model specialized for geological questions and analysis
19
+
20
+ ## Model Details
21
+
22
+ - **Base Model**: Qwen/Qwen2.5-0.5B-Instruct
23
+ - **Training Method**: GRPO (Generalized Reward Preference Optimization)
24
+ - **Domain**: Geology and Earth Sciences
25
+ - **Model Type**: Causal Language Model
26
+ - **Architecture**: Transformer-based
27
+
28
+ ## Training Details
29
+
30
+ This model was trained using GRPO (Generalized Reward Preference Optimization) on geological datasets. The training process included:
31
+
32
+ - **Reward Functions**:
33
+ - Geological accuracy reward
34
+ - Format compliance reward
35
+ - Reasoning steps reward
36
+ - **System Prompt**: Specialized geological expert system prompt
37
+ - **Response Format**: Structured thinking process with solution tags
38
+
39
+ ## Intended Use
40
+
41
+ This model is designed for:
42
+ - Answering geological questions
43
+ - Providing educational content about earth sciences
44
+ - Assisting with mineral identification
45
+ - Explaining geological processes
46
+ - Rock and mineral analysis
47
+
48
+ ## Usage Example
49
+
50
+ ```python
51
+ from transformers import AutoTokenizer, AutoModelForCausalLM
52
+ import torch
53
+
54
+ # Load the model
55
+ model_name = "joe-xhedi/Qwen-GRPO-geological-training"
56
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
57
+ model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
58
+
59
+ # Geological system prompt
60
+ system_prompt = '''You are a geological expert assistant. When answering geological questions, follow this format:
61
+ First, analyze the problem step by step in your thinking process within <|begin_of_thought|> and <|end_of_thought|> tags.
62
+ Then provide your solution within <|begin_of_solution|> and <|end_of_solution|> tags.
63
+ Your thinking process should include geological principles, data analysis, and reasoning.
64
+ Your solution should be clear, accurate, and based on geological expertise.'''
65
+
66
+ # Example usage
67
+ messages = [
68
+ {"role": "system", "content": system_prompt},
69
+ {"role": "user", "content": "What type of rock is formed by cooling magma?"}
70
+ ]
71
+
72
+ # Generate response
73
+ text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
74
+ inputs = tokenizer(text, return_tensors="pt")
75
+ outputs = model.generate(**inputs, max_new_tokens=300, do_sample=True, temperature=0.7)
76
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
77
+ print(response)
78
+ ```
79
+
80
+ ## Response Format
81
+
82
+ The model is trained to respond in a structured format:
83
+
84
+ ```
85
+ <|begin_of_thought|>
86
+ [Step-by-step geological reasoning and analysis]
87
+ <|end_of_thought|>
88
+
89
+ <|begin_of_solution|>
90
+ [Clear, accurate geological solution or explanation]
91
+ <|end_of_solution|>
92
+ ```
93
+
94
+ ## Limitations
95
+
96
+ - Specialized for geological topics
97
+ - May not perform well on general conversational tasks
98
+ - Responses are structured and may seem formal
99
+ - Based on training data available up to the training cutoff
100
+
101
+ ## Training Data
102
+
103
+ The model was trained on geological datasets including:
104
+ - Mineral identification questions
105
+ - Rock formation processes
106
+ - Geological principles and concepts
107
+ - Earth science educational content
108
+
109
+ ## Ethical Considerations
110
+
111
+ - This model is designed for educational and research purposes
112
+ - Users should verify geological information for professional applications
113
+ - The model may have biases present in the training data
114
+
115
+ ## Citation
116
+
117
+ If you use this model in your research, please cite:
118
+
119
+ ```bibtex
120
+ @model{qwen-geological-expert,
121
+ author = {joe-xhedi},
122
+ title = {GRPO-trained Qwen Model for Geological Analysis},
123
+ year = {2025},
124
+ url = {https://huggingface.co/joe-xhedi/Qwen-GRPO-geological-training}
125
+ }
126
+ ```
127
+
128
+ ## Model Card Contact
129
+
130
+ For questions about this model, please contact the model author through Hugging Face.
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-100/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-100/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-100/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 21,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 14,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.52.4",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.52.4"
14
+ }
checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0aa194a23989d8df6c6ee05214c31c91564c72fb4d415c3fd5e73dc11bee75
3
+ size 988097824
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41aab2315f60d8400d2fe2b137ef904df286dac3d9c9a85e5c72033c0b6b03a7
3
+ size 1976374202
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb8cfbc8c75abba80e348e52099950a192c6c7171309e2206e248ff223471a2
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd60da393ff67ad2f08779377eeaa08189a6bf520f752442788825d9bce1449
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "left",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,334 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 50,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.825,
19
+ "completions/max_length": 256.0,
20
+ "completions/max_terminated_length": 114.1,
21
+ "completions/mean_length": 234.4875,
22
+ "completions/mean_terminated_length": 81.88557739257813,
23
+ "completions/min_length": 183.2,
24
+ "completions/min_terminated_length": 55.2,
25
+ "epoch": 0.2,
26
+ "frac_reward_zero_std": 0.0,
27
+ "grad_norm": 5.84375,
28
+ "kl": 0.048543618264375255,
29
+ "learning_rate": 4.5e-05,
30
+ "loss": -0.0663,
31
+ "num_tokens": 56238.0,
32
+ "reward": 1.7609375,
33
+ "reward_std": 0.24403530955314637,
34
+ "rewards/format_reward/mean": 0.003125,
35
+ "rewards/format_reward/std": 0.0125,
36
+ "rewards/geological_accuracy_reward/mean": 0.926562488079071,
37
+ "rewards/geological_accuracy_reward/std": 0.09429793991148472,
38
+ "rewards/reasoning_steps_reward/mean": 0.8312500208616257,
39
+ "rewards/reasoning_steps_reward/std": 0.200314299762249,
40
+ "step": 10
41
+ },
42
+ {
43
+ "clip_ratio/high_max": 0.0,
44
+ "clip_ratio/high_mean": 0.0,
45
+ "clip_ratio/low_mean": 0.0,
46
+ "clip_ratio/low_min": 0.0,
47
+ "clip_ratio/region_mean": 0.0,
48
+ "completions/clipped_ratio": 1.0,
49
+ "completions/max_length": 256.0,
50
+ "completions/max_terminated_length": 0.0,
51
+ "completions/mean_length": 256.0,
52
+ "completions/mean_terminated_length": 0.0,
53
+ "completions/min_length": 256.0,
54
+ "completions/min_terminated_length": 0.0,
55
+ "epoch": 0.4,
56
+ "frac_reward_zero_std": 0.35,
57
+ "grad_norm": 5.8125,
58
+ "kl": 0.35692137740552426,
59
+ "learning_rate": 4.5e-05,
60
+ "loss": 0.0143,
61
+ "num_tokens": 115918.0,
62
+ "reward": 1.956250011920929,
63
+ "reward_std": 0.08733109515160323,
64
+ "rewards/format_reward/mean": 0.0,
65
+ "rewards/format_reward/std": 0.0,
66
+ "rewards/geological_accuracy_reward/mean": 0.9791666865348816,
67
+ "rewards/geological_accuracy_reward/std": 0.03408404756337404,
68
+ "rewards/reasoning_steps_reward/mean": 0.9770833432674408,
69
+ "rewards/reasoning_steps_reward/std": 0.07159363627433776,
70
+ "step": 20
71
+ },
72
+ {
73
+ "clip_ratio/high_max": 0.0,
74
+ "clip_ratio/high_mean": 0.0,
75
+ "clip_ratio/low_mean": 0.0,
76
+ "clip_ratio/low_min": 0.0,
77
+ "clip_ratio/region_mean": 0.0,
78
+ "completions/clipped_ratio": 1.0,
79
+ "completions/max_length": 256.0,
80
+ "completions/max_terminated_length": 0.0,
81
+ "completions/mean_length": 256.0,
82
+ "completions/mean_terminated_length": 0.0,
83
+ "completions/min_length": 256.0,
84
+ "completions/min_terminated_length": 0.0,
85
+ "epoch": 0.6,
86
+ "frac_reward_zero_std": 0.15,
87
+ "grad_norm": 3.359375,
88
+ "kl": 0.4627214014530182,
89
+ "learning_rate": 3.944444444444445e-05,
90
+ "loss": 0.0185,
91
+ "num_tokens": 175598.0,
92
+ "reward": 1.7921874880790711,
93
+ "reward_std": 0.16298287846148013,
94
+ "rewards/format_reward/mean": 0.0,
95
+ "rewards/format_reward/std": 0.0,
96
+ "rewards/geological_accuracy_reward/mean": 0.9151041746139527,
97
+ "rewards/geological_accuracy_reward/std": 0.0694254757836461,
98
+ "rewards/reasoning_steps_reward/mean": 0.8770833522081375,
99
+ "rewards/reasoning_steps_reward/std": 0.14224028438329697,
100
+ "step": 30
101
+ },
102
+ {
103
+ "clip_ratio/high_max": 0.0,
104
+ "clip_ratio/high_mean": 0.0,
105
+ "clip_ratio/low_mean": 0.0,
106
+ "clip_ratio/low_min": 0.0,
107
+ "clip_ratio/region_mean": 0.0,
108
+ "completions/clipped_ratio": 1.0,
109
+ "completions/max_length": 256.0,
110
+ "completions/max_terminated_length": 0.0,
111
+ "completions/mean_length": 256.0,
112
+ "completions/mean_terminated_length": 0.0,
113
+ "completions/min_length": 256.0,
114
+ "completions/min_terminated_length": 0.0,
115
+ "epoch": 0.8,
116
+ "frac_reward_zero_std": 0.35,
117
+ "grad_norm": 5.40625,
118
+ "kl": 0.5263503693044186,
119
+ "learning_rate": 3.388888888888889e-05,
120
+ "loss": 0.0211,
121
+ "num_tokens": 235278.0,
122
+ "reward": 1.94375,
123
+ "reward_std": 0.1184962541796267,
124
+ "rewards/format_reward/mean": 0.0,
125
+ "rewards/format_reward/std": 0.0,
126
+ "rewards/geological_accuracy_reward/mean": 0.9875,
127
+ "rewards/geological_accuracy_reward/std": 0.03671900928020477,
128
+ "rewards/reasoning_steps_reward/mean": 0.9562500059604645,
129
+ "rewards/reasoning_steps_reward/std": 0.11177612692117692,
130
+ "step": 40
131
+ },
132
+ {
133
+ "clip_ratio/high_max": 0.0,
134
+ "clip_ratio/high_mean": 0.0,
135
+ "clip_ratio/low_mean": 0.0,
136
+ "clip_ratio/low_min": 0.0,
137
+ "clip_ratio/region_mean": 0.0,
138
+ "completions/clipped_ratio": 0.88125,
139
+ "completions/max_length": 256.0,
140
+ "completions/max_terminated_length": 189.7,
141
+ "completions/mean_length": 252.6125,
142
+ "completions/mean_terminated_length": 183.0683349609375,
143
+ "completions/min_length": 222.0,
144
+ "completions/min_terminated_length": 170.8,
145
+ "epoch": 1.0,
146
+ "frac_reward_zero_std": 0.3,
147
+ "grad_norm": 5.8125,
148
+ "kl": 0.6550503380596637,
149
+ "learning_rate": 2.8333333333333335e-05,
150
+ "loss": 0.0188,
151
+ "num_tokens": 294416.0,
152
+ "reward": 1.9708333492279053,
153
+ "reward_std": 0.07019809372723103,
154
+ "rewards/format_reward/mean": 0.0,
155
+ "rewards/format_reward/std": 0.0,
156
+ "rewards/geological_accuracy_reward/mean": 0.9895833373069763,
157
+ "rewards/geological_accuracy_reward/std": 0.02728722561150789,
158
+ "rewards/reasoning_steps_reward/mean": 0.981250011920929,
159
+ "rewards/reasoning_steps_reward/std": 0.06284901946783066,
160
+ "step": 50
161
+ },
162
+ {
163
+ "clip_ratio/high_max": 0.0,
164
+ "clip_ratio/high_mean": 0.0,
165
+ "clip_ratio/low_mean": 0.0,
166
+ "clip_ratio/low_min": 0.0,
167
+ "clip_ratio/region_mean": 0.0,
168
+ "completions/clipped_ratio": 0.8625,
169
+ "completions/max_length": 256.0,
170
+ "completions/max_terminated_length": 200.8,
171
+ "completions/mean_length": 247.26875,
172
+ "completions/mean_terminated_length": 170.6866668701172,
173
+ "completions/min_length": 150.4,
174
+ "completions/min_terminated_length": 124.8,
175
+ "epoch": 1.2,
176
+ "frac_reward_zero_std": 0.55,
177
+ "grad_norm": 3.671875,
178
+ "kl": 0.4722647413611412,
179
+ "learning_rate": 2.277777777777778e-05,
180
+ "loss": -0.0131,
181
+ "num_tokens": 352699.0,
182
+ "reward": 1.976562488079071,
183
+ "reward_std": 0.05695933178067207,
184
+ "rewards/format_reward/mean": 0.0,
185
+ "rewards/format_reward/std": 0.0,
186
+ "rewards/geological_accuracy_reward/mean": 0.9953125,
187
+ "rewards/geological_accuracy_reward/std": 0.01414182111620903,
188
+ "rewards/reasoning_steps_reward/mean": 0.9812500059604645,
189
+ "rewards/reasoning_steps_reward/std": 0.06343709379434585,
190
+ "step": 60
191
+ },
192
+ {
193
+ "clip_ratio/high_max": 0.0,
194
+ "clip_ratio/high_mean": 0.0,
195
+ "clip_ratio/low_mean": 0.0,
196
+ "clip_ratio/low_min": 0.0,
197
+ "clip_ratio/region_mean": 0.0,
198
+ "completions/clipped_ratio": 0.9875,
199
+ "completions/max_length": 256.0,
200
+ "completions/max_terminated_length": 43.3,
201
+ "completions/mean_length": 255.50625,
202
+ "completions/mean_terminated_length": 43.3,
203
+ "completions/min_length": 248.1,
204
+ "completions/min_terminated_length": 43.3,
205
+ "epoch": 1.4,
206
+ "frac_reward_zero_std": 0.65,
207
+ "grad_norm": 5.25,
208
+ "kl": 0.40357689931988716,
209
+ "learning_rate": 1.7222222222222224e-05,
210
+ "loss": 0.0158,
211
+ "num_tokens": 412300.0,
212
+ "reward": 1.9869791626930238,
213
+ "reward_std": 0.029759517684578896,
214
+ "rewards/format_reward/mean": 0.0,
215
+ "rewards/format_reward/std": 0.0,
216
+ "rewards/geological_accuracy_reward/mean": 0.9932291626930236,
217
+ "rewards/geological_accuracy_reward/std": 0.02023173440247774,
218
+ "rewards/reasoning_steps_reward/mean": 0.9937500059604645,
219
+ "rewards/reasoning_steps_reward/std": 0.02499999850988388,
220
+ "step": 70
221
+ },
222
+ {
223
+ "clip_ratio/high_max": 0.0,
224
+ "clip_ratio/high_mean": 0.0,
225
+ "clip_ratio/low_mean": 0.0,
226
+ "clip_ratio/low_min": 0.0,
227
+ "clip_ratio/region_mean": 0.0,
228
+ "completions/clipped_ratio": 0.95625,
229
+ "completions/max_length": 256.0,
230
+ "completions/max_terminated_length": 117.9,
231
+ "completions/mean_length": 254.89375,
232
+ "completions/mean_terminated_length": 116.65,
233
+ "completions/min_length": 243.4,
234
+ "completions/min_terminated_length": 115.4,
235
+ "epoch": 1.6,
236
+ "frac_reward_zero_std": 0.35,
237
+ "grad_norm": 5.0625,
238
+ "kl": 0.35717245303094386,
239
+ "learning_rate": 1.1666666666666668e-05,
240
+ "loss": 0.0141,
241
+ "num_tokens": 471803.0,
242
+ "reward": 1.9718750596046448,
243
+ "reward_std": 0.07427498577162624,
244
+ "rewards/format_reward/mean": 0.0,
245
+ "rewards/format_reward/std": 0.0,
246
+ "rewards/geological_accuracy_reward/mean": 0.9927083432674408,
247
+ "rewards/geological_accuracy_reward/std": 0.019555205665528774,
248
+ "rewards/reasoning_steps_reward/mean": 0.9791666746139527,
249
+ "rewards/reasoning_steps_reward/std": 0.07581988722085953,
250
+ "step": 80
251
+ },
252
+ {
253
+ "clip_ratio/high_max": 0.0,
254
+ "clip_ratio/high_mean": 0.0,
255
+ "clip_ratio/low_mean": 0.0,
256
+ "clip_ratio/low_min": 0.0,
257
+ "clip_ratio/region_mean": 0.0,
258
+ "completions/clipped_ratio": 0.9875,
259
+ "completions/max_length": 256.0,
260
+ "completions/max_terminated_length": 45.0,
261
+ "completions/mean_length": 255.6125,
262
+ "completions/mean_terminated_length": 45.0,
263
+ "completions/min_length": 249.8,
264
+ "completions/min_terminated_length": 45.0,
265
+ "epoch": 1.8,
266
+ "frac_reward_zero_std": 0.45,
267
+ "grad_norm": 4.9375,
268
+ "kl": 0.3294585730880499,
269
+ "learning_rate": 6.111111111111111e-06,
270
+ "loss": 0.0132,
271
+ "num_tokens": 531421.0,
272
+ "reward": 1.9791666626930238,
273
+ "reward_std": 0.05486339293420315,
274
+ "rewards/format_reward/mean": 0.0,
275
+ "rewards/format_reward/std": 0.0,
276
+ "rewards/geological_accuracy_reward/mean": 0.9916666626930237,
277
+ "rewards/geological_accuracy_reward/std": 0.02227458208799362,
278
+ "rewards/reasoning_steps_reward/mean": 0.987500011920929,
279
+ "rewards/reasoning_steps_reward/std": 0.04999999701976776,
280
+ "step": 90
281
+ },
282
+ {
283
+ "clip_ratio/high_max": 0.0,
284
+ "clip_ratio/high_mean": 0.0,
285
+ "clip_ratio/low_mean": 0.0,
286
+ "clip_ratio/low_min": 0.0,
287
+ "clip_ratio/region_mean": 0.0,
288
+ "completions/clipped_ratio": 0.98125,
289
+ "completions/max_length": 256.0,
290
+ "completions/max_terminated_length": 70.9,
291
+ "completions/mean_length": 255.63125,
292
+ "completions/mean_terminated_length": 70.9,
293
+ "completions/min_length": 250.1,
294
+ "completions/min_terminated_length": 70.9,
295
+ "epoch": 2.0,
296
+ "frac_reward_zero_std": 0.4,
297
+ "grad_norm": 5.25,
298
+ "kl": 0.3567266438156366,
299
+ "learning_rate": 5.555555555555556e-07,
300
+ "loss": 0.0146,
301
+ "num_tokens": 591042.0,
302
+ "reward": 1.9807291865348815,
303
+ "reward_std": 0.05036611668765545,
304
+ "rewards/format_reward/mean": 0.0,
305
+ "rewards/format_reward/std": 0.0,
306
+ "rewards/geological_accuracy_reward/mean": 0.9932291746139527,
307
+ "rewards/geological_accuracy_reward/std": 0.02180216647684574,
308
+ "rewards/reasoning_steps_reward/mean": 0.9875000059604645,
309
+ "rewards/reasoning_steps_reward/std": 0.04999999850988388,
310
+ "step": 100
311
+ }
312
+ ],
313
+ "logging_steps": 10,
314
+ "max_steps": 100,
315
+ "num_input_tokens_seen": 591042,
316
+ "num_train_epochs": 2,
317
+ "save_steps": 50,
318
+ "stateful_callbacks": {
319
+ "TrainerControl": {
320
+ "args": {
321
+ "should_epoch_stop": false,
322
+ "should_evaluate": false,
323
+ "should_log": false,
324
+ "should_save": true,
325
+ "should_training_stop": true
326
+ },
327
+ "attributes": {}
328
+ }
329
+ },
330
+ "total_flos": 0.0,
331
+ "train_batch_size": 4,
332
+ "trial_name": null,
333
+ "trial_params": null
334
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7e9306ac8309c6f9cbefd32f046d2a5215da8c391890b8abf572362322e57c
3
+ size 6392
checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-50/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-50/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 21,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 14,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.52.4",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
checkpoint-50/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.52.4"
14
+ }
checkpoint-50/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498a6fd3fa94ea582a82086ef01a176d5dea0855bccb26030fba45034f379b08
3
+ size 988097824
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2acd388b5aa678146ebe8d6290f9a8ffa426783ea3e22e8bd40062e8ae02b426
3
+ size 1976374202
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e7a9d23dbdac208a082011444804241e8b14484b9a5a87ca9a9c2d1e1176b6
3
+ size 14244
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b7c0b6e393376d6504c437ab6a7e5facb4a479c82eb39617879a36367da38f
3
+ size 1064
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-50/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "left",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 50,
7
+ "global_step": 50,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.825,
19
+ "completions/max_length": 256.0,
20
+ "completions/max_terminated_length": 114.1,
21
+ "completions/mean_length": 234.4875,
22
+ "completions/mean_terminated_length": 81.88557739257813,
23
+ "completions/min_length": 183.2,
24
+ "completions/min_terminated_length": 55.2,
25
+ "epoch": 0.2,
26
+ "frac_reward_zero_std": 0.0,
27
+ "grad_norm": 5.84375,
28
+ "kl": 0.048543618264375255,
29
+ "learning_rate": 4.5e-05,
30
+ "loss": -0.0663,
31
+ "num_tokens": 56238.0,
32
+ "reward": 1.7609375,
33
+ "reward_std": 0.24403530955314637,
34
+ "rewards/format_reward/mean": 0.003125,
35
+ "rewards/format_reward/std": 0.0125,
36
+ "rewards/geological_accuracy_reward/mean": 0.926562488079071,
37
+ "rewards/geological_accuracy_reward/std": 0.09429793991148472,
38
+ "rewards/reasoning_steps_reward/mean": 0.8312500208616257,
39
+ "rewards/reasoning_steps_reward/std": 0.200314299762249,
40
+ "step": 10
41
+ },
42
+ {
43
+ "clip_ratio/high_max": 0.0,
44
+ "clip_ratio/high_mean": 0.0,
45
+ "clip_ratio/low_mean": 0.0,
46
+ "clip_ratio/low_min": 0.0,
47
+ "clip_ratio/region_mean": 0.0,
48
+ "completions/clipped_ratio": 1.0,
49
+ "completions/max_length": 256.0,
50
+ "completions/max_terminated_length": 0.0,
51
+ "completions/mean_length": 256.0,
52
+ "completions/mean_terminated_length": 0.0,
53
+ "completions/min_length": 256.0,
54
+ "completions/min_terminated_length": 0.0,
55
+ "epoch": 0.4,
56
+ "frac_reward_zero_std": 0.35,
57
+ "grad_norm": 5.8125,
58
+ "kl": 0.35692137740552426,
59
+ "learning_rate": 4.5e-05,
60
+ "loss": 0.0143,
61
+ "num_tokens": 115918.0,
62
+ "reward": 1.956250011920929,
63
+ "reward_std": 0.08733109515160323,
64
+ "rewards/format_reward/mean": 0.0,
65
+ "rewards/format_reward/std": 0.0,
66
+ "rewards/geological_accuracy_reward/mean": 0.9791666865348816,
67
+ "rewards/geological_accuracy_reward/std": 0.03408404756337404,
68
+ "rewards/reasoning_steps_reward/mean": 0.9770833432674408,
69
+ "rewards/reasoning_steps_reward/std": 0.07159363627433776,
70
+ "step": 20
71
+ },
72
+ {
73
+ "clip_ratio/high_max": 0.0,
74
+ "clip_ratio/high_mean": 0.0,
75
+ "clip_ratio/low_mean": 0.0,
76
+ "clip_ratio/low_min": 0.0,
77
+ "clip_ratio/region_mean": 0.0,
78
+ "completions/clipped_ratio": 1.0,
79
+ "completions/max_length": 256.0,
80
+ "completions/max_terminated_length": 0.0,
81
+ "completions/mean_length": 256.0,
82
+ "completions/mean_terminated_length": 0.0,
83
+ "completions/min_length": 256.0,
84
+ "completions/min_terminated_length": 0.0,
85
+ "epoch": 0.6,
86
+ "frac_reward_zero_std": 0.15,
87
+ "grad_norm": 3.359375,
88
+ "kl": 0.4627214014530182,
89
+ "learning_rate": 3.944444444444445e-05,
90
+ "loss": 0.0185,
91
+ "num_tokens": 175598.0,
92
+ "reward": 1.7921874880790711,
93
+ "reward_std": 0.16298287846148013,
94
+ "rewards/format_reward/mean": 0.0,
95
+ "rewards/format_reward/std": 0.0,
96
+ "rewards/geological_accuracy_reward/mean": 0.9151041746139527,
97
+ "rewards/geological_accuracy_reward/std": 0.0694254757836461,
98
+ "rewards/reasoning_steps_reward/mean": 0.8770833522081375,
99
+ "rewards/reasoning_steps_reward/std": 0.14224028438329697,
100
+ "step": 30
101
+ },
102
+ {
103
+ "clip_ratio/high_max": 0.0,
104
+ "clip_ratio/high_mean": 0.0,
105
+ "clip_ratio/low_mean": 0.0,
106
+ "clip_ratio/low_min": 0.0,
107
+ "clip_ratio/region_mean": 0.0,
108
+ "completions/clipped_ratio": 1.0,
109
+ "completions/max_length": 256.0,
110
+ "completions/max_terminated_length": 0.0,
111
+ "completions/mean_length": 256.0,
112
+ "completions/mean_terminated_length": 0.0,
113
+ "completions/min_length": 256.0,
114
+ "completions/min_terminated_length": 0.0,
115
+ "epoch": 0.8,
116
+ "frac_reward_zero_std": 0.35,
117
+ "grad_norm": 5.40625,
118
+ "kl": 0.5263503693044186,
119
+ "learning_rate": 3.388888888888889e-05,
120
+ "loss": 0.0211,
121
+ "num_tokens": 235278.0,
122
+ "reward": 1.94375,
123
+ "reward_std": 0.1184962541796267,
124
+ "rewards/format_reward/mean": 0.0,
125
+ "rewards/format_reward/std": 0.0,
126
+ "rewards/geological_accuracy_reward/mean": 0.9875,
127
+ "rewards/geological_accuracy_reward/std": 0.03671900928020477,
128
+ "rewards/reasoning_steps_reward/mean": 0.9562500059604645,
129
+ "rewards/reasoning_steps_reward/std": 0.11177612692117692,
130
+ "step": 40
131
+ },
132
+ {
133
+ "clip_ratio/high_max": 0.0,
134
+ "clip_ratio/high_mean": 0.0,
135
+ "clip_ratio/low_mean": 0.0,
136
+ "clip_ratio/low_min": 0.0,
137
+ "clip_ratio/region_mean": 0.0,
138
+ "completions/clipped_ratio": 0.88125,
139
+ "completions/max_length": 256.0,
140
+ "completions/max_terminated_length": 189.7,
141
+ "completions/mean_length": 252.6125,
142
+ "completions/mean_terminated_length": 183.0683349609375,
143
+ "completions/min_length": 222.0,
144
+ "completions/min_terminated_length": 170.8,
145
+ "epoch": 1.0,
146
+ "frac_reward_zero_std": 0.3,
147
+ "grad_norm": 5.8125,
148
+ "kl": 0.6550503380596637,
149
+ "learning_rate": 2.8333333333333335e-05,
150
+ "loss": 0.0188,
151
+ "num_tokens": 294416.0,
152
+ "reward": 1.9708333492279053,
153
+ "reward_std": 0.07019809372723103,
154
+ "rewards/format_reward/mean": 0.0,
155
+ "rewards/format_reward/std": 0.0,
156
+ "rewards/geological_accuracy_reward/mean": 0.9895833373069763,
157
+ "rewards/geological_accuracy_reward/std": 0.02728722561150789,
158
+ "rewards/reasoning_steps_reward/mean": 0.981250011920929,
159
+ "rewards/reasoning_steps_reward/std": 0.06284901946783066,
160
+ "step": 50
161
+ }
162
+ ],
163
+ "logging_steps": 10,
164
+ "max_steps": 100,
165
+ "num_input_tokens_seen": 294416,
166
+ "num_train_epochs": 2,
167
+ "save_steps": 50,
168
+ "stateful_callbacks": {
169
+ "TrainerControl": {
170
+ "args": {
171
+ "should_epoch_stop": false,
172
+ "should_evaluate": false,
173
+ "should_log": false,
174
+ "should_save": true,
175
+ "should_training_stop": false
176
+ },
177
+ "attributes": {}
178
+ }
179
+ },
180
+ "total_flos": 0.0,
181
+ "train_batch_size": 4,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7e9306ac8309c6f9cbefd32f046d2a5215da8c391890b8abf572362322e57c
3
+ size 6392
checkpoint-50/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 21,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 14,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.52.4",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.52.4"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0aa194a23989d8df6c6ee05214c31c91564c72fb4d415c3fd5e73dc11bee75
3
+ size 988097824
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "left",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7e9306ac8309c6f9cbefd32f046d2a5215da8c391890b8abf572362322e57c
3
+ size 6392
vocab.json ADDED
The diff for this file is too large to render. See raw diff