Hugging Face's logo

MMattaparthy
/
sft_rewardmodel_final

Text Classification
Transformers
Safetensors
qwen2
Generated from Trainer
trl
reward-trainer
Model card Files
xet
Community
MMattaparthy commited on
Commit
12bf163
·
verified ·
1 Parent(s): 945785a

Upload reward model

Browse files
Files changed (36) hide show
  1. README.md +58 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +54 -0
  4. checkpoint-100/added_tokens.json +24 -0
  5. checkpoint-100/chat_template.jinja +54 -0
  6. checkpoint-100/config.json +64 -0
  7. checkpoint-100/merges.txt +0 -0
  8. checkpoint-100/model.safetensors +3 -0
  9. checkpoint-100/optimizer.pt +3 -0
  10. checkpoint-100/rng_state.pth +3 -0
  11. checkpoint-100/scheduler.pt +3 -0
  12. checkpoint-100/special_tokens_map.json +25 -0
  13. checkpoint-100/tokenizer_config.json +207 -0
  14. checkpoint-100/trainer_state.json +192 -0
  15. checkpoint-100/training_args.bin +3 -0
  16. checkpoint-100/vocab.json +0 -0
  17. checkpoint-111/added_tokens.json +24 -0
  18. checkpoint-111/chat_template.jinja +54 -0
  19. checkpoint-111/config.json +64 -0
  20. checkpoint-111/merges.txt +0 -0
  21. checkpoint-111/model.safetensors +3 -0
  22. checkpoint-111/optimizer.pt +3 -0
  23. checkpoint-111/rng_state.pth +3 -0
  24. checkpoint-111/scheduler.pt +3 -0
  25. checkpoint-111/special_tokens_map.json +25 -0
  26. checkpoint-111/tokenizer_config.json +207 -0
  27. checkpoint-111/trainer_state.json +205 -0
  28. checkpoint-111/training_args.bin +3 -0
  29. checkpoint-111/vocab.json +0 -0
  30. config.json +64 -0
  31. merges.txt +0 -0
  32. model.safetensors +3 -0
  33. special_tokens_map.json +25 -0
  34. tokenizer_config.json +207 -0
  35. training_args.bin +3 -0
  36. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: MMattaparthy/sft_finetined_final
3
+ library_name: transformers
4
+ model_name: reward-model
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - reward-trainer
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for reward-model
13
+
14
+ This model is a fine-tuned version of [MMattaparthy/sft_finetined_final](https://huggingface.co/MMattaparthy/sft_finetined_final).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ text = "The capital of France is Paris."
23
+ rewarder = pipeline(model="None", device="cuda")
24
+ output = rewarder(text)[0]
25
+ print(output["score"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with Reward.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.24.0
38
+ - Transformers: 4.57.1
39
+ - Pytorch: 2.8.0+cu126
40
+ - Datasets: 4.0.0
41
+ - Tokenizers: 0.22.1
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForSequenceClassification"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8960,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_types": [
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention"
47
+ ],
48
+ "max_position_embeddings": 32768,
49
+ "max_window_layers": 21,
50
+ "model_type": "qwen2",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 28,
53
+ "num_key_value_heads": 2,
54
+ "pad_token_id": 151643,
55
+ "rms_norm_eps": 1e-06,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000.0,
58
+ "sliding_window": null,
59
+ "tie_word_embeddings": true,
60
+ "transformers_version": "4.57.1",
61
+ "use_cache": false,
62
+ "use_sliding_window": false,
63
+ "vocab_size": 151936
64
+ }
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 sha256:7b38ca0631c6e2f17358511f2fcd1fafbb0aedbc6ff64fad0de2b3be597536c5
3
+ size 3087470304
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0803422231b9230816ac6ada61af4d0e4b39611648821e94f8e96b0856e992c
3
+ size 6175160780
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
3
+ size 14645
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7c349d29b0b8d14cd2c51a07bbaf5e6a2d10e6b1a0265a098a619addd9814f
3
+ size 1465
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 7.878235010139178e-06,
4
+ "best_model_checkpoint": "models/reward-model/checkpoint-100",
5
+ "epoch": 2.712328767123288,
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
+ "accuracy": 0.475,
14
+ "epoch": 0.273972602739726,
15
+ "grad_norm": 30.625,
16
+ "learning_rate": 9.000000000000001e-07,
17
+ "loss": 0.6891,
18
+ "margin": 0.01259765625,
19
+ "max_reward": 0.8927734375,
20
+ "mean_reward": 0.841064453125,
21
+ "min_reward": 0.78935546875,
22
+ "num_tokens": 33836.0,
23
+ "step": 10
24
+ },
25
+ {
26
+ "accuracy": 0.7,
27
+ "epoch": 0.547945205479452,
28
+ "grad_norm": 31.0,
29
+ "learning_rate": 1.9000000000000002e-06,
30
+ "loss": 0.6556,
31
+ "margin": 0.08076171875,
32
+ "max_reward": 0.940087890625,
33
+ "mean_reward": 0.881591796875,
34
+ "min_reward": 0.823095703125,
35
+ "num_tokens": 68438.0,
36
+ "step": 20
37
+ },
38
+ {
39
+ "accuracy": 0.875,
40
+ "epoch": 0.821917808219178,
41
+ "grad_norm": 42.75,
42
+ "learning_rate": 2.9e-06,
43
+ "loss": 0.5442,
44
+ "margin": 0.348681640625,
45
+ "max_reward": 1.237109375,
46
+ "mean_reward": 1.0571533203125,
47
+ "min_reward": 0.877197265625,
48
+ "num_tokens": 102129.0,
49
+ "step": 30
50
+ },
51
+ {
52
+ "accuracy": 0.9473684210526315,
53
+ "epoch": 1.0821917808219177,
54
+ "grad_norm": 33.5,
55
+ "learning_rate": 3.900000000000001e-06,
56
+ "loss": 0.3195,
57
+ "margin": 1.2310598273026316,
58
+ "max_reward": 2.8731496710526314,
59
+ "mean_reward": 2.2488820929276314,
60
+ "min_reward": 1.6246145148026316,
61
+ "num_tokens": 134446.0,
62
+ "step": 40
63
+ },
64
+ {
65
+ "accuracy": 1.0,
66
+ "epoch": 1.356164383561644,
67
+ "grad_norm": 0.357421875,
68
+ "learning_rate": 4.9000000000000005e-06,
69
+ "loss": 0.0364,
70
+ "margin": 6.142855834960938,
71
+ "max_reward": 5.8197265625,
72
+ "mean_reward": 2.7482986450195312,
73
+ "min_reward": -0.3231292724609375,
74
+ "num_tokens": 168483.0,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 1.356164383561644,
79
+ "eval_accuracy": 1.0,
80
+ "eval_loss": 9.938376024365425e-05,
81
+ "eval_margin": 12.761437618371213,
82
+ "eval_max_reward": 9.329545454545455,
83
+ "eval_mean_reward": 2.9488266453598486,
84
+ "eval_min_reward": -3.431892163825758,
85
+ "eval_num_tokens": 168483.0,
86
+ "eval_runtime": 1.3469,
87
+ "eval_samples_per_second": 24.501,
88
+ "eval_steps_per_second": 24.501,
89
+ "step": 50
90
+ },
91
+ {
92
+ "accuracy": 1.0,
93
+ "epoch": 1.6301369863013697,
94
+ "grad_norm": 2.86102294921875e-05,
95
+ "learning_rate": 4.736217705571989e-06,
96
+ "loss": 0.0,
97
+ "margin": 17.22467498779297,
98
+ "max_reward": 11.6734375,
99
+ "mean_reward": 3.0611000061035156,
100
+ "min_reward": -5.551237487792969,
101
+ "num_tokens": 202410.0,
102
+ "step": 60
103
+ },
104
+ {
105
+ "accuracy": 1.0,
106
+ "epoch": 1.904109589041096,
107
+ "grad_norm": 0.2412109375,
108
+ "learning_rate": 3.895609305067162e-06,
109
+ "loss": 0.0001,
110
+ "margin": 19.885546875,
111
+ "max_reward": 12.878125,
112
+ "mean_reward": 2.9353515625,
113
+ "min_reward": -7.007421875,
114
+ "num_tokens": 236144.0,
115
+ "step": 70
116
+ },
117
+ {
118
+ "accuracy": 1.0,
119
+ "epoch": 2.1643835616438354,
120
+ "grad_norm": 0.00116729736328125,
121
+ "learning_rate": 2.6929386553166165e-06,
122
+ "loss": 0.0,
123
+ "margin": 19.66786595394737,
124
+ "max_reward": 12.293071546052632,
125
+ "mean_reward": 2.4591385690789473,
126
+ "min_reward": -7.374794407894737,
127
+ "num_tokens": 268578.0,
128
+ "step": 80
129
+ },
130
+ {
131
+ "accuracy": 1.0,
132
+ "epoch": 2.4383561643835616,
133
+ "grad_norm": 2.396106719970703e-05,
134
+ "learning_rate": 1.4402140232253486e-06,
135
+ "loss": 0.0,
136
+ "margin": 20.334765625,
137
+ "max_reward": 12.90859375,
138
+ "mean_reward": 2.7412109375,
139
+ "min_reward": -7.426171875,
140
+ "num_tokens": 303010.0,
141
+ "step": 90
142
+ },
143
+ {
144
+ "accuracy": 1.0,
145
+ "epoch": 2.712328767123288,
146
+ "grad_norm": 0.00677490234375,
147
+ "learning_rate": 4.624291562079719e-07,
148
+ "loss": 0.0,
149
+ "margin": 19.507958984375,
150
+ "max_reward": 12.3116943359375,
151
+ "mean_reward": 2.55771484375,
152
+ "min_reward": -7.1962646484375,
153
+ "num_tokens": 336849.0,
154
+ "step": 100
155
+ },
156
+ {
157
+ "epoch": 2.712328767123288,
158
+ "eval_accuracy": 1.0,
159
+ "eval_loss": 7.878235010139178e-06,
160
+ "eval_margin": 19.414299242424242,
161
+ "eval_max_reward": 12.067708333333334,
162
+ "eval_mean_reward": 2.360558712121212,
163
+ "eval_min_reward": -7.346590909090909,
164
+ "eval_num_tokens": 336849.0,
165
+ "eval_runtime": 1.3603,
166
+ "eval_samples_per_second": 24.26,
167
+ "eval_steps_per_second": 24.26,
168
+ "step": 100
169
+ }
170
+ ],
171
+ "logging_steps": 10,
172
+ "max_steps": 111,
173
+ "num_input_tokens_seen": 0,
174
+ "num_train_epochs": 3,
175
+ "save_steps": 50,
176
+ "stateful_callbacks": {
177
+ "TrainerControl": {
178
+ "args": {
179
+ "should_epoch_stop": false,
180
+ "should_evaluate": false,
181
+ "should_log": false,
182
+ "should_save": true,
183
+ "should_training_stop": false
184
+ },
185
+ "attributes": {}
186
+ }
187
+ },
188
+ "total_flos": 2867841023201280.0,
189
+ "train_batch_size": 1,
190
+ "trial_name": null,
191
+ "trial_params": null
192
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e0f7bd6a9b4ac0438041839da49be75d09ce59ae00987578bd88e38b213335
3
+ size 6033
checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-111/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-111/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-111/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForSequenceClassification"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8960,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_types": [
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention"
47
+ ],
48
+ "max_position_embeddings": 32768,
49
+ "max_window_layers": 21,
50
+ "model_type": "qwen2",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 28,
53
+ "num_key_value_heads": 2,
54
+ "pad_token_id": 151643,
55
+ "rms_norm_eps": 1e-06,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000.0,
58
+ "sliding_window": null,
59
+ "tie_word_embeddings": true,
60
+ "transformers_version": "4.57.1",
61
+ "use_cache": false,
62
+ "use_sliding_window": false,
63
+ "vocab_size": 151936
64
+ }
checkpoint-111/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-111/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2720065823d0e3e9ec80926c7a0dfc6b9275d95eb9d5975e610724f96b0f8c
3
+ size 3087470304
checkpoint-111/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f801f831ca49e92fa74667a97eaa3fe8c0b8efffb09c3046bc91864857771ab7
3
+ size 6175160780
checkpoint-111/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
3
+ size 14645
checkpoint-111/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a31479958e7f1ee6e177b124124820210904982e74490325373877a6570f92
3
+ size 1465
checkpoint-111/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
checkpoint-111/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-111/trainer_state.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 7.878235010139178e-06,
4
+ "best_model_checkpoint": "models/reward-model/checkpoint-100",
5
+ "epoch": 3.0,
6
+ "eval_steps": 50,
7
+ "global_step": 111,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "accuracy": 0.475,
14
+ "epoch": 0.273972602739726,
15
+ "grad_norm": 30.625,
16
+ "learning_rate": 9.000000000000001e-07,
17
+ "loss": 0.6891,
18
+ "margin": 0.01259765625,
19
+ "max_reward": 0.8927734375,
20
+ "mean_reward": 0.841064453125,
21
+ "min_reward": 0.78935546875,
22
+ "num_tokens": 33836.0,
23
+ "step": 10
24
+ },
25
+ {
26
+ "accuracy": 0.7,
27
+ "epoch": 0.547945205479452,
28
+ "grad_norm": 31.0,
29
+ "learning_rate": 1.9000000000000002e-06,
30
+ "loss": 0.6556,
31
+ "margin": 0.08076171875,
32
+ "max_reward": 0.940087890625,
33
+ "mean_reward": 0.881591796875,
34
+ "min_reward": 0.823095703125,
35
+ "num_tokens": 68438.0,
36
+ "step": 20
37
+ },
38
+ {
39
+ "accuracy": 0.875,
40
+ "epoch": 0.821917808219178,
41
+ "grad_norm": 42.75,
42
+ "learning_rate": 2.9e-06,
43
+ "loss": 0.5442,
44
+ "margin": 0.348681640625,
45
+ "max_reward": 1.237109375,
46
+ "mean_reward": 1.0571533203125,
47
+ "min_reward": 0.877197265625,
48
+ "num_tokens": 102129.0,
49
+ "step": 30
50
+ },
51
+ {
52
+ "accuracy": 0.9473684210526315,
53
+ "epoch": 1.0821917808219177,
54
+ "grad_norm": 33.5,
55
+ "learning_rate": 3.900000000000001e-06,
56
+ "loss": 0.3195,
57
+ "margin": 1.2310598273026316,
58
+ "max_reward": 2.8731496710526314,
59
+ "mean_reward": 2.2488820929276314,
60
+ "min_reward": 1.6246145148026316,
61
+ "num_tokens": 134446.0,
62
+ "step": 40
63
+ },
64
+ {
65
+ "accuracy": 1.0,
66
+ "epoch": 1.356164383561644,
67
+ "grad_norm": 0.357421875,
68
+ "learning_rate": 4.9000000000000005e-06,
69
+ "loss": 0.0364,
70
+ "margin": 6.142855834960938,
71
+ "max_reward": 5.8197265625,
72
+ "mean_reward": 2.7482986450195312,
73
+ "min_reward": -0.3231292724609375,
74
+ "num_tokens": 168483.0,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 1.356164383561644,
79
+ "eval_accuracy": 1.0,
80
+ "eval_loss": 9.938376024365425e-05,
81
+ "eval_margin": 12.761437618371213,
82
+ "eval_max_reward": 9.329545454545455,
83
+ "eval_mean_reward": 2.9488266453598486,
84
+ "eval_min_reward": -3.431892163825758,
85
+ "eval_num_tokens": 168483.0,
86
+ "eval_runtime": 1.3469,
87
+ "eval_samples_per_second": 24.501,
88
+ "eval_steps_per_second": 24.501,
89
+ "step": 50
90
+ },
91
+ {
92
+ "accuracy": 1.0,
93
+ "epoch": 1.6301369863013697,
94
+ "grad_norm": 2.86102294921875e-05,
95
+ "learning_rate": 4.736217705571989e-06,
96
+ "loss": 0.0,
97
+ "margin": 17.22467498779297,
98
+ "max_reward": 11.6734375,
99
+ "mean_reward": 3.0611000061035156,
100
+ "min_reward": -5.551237487792969,
101
+ "num_tokens": 202410.0,
102
+ "step": 60
103
+ },
104
+ {
105
+ "accuracy": 1.0,
106
+ "epoch": 1.904109589041096,
107
+ "grad_norm": 0.2412109375,
108
+ "learning_rate": 3.895609305067162e-06,
109
+ "loss": 0.0001,
110
+ "margin": 19.885546875,
111
+ "max_reward": 12.878125,
112
+ "mean_reward": 2.9353515625,
113
+ "min_reward": -7.007421875,
114
+ "num_tokens": 236144.0,
115
+ "step": 70
116
+ },
117
+ {
118
+ "accuracy": 1.0,
119
+ "epoch": 2.1643835616438354,
120
+ "grad_norm": 0.00116729736328125,
121
+ "learning_rate": 2.6929386553166165e-06,
122
+ "loss": 0.0,
123
+ "margin": 19.66786595394737,
124
+ "max_reward": 12.293071546052632,
125
+ "mean_reward": 2.4591385690789473,
126
+ "min_reward": -7.374794407894737,
127
+ "num_tokens": 268578.0,
128
+ "step": 80
129
+ },
130
+ {
131
+ "accuracy": 1.0,
132
+ "epoch": 2.4383561643835616,
133
+ "grad_norm": 2.396106719970703e-05,
134
+ "learning_rate": 1.4402140232253486e-06,
135
+ "loss": 0.0,
136
+ "margin": 20.334765625,
137
+ "max_reward": 12.90859375,
138
+ "mean_reward": 2.7412109375,
139
+ "min_reward": -7.426171875,
140
+ "num_tokens": 303010.0,
141
+ "step": 90
142
+ },
143
+ {
144
+ "accuracy": 1.0,
145
+ "epoch": 2.712328767123288,
146
+ "grad_norm": 0.00677490234375,
147
+ "learning_rate": 4.624291562079719e-07,
148
+ "loss": 0.0,
149
+ "margin": 19.507958984375,
150
+ "max_reward": 12.3116943359375,
151
+ "mean_reward": 2.55771484375,
152
+ "min_reward": -7.1962646484375,
153
+ "num_tokens": 336849.0,
154
+ "step": 100
155
+ },
156
+ {
157
+ "epoch": 2.712328767123288,
158
+ "eval_accuracy": 1.0,
159
+ "eval_loss": 7.878235010139178e-06,
160
+ "eval_margin": 19.414299242424242,
161
+ "eval_max_reward": 12.067708333333334,
162
+ "eval_mean_reward": 2.360558712121212,
163
+ "eval_min_reward": -7.346590909090909,
164
+ "eval_num_tokens": 336849.0,
165
+ "eval_runtime": 1.3603,
166
+ "eval_samples_per_second": 24.26,
167
+ "eval_steps_per_second": 24.26,
168
+ "step": 100
169
+ },
170
+ {
171
+ "accuracy": 1.0,
172
+ "epoch": 2.9863013698630136,
173
+ "grad_norm": 6.866455078125e-05,
174
+ "learning_rate": 1.3250310963527358e-08,
175
+ "loss": 0.0,
176
+ "margin": 20.3682373046875,
177
+ "max_reward": 12.6564453125,
178
+ "mean_reward": 2.47232666015625,
179
+ "min_reward": -7.7117919921875,
180
+ "num_tokens": 370214.0,
181
+ "step": 110
182
+ }
183
+ ],
184
+ "logging_steps": 10,
185
+ "max_steps": 111,
186
+ "num_input_tokens_seen": 0,
187
+ "num_train_epochs": 3,
188
+ "save_steps": 50,
189
+ "stateful_callbacks": {
190
+ "TrainerControl": {
191
+ "args": {
192
+ "should_epoch_stop": false,
193
+ "should_evaluate": false,
194
+ "should_log": false,
195
+ "should_save": true,
196
+ "should_training_stop": true
197
+ },
198
+ "attributes": {}
199
+ }
200
+ },
201
+ "total_flos": 3167290892685312.0,
202
+ "train_batch_size": 1,
203
+ "trial_name": null,
204
+ "trial_params": null
205
+ }
checkpoint-111/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e0f7bd6a9b4ac0438041839da49be75d09ce59ae00987578bd88e38b213335
3
+ size 6033
checkpoint-111/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForSequenceClassification"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8960,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_types": [
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention"
47
+ ],
48
+ "max_position_embeddings": 32768,
49
+ "max_window_layers": 21,
50
+ "model_type": "qwen2",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 28,
53
+ "num_key_value_heads": 2,
54
+ "pad_token_id": 151643,
55
+ "rms_norm_eps": 1e-06,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000.0,
58
+ "sliding_window": null,
59
+ "tie_word_embeddings": true,
60
+ "transformers_version": "4.57.1",
61
+ "use_cache": false,
62
+ "use_sliding_window": false,
63
+ "vocab_size": 151936
64
+ }
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 sha256:7b38ca0631c6e2f17358511f2fcd1fafbb0aedbc6ff64fad0de2b3be597536c5
3
+ size 3087470304
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e0f7bd6a9b4ac0438041839da49be75d09ce59ae00987578bd88e38b213335
3
+ size 6033
vocab.json ADDED
The diff for this file is too large to render. See raw diff