Hugging Face's logo

EdgarDesnos
/
MNLP_M2_quantized_model

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
EdgarDesnos commited on
Commit
b022a3f
·
verified ·
1 Parent(s): 6e73df0

Training in progress, step 162

Browse files
Files changed (38) hide show
  1. .gitattributes +3 -0
  2. added_tokens.json +28 -0
  3. config.json +30 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. sciq-ft/checkpoint-8000/added_tokens.json +28 -0
  7. sciq-ft/checkpoint-8000/config.json +30 -0
  8. sciq-ft/checkpoint-8000/generation_config.json +6 -0
  9. sciq-ft/checkpoint-8000/merges.txt +0 -0
  10. sciq-ft/checkpoint-8000/model.safetensors +3 -0
  11. sciq-ft/checkpoint-8000/optimizer.pt +3 -0
  12. sciq-ft/checkpoint-8000/rng_state.pth +3 -0
  13. sciq-ft/checkpoint-8000/scheduler.pt +3 -0
  14. sciq-ft/checkpoint-8000/special_tokens_map.json +31 -0
  15. sciq-ft/checkpoint-8000/tokenizer.json +3 -0
  16. sciq-ft/checkpoint-8000/tokenizer_config.json +240 -0
  17. sciq-ft/checkpoint-8000/trainer_state.json +274 -0
  18. sciq-ft/checkpoint-8000/training_args.bin +3 -0
  19. sciq-ft/checkpoint-8000/vocab.json +0 -0
  20. sciq-ft/checkpoint-8760/added_tokens.json +28 -0
  21. sciq-ft/checkpoint-8760/config.json +30 -0
  22. sciq-ft/checkpoint-8760/generation_config.json +6 -0
  23. sciq-ft/checkpoint-8760/merges.txt +0 -0
  24. sciq-ft/checkpoint-8760/model.safetensors +3 -0
  25. sciq-ft/checkpoint-8760/optimizer.pt +3 -0
  26. sciq-ft/checkpoint-8760/rng_state.pth +3 -0
  27. sciq-ft/checkpoint-8760/scheduler.pt +3 -0
  28. sciq-ft/checkpoint-8760/special_tokens_map.json +31 -0
  29. sciq-ft/checkpoint-8760/tokenizer.json +3 -0
  30. sciq-ft/checkpoint-8760/tokenizer_config.json +240 -0
  31. sciq-ft/checkpoint-8760/trainer_state.json +289 -0
  32. sciq-ft/checkpoint-8760/training_args.bin +3 -0
  33. sciq-ft/checkpoint-8760/vocab.json +0 -0
  34. special_tokens_map.json +31 -0
  35. tokenizer.json +3 -0
  36. tokenizer_config.json +240 -0
  37. training_args.bin +3 -0
  38. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ sciq-ft/checkpoint-8000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ sciq-ft/checkpoint-8760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
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:e9b596032d64c59bfa97e3a33bb7822b9b4c8783550ddc9652cc720f91cdf839
3
+ size 1192135096
sciq-ft/checkpoint-8000/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
sciq-ft/checkpoint-8000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
sciq-ft/checkpoint-8000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.51.3"
6
+ }
sciq-ft/checkpoint-8000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sciq-ft/checkpoint-8000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c98b1d482113169a8efecb8aa5eabdca548b413870999cfea9ab3768fd500d
3
+ size 1192135096
sciq-ft/checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f21a6cbeedd8fa50f36414e0037bf488142923642c611fdf2a708e5f85e8e6
3
+ size 2384459962
sciq-ft/checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d10ad6c90de119ae0a3eeecda7366634ce107ef267b5fdd3ddd046f0a5ae742
3
+ size 14244
sciq-ft/checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d934696cb13700fcf08600971e08a9eb843f07302bef593ca56a087829a435
3
+ size 1064
sciq-ft/checkpoint-8000/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
+ }
sciq-ft/checkpoint-8000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34931275ec59c5cdd5d27556564a3b1b9afb4a0706c8b785f0ee26b9c11b05e7
3
+ size 11422752
sciq-ft/checkpoint-8000/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
sciq-ft/checkpoint-8000/trainer_state.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.73972602739726,
6
+ "eval_steps": 500,
7
+ "global_step": 8000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17123287671232876,
14
+ "grad_norm": 153.0,
15
+ "learning_rate": 4.715182648401827e-05,
16
+ "loss": 2.2654,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.17123287671232876,
21
+ "eval_loss": 2.029487371444702,
22
+ "eval_runtime": 55.5788,
23
+ "eval_samples_per_second": 17.992,
24
+ "eval_steps_per_second": 4.498,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 0.3424657534246575,
29
+ "grad_norm": 12.3125,
30
+ "learning_rate": 4.429794520547945e-05,
31
+ "loss": 1.8311,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.3424657534246575,
36
+ "eval_loss": 1.7354652881622314,
37
+ "eval_runtime": 55.5711,
38
+ "eval_samples_per_second": 17.995,
39
+ "eval_steps_per_second": 4.499,
40
+ "step": 1000
41
+ },
42
+ {
43
+ "epoch": 0.5136986301369864,
44
+ "grad_norm": 12.1875,
45
+ "learning_rate": 4.1444063926940644e-05,
46
+ "loss": 1.7299,
47
+ "step": 1500
48
+ },
49
+ {
50
+ "epoch": 0.5136986301369864,
51
+ "eval_loss": 1.6786140203475952,
52
+ "eval_runtime": 55.522,
53
+ "eval_samples_per_second": 18.011,
54
+ "eval_steps_per_second": 4.503,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.684931506849315,
59
+ "grad_norm": 9.6875,
60
+ "learning_rate": 3.859018264840183e-05,
61
+ "loss": 1.6692,
62
+ "step": 2000
63
+ },
64
+ {
65
+ "epoch": 0.684931506849315,
66
+ "eval_loss": 1.6051782369613647,
67
+ "eval_runtime": 55.5564,
68
+ "eval_samples_per_second": 18.0,
69
+ "eval_steps_per_second": 4.5,
70
+ "step": 2000
71
+ },
72
+ {
73
+ "epoch": 0.8561643835616438,
74
+ "grad_norm": 10.75,
75
+ "learning_rate": 3.5736301369863016e-05,
76
+ "loss": 1.6183,
77
+ "step": 2500
78
+ },
79
+ {
80
+ "epoch": 0.8561643835616438,
81
+ "eval_loss": 1.58013916015625,
82
+ "eval_runtime": 55.5622,
83
+ "eval_samples_per_second": 17.998,
84
+ "eval_steps_per_second": 4.499,
85
+ "step": 2500
86
+ },
87
+ {
88
+ "epoch": 1.0273972602739727,
89
+ "grad_norm": 12.9375,
90
+ "learning_rate": 3.28824200913242e-05,
91
+ "loss": 1.5077,
92
+ "step": 3000
93
+ },
94
+ {
95
+ "epoch": 1.0273972602739727,
96
+ "eval_loss": 1.5768251419067383,
97
+ "eval_runtime": 55.5815,
98
+ "eval_samples_per_second": 17.992,
99
+ "eval_steps_per_second": 4.498,
100
+ "step": 3000
101
+ },
102
+ {
103
+ "epoch": 1.1986301369863013,
104
+ "grad_norm": 22.0,
105
+ "learning_rate": 3.002853881278539e-05,
106
+ "loss": 1.1265,
107
+ "step": 3500
108
+ },
109
+ {
110
+ "epoch": 1.1986301369863013,
111
+ "eval_loss": 1.5545296669006348,
112
+ "eval_runtime": 55.5906,
113
+ "eval_samples_per_second": 17.989,
114
+ "eval_steps_per_second": 4.497,
115
+ "step": 3500
116
+ },
117
+ {
118
+ "epoch": 1.36986301369863,
119
+ "grad_norm": 12.875,
120
+ "learning_rate": 2.717465753424658e-05,
121
+ "loss": 1.1601,
122
+ "step": 4000
123
+ },
124
+ {
125
+ "epoch": 1.36986301369863,
126
+ "eval_loss": 1.5548871755599976,
127
+ "eval_runtime": 55.6195,
128
+ "eval_samples_per_second": 17.979,
129
+ "eval_steps_per_second": 4.495,
130
+ "step": 4000
131
+ },
132
+ {
133
+ "epoch": 1.541095890410959,
134
+ "grad_norm": 11.6875,
135
+ "learning_rate": 2.4320776255707765e-05,
136
+ "loss": 1.1706,
137
+ "step": 4500
138
+ },
139
+ {
140
+ "epoch": 1.541095890410959,
141
+ "eval_loss": 1.5420197248458862,
142
+ "eval_runtime": 55.6325,
143
+ "eval_samples_per_second": 17.975,
144
+ "eval_steps_per_second": 4.494,
145
+ "step": 4500
146
+ },
147
+ {
148
+ "epoch": 1.7123287671232876,
149
+ "grad_norm": 12.5625,
150
+ "learning_rate": 2.146689497716895e-05,
151
+ "loss": 1.1838,
152
+ "step": 5000
153
+ },
154
+ {
155
+ "epoch": 1.7123287671232876,
156
+ "eval_loss": 1.5276223421096802,
157
+ "eval_runtime": 55.5066,
158
+ "eval_samples_per_second": 18.016,
159
+ "eval_steps_per_second": 4.504,
160
+ "step": 5000
161
+ },
162
+ {
163
+ "epoch": 1.8835616438356164,
164
+ "grad_norm": 10.25,
165
+ "learning_rate": 1.8613013698630137e-05,
166
+ "loss": 1.1338,
167
+ "step": 5500
168
+ },
169
+ {
170
+ "epoch": 1.8835616438356164,
171
+ "eval_loss": 1.5283408164978027,
172
+ "eval_runtime": 55.5647,
173
+ "eval_samples_per_second": 17.997,
174
+ "eval_steps_per_second": 4.499,
175
+ "step": 5500
176
+ },
177
+ {
178
+ "epoch": 2.0547945205479454,
179
+ "grad_norm": 12.5625,
180
+ "learning_rate": 1.5759132420091324e-05,
181
+ "loss": 1.0613,
182
+ "step": 6000
183
+ },
184
+ {
185
+ "epoch": 2.0547945205479454,
186
+ "eval_loss": 1.6014325618743896,
187
+ "eval_runtime": 55.5549,
188
+ "eval_samples_per_second": 18.0,
189
+ "eval_steps_per_second": 4.5,
190
+ "step": 6000
191
+ },
192
+ {
193
+ "epoch": 2.2260273972602738,
194
+ "grad_norm": 14.3125,
195
+ "learning_rate": 1.2905251141552513e-05,
196
+ "loss": 0.9625,
197
+ "step": 6500
198
+ },
199
+ {
200
+ "epoch": 2.2260273972602738,
201
+ "eval_loss": 1.6062899827957153,
202
+ "eval_runtime": 55.5464,
203
+ "eval_samples_per_second": 18.003,
204
+ "eval_steps_per_second": 4.501,
205
+ "step": 6500
206
+ },
207
+ {
208
+ "epoch": 2.3972602739726026,
209
+ "grad_norm": 20.25,
210
+ "learning_rate": 1.00513698630137e-05,
211
+ "loss": 0.9673,
212
+ "step": 7000
213
+ },
214
+ {
215
+ "epoch": 2.3972602739726026,
216
+ "eval_loss": 1.604617714881897,
217
+ "eval_runtime": 55.51,
218
+ "eval_samples_per_second": 18.015,
219
+ "eval_steps_per_second": 4.504,
220
+ "step": 7000
221
+ },
222
+ {
223
+ "epoch": 2.5684931506849313,
224
+ "grad_norm": 9.9375,
225
+ "learning_rate": 7.197488584474886e-06,
226
+ "loss": 0.9199,
227
+ "step": 7500
228
+ },
229
+ {
230
+ "epoch": 2.5684931506849313,
231
+ "eval_loss": 1.6071116924285889,
232
+ "eval_runtime": 55.5428,
233
+ "eval_samples_per_second": 18.004,
234
+ "eval_steps_per_second": 4.501,
235
+ "step": 7500
236
+ },
237
+ {
238
+ "epoch": 2.73972602739726,
239
+ "grad_norm": 14.0625,
240
+ "learning_rate": 4.343607305936073e-06,
241
+ "loss": 0.9577,
242
+ "step": 8000
243
+ },
244
+ {
245
+ "epoch": 2.73972602739726,
246
+ "eval_loss": 1.6057485342025757,
247
+ "eval_runtime": 55.568,
248
+ "eval_samples_per_second": 17.996,
249
+ "eval_steps_per_second": 4.499,
250
+ "step": 8000
251
+ }
252
+ ],
253
+ "logging_steps": 500,
254
+ "max_steps": 8760,
255
+ "num_input_tokens_seen": 0,
256
+ "num_train_epochs": 3,
257
+ "save_steps": 1000,
258
+ "stateful_callbacks": {
259
+ "TrainerControl": {
260
+ "args": {
261
+ "should_epoch_stop": false,
262
+ "should_evaluate": false,
263
+ "should_log": false,
264
+ "should_save": true,
265
+ "should_training_stop": false
266
+ },
267
+ "attributes": {}
268
+ }
269
+ },
270
+ "total_flos": 4.329700656257434e+16,
271
+ "train_batch_size": 4,
272
+ "trial_name": null,
273
+ "trial_params": null
274
+ }
sciq-ft/checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce27d5d8aa02275ab40c274f23da75bd9918644bec49abd3300c846e35d8df5
3
+ size 5240
sciq-ft/checkpoint-8000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sciq-ft/checkpoint-8760/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
sciq-ft/checkpoint-8760/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
sciq-ft/checkpoint-8760/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.51.3"
6
+ }
sciq-ft/checkpoint-8760/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sciq-ft/checkpoint-8760/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599640a35eb92d1671e812a00a736ce8fa7804a30fb20e42b37646d55572dea3
3
+ size 1192135096
sciq-ft/checkpoint-8760/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b73c082cc3d6a744ed730c1be9ada14fd537ad9bb25fc8c58bf4da691f448a7
3
+ size 2384459962
sciq-ft/checkpoint-8760/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afbf853352cfbcfea61884ff6a2ddcd2aee1ce8618589cf5b56912c1b160011
3
+ size 14244
sciq-ft/checkpoint-8760/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae960363f46a90de9efe4a47b990dcdc60045d95b3ed220fd91bbd6521e43161
3
+ size 1064
sciq-ft/checkpoint-8760/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
+ }
sciq-ft/checkpoint-8760/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34931275ec59c5cdd5d27556564a3b1b9afb4a0706c8b785f0ee26b9c11b05e7
3
+ size 11422752
sciq-ft/checkpoint-8760/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
sciq-ft/checkpoint-8760/trainer_state.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 8760,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17123287671232876,
14
+ "grad_norm": 153.0,
15
+ "learning_rate": 4.715182648401827e-05,
16
+ "loss": 2.2654,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.17123287671232876,
21
+ "eval_loss": 2.029487371444702,
22
+ "eval_runtime": 55.5788,
23
+ "eval_samples_per_second": 17.992,
24
+ "eval_steps_per_second": 4.498,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 0.3424657534246575,
29
+ "grad_norm": 12.3125,
30
+ "learning_rate": 4.429794520547945e-05,
31
+ "loss": 1.8311,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.3424657534246575,
36
+ "eval_loss": 1.7354652881622314,
37
+ "eval_runtime": 55.5711,
38
+ "eval_samples_per_second": 17.995,
39
+ "eval_steps_per_second": 4.499,
40
+ "step": 1000
41
+ },
42
+ {
43
+ "epoch": 0.5136986301369864,
44
+ "grad_norm": 12.1875,
45
+ "learning_rate": 4.1444063926940644e-05,
46
+ "loss": 1.7299,
47
+ "step": 1500
48
+ },
49
+ {
50
+ "epoch": 0.5136986301369864,
51
+ "eval_loss": 1.6786140203475952,
52
+ "eval_runtime": 55.522,
53
+ "eval_samples_per_second": 18.011,
54
+ "eval_steps_per_second": 4.503,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.684931506849315,
59
+ "grad_norm": 9.6875,
60
+ "learning_rate": 3.859018264840183e-05,
61
+ "loss": 1.6692,
62
+ "step": 2000
63
+ },
64
+ {
65
+ "epoch": 0.684931506849315,
66
+ "eval_loss": 1.6051782369613647,
67
+ "eval_runtime": 55.5564,
68
+ "eval_samples_per_second": 18.0,
69
+ "eval_steps_per_second": 4.5,
70
+ "step": 2000
71
+ },
72
+ {
73
+ "epoch": 0.8561643835616438,
74
+ "grad_norm": 10.75,
75
+ "learning_rate": 3.5736301369863016e-05,
76
+ "loss": 1.6183,
77
+ "step": 2500
78
+ },
79
+ {
80
+ "epoch": 0.8561643835616438,
81
+ "eval_loss": 1.58013916015625,
82
+ "eval_runtime": 55.5622,
83
+ "eval_samples_per_second": 17.998,
84
+ "eval_steps_per_second": 4.499,
85
+ "step": 2500
86
+ },
87
+ {
88
+ "epoch": 1.0273972602739727,
89
+ "grad_norm": 12.9375,
90
+ "learning_rate": 3.28824200913242e-05,
91
+ "loss": 1.5077,
92
+ "step": 3000
93
+ },
94
+ {
95
+ "epoch": 1.0273972602739727,
96
+ "eval_loss": 1.5768251419067383,
97
+ "eval_runtime": 55.5815,
98
+ "eval_samples_per_second": 17.992,
99
+ "eval_steps_per_second": 4.498,
100
+ "step": 3000
101
+ },
102
+ {
103
+ "epoch": 1.1986301369863013,
104
+ "grad_norm": 22.0,
105
+ "learning_rate": 3.002853881278539e-05,
106
+ "loss": 1.1265,
107
+ "step": 3500
108
+ },
109
+ {
110
+ "epoch": 1.1986301369863013,
111
+ "eval_loss": 1.5545296669006348,
112
+ "eval_runtime": 55.5906,
113
+ "eval_samples_per_second": 17.989,
114
+ "eval_steps_per_second": 4.497,
115
+ "step": 3500
116
+ },
117
+ {
118
+ "epoch": 1.36986301369863,
119
+ "grad_norm": 12.875,
120
+ "learning_rate": 2.717465753424658e-05,
121
+ "loss": 1.1601,
122
+ "step": 4000
123
+ },
124
+ {
125
+ "epoch": 1.36986301369863,
126
+ "eval_loss": 1.5548871755599976,
127
+ "eval_runtime": 55.6195,
128
+ "eval_samples_per_second": 17.979,
129
+ "eval_steps_per_second": 4.495,
130
+ "step": 4000
131
+ },
132
+ {
133
+ "epoch": 1.541095890410959,
134
+ "grad_norm": 11.6875,
135
+ "learning_rate": 2.4320776255707765e-05,
136
+ "loss": 1.1706,
137
+ "step": 4500
138
+ },
139
+ {
140
+ "epoch": 1.541095890410959,
141
+ "eval_loss": 1.5420197248458862,
142
+ "eval_runtime": 55.6325,
143
+ "eval_samples_per_second": 17.975,
144
+ "eval_steps_per_second": 4.494,
145
+ "step": 4500
146
+ },
147
+ {
148
+ "epoch": 1.7123287671232876,
149
+ "grad_norm": 12.5625,
150
+ "learning_rate": 2.146689497716895e-05,
151
+ "loss": 1.1838,
152
+ "step": 5000
153
+ },
154
+ {
155
+ "epoch": 1.7123287671232876,
156
+ "eval_loss": 1.5276223421096802,
157
+ "eval_runtime": 55.5066,
158
+ "eval_samples_per_second": 18.016,
159
+ "eval_steps_per_second": 4.504,
160
+ "step": 5000
161
+ },
162
+ {
163
+ "epoch": 1.8835616438356164,
164
+ "grad_norm": 10.25,
165
+ "learning_rate": 1.8613013698630137e-05,
166
+ "loss": 1.1338,
167
+ "step": 5500
168
+ },
169
+ {
170
+ "epoch": 1.8835616438356164,
171
+ "eval_loss": 1.5283408164978027,
172
+ "eval_runtime": 55.5647,
173
+ "eval_samples_per_second": 17.997,
174
+ "eval_steps_per_second": 4.499,
175
+ "step": 5500
176
+ },
177
+ {
178
+ "epoch": 2.0547945205479454,
179
+ "grad_norm": 12.5625,
180
+ "learning_rate": 1.5759132420091324e-05,
181
+ "loss": 1.0613,
182
+ "step": 6000
183
+ },
184
+ {
185
+ "epoch": 2.0547945205479454,
186
+ "eval_loss": 1.6014325618743896,
187
+ "eval_runtime": 55.5549,
188
+ "eval_samples_per_second": 18.0,
189
+ "eval_steps_per_second": 4.5,
190
+ "step": 6000
191
+ },
192
+ {
193
+ "epoch": 2.2260273972602738,
194
+ "grad_norm": 14.3125,
195
+ "learning_rate": 1.2905251141552513e-05,
196
+ "loss": 0.9625,
197
+ "step": 6500
198
+ },
199
+ {
200
+ "epoch": 2.2260273972602738,
201
+ "eval_loss": 1.6062899827957153,
202
+ "eval_runtime": 55.5464,
203
+ "eval_samples_per_second": 18.003,
204
+ "eval_steps_per_second": 4.501,
205
+ "step": 6500
206
+ },
207
+ {
208
+ "epoch": 2.3972602739726026,
209
+ "grad_norm": 20.25,
210
+ "learning_rate": 1.00513698630137e-05,
211
+ "loss": 0.9673,
212
+ "step": 7000
213
+ },
214
+ {
215
+ "epoch": 2.3972602739726026,
216
+ "eval_loss": 1.604617714881897,
217
+ "eval_runtime": 55.51,
218
+ "eval_samples_per_second": 18.015,
219
+ "eval_steps_per_second": 4.504,
220
+ "step": 7000
221
+ },
222
+ {
223
+ "epoch": 2.5684931506849313,
224
+ "grad_norm": 9.9375,
225
+ "learning_rate": 7.197488584474886e-06,
226
+ "loss": 0.9199,
227
+ "step": 7500
228
+ },
229
+ {
230
+ "epoch": 2.5684931506849313,
231
+ "eval_loss": 1.6071116924285889,
232
+ "eval_runtime": 55.5428,
233
+ "eval_samples_per_second": 18.004,
234
+ "eval_steps_per_second": 4.501,
235
+ "step": 7500
236
+ },
237
+ {
238
+ "epoch": 2.73972602739726,
239
+ "grad_norm": 14.0625,
240
+ "learning_rate": 4.343607305936073e-06,
241
+ "loss": 0.9577,
242
+ "step": 8000
243
+ },
244
+ {
245
+ "epoch": 2.73972602739726,
246
+ "eval_loss": 1.6057485342025757,
247
+ "eval_runtime": 55.568,
248
+ "eval_samples_per_second": 17.996,
249
+ "eval_steps_per_second": 4.499,
250
+ "step": 8000
251
+ },
252
+ {
253
+ "epoch": 2.910958904109589,
254
+ "grad_norm": 3.765625,
255
+ "learning_rate": 1.4897260273972603e-06,
256
+ "loss": 0.9317,
257
+ "step": 8500
258
+ },
259
+ {
260
+ "epoch": 2.910958904109589,
261
+ "eval_loss": 1.6053234338760376,
262
+ "eval_runtime": 55.5504,
263
+ "eval_samples_per_second": 18.002,
264
+ "eval_steps_per_second": 4.5,
265
+ "step": 8500
266
+ }
267
+ ],
268
+ "logging_steps": 500,
269
+ "max_steps": 8760,
270
+ "num_input_tokens_seen": 0,
271
+ "num_train_epochs": 3,
272
+ "save_steps": 1000,
273
+ "stateful_callbacks": {
274
+ "TrainerControl": {
275
+ "args": {
276
+ "should_epoch_stop": false,
277
+ "should_evaluate": false,
278
+ "should_log": false,
279
+ "should_save": true,
280
+ "should_training_stop": true
281
+ },
282
+ "attributes": {}
283
+ }
284
+ },
285
+ "total_flos": 4.740912616203878e+16,
286
+ "train_batch_size": 4,
287
+ "trial_name": null,
288
+ "trial_params": null
289
+ }
sciq-ft/checkpoint-8760/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce27d5d8aa02275ab40c274f23da75bd9918644bec49abd3300c846e35d8df5
3
+ size 5240
sciq-ft/checkpoint-8760/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c760c4e715b8fa39254607191eca619d9b0612d5b29d3002ac512a5b6cad7d55
3
+ size 11422934
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|endoftext|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed247a2bd9b2bc333f59fbef360bef7ac4fb6a792acad6c02b3b7574f22b20b
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff