lathug commited on
Commit
89ff672
·
verified ·
1 Parent(s): 7bd2137

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-17000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-17256/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/config-checkpoint.json ADDED
File without changes
.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
File without changes
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-17000/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-17000/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForSequenceClassification"
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
+ "pad_token_id": 151643,
21
+ "problem_type": "single_label_classification",
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000000,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.51.3",
29
+ "use_cache": true,
30
+ "use_sliding_window": false,
31
+ "vocab_size": 151936
32
+ }
checkpoint-17000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c166b9b50d3f6eda10204c6d98e30380c4f922b42b63f368affe5452dc5dc166
3
+ size 2384243248
checkpoint-17000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69092608cb2dce09bdac3a8ef8325b0aad1e8afab5cb61549989e6a5c3735634
3
+ size 4768680162
checkpoint-17000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
3
+ size 14244
checkpoint-17000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd76d09d4839d3ec8d0a83abdcb811ed9da5651592a5c391149417d7f1d30fb1
3
+ size 988
checkpoint-17000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c40f4da9303bce921e7e43188534d9637d8e3b22d8e3e76776e7907ad102653
3
+ size 1064
checkpoint-17000/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-17000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
3
+ size 11422932
checkpoint-17000/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
+ }
checkpoint-17000/trainer_state.json ADDED
@@ -0,0 +1,1264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.955493741307371,
6
+ "eval_steps": 3000,
7
+ "global_step": 17000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.017385257301808066,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 4.9727630968938346e-05,
16
+ "loss": 0.177,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.03477051460361613,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 4.943787668057488e-05,
23
+ "loss": 0.0,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.0521557719054242,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 4.914812239221141e-05,
30
+ "loss": 0.0,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.06954102920723226,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 4.885836810384794e-05,
37
+ "loss": 0.0,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.08692628650904033,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 4.856861381548447e-05,
44
+ "loss": 0.0,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.1043115438108484,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 4.827885952712101e-05,
51
+ "loss": 0.0,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.12169680111265646,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 4.798910523875754e-05,
58
+ "loss": 0.0,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.13908205841446453,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 4.769935095039407e-05,
65
+ "loss": 0.0,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.1564673157162726,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 4.74095966620306e-05,
72
+ "loss": 0.0,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.17385257301808066,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 4.711984237366713e-05,
79
+ "loss": 0.0,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.19123783031988872,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 4.683008808530366e-05,
86
+ "loss": 0.0,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.2086230876216968,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 4.6540333796940194e-05,
93
+ "loss": 0.0,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.22600834492350486,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 4.625057950857673e-05,
100
+ "loss": 0.0,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.24339360222531292,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 4.596082522021326e-05,
107
+ "loss": 0.0,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.260778859527121,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 4.5671070931849794e-05,
114
+ "loss": 0.0,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.27816411682892905,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 4.5381316643486325e-05,
121
+ "loss": 0.0,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.2955493741307371,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 4.5091562355122856e-05,
128
+ "loss": 0.0,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.3129346314325452,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 4.480180806675939e-05,
135
+ "loss": 0.0,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.33031988873435325,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 4.4512053778395924e-05,
142
+ "loss": 0.0,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.3477051460361613,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 4.4222299490032455e-05,
149
+ "loss": 0.0,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.3650904033379694,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 4.3932545201668987e-05,
156
+ "loss": 0.0,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.38247566063977745,
161
+ "grad_norm": 0.0,
162
+ "learning_rate": 4.364279091330552e-05,
163
+ "loss": 0.0,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.3998609179415855,
168
+ "grad_norm": 0.0,
169
+ "learning_rate": 4.335303662494205e-05,
170
+ "loss": 0.0,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.4172461752433936,
175
+ "grad_norm": 0.0,
176
+ "learning_rate": 4.306328233657858e-05,
177
+ "loss": 0.0,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.43463143254520165,
182
+ "grad_norm": 0.0,
183
+ "learning_rate": 4.277352804821512e-05,
184
+ "loss": 0.0,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.4520166898470097,
189
+ "grad_norm": 0.0,
190
+ "learning_rate": 4.248377375985165e-05,
191
+ "loss": 0.0,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 0.4694019471488178,
196
+ "grad_norm": 0.0,
197
+ "learning_rate": 4.219401947148818e-05,
198
+ "loss": 0.0,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 0.48678720445062584,
203
+ "grad_norm": 0.0,
204
+ "learning_rate": 4.190426518312471e-05,
205
+ "loss": 0.0,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 0.5041724617524339,
210
+ "grad_norm": 0.0,
211
+ "learning_rate": 4.161451089476124e-05,
212
+ "loss": 0.0,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 0.521557719054242,
217
+ "grad_norm": 0.0,
218
+ "learning_rate": 4.132475660639777e-05,
219
+ "loss": 0.0,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 0.521557719054242,
224
+ "eval_loss": 0.0,
225
+ "eval_runtime": 667.343,
226
+ "eval_samples_per_second": 17.239,
227
+ "eval_steps_per_second": 8.619,
228
+ "step": 3000
229
+ },
230
+ {
231
+ "epoch": 0.53894297635605,
232
+ "grad_norm": 0.0,
233
+ "learning_rate": 4.103500231803431e-05,
234
+ "loss": 0.0,
235
+ "step": 3100
236
+ },
237
+ {
238
+ "epoch": 0.5563282336578581,
239
+ "grad_norm": 0.0,
240
+ "learning_rate": 4.074524802967084e-05,
241
+ "loss": 0.0,
242
+ "step": 3200
243
+ },
244
+ {
245
+ "epoch": 0.5737134909596662,
246
+ "grad_norm": 0.0,
247
+ "learning_rate": 4.045549374130737e-05,
248
+ "loss": 0.0,
249
+ "step": 3300
250
+ },
251
+ {
252
+ "epoch": 0.5910987482614742,
253
+ "grad_norm": 0.0,
254
+ "learning_rate": 4.016573945294391e-05,
255
+ "loss": 0.0,
256
+ "step": 3400
257
+ },
258
+ {
259
+ "epoch": 0.6084840055632823,
260
+ "grad_norm": 0.0,
261
+ "learning_rate": 3.9875985164580434e-05,
262
+ "loss": 0.0,
263
+ "step": 3500
264
+ },
265
+ {
266
+ "epoch": 0.6258692628650904,
267
+ "grad_norm": 0.0,
268
+ "learning_rate": 3.9586230876216965e-05,
269
+ "loss": 0.0,
270
+ "step": 3600
271
+ },
272
+ {
273
+ "epoch": 0.6432545201668984,
274
+ "grad_norm": 0.0,
275
+ "learning_rate": 3.92964765878535e-05,
276
+ "loss": 0.0,
277
+ "step": 3700
278
+ },
279
+ {
280
+ "epoch": 0.6606397774687065,
281
+ "grad_norm": 0.0,
282
+ "learning_rate": 3.9006722299490034e-05,
283
+ "loss": 0.0,
284
+ "step": 3800
285
+ },
286
+ {
287
+ "epoch": 0.6780250347705146,
288
+ "grad_norm": 0.0,
289
+ "learning_rate": 3.8716968011126565e-05,
290
+ "loss": 0.0,
291
+ "step": 3900
292
+ },
293
+ {
294
+ "epoch": 0.6954102920723226,
295
+ "grad_norm": 0.0,
296
+ "learning_rate": 3.84272137227631e-05,
297
+ "loss": 0.0,
298
+ "step": 4000
299
+ },
300
+ {
301
+ "epoch": 0.7127955493741307,
302
+ "grad_norm": 0.0,
303
+ "learning_rate": 3.8137459434399634e-05,
304
+ "loss": 0.0,
305
+ "step": 4100
306
+ },
307
+ {
308
+ "epoch": 0.7301808066759388,
309
+ "grad_norm": 0.0,
310
+ "learning_rate": 3.784770514603616e-05,
311
+ "loss": 0.0,
312
+ "step": 4200
313
+ },
314
+ {
315
+ "epoch": 0.7475660639777468,
316
+ "grad_norm": 0.0,
317
+ "learning_rate": 3.7557950857672696e-05,
318
+ "loss": 0.0,
319
+ "step": 4300
320
+ },
321
+ {
322
+ "epoch": 0.7649513212795549,
323
+ "grad_norm": 0.0,
324
+ "learning_rate": 3.726819656930923e-05,
325
+ "loss": 0.0,
326
+ "step": 4400
327
+ },
328
+ {
329
+ "epoch": 0.782336578581363,
330
+ "grad_norm": 0.0,
331
+ "learning_rate": 3.697844228094576e-05,
332
+ "loss": 0.0,
333
+ "step": 4500
334
+ },
335
+ {
336
+ "epoch": 0.799721835883171,
337
+ "grad_norm": 0.0,
338
+ "learning_rate": 3.6688687992582296e-05,
339
+ "loss": 0.0,
340
+ "step": 4600
341
+ },
342
+ {
343
+ "epoch": 0.8171070931849791,
344
+ "grad_norm": 0.0,
345
+ "learning_rate": 3.639893370421883e-05,
346
+ "loss": 0.0,
347
+ "step": 4700
348
+ },
349
+ {
350
+ "epoch": 0.8344923504867872,
351
+ "grad_norm": 0.0,
352
+ "learning_rate": 3.610917941585535e-05,
353
+ "loss": 0.0,
354
+ "step": 4800
355
+ },
356
+ {
357
+ "epoch": 0.8518776077885952,
358
+ "grad_norm": 0.0,
359
+ "learning_rate": 3.581942512749189e-05,
360
+ "loss": 0.0,
361
+ "step": 4900
362
+ },
363
+ {
364
+ "epoch": 0.8692628650904033,
365
+ "grad_norm": 0.0,
366
+ "learning_rate": 3.552967083912842e-05,
367
+ "loss": 0.0,
368
+ "step": 5000
369
+ },
370
+ {
371
+ "epoch": 0.8866481223922114,
372
+ "grad_norm": 0.0,
373
+ "learning_rate": 3.523991655076495e-05,
374
+ "loss": 0.0,
375
+ "step": 5100
376
+ },
377
+ {
378
+ "epoch": 0.9040333796940194,
379
+ "grad_norm": 0.0,
380
+ "learning_rate": 3.495016226240149e-05,
381
+ "loss": 0.0,
382
+ "step": 5200
383
+ },
384
+ {
385
+ "epoch": 0.9214186369958275,
386
+ "grad_norm": 0.0,
387
+ "learning_rate": 3.466040797403802e-05,
388
+ "loss": 0.0,
389
+ "step": 5300
390
+ },
391
+ {
392
+ "epoch": 0.9388038942976356,
393
+ "grad_norm": 0.0,
394
+ "learning_rate": 3.437065368567455e-05,
395
+ "loss": 0.0,
396
+ "step": 5400
397
+ },
398
+ {
399
+ "epoch": 0.9561891515994436,
400
+ "grad_norm": 0.0,
401
+ "learning_rate": 3.408089939731108e-05,
402
+ "loss": 0.0,
403
+ "step": 5500
404
+ },
405
+ {
406
+ "epoch": 0.9735744089012517,
407
+ "grad_norm": 0.0,
408
+ "learning_rate": 3.379114510894761e-05,
409
+ "loss": 0.0,
410
+ "step": 5600
411
+ },
412
+ {
413
+ "epoch": 0.9909596662030598,
414
+ "grad_norm": 0.0,
415
+ "learning_rate": 3.3501390820584144e-05,
416
+ "loss": 0.0,
417
+ "step": 5700
418
+ },
419
+ {
420
+ "epoch": 1.0083449235048678,
421
+ "grad_norm": 0.0,
422
+ "learning_rate": 3.321163653222068e-05,
423
+ "loss": 0.0,
424
+ "step": 5800
425
+ },
426
+ {
427
+ "epoch": 1.0257301808066759,
428
+ "grad_norm": 0.0,
429
+ "learning_rate": 3.292188224385721e-05,
430
+ "loss": 0.0,
431
+ "step": 5900
432
+ },
433
+ {
434
+ "epoch": 1.043115438108484,
435
+ "grad_norm": 0.0,
436
+ "learning_rate": 3.2632127955493744e-05,
437
+ "loss": 0.0,
438
+ "step": 6000
439
+ },
440
+ {
441
+ "epoch": 1.043115438108484,
442
+ "eval_loss": 0.0,
443
+ "eval_runtime": 693.3635,
444
+ "eval_samples_per_second": 16.592,
445
+ "eval_steps_per_second": 8.296,
446
+ "step": 6000
447
+ },
448
+ {
449
+ "epoch": 1.060500695410292,
450
+ "grad_norm": 0.0,
451
+ "learning_rate": 3.2342373667130275e-05,
452
+ "loss": 0.0,
453
+ "step": 6100
454
+ },
455
+ {
456
+ "epoch": 1.0778859527121,
457
+ "grad_norm": 0.0,
458
+ "learning_rate": 3.2052619378766806e-05,
459
+ "loss": 0.0,
460
+ "step": 6200
461
+ },
462
+ {
463
+ "epoch": 1.0952712100139081,
464
+ "grad_norm": 0.0,
465
+ "learning_rate": 3.1762865090403337e-05,
466
+ "loss": 0.0,
467
+ "step": 6300
468
+ },
469
+ {
470
+ "epoch": 1.1126564673157162,
471
+ "grad_norm": 0.0,
472
+ "learning_rate": 3.1473110802039874e-05,
473
+ "loss": 0.0,
474
+ "step": 6400
475
+ },
476
+ {
477
+ "epoch": 1.1300417246175243,
478
+ "grad_norm": 0.0,
479
+ "learning_rate": 3.1183356513676405e-05,
480
+ "loss": 0.0,
481
+ "step": 6500
482
+ },
483
+ {
484
+ "epoch": 1.1474269819193323,
485
+ "grad_norm": 0.0,
486
+ "learning_rate": 3.0893602225312936e-05,
487
+ "loss": 0.0,
488
+ "step": 6600
489
+ },
490
+ {
491
+ "epoch": 1.1648122392211404,
492
+ "grad_norm": 0.0,
493
+ "learning_rate": 3.060384793694947e-05,
494
+ "loss": 0.0,
495
+ "step": 6700
496
+ },
497
+ {
498
+ "epoch": 1.1821974965229485,
499
+ "grad_norm": 0.0,
500
+ "learning_rate": 3.0314093648586002e-05,
501
+ "loss": 0.0,
502
+ "step": 6800
503
+ },
504
+ {
505
+ "epoch": 1.1995827538247565,
506
+ "grad_norm": 0.0,
507
+ "learning_rate": 3.002433936022253e-05,
508
+ "loss": 0.0,
509
+ "step": 6900
510
+ },
511
+ {
512
+ "epoch": 1.2169680111265646,
513
+ "grad_norm": 0.0,
514
+ "learning_rate": 2.9734585071859067e-05,
515
+ "loss": 0.0,
516
+ "step": 7000
517
+ },
518
+ {
519
+ "epoch": 1.2343532684283727,
520
+ "grad_norm": 0.0,
521
+ "learning_rate": 2.9444830783495598e-05,
522
+ "loss": 0.0,
523
+ "step": 7100
524
+ },
525
+ {
526
+ "epoch": 1.2517385257301807,
527
+ "grad_norm": 0.0,
528
+ "learning_rate": 2.915507649513213e-05,
529
+ "loss": 0.0,
530
+ "step": 7200
531
+ },
532
+ {
533
+ "epoch": 1.2691237830319888,
534
+ "grad_norm": 0.0,
535
+ "learning_rate": 2.8865322206768664e-05,
536
+ "loss": 0.0,
537
+ "step": 7300
538
+ },
539
+ {
540
+ "epoch": 1.2865090403337969,
541
+ "grad_norm": 0.0,
542
+ "learning_rate": 2.8575567918405195e-05,
543
+ "loss": 0.0,
544
+ "step": 7400
545
+ },
546
+ {
547
+ "epoch": 1.303894297635605,
548
+ "grad_norm": 0.0,
549
+ "learning_rate": 2.8285813630041726e-05,
550
+ "loss": 0.0,
551
+ "step": 7500
552
+ },
553
+ {
554
+ "epoch": 1.321279554937413,
555
+ "grad_norm": 0.0,
556
+ "learning_rate": 2.799605934167826e-05,
557
+ "loss": 0.0,
558
+ "step": 7600
559
+ },
560
+ {
561
+ "epoch": 1.338664812239221,
562
+ "grad_norm": 0.0,
563
+ "learning_rate": 2.770630505331479e-05,
564
+ "loss": 0.0,
565
+ "step": 7700
566
+ },
567
+ {
568
+ "epoch": 1.3560500695410291,
569
+ "grad_norm": 0.0,
570
+ "learning_rate": 2.7416550764951322e-05,
571
+ "loss": 0.0,
572
+ "step": 7800
573
+ },
574
+ {
575
+ "epoch": 1.3734353268428372,
576
+ "grad_norm": 0.0,
577
+ "learning_rate": 2.7126796476587857e-05,
578
+ "loss": 0.0,
579
+ "step": 7900
580
+ },
581
+ {
582
+ "epoch": 1.3908205841446453,
583
+ "grad_norm": 0.0,
584
+ "learning_rate": 2.6837042188224388e-05,
585
+ "loss": 0.0,
586
+ "step": 8000
587
+ },
588
+ {
589
+ "epoch": 1.4082058414464533,
590
+ "grad_norm": 0.0,
591
+ "learning_rate": 2.654728789986092e-05,
592
+ "loss": 0.0,
593
+ "step": 8100
594
+ },
595
+ {
596
+ "epoch": 1.4255910987482614,
597
+ "grad_norm": 0.0,
598
+ "learning_rate": 2.6257533611497453e-05,
599
+ "loss": 0.0,
600
+ "step": 8200
601
+ },
602
+ {
603
+ "epoch": 1.4429763560500695,
604
+ "grad_norm": 0.0,
605
+ "learning_rate": 2.5967779323133984e-05,
606
+ "loss": 0.0,
607
+ "step": 8300
608
+ },
609
+ {
610
+ "epoch": 1.4603616133518775,
611
+ "grad_norm": 0.0,
612
+ "learning_rate": 2.5678025034770515e-05,
613
+ "loss": 0.0,
614
+ "step": 8400
615
+ },
616
+ {
617
+ "epoch": 1.4777468706536856,
618
+ "grad_norm": 0.0,
619
+ "learning_rate": 2.538827074640705e-05,
620
+ "loss": 0.0,
621
+ "step": 8500
622
+ },
623
+ {
624
+ "epoch": 1.4951321279554937,
625
+ "grad_norm": 0.0,
626
+ "learning_rate": 2.509851645804358e-05,
627
+ "loss": 0.0,
628
+ "step": 8600
629
+ },
630
+ {
631
+ "epoch": 1.512517385257302,
632
+ "grad_norm": 0.0,
633
+ "learning_rate": 2.4808762169680115e-05,
634
+ "loss": 0.0,
635
+ "step": 8700
636
+ },
637
+ {
638
+ "epoch": 1.5299026425591098,
639
+ "grad_norm": 0.0,
640
+ "learning_rate": 2.4519007881316642e-05,
641
+ "loss": 0.0,
642
+ "step": 8800
643
+ },
644
+ {
645
+ "epoch": 1.547287899860918,
646
+ "grad_norm": 0.0,
647
+ "learning_rate": 2.4229253592953177e-05,
648
+ "loss": 0.0,
649
+ "step": 8900
650
+ },
651
+ {
652
+ "epoch": 1.564673157162726,
653
+ "grad_norm": 0.0,
654
+ "learning_rate": 2.393949930458971e-05,
655
+ "loss": 0.0,
656
+ "step": 9000
657
+ },
658
+ {
659
+ "epoch": 1.564673157162726,
660
+ "eval_loss": 0.0,
661
+ "eval_runtime": 665.0981,
662
+ "eval_samples_per_second": 17.297,
663
+ "eval_steps_per_second": 8.648,
664
+ "step": 9000
665
+ },
666
+ {
667
+ "epoch": 1.5820584144645342,
668
+ "grad_norm": 0.0,
669
+ "learning_rate": 2.3649745016226242e-05,
670
+ "loss": 0.0,
671
+ "step": 9100
672
+ },
673
+ {
674
+ "epoch": 1.599443671766342,
675
+ "grad_norm": 0.0,
676
+ "learning_rate": 2.3359990727862773e-05,
677
+ "loss": 0.0,
678
+ "step": 9200
679
+ },
680
+ {
681
+ "epoch": 1.6168289290681503,
682
+ "grad_norm": 0.0,
683
+ "learning_rate": 2.3070236439499308e-05,
684
+ "loss": 0.0,
685
+ "step": 9300
686
+ },
687
+ {
688
+ "epoch": 1.6342141863699582,
689
+ "grad_norm": 0.0,
690
+ "learning_rate": 2.278048215113584e-05,
691
+ "loss": 0.0,
692
+ "step": 9400
693
+ },
694
+ {
695
+ "epoch": 1.6515994436717665,
696
+ "grad_norm": 0.0,
697
+ "learning_rate": 2.249072786277237e-05,
698
+ "loss": 0.0,
699
+ "step": 9500
700
+ },
701
+ {
702
+ "epoch": 1.6689847009735743,
703
+ "grad_norm": 0.0,
704
+ "learning_rate": 2.2200973574408904e-05,
705
+ "loss": 0.0,
706
+ "step": 9600
707
+ },
708
+ {
709
+ "epoch": 1.6863699582753826,
710
+ "grad_norm": 0.0,
711
+ "learning_rate": 2.1911219286045435e-05,
712
+ "loss": 0.0,
713
+ "step": 9700
714
+ },
715
+ {
716
+ "epoch": 1.7037552155771905,
717
+ "grad_norm": 0.0,
718
+ "learning_rate": 2.1621464997681966e-05,
719
+ "loss": 0.0,
720
+ "step": 9800
721
+ },
722
+ {
723
+ "epoch": 1.7211404728789987,
724
+ "grad_norm": 0.0,
725
+ "learning_rate": 2.1331710709318497e-05,
726
+ "loss": 0.0,
727
+ "step": 9900
728
+ },
729
+ {
730
+ "epoch": 1.7385257301808066,
731
+ "grad_norm": 0.0,
732
+ "learning_rate": 2.104195642095503e-05,
733
+ "loss": 0.0,
734
+ "step": 10000
735
+ },
736
+ {
737
+ "epoch": 1.7559109874826149,
738
+ "grad_norm": 0.0,
739
+ "learning_rate": 2.0752202132591563e-05,
740
+ "loss": 0.0,
741
+ "step": 10100
742
+ },
743
+ {
744
+ "epoch": 1.7732962447844227,
745
+ "grad_norm": 0.0,
746
+ "learning_rate": 2.0462447844228094e-05,
747
+ "loss": 0.0,
748
+ "step": 10200
749
+ },
750
+ {
751
+ "epoch": 1.790681502086231,
752
+ "grad_norm": 0.0,
753
+ "learning_rate": 2.0172693555864628e-05,
754
+ "loss": 0.0,
755
+ "step": 10300
756
+ },
757
+ {
758
+ "epoch": 1.8080667593880388,
759
+ "grad_norm": 0.0,
760
+ "learning_rate": 1.988293926750116e-05,
761
+ "loss": 0.0,
762
+ "step": 10400
763
+ },
764
+ {
765
+ "epoch": 1.8254520166898471,
766
+ "grad_norm": 0.0,
767
+ "learning_rate": 1.959318497913769e-05,
768
+ "loss": 0.0,
769
+ "step": 10500
770
+ },
771
+ {
772
+ "epoch": 1.842837273991655,
773
+ "grad_norm": 0.0,
774
+ "learning_rate": 1.9303430690774224e-05,
775
+ "loss": 0.0,
776
+ "step": 10600
777
+ },
778
+ {
779
+ "epoch": 1.8602225312934633,
780
+ "grad_norm": 0.0,
781
+ "learning_rate": 1.901367640241076e-05,
782
+ "loss": 0.0,
783
+ "step": 10700
784
+ },
785
+ {
786
+ "epoch": 1.877607788595271,
787
+ "grad_norm": 0.0,
788
+ "learning_rate": 1.8723922114047286e-05,
789
+ "loss": 0.0,
790
+ "step": 10800
791
+ },
792
+ {
793
+ "epoch": 1.8949930458970794,
794
+ "grad_norm": 0.0,
795
+ "learning_rate": 1.843416782568382e-05,
796
+ "loss": 0.0,
797
+ "step": 10900
798
+ },
799
+ {
800
+ "epoch": 1.9123783031988872,
801
+ "grad_norm": 0.0,
802
+ "learning_rate": 1.8144413537320355e-05,
803
+ "loss": 0.0,
804
+ "step": 11000
805
+ },
806
+ {
807
+ "epoch": 1.9297635605006955,
808
+ "grad_norm": 0.0,
809
+ "learning_rate": 1.7854659248956883e-05,
810
+ "loss": 0.0,
811
+ "step": 11100
812
+ },
813
+ {
814
+ "epoch": 1.9471488178025034,
815
+ "grad_norm": 0.0,
816
+ "learning_rate": 1.7564904960593417e-05,
817
+ "loss": 0.0,
818
+ "step": 11200
819
+ },
820
+ {
821
+ "epoch": 1.9645340751043117,
822
+ "grad_norm": 0.0,
823
+ "learning_rate": 1.727515067222995e-05,
824
+ "loss": 0.0,
825
+ "step": 11300
826
+ },
827
+ {
828
+ "epoch": 1.9819193324061195,
829
+ "grad_norm": 0.0,
830
+ "learning_rate": 1.698539638386648e-05,
831
+ "loss": 0.0,
832
+ "step": 11400
833
+ },
834
+ {
835
+ "epoch": 1.9993045897079278,
836
+ "grad_norm": 0.0,
837
+ "learning_rate": 1.6695642095503014e-05,
838
+ "loss": 0.0,
839
+ "step": 11500
840
+ },
841
+ {
842
+ "epoch": 2.0166898470097356,
843
+ "grad_norm": 0.0,
844
+ "learning_rate": 1.6405887807139548e-05,
845
+ "loss": 0.0,
846
+ "step": 11600
847
+ },
848
+ {
849
+ "epoch": 2.034075104311544,
850
+ "grad_norm": 0.0,
851
+ "learning_rate": 1.611613351877608e-05,
852
+ "loss": 0.0,
853
+ "step": 11700
854
+ },
855
+ {
856
+ "epoch": 2.0514603616133518,
857
+ "grad_norm": 0.0,
858
+ "learning_rate": 1.582637923041261e-05,
859
+ "loss": 0.0,
860
+ "step": 11800
861
+ },
862
+ {
863
+ "epoch": 2.06884561891516,
864
+ "grad_norm": 0.0,
865
+ "learning_rate": 1.5536624942049145e-05,
866
+ "loss": 0.0,
867
+ "step": 11900
868
+ },
869
+ {
870
+ "epoch": 2.086230876216968,
871
+ "grad_norm": 0.0,
872
+ "learning_rate": 1.5246870653685674e-05,
873
+ "loss": 0.0,
874
+ "step": 12000
875
+ },
876
+ {
877
+ "epoch": 2.086230876216968,
878
+ "eval_loss": 0.0,
879
+ "eval_runtime": 664.7541,
880
+ "eval_samples_per_second": 17.306,
881
+ "eval_steps_per_second": 8.653,
882
+ "step": 12000
883
+ },
884
+ {
885
+ "epoch": 2.103616133518776,
886
+ "grad_norm": 0.0,
887
+ "learning_rate": 1.4957116365322207e-05,
888
+ "loss": 0.0,
889
+ "step": 12100
890
+ },
891
+ {
892
+ "epoch": 2.121001390820584,
893
+ "grad_norm": 0.0,
894
+ "learning_rate": 1.4667362076958741e-05,
895
+ "loss": 0.0,
896
+ "step": 12200
897
+ },
898
+ {
899
+ "epoch": 2.1383866481223923,
900
+ "grad_norm": 0.0,
901
+ "learning_rate": 1.437760778859527e-05,
902
+ "loss": 0.0,
903
+ "step": 12300
904
+ },
905
+ {
906
+ "epoch": 2.1557719054242,
907
+ "grad_norm": 0.0,
908
+ "learning_rate": 1.4087853500231805e-05,
909
+ "loss": 0.0,
910
+ "step": 12400
911
+ },
912
+ {
913
+ "epoch": 2.1731571627260085,
914
+ "grad_norm": 0.0,
915
+ "learning_rate": 1.3798099211868337e-05,
916
+ "loss": 0.0,
917
+ "step": 12500
918
+ },
919
+ {
920
+ "epoch": 2.1905424200278163,
921
+ "grad_norm": 0.0,
922
+ "learning_rate": 1.3508344923504868e-05,
923
+ "loss": 0.0,
924
+ "step": 12600
925
+ },
926
+ {
927
+ "epoch": 2.2079276773296246,
928
+ "grad_norm": 0.0,
929
+ "learning_rate": 1.3218590635141401e-05,
930
+ "loss": 0.0,
931
+ "step": 12700
932
+ },
933
+ {
934
+ "epoch": 2.2253129346314324,
935
+ "grad_norm": 0.0,
936
+ "learning_rate": 1.2928836346777934e-05,
937
+ "loss": 0.0,
938
+ "step": 12800
939
+ },
940
+ {
941
+ "epoch": 2.2426981919332407,
942
+ "grad_norm": 0.0,
943
+ "learning_rate": 1.2639082058414465e-05,
944
+ "loss": 0.0,
945
+ "step": 12900
946
+ },
947
+ {
948
+ "epoch": 2.2600834492350486,
949
+ "grad_norm": 0.0,
950
+ "learning_rate": 1.2349327770050998e-05,
951
+ "loss": 0.0,
952
+ "step": 13000
953
+ },
954
+ {
955
+ "epoch": 2.277468706536857,
956
+ "grad_norm": 0.0,
957
+ "learning_rate": 1.2059573481687529e-05,
958
+ "loss": 0.0,
959
+ "step": 13100
960
+ },
961
+ {
962
+ "epoch": 2.2948539638386647,
963
+ "grad_norm": 0.0,
964
+ "learning_rate": 1.1769819193324063e-05,
965
+ "loss": 0.0,
966
+ "step": 13200
967
+ },
968
+ {
969
+ "epoch": 2.312239221140473,
970
+ "grad_norm": 0.0,
971
+ "learning_rate": 1.1480064904960594e-05,
972
+ "loss": 0.0,
973
+ "step": 13300
974
+ },
975
+ {
976
+ "epoch": 2.329624478442281,
977
+ "grad_norm": 0.0,
978
+ "learning_rate": 1.1190310616597125e-05,
979
+ "loss": 0.0,
980
+ "step": 13400
981
+ },
982
+ {
983
+ "epoch": 2.347009735744089,
984
+ "grad_norm": 0.0,
985
+ "learning_rate": 1.090055632823366e-05,
986
+ "loss": 0.0,
987
+ "step": 13500
988
+ },
989
+ {
990
+ "epoch": 2.364394993045897,
991
+ "grad_norm": 0.0,
992
+ "learning_rate": 1.061080203987019e-05,
993
+ "loss": 0.0,
994
+ "step": 13600
995
+ },
996
+ {
997
+ "epoch": 2.3817802503477052,
998
+ "grad_norm": 0.0,
999
+ "learning_rate": 1.0321047751506723e-05,
1000
+ "loss": 0.0,
1001
+ "step": 13700
1002
+ },
1003
+ {
1004
+ "epoch": 2.399165507649513,
1005
+ "grad_norm": 0.0,
1006
+ "learning_rate": 1.0031293463143256e-05,
1007
+ "loss": 0.0,
1008
+ "step": 13800
1009
+ },
1010
+ {
1011
+ "epoch": 2.4165507649513214,
1012
+ "grad_norm": 0.0,
1013
+ "learning_rate": 9.741539174779787e-06,
1014
+ "loss": 0.0,
1015
+ "step": 13900
1016
+ },
1017
+ {
1018
+ "epoch": 2.433936022253129,
1019
+ "grad_norm": 0.0,
1020
+ "learning_rate": 9.45178488641632e-06,
1021
+ "loss": 0.0,
1022
+ "step": 14000
1023
+ },
1024
+ {
1025
+ "epoch": 2.4513212795549375,
1026
+ "grad_norm": 0.0,
1027
+ "learning_rate": 9.162030598052852e-06,
1028
+ "loss": 0.0,
1029
+ "step": 14100
1030
+ },
1031
+ {
1032
+ "epoch": 2.4687065368567453,
1033
+ "grad_norm": 0.0,
1034
+ "learning_rate": 8.872276309689383e-06,
1035
+ "loss": 0.0,
1036
+ "step": 14200
1037
+ },
1038
+ {
1039
+ "epoch": 2.4860917941585536,
1040
+ "grad_norm": 0.0,
1041
+ "learning_rate": 8.582522021325916e-06,
1042
+ "loss": 0.0,
1043
+ "step": 14300
1044
+ },
1045
+ {
1046
+ "epoch": 2.5034770514603615,
1047
+ "grad_norm": 0.0,
1048
+ "learning_rate": 8.292767732962447e-06,
1049
+ "loss": 0.0,
1050
+ "step": 14400
1051
+ },
1052
+ {
1053
+ "epoch": 2.5208623087621698,
1054
+ "grad_norm": 0.0,
1055
+ "learning_rate": 8.003013444598981e-06,
1056
+ "loss": 0.0,
1057
+ "step": 14500
1058
+ },
1059
+ {
1060
+ "epoch": 2.5382475660639776,
1061
+ "grad_norm": 0.0,
1062
+ "learning_rate": 7.713259156235512e-06,
1063
+ "loss": 0.0,
1064
+ "step": 14600
1065
+ },
1066
+ {
1067
+ "epoch": 2.555632823365786,
1068
+ "grad_norm": 0.0,
1069
+ "learning_rate": 7.423504867872044e-06,
1070
+ "loss": 0.0,
1071
+ "step": 14700
1072
+ },
1073
+ {
1074
+ "epoch": 2.5730180806675937,
1075
+ "grad_norm": 0.0,
1076
+ "learning_rate": 7.133750579508577e-06,
1077
+ "loss": 0.0,
1078
+ "step": 14800
1079
+ },
1080
+ {
1081
+ "epoch": 2.590403337969402,
1082
+ "grad_norm": 0.0,
1083
+ "learning_rate": 6.843996291145109e-06,
1084
+ "loss": 0.0,
1085
+ "step": 14900
1086
+ },
1087
+ {
1088
+ "epoch": 2.60778859527121,
1089
+ "grad_norm": 0.0,
1090
+ "learning_rate": 6.554242002781641e-06,
1091
+ "loss": 0.0,
1092
+ "step": 15000
1093
+ },
1094
+ {
1095
+ "epoch": 2.60778859527121,
1096
+ "eval_loss": 0.0,
1097
+ "eval_runtime": 666.4751,
1098
+ "eval_samples_per_second": 17.261,
1099
+ "eval_steps_per_second": 8.63,
1100
+ "step": 15000
1101
+ },
1102
+ {
1103
+ "epoch": 2.625173852573018,
1104
+ "grad_norm": 0.0,
1105
+ "learning_rate": 6.264487714418174e-06,
1106
+ "loss": 0.0,
1107
+ "step": 15100
1108
+ },
1109
+ {
1110
+ "epoch": 2.642559109874826,
1111
+ "grad_norm": 0.0,
1112
+ "learning_rate": 5.974733426054706e-06,
1113
+ "loss": 0.0,
1114
+ "step": 15200
1115
+ },
1116
+ {
1117
+ "epoch": 2.6599443671766343,
1118
+ "grad_norm": 0.0,
1119
+ "learning_rate": 5.684979137691238e-06,
1120
+ "loss": 0.0,
1121
+ "step": 15300
1122
+ },
1123
+ {
1124
+ "epoch": 2.677329624478442,
1125
+ "grad_norm": 0.0,
1126
+ "learning_rate": 5.39522484932777e-06,
1127
+ "loss": 0.0,
1128
+ "step": 15400
1129
+ },
1130
+ {
1131
+ "epoch": 2.6947148817802504,
1132
+ "grad_norm": 0.0,
1133
+ "learning_rate": 5.1054705609643026e-06,
1134
+ "loss": 0.0,
1135
+ "step": 15500
1136
+ },
1137
+ {
1138
+ "epoch": 2.7121001390820583,
1139
+ "grad_norm": 0.0,
1140
+ "learning_rate": 4.815716272600835e-06,
1141
+ "loss": 0.0,
1142
+ "step": 15600
1143
+ },
1144
+ {
1145
+ "epoch": 2.7294853963838666,
1146
+ "grad_norm": 0.0,
1147
+ "learning_rate": 4.525961984237367e-06,
1148
+ "loss": 0.0,
1149
+ "step": 15700
1150
+ },
1151
+ {
1152
+ "epoch": 2.7468706536856744,
1153
+ "grad_norm": 0.0,
1154
+ "learning_rate": 4.236207695873899e-06,
1155
+ "loss": 0.0,
1156
+ "step": 15800
1157
+ },
1158
+ {
1159
+ "epoch": 2.7642559109874827,
1160
+ "grad_norm": 0.0,
1161
+ "learning_rate": 3.946453407510432e-06,
1162
+ "loss": 0.0,
1163
+ "step": 15900
1164
+ },
1165
+ {
1166
+ "epoch": 2.7816411682892905,
1167
+ "grad_norm": 0.0,
1168
+ "learning_rate": 3.6566991191469636e-06,
1169
+ "loss": 0.0,
1170
+ "step": 16000
1171
+ },
1172
+ {
1173
+ "epoch": 2.799026425591099,
1174
+ "grad_norm": 0.0,
1175
+ "learning_rate": 3.3698423736671305e-06,
1176
+ "loss": 0.0,
1177
+ "step": 16100
1178
+ },
1179
+ {
1180
+ "epoch": 2.8164116828929067,
1181
+ "grad_norm": 0.0,
1182
+ "learning_rate": 3.0800880853036624e-06,
1183
+ "loss": 0.0,
1184
+ "step": 16200
1185
+ },
1186
+ {
1187
+ "epoch": 2.833796940194715,
1188
+ "grad_norm": 0.0,
1189
+ "learning_rate": 2.790333796940195e-06,
1190
+ "loss": 0.0,
1191
+ "step": 16300
1192
+ },
1193
+ {
1194
+ "epoch": 2.851182197496523,
1195
+ "grad_norm": 0.0,
1196
+ "learning_rate": 2.500579508576727e-06,
1197
+ "loss": 0.0,
1198
+ "step": 16400
1199
+ },
1200
+ {
1201
+ "epoch": 2.868567454798331,
1202
+ "grad_norm": 0.0,
1203
+ "learning_rate": 2.2108252202132593e-06,
1204
+ "loss": 0.0,
1205
+ "step": 16500
1206
+ },
1207
+ {
1208
+ "epoch": 2.885952712100139,
1209
+ "grad_norm": 0.0,
1210
+ "learning_rate": 1.9210709318497915e-06,
1211
+ "loss": 0.0,
1212
+ "step": 16600
1213
+ },
1214
+ {
1215
+ "epoch": 2.903337969401947,
1216
+ "grad_norm": 0.0,
1217
+ "learning_rate": 1.6313166434863236e-06,
1218
+ "loss": 0.0,
1219
+ "step": 16700
1220
+ },
1221
+ {
1222
+ "epoch": 2.920723226703755,
1223
+ "grad_norm": 0.0,
1224
+ "learning_rate": 1.341562355122856e-06,
1225
+ "loss": 0.0,
1226
+ "step": 16800
1227
+ },
1228
+ {
1229
+ "epoch": 2.9381084840055633,
1230
+ "grad_norm": 0.0,
1231
+ "learning_rate": 1.051808066759388e-06,
1232
+ "loss": 0.0,
1233
+ "step": 16900
1234
+ },
1235
+ {
1236
+ "epoch": 2.955493741307371,
1237
+ "grad_norm": 0.0,
1238
+ "learning_rate": 7.620537783959203e-07,
1239
+ "loss": 0.0,
1240
+ "step": 17000
1241
+ }
1242
+ ],
1243
+ "logging_steps": 100,
1244
+ "max_steps": 17256,
1245
+ "num_input_tokens_seen": 0,
1246
+ "num_train_epochs": 3,
1247
+ "save_steps": 500,
1248
+ "stateful_callbacks": {
1249
+ "TrainerControl": {
1250
+ "args": {
1251
+ "should_epoch_stop": false,
1252
+ "should_evaluate": false,
1253
+ "should_log": false,
1254
+ "should_save": true,
1255
+ "should_training_stop": false
1256
+ },
1257
+ "attributes": {}
1258
+ }
1259
+ },
1260
+ "total_flos": 1.84024635015168e+17,
1261
+ "train_batch_size": 2,
1262
+ "trial_name": null,
1263
+ "trial_params": null
1264
+ }
checkpoint-17000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f56e75948c29c4f566977160640ec15a3fa7bd8fb9fa9a8775420935c2e28c
3
+ size 5240
checkpoint-17000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17256/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-17256/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForSequenceClassification"
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
+ "pad_token_id": 151643,
21
+ "problem_type": "single_label_classification",
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000000,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.51.3",
29
+ "use_cache": true,
30
+ "use_sliding_window": false,
31
+ "vocab_size": 151936
32
+ }
checkpoint-17256/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17256/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69a32798954ae4639f94adebbf6003de9a48b5bedd9636431c895f243d55eeb
3
+ size 2384243248
checkpoint-17256/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6d054755bdd73d910f1b34944d637314e6217e89caa162f6913ea9784ab7a7
3
+ size 4768680162
checkpoint-17256/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
3
+ size 14244
checkpoint-17256/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c48374a7f1f6827032081497a611f9ea7d05478ad3a1d0066ce2bc50b310e3
3
+ size 988
checkpoint-17256/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8868c7532d53fd484ab6f54720b1552bea5c7b2492e5e19a363aaf909784d3ce
3
+ size 1064
checkpoint-17256/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-17256/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
3
+ size 11422932
checkpoint-17256/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
+ }
checkpoint-17256/trainer_state.json ADDED
@@ -0,0 +1,1278 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 3000,
7
+ "global_step": 17256,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.017385257301808066,
14
+ "grad_norm": 0.0,
15
+ "learning_rate": 4.9727630968938346e-05,
16
+ "loss": 0.177,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.03477051460361613,
21
+ "grad_norm": 0.0,
22
+ "learning_rate": 4.943787668057488e-05,
23
+ "loss": 0.0,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.0521557719054242,
28
+ "grad_norm": 0.0,
29
+ "learning_rate": 4.914812239221141e-05,
30
+ "loss": 0.0,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.06954102920723226,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 4.885836810384794e-05,
37
+ "loss": 0.0,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.08692628650904033,
42
+ "grad_norm": 0.0,
43
+ "learning_rate": 4.856861381548447e-05,
44
+ "loss": 0.0,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.1043115438108484,
49
+ "grad_norm": 0.0,
50
+ "learning_rate": 4.827885952712101e-05,
51
+ "loss": 0.0,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.12169680111265646,
56
+ "grad_norm": 0.0,
57
+ "learning_rate": 4.798910523875754e-05,
58
+ "loss": 0.0,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.13908205841446453,
63
+ "grad_norm": 0.0,
64
+ "learning_rate": 4.769935095039407e-05,
65
+ "loss": 0.0,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.1564673157162726,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 4.74095966620306e-05,
72
+ "loss": 0.0,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.17385257301808066,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 4.711984237366713e-05,
79
+ "loss": 0.0,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.19123783031988872,
84
+ "grad_norm": 0.0,
85
+ "learning_rate": 4.683008808530366e-05,
86
+ "loss": 0.0,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.2086230876216968,
91
+ "grad_norm": 0.0,
92
+ "learning_rate": 4.6540333796940194e-05,
93
+ "loss": 0.0,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.22600834492350486,
98
+ "grad_norm": 0.0,
99
+ "learning_rate": 4.625057950857673e-05,
100
+ "loss": 0.0,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.24339360222531292,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 4.596082522021326e-05,
107
+ "loss": 0.0,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.260778859527121,
112
+ "grad_norm": 0.0,
113
+ "learning_rate": 4.5671070931849794e-05,
114
+ "loss": 0.0,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.27816411682892905,
119
+ "grad_norm": 0.0,
120
+ "learning_rate": 4.5381316643486325e-05,
121
+ "loss": 0.0,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.2955493741307371,
126
+ "grad_norm": 0.0,
127
+ "learning_rate": 4.5091562355122856e-05,
128
+ "loss": 0.0,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.3129346314325452,
133
+ "grad_norm": 0.0,
134
+ "learning_rate": 4.480180806675939e-05,
135
+ "loss": 0.0,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.33031988873435325,
140
+ "grad_norm": 0.0,
141
+ "learning_rate": 4.4512053778395924e-05,
142
+ "loss": 0.0,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.3477051460361613,
147
+ "grad_norm": 0.0,
148
+ "learning_rate": 4.4222299490032455e-05,
149
+ "loss": 0.0,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.3650904033379694,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 4.3932545201668987e-05,
156
+ "loss": 0.0,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.38247566063977745,
161
+ "grad_norm": 0.0,
162
+ "learning_rate": 4.364279091330552e-05,
163
+ "loss": 0.0,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.3998609179415855,
168
+ "grad_norm": 0.0,
169
+ "learning_rate": 4.335303662494205e-05,
170
+ "loss": 0.0,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.4172461752433936,
175
+ "grad_norm": 0.0,
176
+ "learning_rate": 4.306328233657858e-05,
177
+ "loss": 0.0,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.43463143254520165,
182
+ "grad_norm": 0.0,
183
+ "learning_rate": 4.277352804821512e-05,
184
+ "loss": 0.0,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.4520166898470097,
189
+ "grad_norm": 0.0,
190
+ "learning_rate": 4.248377375985165e-05,
191
+ "loss": 0.0,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 0.4694019471488178,
196
+ "grad_norm": 0.0,
197
+ "learning_rate": 4.219401947148818e-05,
198
+ "loss": 0.0,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 0.48678720445062584,
203
+ "grad_norm": 0.0,
204
+ "learning_rate": 4.190426518312471e-05,
205
+ "loss": 0.0,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 0.5041724617524339,
210
+ "grad_norm": 0.0,
211
+ "learning_rate": 4.161451089476124e-05,
212
+ "loss": 0.0,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 0.521557719054242,
217
+ "grad_norm": 0.0,
218
+ "learning_rate": 4.132475660639777e-05,
219
+ "loss": 0.0,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 0.521557719054242,
224
+ "eval_loss": 0.0,
225
+ "eval_runtime": 667.343,
226
+ "eval_samples_per_second": 17.239,
227
+ "eval_steps_per_second": 8.619,
228
+ "step": 3000
229
+ },
230
+ {
231
+ "epoch": 0.53894297635605,
232
+ "grad_norm": 0.0,
233
+ "learning_rate": 4.103500231803431e-05,
234
+ "loss": 0.0,
235
+ "step": 3100
236
+ },
237
+ {
238
+ "epoch": 0.5563282336578581,
239
+ "grad_norm": 0.0,
240
+ "learning_rate": 4.074524802967084e-05,
241
+ "loss": 0.0,
242
+ "step": 3200
243
+ },
244
+ {
245
+ "epoch": 0.5737134909596662,
246
+ "grad_norm": 0.0,
247
+ "learning_rate": 4.045549374130737e-05,
248
+ "loss": 0.0,
249
+ "step": 3300
250
+ },
251
+ {
252
+ "epoch": 0.5910987482614742,
253
+ "grad_norm": 0.0,
254
+ "learning_rate": 4.016573945294391e-05,
255
+ "loss": 0.0,
256
+ "step": 3400
257
+ },
258
+ {
259
+ "epoch": 0.6084840055632823,
260
+ "grad_norm": 0.0,
261
+ "learning_rate": 3.9875985164580434e-05,
262
+ "loss": 0.0,
263
+ "step": 3500
264
+ },
265
+ {
266
+ "epoch": 0.6258692628650904,
267
+ "grad_norm": 0.0,
268
+ "learning_rate": 3.9586230876216965e-05,
269
+ "loss": 0.0,
270
+ "step": 3600
271
+ },
272
+ {
273
+ "epoch": 0.6432545201668984,
274
+ "grad_norm": 0.0,
275
+ "learning_rate": 3.92964765878535e-05,
276
+ "loss": 0.0,
277
+ "step": 3700
278
+ },
279
+ {
280
+ "epoch": 0.6606397774687065,
281
+ "grad_norm": 0.0,
282
+ "learning_rate": 3.9006722299490034e-05,
283
+ "loss": 0.0,
284
+ "step": 3800
285
+ },
286
+ {
287
+ "epoch": 0.6780250347705146,
288
+ "grad_norm": 0.0,
289
+ "learning_rate": 3.8716968011126565e-05,
290
+ "loss": 0.0,
291
+ "step": 3900
292
+ },
293
+ {
294
+ "epoch": 0.6954102920723226,
295
+ "grad_norm": 0.0,
296
+ "learning_rate": 3.84272137227631e-05,
297
+ "loss": 0.0,
298
+ "step": 4000
299
+ },
300
+ {
301
+ "epoch": 0.7127955493741307,
302
+ "grad_norm": 0.0,
303
+ "learning_rate": 3.8137459434399634e-05,
304
+ "loss": 0.0,
305
+ "step": 4100
306
+ },
307
+ {
308
+ "epoch": 0.7301808066759388,
309
+ "grad_norm": 0.0,
310
+ "learning_rate": 3.784770514603616e-05,
311
+ "loss": 0.0,
312
+ "step": 4200
313
+ },
314
+ {
315
+ "epoch": 0.7475660639777468,
316
+ "grad_norm": 0.0,
317
+ "learning_rate": 3.7557950857672696e-05,
318
+ "loss": 0.0,
319
+ "step": 4300
320
+ },
321
+ {
322
+ "epoch": 0.7649513212795549,
323
+ "grad_norm": 0.0,
324
+ "learning_rate": 3.726819656930923e-05,
325
+ "loss": 0.0,
326
+ "step": 4400
327
+ },
328
+ {
329
+ "epoch": 0.782336578581363,
330
+ "grad_norm": 0.0,
331
+ "learning_rate": 3.697844228094576e-05,
332
+ "loss": 0.0,
333
+ "step": 4500
334
+ },
335
+ {
336
+ "epoch": 0.799721835883171,
337
+ "grad_norm": 0.0,
338
+ "learning_rate": 3.6688687992582296e-05,
339
+ "loss": 0.0,
340
+ "step": 4600
341
+ },
342
+ {
343
+ "epoch": 0.8171070931849791,
344
+ "grad_norm": 0.0,
345
+ "learning_rate": 3.639893370421883e-05,
346
+ "loss": 0.0,
347
+ "step": 4700
348
+ },
349
+ {
350
+ "epoch": 0.8344923504867872,
351
+ "grad_norm": 0.0,
352
+ "learning_rate": 3.610917941585535e-05,
353
+ "loss": 0.0,
354
+ "step": 4800
355
+ },
356
+ {
357
+ "epoch": 0.8518776077885952,
358
+ "grad_norm": 0.0,
359
+ "learning_rate": 3.581942512749189e-05,
360
+ "loss": 0.0,
361
+ "step": 4900
362
+ },
363
+ {
364
+ "epoch": 0.8692628650904033,
365
+ "grad_norm": 0.0,
366
+ "learning_rate": 3.552967083912842e-05,
367
+ "loss": 0.0,
368
+ "step": 5000
369
+ },
370
+ {
371
+ "epoch": 0.8866481223922114,
372
+ "grad_norm": 0.0,
373
+ "learning_rate": 3.523991655076495e-05,
374
+ "loss": 0.0,
375
+ "step": 5100
376
+ },
377
+ {
378
+ "epoch": 0.9040333796940194,
379
+ "grad_norm": 0.0,
380
+ "learning_rate": 3.495016226240149e-05,
381
+ "loss": 0.0,
382
+ "step": 5200
383
+ },
384
+ {
385
+ "epoch": 0.9214186369958275,
386
+ "grad_norm": 0.0,
387
+ "learning_rate": 3.466040797403802e-05,
388
+ "loss": 0.0,
389
+ "step": 5300
390
+ },
391
+ {
392
+ "epoch": 0.9388038942976356,
393
+ "grad_norm": 0.0,
394
+ "learning_rate": 3.437065368567455e-05,
395
+ "loss": 0.0,
396
+ "step": 5400
397
+ },
398
+ {
399
+ "epoch": 0.9561891515994436,
400
+ "grad_norm": 0.0,
401
+ "learning_rate": 3.408089939731108e-05,
402
+ "loss": 0.0,
403
+ "step": 5500
404
+ },
405
+ {
406
+ "epoch": 0.9735744089012517,
407
+ "grad_norm": 0.0,
408
+ "learning_rate": 3.379114510894761e-05,
409
+ "loss": 0.0,
410
+ "step": 5600
411
+ },
412
+ {
413
+ "epoch": 0.9909596662030598,
414
+ "grad_norm": 0.0,
415
+ "learning_rate": 3.3501390820584144e-05,
416
+ "loss": 0.0,
417
+ "step": 5700
418
+ },
419
+ {
420
+ "epoch": 1.0083449235048678,
421
+ "grad_norm": 0.0,
422
+ "learning_rate": 3.321163653222068e-05,
423
+ "loss": 0.0,
424
+ "step": 5800
425
+ },
426
+ {
427
+ "epoch": 1.0257301808066759,
428
+ "grad_norm": 0.0,
429
+ "learning_rate": 3.292188224385721e-05,
430
+ "loss": 0.0,
431
+ "step": 5900
432
+ },
433
+ {
434
+ "epoch": 1.043115438108484,
435
+ "grad_norm": 0.0,
436
+ "learning_rate": 3.2632127955493744e-05,
437
+ "loss": 0.0,
438
+ "step": 6000
439
+ },
440
+ {
441
+ "epoch": 1.043115438108484,
442
+ "eval_loss": 0.0,
443
+ "eval_runtime": 693.3635,
444
+ "eval_samples_per_second": 16.592,
445
+ "eval_steps_per_second": 8.296,
446
+ "step": 6000
447
+ },
448
+ {
449
+ "epoch": 1.060500695410292,
450
+ "grad_norm": 0.0,
451
+ "learning_rate": 3.2342373667130275e-05,
452
+ "loss": 0.0,
453
+ "step": 6100
454
+ },
455
+ {
456
+ "epoch": 1.0778859527121,
457
+ "grad_norm": 0.0,
458
+ "learning_rate": 3.2052619378766806e-05,
459
+ "loss": 0.0,
460
+ "step": 6200
461
+ },
462
+ {
463
+ "epoch": 1.0952712100139081,
464
+ "grad_norm": 0.0,
465
+ "learning_rate": 3.1762865090403337e-05,
466
+ "loss": 0.0,
467
+ "step": 6300
468
+ },
469
+ {
470
+ "epoch": 1.1126564673157162,
471
+ "grad_norm": 0.0,
472
+ "learning_rate": 3.1473110802039874e-05,
473
+ "loss": 0.0,
474
+ "step": 6400
475
+ },
476
+ {
477
+ "epoch": 1.1300417246175243,
478
+ "grad_norm": 0.0,
479
+ "learning_rate": 3.1183356513676405e-05,
480
+ "loss": 0.0,
481
+ "step": 6500
482
+ },
483
+ {
484
+ "epoch": 1.1474269819193323,
485
+ "grad_norm": 0.0,
486
+ "learning_rate": 3.0893602225312936e-05,
487
+ "loss": 0.0,
488
+ "step": 6600
489
+ },
490
+ {
491
+ "epoch": 1.1648122392211404,
492
+ "grad_norm": 0.0,
493
+ "learning_rate": 3.060384793694947e-05,
494
+ "loss": 0.0,
495
+ "step": 6700
496
+ },
497
+ {
498
+ "epoch": 1.1821974965229485,
499
+ "grad_norm": 0.0,
500
+ "learning_rate": 3.0314093648586002e-05,
501
+ "loss": 0.0,
502
+ "step": 6800
503
+ },
504
+ {
505
+ "epoch": 1.1995827538247565,
506
+ "grad_norm": 0.0,
507
+ "learning_rate": 3.002433936022253e-05,
508
+ "loss": 0.0,
509
+ "step": 6900
510
+ },
511
+ {
512
+ "epoch": 1.2169680111265646,
513
+ "grad_norm": 0.0,
514
+ "learning_rate": 2.9734585071859067e-05,
515
+ "loss": 0.0,
516
+ "step": 7000
517
+ },
518
+ {
519
+ "epoch": 1.2343532684283727,
520
+ "grad_norm": 0.0,
521
+ "learning_rate": 2.9444830783495598e-05,
522
+ "loss": 0.0,
523
+ "step": 7100
524
+ },
525
+ {
526
+ "epoch": 1.2517385257301807,
527
+ "grad_norm": 0.0,
528
+ "learning_rate": 2.915507649513213e-05,
529
+ "loss": 0.0,
530
+ "step": 7200
531
+ },
532
+ {
533
+ "epoch": 1.2691237830319888,
534
+ "grad_norm": 0.0,
535
+ "learning_rate": 2.8865322206768664e-05,
536
+ "loss": 0.0,
537
+ "step": 7300
538
+ },
539
+ {
540
+ "epoch": 1.2865090403337969,
541
+ "grad_norm": 0.0,
542
+ "learning_rate": 2.8575567918405195e-05,
543
+ "loss": 0.0,
544
+ "step": 7400
545
+ },
546
+ {
547
+ "epoch": 1.303894297635605,
548
+ "grad_norm": 0.0,
549
+ "learning_rate": 2.8285813630041726e-05,
550
+ "loss": 0.0,
551
+ "step": 7500
552
+ },
553
+ {
554
+ "epoch": 1.321279554937413,
555
+ "grad_norm": 0.0,
556
+ "learning_rate": 2.799605934167826e-05,
557
+ "loss": 0.0,
558
+ "step": 7600
559
+ },
560
+ {
561
+ "epoch": 1.338664812239221,
562
+ "grad_norm": 0.0,
563
+ "learning_rate": 2.770630505331479e-05,
564
+ "loss": 0.0,
565
+ "step": 7700
566
+ },
567
+ {
568
+ "epoch": 1.3560500695410291,
569
+ "grad_norm": 0.0,
570
+ "learning_rate": 2.7416550764951322e-05,
571
+ "loss": 0.0,
572
+ "step": 7800
573
+ },
574
+ {
575
+ "epoch": 1.3734353268428372,
576
+ "grad_norm": 0.0,
577
+ "learning_rate": 2.7126796476587857e-05,
578
+ "loss": 0.0,
579
+ "step": 7900
580
+ },
581
+ {
582
+ "epoch": 1.3908205841446453,
583
+ "grad_norm": 0.0,
584
+ "learning_rate": 2.6837042188224388e-05,
585
+ "loss": 0.0,
586
+ "step": 8000
587
+ },
588
+ {
589
+ "epoch": 1.4082058414464533,
590
+ "grad_norm": 0.0,
591
+ "learning_rate": 2.654728789986092e-05,
592
+ "loss": 0.0,
593
+ "step": 8100
594
+ },
595
+ {
596
+ "epoch": 1.4255910987482614,
597
+ "grad_norm": 0.0,
598
+ "learning_rate": 2.6257533611497453e-05,
599
+ "loss": 0.0,
600
+ "step": 8200
601
+ },
602
+ {
603
+ "epoch": 1.4429763560500695,
604
+ "grad_norm": 0.0,
605
+ "learning_rate": 2.5967779323133984e-05,
606
+ "loss": 0.0,
607
+ "step": 8300
608
+ },
609
+ {
610
+ "epoch": 1.4603616133518775,
611
+ "grad_norm": 0.0,
612
+ "learning_rate": 2.5678025034770515e-05,
613
+ "loss": 0.0,
614
+ "step": 8400
615
+ },
616
+ {
617
+ "epoch": 1.4777468706536856,
618
+ "grad_norm": 0.0,
619
+ "learning_rate": 2.538827074640705e-05,
620
+ "loss": 0.0,
621
+ "step": 8500
622
+ },
623
+ {
624
+ "epoch": 1.4951321279554937,
625
+ "grad_norm": 0.0,
626
+ "learning_rate": 2.509851645804358e-05,
627
+ "loss": 0.0,
628
+ "step": 8600
629
+ },
630
+ {
631
+ "epoch": 1.512517385257302,
632
+ "grad_norm": 0.0,
633
+ "learning_rate": 2.4808762169680115e-05,
634
+ "loss": 0.0,
635
+ "step": 8700
636
+ },
637
+ {
638
+ "epoch": 1.5299026425591098,
639
+ "grad_norm": 0.0,
640
+ "learning_rate": 2.4519007881316642e-05,
641
+ "loss": 0.0,
642
+ "step": 8800
643
+ },
644
+ {
645
+ "epoch": 1.547287899860918,
646
+ "grad_norm": 0.0,
647
+ "learning_rate": 2.4229253592953177e-05,
648
+ "loss": 0.0,
649
+ "step": 8900
650
+ },
651
+ {
652
+ "epoch": 1.564673157162726,
653
+ "grad_norm": 0.0,
654
+ "learning_rate": 2.393949930458971e-05,
655
+ "loss": 0.0,
656
+ "step": 9000
657
+ },
658
+ {
659
+ "epoch": 1.564673157162726,
660
+ "eval_loss": 0.0,
661
+ "eval_runtime": 665.0981,
662
+ "eval_samples_per_second": 17.297,
663
+ "eval_steps_per_second": 8.648,
664
+ "step": 9000
665
+ },
666
+ {
667
+ "epoch": 1.5820584144645342,
668
+ "grad_norm": 0.0,
669
+ "learning_rate": 2.3649745016226242e-05,
670
+ "loss": 0.0,
671
+ "step": 9100
672
+ },
673
+ {
674
+ "epoch": 1.599443671766342,
675
+ "grad_norm": 0.0,
676
+ "learning_rate": 2.3359990727862773e-05,
677
+ "loss": 0.0,
678
+ "step": 9200
679
+ },
680
+ {
681
+ "epoch": 1.6168289290681503,
682
+ "grad_norm": 0.0,
683
+ "learning_rate": 2.3070236439499308e-05,
684
+ "loss": 0.0,
685
+ "step": 9300
686
+ },
687
+ {
688
+ "epoch": 1.6342141863699582,
689
+ "grad_norm": 0.0,
690
+ "learning_rate": 2.278048215113584e-05,
691
+ "loss": 0.0,
692
+ "step": 9400
693
+ },
694
+ {
695
+ "epoch": 1.6515994436717665,
696
+ "grad_norm": 0.0,
697
+ "learning_rate": 2.249072786277237e-05,
698
+ "loss": 0.0,
699
+ "step": 9500
700
+ },
701
+ {
702
+ "epoch": 1.6689847009735743,
703
+ "grad_norm": 0.0,
704
+ "learning_rate": 2.2200973574408904e-05,
705
+ "loss": 0.0,
706
+ "step": 9600
707
+ },
708
+ {
709
+ "epoch": 1.6863699582753826,
710
+ "grad_norm": 0.0,
711
+ "learning_rate": 2.1911219286045435e-05,
712
+ "loss": 0.0,
713
+ "step": 9700
714
+ },
715
+ {
716
+ "epoch": 1.7037552155771905,
717
+ "grad_norm": 0.0,
718
+ "learning_rate": 2.1621464997681966e-05,
719
+ "loss": 0.0,
720
+ "step": 9800
721
+ },
722
+ {
723
+ "epoch": 1.7211404728789987,
724
+ "grad_norm": 0.0,
725
+ "learning_rate": 2.1331710709318497e-05,
726
+ "loss": 0.0,
727
+ "step": 9900
728
+ },
729
+ {
730
+ "epoch": 1.7385257301808066,
731
+ "grad_norm": 0.0,
732
+ "learning_rate": 2.104195642095503e-05,
733
+ "loss": 0.0,
734
+ "step": 10000
735
+ },
736
+ {
737
+ "epoch": 1.7559109874826149,
738
+ "grad_norm": 0.0,
739
+ "learning_rate": 2.0752202132591563e-05,
740
+ "loss": 0.0,
741
+ "step": 10100
742
+ },
743
+ {
744
+ "epoch": 1.7732962447844227,
745
+ "grad_norm": 0.0,
746
+ "learning_rate": 2.0462447844228094e-05,
747
+ "loss": 0.0,
748
+ "step": 10200
749
+ },
750
+ {
751
+ "epoch": 1.790681502086231,
752
+ "grad_norm": 0.0,
753
+ "learning_rate": 2.0172693555864628e-05,
754
+ "loss": 0.0,
755
+ "step": 10300
756
+ },
757
+ {
758
+ "epoch": 1.8080667593880388,
759
+ "grad_norm": 0.0,
760
+ "learning_rate": 1.988293926750116e-05,
761
+ "loss": 0.0,
762
+ "step": 10400
763
+ },
764
+ {
765
+ "epoch": 1.8254520166898471,
766
+ "grad_norm": 0.0,
767
+ "learning_rate": 1.959318497913769e-05,
768
+ "loss": 0.0,
769
+ "step": 10500
770
+ },
771
+ {
772
+ "epoch": 1.842837273991655,
773
+ "grad_norm": 0.0,
774
+ "learning_rate": 1.9303430690774224e-05,
775
+ "loss": 0.0,
776
+ "step": 10600
777
+ },
778
+ {
779
+ "epoch": 1.8602225312934633,
780
+ "grad_norm": 0.0,
781
+ "learning_rate": 1.901367640241076e-05,
782
+ "loss": 0.0,
783
+ "step": 10700
784
+ },
785
+ {
786
+ "epoch": 1.877607788595271,
787
+ "grad_norm": 0.0,
788
+ "learning_rate": 1.8723922114047286e-05,
789
+ "loss": 0.0,
790
+ "step": 10800
791
+ },
792
+ {
793
+ "epoch": 1.8949930458970794,
794
+ "grad_norm": 0.0,
795
+ "learning_rate": 1.843416782568382e-05,
796
+ "loss": 0.0,
797
+ "step": 10900
798
+ },
799
+ {
800
+ "epoch": 1.9123783031988872,
801
+ "grad_norm": 0.0,
802
+ "learning_rate": 1.8144413537320355e-05,
803
+ "loss": 0.0,
804
+ "step": 11000
805
+ },
806
+ {
807
+ "epoch": 1.9297635605006955,
808
+ "grad_norm": 0.0,
809
+ "learning_rate": 1.7854659248956883e-05,
810
+ "loss": 0.0,
811
+ "step": 11100
812
+ },
813
+ {
814
+ "epoch": 1.9471488178025034,
815
+ "grad_norm": 0.0,
816
+ "learning_rate": 1.7564904960593417e-05,
817
+ "loss": 0.0,
818
+ "step": 11200
819
+ },
820
+ {
821
+ "epoch": 1.9645340751043117,
822
+ "grad_norm": 0.0,
823
+ "learning_rate": 1.727515067222995e-05,
824
+ "loss": 0.0,
825
+ "step": 11300
826
+ },
827
+ {
828
+ "epoch": 1.9819193324061195,
829
+ "grad_norm": 0.0,
830
+ "learning_rate": 1.698539638386648e-05,
831
+ "loss": 0.0,
832
+ "step": 11400
833
+ },
834
+ {
835
+ "epoch": 1.9993045897079278,
836
+ "grad_norm": 0.0,
837
+ "learning_rate": 1.6695642095503014e-05,
838
+ "loss": 0.0,
839
+ "step": 11500
840
+ },
841
+ {
842
+ "epoch": 2.0166898470097356,
843
+ "grad_norm": 0.0,
844
+ "learning_rate": 1.6405887807139548e-05,
845
+ "loss": 0.0,
846
+ "step": 11600
847
+ },
848
+ {
849
+ "epoch": 2.034075104311544,
850
+ "grad_norm": 0.0,
851
+ "learning_rate": 1.611613351877608e-05,
852
+ "loss": 0.0,
853
+ "step": 11700
854
+ },
855
+ {
856
+ "epoch": 2.0514603616133518,
857
+ "grad_norm": 0.0,
858
+ "learning_rate": 1.582637923041261e-05,
859
+ "loss": 0.0,
860
+ "step": 11800
861
+ },
862
+ {
863
+ "epoch": 2.06884561891516,
864
+ "grad_norm": 0.0,
865
+ "learning_rate": 1.5536624942049145e-05,
866
+ "loss": 0.0,
867
+ "step": 11900
868
+ },
869
+ {
870
+ "epoch": 2.086230876216968,
871
+ "grad_norm": 0.0,
872
+ "learning_rate": 1.5246870653685674e-05,
873
+ "loss": 0.0,
874
+ "step": 12000
875
+ },
876
+ {
877
+ "epoch": 2.086230876216968,
878
+ "eval_loss": 0.0,
879
+ "eval_runtime": 664.7541,
880
+ "eval_samples_per_second": 17.306,
881
+ "eval_steps_per_second": 8.653,
882
+ "step": 12000
883
+ },
884
+ {
885
+ "epoch": 2.103616133518776,
886
+ "grad_norm": 0.0,
887
+ "learning_rate": 1.4957116365322207e-05,
888
+ "loss": 0.0,
889
+ "step": 12100
890
+ },
891
+ {
892
+ "epoch": 2.121001390820584,
893
+ "grad_norm": 0.0,
894
+ "learning_rate": 1.4667362076958741e-05,
895
+ "loss": 0.0,
896
+ "step": 12200
897
+ },
898
+ {
899
+ "epoch": 2.1383866481223923,
900
+ "grad_norm": 0.0,
901
+ "learning_rate": 1.437760778859527e-05,
902
+ "loss": 0.0,
903
+ "step": 12300
904
+ },
905
+ {
906
+ "epoch": 2.1557719054242,
907
+ "grad_norm": 0.0,
908
+ "learning_rate": 1.4087853500231805e-05,
909
+ "loss": 0.0,
910
+ "step": 12400
911
+ },
912
+ {
913
+ "epoch": 2.1731571627260085,
914
+ "grad_norm": 0.0,
915
+ "learning_rate": 1.3798099211868337e-05,
916
+ "loss": 0.0,
917
+ "step": 12500
918
+ },
919
+ {
920
+ "epoch": 2.1905424200278163,
921
+ "grad_norm": 0.0,
922
+ "learning_rate": 1.3508344923504868e-05,
923
+ "loss": 0.0,
924
+ "step": 12600
925
+ },
926
+ {
927
+ "epoch": 2.2079276773296246,
928
+ "grad_norm": 0.0,
929
+ "learning_rate": 1.3218590635141401e-05,
930
+ "loss": 0.0,
931
+ "step": 12700
932
+ },
933
+ {
934
+ "epoch": 2.2253129346314324,
935
+ "grad_norm": 0.0,
936
+ "learning_rate": 1.2928836346777934e-05,
937
+ "loss": 0.0,
938
+ "step": 12800
939
+ },
940
+ {
941
+ "epoch": 2.2426981919332407,
942
+ "grad_norm": 0.0,
943
+ "learning_rate": 1.2639082058414465e-05,
944
+ "loss": 0.0,
945
+ "step": 12900
946
+ },
947
+ {
948
+ "epoch": 2.2600834492350486,
949
+ "grad_norm": 0.0,
950
+ "learning_rate": 1.2349327770050998e-05,
951
+ "loss": 0.0,
952
+ "step": 13000
953
+ },
954
+ {
955
+ "epoch": 2.277468706536857,
956
+ "grad_norm": 0.0,
957
+ "learning_rate": 1.2059573481687529e-05,
958
+ "loss": 0.0,
959
+ "step": 13100
960
+ },
961
+ {
962
+ "epoch": 2.2948539638386647,
963
+ "grad_norm": 0.0,
964
+ "learning_rate": 1.1769819193324063e-05,
965
+ "loss": 0.0,
966
+ "step": 13200
967
+ },
968
+ {
969
+ "epoch": 2.312239221140473,
970
+ "grad_norm": 0.0,
971
+ "learning_rate": 1.1480064904960594e-05,
972
+ "loss": 0.0,
973
+ "step": 13300
974
+ },
975
+ {
976
+ "epoch": 2.329624478442281,
977
+ "grad_norm": 0.0,
978
+ "learning_rate": 1.1190310616597125e-05,
979
+ "loss": 0.0,
980
+ "step": 13400
981
+ },
982
+ {
983
+ "epoch": 2.347009735744089,
984
+ "grad_norm": 0.0,
985
+ "learning_rate": 1.090055632823366e-05,
986
+ "loss": 0.0,
987
+ "step": 13500
988
+ },
989
+ {
990
+ "epoch": 2.364394993045897,
991
+ "grad_norm": 0.0,
992
+ "learning_rate": 1.061080203987019e-05,
993
+ "loss": 0.0,
994
+ "step": 13600
995
+ },
996
+ {
997
+ "epoch": 2.3817802503477052,
998
+ "grad_norm": 0.0,
999
+ "learning_rate": 1.0321047751506723e-05,
1000
+ "loss": 0.0,
1001
+ "step": 13700
1002
+ },
1003
+ {
1004
+ "epoch": 2.399165507649513,
1005
+ "grad_norm": 0.0,
1006
+ "learning_rate": 1.0031293463143256e-05,
1007
+ "loss": 0.0,
1008
+ "step": 13800
1009
+ },
1010
+ {
1011
+ "epoch": 2.4165507649513214,
1012
+ "grad_norm": 0.0,
1013
+ "learning_rate": 9.741539174779787e-06,
1014
+ "loss": 0.0,
1015
+ "step": 13900
1016
+ },
1017
+ {
1018
+ "epoch": 2.433936022253129,
1019
+ "grad_norm": 0.0,
1020
+ "learning_rate": 9.45178488641632e-06,
1021
+ "loss": 0.0,
1022
+ "step": 14000
1023
+ },
1024
+ {
1025
+ "epoch": 2.4513212795549375,
1026
+ "grad_norm": 0.0,
1027
+ "learning_rate": 9.162030598052852e-06,
1028
+ "loss": 0.0,
1029
+ "step": 14100
1030
+ },
1031
+ {
1032
+ "epoch": 2.4687065368567453,
1033
+ "grad_norm": 0.0,
1034
+ "learning_rate": 8.872276309689383e-06,
1035
+ "loss": 0.0,
1036
+ "step": 14200
1037
+ },
1038
+ {
1039
+ "epoch": 2.4860917941585536,
1040
+ "grad_norm": 0.0,
1041
+ "learning_rate": 8.582522021325916e-06,
1042
+ "loss": 0.0,
1043
+ "step": 14300
1044
+ },
1045
+ {
1046
+ "epoch": 2.5034770514603615,
1047
+ "grad_norm": 0.0,
1048
+ "learning_rate": 8.292767732962447e-06,
1049
+ "loss": 0.0,
1050
+ "step": 14400
1051
+ },
1052
+ {
1053
+ "epoch": 2.5208623087621698,
1054
+ "grad_norm": 0.0,
1055
+ "learning_rate": 8.003013444598981e-06,
1056
+ "loss": 0.0,
1057
+ "step": 14500
1058
+ },
1059
+ {
1060
+ "epoch": 2.5382475660639776,
1061
+ "grad_norm": 0.0,
1062
+ "learning_rate": 7.713259156235512e-06,
1063
+ "loss": 0.0,
1064
+ "step": 14600
1065
+ },
1066
+ {
1067
+ "epoch": 2.555632823365786,
1068
+ "grad_norm": 0.0,
1069
+ "learning_rate": 7.423504867872044e-06,
1070
+ "loss": 0.0,
1071
+ "step": 14700
1072
+ },
1073
+ {
1074
+ "epoch": 2.5730180806675937,
1075
+ "grad_norm": 0.0,
1076
+ "learning_rate": 7.133750579508577e-06,
1077
+ "loss": 0.0,
1078
+ "step": 14800
1079
+ },
1080
+ {
1081
+ "epoch": 2.590403337969402,
1082
+ "grad_norm": 0.0,
1083
+ "learning_rate": 6.843996291145109e-06,
1084
+ "loss": 0.0,
1085
+ "step": 14900
1086
+ },
1087
+ {
1088
+ "epoch": 2.60778859527121,
1089
+ "grad_norm": 0.0,
1090
+ "learning_rate": 6.554242002781641e-06,
1091
+ "loss": 0.0,
1092
+ "step": 15000
1093
+ },
1094
+ {
1095
+ "epoch": 2.60778859527121,
1096
+ "eval_loss": 0.0,
1097
+ "eval_runtime": 666.4751,
1098
+ "eval_samples_per_second": 17.261,
1099
+ "eval_steps_per_second": 8.63,
1100
+ "step": 15000
1101
+ },
1102
+ {
1103
+ "epoch": 2.625173852573018,
1104
+ "grad_norm": 0.0,
1105
+ "learning_rate": 6.264487714418174e-06,
1106
+ "loss": 0.0,
1107
+ "step": 15100
1108
+ },
1109
+ {
1110
+ "epoch": 2.642559109874826,
1111
+ "grad_norm": 0.0,
1112
+ "learning_rate": 5.974733426054706e-06,
1113
+ "loss": 0.0,
1114
+ "step": 15200
1115
+ },
1116
+ {
1117
+ "epoch": 2.6599443671766343,
1118
+ "grad_norm": 0.0,
1119
+ "learning_rate": 5.684979137691238e-06,
1120
+ "loss": 0.0,
1121
+ "step": 15300
1122
+ },
1123
+ {
1124
+ "epoch": 2.677329624478442,
1125
+ "grad_norm": 0.0,
1126
+ "learning_rate": 5.39522484932777e-06,
1127
+ "loss": 0.0,
1128
+ "step": 15400
1129
+ },
1130
+ {
1131
+ "epoch": 2.6947148817802504,
1132
+ "grad_norm": 0.0,
1133
+ "learning_rate": 5.1054705609643026e-06,
1134
+ "loss": 0.0,
1135
+ "step": 15500
1136
+ },
1137
+ {
1138
+ "epoch": 2.7121001390820583,
1139
+ "grad_norm": 0.0,
1140
+ "learning_rate": 4.815716272600835e-06,
1141
+ "loss": 0.0,
1142
+ "step": 15600
1143
+ },
1144
+ {
1145
+ "epoch": 2.7294853963838666,
1146
+ "grad_norm": 0.0,
1147
+ "learning_rate": 4.525961984237367e-06,
1148
+ "loss": 0.0,
1149
+ "step": 15700
1150
+ },
1151
+ {
1152
+ "epoch": 2.7468706536856744,
1153
+ "grad_norm": 0.0,
1154
+ "learning_rate": 4.236207695873899e-06,
1155
+ "loss": 0.0,
1156
+ "step": 15800
1157
+ },
1158
+ {
1159
+ "epoch": 2.7642559109874827,
1160
+ "grad_norm": 0.0,
1161
+ "learning_rate": 3.946453407510432e-06,
1162
+ "loss": 0.0,
1163
+ "step": 15900
1164
+ },
1165
+ {
1166
+ "epoch": 2.7816411682892905,
1167
+ "grad_norm": 0.0,
1168
+ "learning_rate": 3.6566991191469636e-06,
1169
+ "loss": 0.0,
1170
+ "step": 16000
1171
+ },
1172
+ {
1173
+ "epoch": 2.799026425591099,
1174
+ "grad_norm": 0.0,
1175
+ "learning_rate": 3.3698423736671305e-06,
1176
+ "loss": 0.0,
1177
+ "step": 16100
1178
+ },
1179
+ {
1180
+ "epoch": 2.8164116828929067,
1181
+ "grad_norm": 0.0,
1182
+ "learning_rate": 3.0800880853036624e-06,
1183
+ "loss": 0.0,
1184
+ "step": 16200
1185
+ },
1186
+ {
1187
+ "epoch": 2.833796940194715,
1188
+ "grad_norm": 0.0,
1189
+ "learning_rate": 2.790333796940195e-06,
1190
+ "loss": 0.0,
1191
+ "step": 16300
1192
+ },
1193
+ {
1194
+ "epoch": 2.851182197496523,
1195
+ "grad_norm": 0.0,
1196
+ "learning_rate": 2.500579508576727e-06,
1197
+ "loss": 0.0,
1198
+ "step": 16400
1199
+ },
1200
+ {
1201
+ "epoch": 2.868567454798331,
1202
+ "grad_norm": 0.0,
1203
+ "learning_rate": 2.2108252202132593e-06,
1204
+ "loss": 0.0,
1205
+ "step": 16500
1206
+ },
1207
+ {
1208
+ "epoch": 2.885952712100139,
1209
+ "grad_norm": 0.0,
1210
+ "learning_rate": 1.9210709318497915e-06,
1211
+ "loss": 0.0,
1212
+ "step": 16600
1213
+ },
1214
+ {
1215
+ "epoch": 2.903337969401947,
1216
+ "grad_norm": 0.0,
1217
+ "learning_rate": 1.6313166434863236e-06,
1218
+ "loss": 0.0,
1219
+ "step": 16700
1220
+ },
1221
+ {
1222
+ "epoch": 2.920723226703755,
1223
+ "grad_norm": 0.0,
1224
+ "learning_rate": 1.341562355122856e-06,
1225
+ "loss": 0.0,
1226
+ "step": 16800
1227
+ },
1228
+ {
1229
+ "epoch": 2.9381084840055633,
1230
+ "grad_norm": 0.0,
1231
+ "learning_rate": 1.051808066759388e-06,
1232
+ "loss": 0.0,
1233
+ "step": 16900
1234
+ },
1235
+ {
1236
+ "epoch": 2.955493741307371,
1237
+ "grad_norm": 0.0,
1238
+ "learning_rate": 7.620537783959203e-07,
1239
+ "loss": 0.0,
1240
+ "step": 17000
1241
+ },
1242
+ {
1243
+ "epoch": 2.9728789986091795,
1244
+ "grad_norm": 0.0,
1245
+ "learning_rate": 4.7229949003245244e-07,
1246
+ "loss": 0.0,
1247
+ "step": 17100
1248
+ },
1249
+ {
1250
+ "epoch": 2.9902642559109873,
1251
+ "grad_norm": 0.0,
1252
+ "learning_rate": 1.825452016689847e-07,
1253
+ "loss": 0.0,
1254
+ "step": 17200
1255
+ }
1256
+ ],
1257
+ "logging_steps": 100,
1258
+ "max_steps": 17256,
1259
+ "num_input_tokens_seen": 0,
1260
+ "num_train_epochs": 3,
1261
+ "save_steps": 500,
1262
+ "stateful_callbacks": {
1263
+ "TrainerControl": {
1264
+ "args": {
1265
+ "should_epoch_stop": false,
1266
+ "should_evaluate": false,
1267
+ "should_log": false,
1268
+ "should_save": true,
1269
+ "should_training_stop": true
1270
+ },
1271
+ "attributes": {}
1272
+ }
1273
+ },
1274
+ "total_flos": 1.8679582951892582e+17,
1275
+ "train_batch_size": 2,
1276
+ "trial_name": null,
1277
+ "trial_params": null
1278
+ }
checkpoint-17256/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f56e75948c29c4f566977160640ec15a3fa7bd8fb9fa9a8775420935c2e28c
3
+ size 5240
checkpoint-17256/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForSequenceClassification"
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
+ "pad_token_id": 151643,
21
+ "problem_type": "single_label_classification",
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000000,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.51.3",
29
+ "use_cache": true,
30
+ "use_sliding_window": false,
31
+ "vocab_size": 151936
32
+ }
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:d69a32798954ae4639f94adebbf6003de9a48b5bedd9636431c895f243d55eeb
3
+ size 2384243248
pytorch_model.bin ADDED
File without changes
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
3
+ size 11422932
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
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff