Hugging Face's logo

Rithankoushik
/
job-parser-model-qwen

Text Generation
Safetensors
English
qwen3
conversational
Model card Files
xet
Community
1
Rithankoushik commited on
Commit
2ff9105
·
verified ·
1 Parent(s): 7202f6c

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +89 -0
  4. config.json +60 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. rng_state.pth +3 -0
  9. scheduler.pt +3 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +239 -0
  13. trainer_state.json +594 -0
  14. training_args.bin +3 -0
  15. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 40960,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen3",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 8,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": null,
52
+ "rope_theta": 1000000,
53
+ "sliding_window": null,
54
+ "tie_word_embeddings": true,
55
+ "torch_dtype": "bfloat16",
56
+ "transformers_version": "4.54.1",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.54.1"
13
+ }
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:f7fc16cf12eda50b2f1b4928a07917dca2bae460f4acef4ecdaa9db77ff10629
3
+ size 1192135096
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58445eff8cfea6167d69710c1c3e8b46f4af1c16da39f8fe17f7ddecfb128b91
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d23b4f208a9403528cc4590d75da0ba9842779b9cd25a1b5978ffbe9bcceb1
3
+ size 1064
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 190,
3
+ "best_metric": 6.224213600158691,
4
+ "best_model_checkpoint": "/kaggle/working/qwen-model-finetuned/checkpoint-190",
5
+ "epoch": 20.0,
6
+ "eval_steps": 500,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5194805194805194,
14
+ "grad_norm": 504.0,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 10.9305,
17
+ "mean_token_accuracy": 0.022239863348659128,
18
+ "num_tokens": 81920.0,
19
+ "step": 5
20
+ },
21
+ {
22
+ "epoch": 1.0,
23
+ "grad_norm": 528.0,
24
+ "learning_rate": 9.55e-06,
25
+ "loss": 9.7037,
26
+ "mean_token_accuracy": 0.03139729846923335,
27
+ "num_tokens": 157696.0,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 1.0,
32
+ "eval_loss": 9.371186256408691,
33
+ "eval_mean_token_accuracy": 0.025891548436548974,
34
+ "eval_num_tokens": 157696.0,
35
+ "eval_runtime": 10.0705,
36
+ "eval_samples_per_second": 0.894,
37
+ "eval_steps_per_second": 0.894,
38
+ "step": 10
39
+ },
40
+ {
41
+ "epoch": 1.5194805194805194,
42
+ "grad_norm": 374.0,
43
+ "learning_rate": 9.3e-06,
44
+ "loss": 9.0276,
45
+ "mean_token_accuracy": 0.04255007305182516,
46
+ "num_tokens": 239616.0,
47
+ "step": 15
48
+ },
49
+ {
50
+ "epoch": 2.0,
51
+ "grad_norm": 3504.0,
52
+ "learning_rate": 9.050000000000001e-06,
53
+ "loss": 8.5915,
54
+ "mean_token_accuracy": 0.06423375010490417,
55
+ "num_tokens": 315392.0,
56
+ "step": 20
57
+ },
58
+ {
59
+ "epoch": 2.0,
60
+ "eval_loss": 8.596755981445312,
61
+ "eval_mean_token_accuracy": 0.06323617200056712,
62
+ "eval_num_tokens": 315392.0,
63
+ "eval_runtime": 9.9888,
64
+ "eval_samples_per_second": 0.901,
65
+ "eval_steps_per_second": 0.901,
66
+ "step": 20
67
+ },
68
+ {
69
+ "epoch": 2.5194805194805197,
70
+ "grad_norm": 502.0,
71
+ "learning_rate": 8.8e-06,
72
+ "loss": 8.3693,
73
+ "mean_token_accuracy": 0.0784318515099585,
74
+ "num_tokens": 397312.0,
75
+ "step": 25
76
+ },
77
+ {
78
+ "epoch": 3.0,
79
+ "grad_norm": 288.0,
80
+ "learning_rate": 8.550000000000001e-06,
81
+ "loss": 8.2333,
82
+ "mean_token_accuracy": 0.07881012428048495,
83
+ "num_tokens": 473088.0,
84
+ "step": 30
85
+ },
86
+ {
87
+ "epoch": 3.0,
88
+ "eval_loss": 8.20586109161377,
89
+ "eval_mean_token_accuracy": 0.06926124874088499,
90
+ "eval_num_tokens": 473088.0,
91
+ "eval_runtime": 9.9908,
92
+ "eval_samples_per_second": 0.901,
93
+ "eval_steps_per_second": 0.901,
94
+ "step": 30
95
+ },
96
+ {
97
+ "epoch": 3.5194805194805197,
98
+ "grad_norm": 249.0,
99
+ "learning_rate": 8.3e-06,
100
+ "loss": 8.0225,
101
+ "mean_token_accuracy": 0.09137762561440468,
102
+ "num_tokens": 555008.0,
103
+ "step": 35
104
+ },
105
+ {
106
+ "epoch": 4.0,
107
+ "grad_norm": 218.0,
108
+ "learning_rate": 8.050000000000001e-06,
109
+ "loss": 7.8343,
110
+ "mean_token_accuracy": 0.09395423753036035,
111
+ "num_tokens": 630784.0,
112
+ "step": 40
113
+ },
114
+ {
115
+ "epoch": 4.0,
116
+ "eval_loss": 7.793511390686035,
117
+ "eval_mean_token_accuracy": 0.0885306414630678,
118
+ "eval_num_tokens": 630784.0,
119
+ "eval_runtime": 9.9692,
120
+ "eval_samples_per_second": 0.903,
121
+ "eval_steps_per_second": 0.903,
122
+ "step": 40
123
+ },
124
+ {
125
+ "epoch": 4.51948051948052,
126
+ "grad_norm": 124.5,
127
+ "learning_rate": 7.800000000000002e-06,
128
+ "loss": 7.667,
129
+ "mean_token_accuracy": 0.10079384371638297,
130
+ "num_tokens": 712704.0,
131
+ "step": 45
132
+ },
133
+ {
134
+ "epoch": 5.0,
135
+ "grad_norm": 199.0,
136
+ "learning_rate": 7.5500000000000006e-06,
137
+ "loss": 7.5062,
138
+ "mean_token_accuracy": 0.10965288692229502,
139
+ "num_tokens": 788480.0,
140
+ "step": 50
141
+ },
142
+ {
143
+ "epoch": 5.0,
144
+ "eval_loss": 7.532417297363281,
145
+ "eval_mean_token_accuracy": 0.11339086873663796,
146
+ "eval_num_tokens": 788480.0,
147
+ "eval_runtime": 9.9854,
148
+ "eval_samples_per_second": 0.901,
149
+ "eval_steps_per_second": 0.901,
150
+ "step": 50
151
+ },
152
+ {
153
+ "epoch": 5.51948051948052,
154
+ "grad_norm": 189.0,
155
+ "learning_rate": 7.3e-06,
156
+ "loss": 7.4228,
157
+ "mean_token_accuracy": 0.14055935498327016,
158
+ "num_tokens": 870400.0,
159
+ "step": 55
160
+ },
161
+ {
162
+ "epoch": 6.0,
163
+ "grad_norm": 179.0,
164
+ "learning_rate": 7.05e-06,
165
+ "loss": 7.1983,
166
+ "mean_token_accuracy": 0.1601288616657257,
167
+ "num_tokens": 946176.0,
168
+ "step": 60
169
+ },
170
+ {
171
+ "epoch": 6.0,
172
+ "eval_loss": 7.2402825355529785,
173
+ "eval_mean_token_accuracy": 0.15719481143686506,
174
+ "eval_num_tokens": 946176.0,
175
+ "eval_runtime": 9.9843,
176
+ "eval_samples_per_second": 0.901,
177
+ "eval_steps_per_second": 0.901,
178
+ "step": 60
179
+ },
180
+ {
181
+ "epoch": 6.51948051948052,
182
+ "grad_norm": 212.0,
183
+ "learning_rate": 6.800000000000001e-06,
184
+ "loss": 7.1554,
185
+ "mean_token_accuracy": 0.16111382581293582,
186
+ "num_tokens": 1028096.0,
187
+ "step": 65
188
+ },
189
+ {
190
+ "epoch": 7.0,
191
+ "grad_norm": 240.0,
192
+ "learning_rate": 6.550000000000001e-06,
193
+ "loss": 7.0146,
194
+ "mean_token_accuracy": 0.16839409096015467,
195
+ "num_tokens": 1103872.0,
196
+ "step": 70
197
+ },
198
+ {
199
+ "epoch": 7.0,
200
+ "eval_loss": 7.037937641143799,
201
+ "eval_mean_token_accuracy": 0.16300277080800799,
202
+ "eval_num_tokens": 1103872.0,
203
+ "eval_runtime": 9.9771,
204
+ "eval_samples_per_second": 0.902,
205
+ "eval_steps_per_second": 0.902,
206
+ "step": 70
207
+ },
208
+ {
209
+ "epoch": 7.51948051948052,
210
+ "grad_norm": 89.0,
211
+ "learning_rate": 6.300000000000001e-06,
212
+ "loss": 6.9988,
213
+ "mean_token_accuracy": 0.1658891063183546,
214
+ "num_tokens": 1185792.0,
215
+ "step": 75
216
+ },
217
+ {
218
+ "epoch": 8.0,
219
+ "grad_norm": 99.5,
220
+ "learning_rate": 6.0500000000000005e-06,
221
+ "loss": 6.8182,
222
+ "mean_token_accuracy": 0.1801449720923965,
223
+ "num_tokens": 1261568.0,
224
+ "step": 80
225
+ },
226
+ {
227
+ "epoch": 8.0,
228
+ "eval_loss": 6.879114627838135,
229
+ "eval_mean_token_accuracy": 0.17081908716095817,
230
+ "eval_num_tokens": 1261568.0,
231
+ "eval_runtime": 9.9794,
232
+ "eval_samples_per_second": 0.902,
233
+ "eval_steps_per_second": 0.902,
234
+ "step": 80
235
+ },
236
+ {
237
+ "epoch": 8.519480519480519,
238
+ "grad_norm": 79.0,
239
+ "learning_rate": 5.8e-06,
240
+ "loss": 6.7599,
241
+ "mean_token_accuracy": 0.18248656746000053,
242
+ "num_tokens": 1343488.0,
243
+ "step": 85
244
+ },
245
+ {
246
+ "epoch": 9.0,
247
+ "grad_norm": 244.0,
248
+ "learning_rate": 5.550000000000001e-06,
249
+ "loss": 6.7712,
250
+ "mean_token_accuracy": 0.18557150158527735,
251
+ "num_tokens": 1419264.0,
252
+ "step": 90
253
+ },
254
+ {
255
+ "epoch": 9.0,
256
+ "eval_loss": 6.76102352142334,
257
+ "eval_mean_token_accuracy": 0.18694023622406852,
258
+ "eval_num_tokens": 1419264.0,
259
+ "eval_runtime": 9.9905,
260
+ "eval_samples_per_second": 0.901,
261
+ "eval_steps_per_second": 0.901,
262
+ "step": 90
263
+ },
264
+ {
265
+ "epoch": 9.519480519480519,
266
+ "grad_norm": 122.0,
267
+ "learning_rate": 5.300000000000001e-06,
268
+ "loss": 6.7039,
269
+ "mean_token_accuracy": 0.18946018554270266,
270
+ "num_tokens": 1501184.0,
271
+ "step": 95
272
+ },
273
+ {
274
+ "epoch": 10.0,
275
+ "grad_norm": 182.0,
276
+ "learning_rate": 5.050000000000001e-06,
277
+ "loss": 6.618,
278
+ "mean_token_accuracy": 0.1998177944002925,
279
+ "num_tokens": 1576960.0,
280
+ "step": 100
281
+ },
282
+ {
283
+ "epoch": 10.0,
284
+ "eval_loss": 6.640429496765137,
285
+ "eval_mean_token_accuracy": 0.19361667500601876,
286
+ "eval_num_tokens": 1576960.0,
287
+ "eval_runtime": 9.9854,
288
+ "eval_samples_per_second": 0.901,
289
+ "eval_steps_per_second": 0.901,
290
+ "step": 100
291
+ },
292
+ {
293
+ "epoch": 10.519480519480519,
294
+ "grad_norm": 103.5,
295
+ "learning_rate": 4.800000000000001e-06,
296
+ "loss": 6.5581,
297
+ "mean_token_accuracy": 0.19838788434863092,
298
+ "num_tokens": 1658880.0,
299
+ "step": 105
300
+ },
301
+ {
302
+ "epoch": 11.0,
303
+ "grad_norm": 132.0,
304
+ "learning_rate": 4.5500000000000005e-06,
305
+ "loss": 6.5207,
306
+ "mean_token_accuracy": 0.19835223559592222,
307
+ "num_tokens": 1734656.0,
308
+ "step": 110
309
+ },
310
+ {
311
+ "epoch": 11.0,
312
+ "eval_loss": 6.540436744689941,
313
+ "eval_mean_token_accuracy": 0.19757911231782702,
314
+ "eval_num_tokens": 1734656.0,
315
+ "eval_runtime": 9.9902,
316
+ "eval_samples_per_second": 0.901,
317
+ "eval_steps_per_second": 0.901,
318
+ "step": 110
319
+ },
320
+ {
321
+ "epoch": 11.519480519480519,
322
+ "grad_norm": 82.0,
323
+ "learning_rate": 4.3e-06,
324
+ "loss": 6.487,
325
+ "mean_token_accuracy": 0.1987176351249218,
326
+ "num_tokens": 1816576.0,
327
+ "step": 115
328
+ },
329
+ {
330
+ "epoch": 12.0,
331
+ "grad_norm": 55.0,
332
+ "learning_rate": 4.05e-06,
333
+ "loss": 6.381,
334
+ "mean_token_accuracy": 0.20363352991439201,
335
+ "num_tokens": 1892352.0,
336
+ "step": 120
337
+ },
338
+ {
339
+ "epoch": 12.0,
340
+ "eval_loss": 6.44816255569458,
341
+ "eval_mean_token_accuracy": 0.19850187169180977,
342
+ "eval_num_tokens": 1892352.0,
343
+ "eval_runtime": 9.9827,
344
+ "eval_samples_per_second": 0.902,
345
+ "eval_steps_per_second": 0.902,
346
+ "step": 120
347
+ },
348
+ {
349
+ "epoch": 12.519480519480519,
350
+ "grad_norm": 109.5,
351
+ "learning_rate": 3.8000000000000005e-06,
352
+ "loss": 6.3201,
353
+ "mean_token_accuracy": 0.207901806011796,
354
+ "num_tokens": 1974272.0,
355
+ "step": 125
356
+ },
357
+ {
358
+ "epoch": 13.0,
359
+ "grad_norm": 81.0,
360
+ "learning_rate": 3.5500000000000003e-06,
361
+ "loss": 6.3889,
362
+ "mean_token_accuracy": 0.1981937969858582,
363
+ "num_tokens": 2050048.0,
364
+ "step": 130
365
+ },
366
+ {
367
+ "epoch": 13.0,
368
+ "eval_loss": 6.373791217803955,
369
+ "eval_mean_token_accuracy": 0.19828475183910793,
370
+ "eval_num_tokens": 2050048.0,
371
+ "eval_runtime": 9.9649,
372
+ "eval_samples_per_second": 0.903,
373
+ "eval_steps_per_second": 0.903,
374
+ "step": 130
375
+ },
376
+ {
377
+ "epoch": 13.519480519480519,
378
+ "grad_norm": 57.75,
379
+ "learning_rate": 3.3000000000000006e-06,
380
+ "loss": 6.3537,
381
+ "mean_token_accuracy": 0.20020762123167515,
382
+ "num_tokens": 2131968.0,
383
+ "step": 135
384
+ },
385
+ {
386
+ "epoch": 14.0,
387
+ "grad_norm": 131.0,
388
+ "learning_rate": 3.05e-06,
389
+ "loss": 6.2238,
390
+ "mean_token_accuracy": 0.20939014046578794,
391
+ "num_tokens": 2207744.0,
392
+ "step": 140
393
+ },
394
+ {
395
+ "epoch": 14.0,
396
+ "eval_loss": 6.317364692687988,
397
+ "eval_mean_token_accuracy": 0.20094447003470528,
398
+ "eval_num_tokens": 2207744.0,
399
+ "eval_runtime": 9.9793,
400
+ "eval_samples_per_second": 0.902,
401
+ "eval_steps_per_second": 0.902,
402
+ "step": 140
403
+ },
404
+ {
405
+ "epoch": 14.519480519480519,
406
+ "grad_norm": 111.0,
407
+ "learning_rate": 2.8000000000000003e-06,
408
+ "loss": 6.2564,
409
+ "mean_token_accuracy": 0.2047997061163187,
410
+ "num_tokens": 2289664.0,
411
+ "step": 145
412
+ },
413
+ {
414
+ "epoch": 15.0,
415
+ "grad_norm": 60.5,
416
+ "learning_rate": 2.55e-06,
417
+ "loss": 6.237,
418
+ "mean_token_accuracy": 0.2071191845713435,
419
+ "num_tokens": 2365440.0,
420
+ "step": 150
421
+ },
422
+ {
423
+ "epoch": 15.0,
424
+ "eval_loss": 6.276952743530273,
425
+ "eval_mean_token_accuracy": 0.20354990826712716,
426
+ "eval_num_tokens": 2365440.0,
427
+ "eval_runtime": 9.9884,
428
+ "eval_samples_per_second": 0.901,
429
+ "eval_steps_per_second": 0.901,
430
+ "step": 150
431
+ },
432
+ {
433
+ "epoch": 15.519480519480519,
434
+ "grad_norm": 57.0,
435
+ "learning_rate": 2.3000000000000004e-06,
436
+ "loss": 6.1936,
437
+ "mean_token_accuracy": 0.2097093306481838,
438
+ "num_tokens": 2447360.0,
439
+ "step": 155
440
+ },
441
+ {
442
+ "epoch": 16.0,
443
+ "grad_norm": 92.5,
444
+ "learning_rate": 2.05e-06,
445
+ "loss": 6.2567,
446
+ "mean_token_accuracy": 0.20516510428609075,
447
+ "num_tokens": 2523136.0,
448
+ "step": 160
449
+ },
450
+ {
451
+ "epoch": 16.0,
452
+ "eval_loss": 6.257329940795898,
453
+ "eval_mean_token_accuracy": 0.20631818804475996,
454
+ "eval_num_tokens": 2523136.0,
455
+ "eval_runtime": 10.0306,
456
+ "eval_samples_per_second": 0.897,
457
+ "eval_steps_per_second": 0.897,
458
+ "step": 160
459
+ },
460
+ {
461
+ "epoch": 16.51948051948052,
462
+ "grad_norm": 57.75,
463
+ "learning_rate": 1.8000000000000001e-06,
464
+ "loss": 6.1925,
465
+ "mean_token_accuracy": 0.2081704933196306,
466
+ "num_tokens": 2605056.0,
467
+ "step": 165
468
+ },
469
+ {
470
+ "epoch": 17.0,
471
+ "grad_norm": 67.5,
472
+ "learning_rate": 1.5500000000000002e-06,
473
+ "loss": 6.2109,
474
+ "mean_token_accuracy": 0.2084659144685075,
475
+ "num_tokens": 2680832.0,
476
+ "step": 170
477
+ },
478
+ {
479
+ "epoch": 17.0,
480
+ "eval_loss": 6.232978343963623,
481
+ "eval_mean_token_accuracy": 0.20924930771191916,
482
+ "eval_num_tokens": 2680832.0,
483
+ "eval_runtime": 9.9679,
484
+ "eval_samples_per_second": 0.903,
485
+ "eval_steps_per_second": 0.903,
486
+ "step": 170
487
+ },
488
+ {
489
+ "epoch": 17.51948051948052,
490
+ "grad_norm": 66.0,
491
+ "learning_rate": 1.3e-06,
492
+ "loss": 6.1513,
493
+ "mean_token_accuracy": 0.21311675421893597,
494
+ "num_tokens": 2762752.0,
495
+ "step": 175
496
+ },
497
+ {
498
+ "epoch": 18.0,
499
+ "grad_norm": 62.25,
500
+ "learning_rate": 1.0500000000000001e-06,
501
+ "loss": 6.2227,
502
+ "mean_token_accuracy": 0.20644582042822968,
503
+ "num_tokens": 2838528.0,
504
+ "step": 180
505
+ },
506
+ {
507
+ "epoch": 18.0,
508
+ "eval_loss": 6.226585388183594,
509
+ "eval_mean_token_accuracy": 0.19757911231782702,
510
+ "eval_num_tokens": 2838528.0,
511
+ "eval_runtime": 9.9755,
512
+ "eval_samples_per_second": 0.902,
513
+ "eval_steps_per_second": 0.902,
514
+ "step": 180
515
+ },
516
+ {
517
+ "epoch": 18.51948051948052,
518
+ "grad_norm": 47.75,
519
+ "learning_rate": 8.000000000000001e-07,
520
+ "loss": 6.1354,
521
+ "mean_token_accuracy": 0.20610649585723878,
522
+ "num_tokens": 2920448.0,
523
+ "step": 185
524
+ },
525
+ {
526
+ "epoch": 19.0,
527
+ "grad_norm": 58.25,
528
+ "learning_rate": 5.5e-07,
529
+ "loss": 6.2115,
530
+ "mean_token_accuracy": 0.20702676193134203,
531
+ "num_tokens": 2996224.0,
532
+ "step": 190
533
+ },
534
+ {
535
+ "epoch": 19.0,
536
+ "eval_loss": 6.224213600158691,
537
+ "eval_mean_token_accuracy": 0.20870650642448002,
538
+ "eval_num_tokens": 2996224.0,
539
+ "eval_runtime": 9.9648,
540
+ "eval_samples_per_second": 0.903,
541
+ "eval_steps_per_second": 0.903,
542
+ "step": 190
543
+ },
544
+ {
545
+ "epoch": 19.51948051948052,
546
+ "grad_norm": 58.75,
547
+ "learning_rate": 3.0000000000000004e-07,
548
+ "loss": 6.1279,
549
+ "mean_token_accuracy": 0.21613336391746998,
550
+ "num_tokens": 3078144.0,
551
+ "step": 195
552
+ },
553
+ {
554
+ "epoch": 20.0,
555
+ "grad_norm": 57.75,
556
+ "learning_rate": 5.0000000000000004e-08,
557
+ "loss": 6.2165,
558
+ "mean_token_accuracy": 0.20515190266274116,
559
+ "num_tokens": 3153920.0,
560
+ "step": 200
561
+ },
562
+ {
563
+ "epoch": 20.0,
564
+ "eval_loss": 6.226177215576172,
565
+ "eval_mean_token_accuracy": 0.20892362627718183,
566
+ "eval_num_tokens": 3153920.0,
567
+ "eval_runtime": 9.9552,
568
+ "eval_samples_per_second": 0.904,
569
+ "eval_steps_per_second": 0.904,
570
+ "step": 200
571
+ }
572
+ ],
573
+ "logging_steps": 5,
574
+ "max_steps": 200,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 20,
577
+ "save_steps": 500,
578
+ "stateful_callbacks": {
579
+ "TrainerControl": {
580
+ "args": {
581
+ "should_epoch_stop": false,
582
+ "should_evaluate": false,
583
+ "should_log": false,
584
+ "should_save": true,
585
+ "should_training_stop": true
586
+ },
587
+ "attributes": {}
588
+ }
589
+ },
590
+ "total_flos": 8335194712965120.0,
591
+ "train_batch_size": 1,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2f8c22d0fee50998d86060e9500f318e469d54dd930d192c0716e06235eef1
3
+ size 5752
vocab.json ADDED
The diff for this file is too large to render. See raw diff