DrNicefellow commited on
Commit
d2afa51
·
verified ·
1 Parent(s): b7752d2

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. README.md +58 -0
  3. added_tokens.json +24 -0
  4. chat_template.jinja +331 -0
  5. checkpoint-300/README.md +209 -0
  6. checkpoint-300/adapter_config.json +42 -0
  7. checkpoint-300/adapter_model.safetensors +3 -0
  8. checkpoint-300/added_tokens.json +24 -0
  9. checkpoint-300/chat_template.jinja +54 -0
  10. checkpoint-300/merges.txt +0 -0
  11. checkpoint-300/optimizer.pt +3 -0
  12. checkpoint-300/rng_state.pth +3 -0
  13. checkpoint-300/scheduler.pt +3 -0
  14. checkpoint-300/special_tokens_map.json +31 -0
  15. checkpoint-300/tokenizer.json +3 -0
  16. checkpoint-300/tokenizer_config.json +207 -0
  17. checkpoint-300/trainer_state.json +3034 -0
  18. checkpoint-300/training_args.bin +3 -0
  19. checkpoint-300/vocab.json +0 -0
  20. checkpoint-50/README.md +209 -0
  21. checkpoint-50/adapter_config.json +42 -0
  22. checkpoint-50/adapter_model.safetensors +3 -0
  23. checkpoint-50/added_tokens.json +24 -0
  24. checkpoint-50/chat_template.jinja +331 -0
  25. checkpoint-50/merges.txt +0 -0
  26. checkpoint-50/optimizer.pt +3 -0
  27. checkpoint-50/rng_state.pth +3 -0
  28. checkpoint-50/scheduler.pt +3 -0
  29. checkpoint-50/special_tokens_map.json +23 -0
  30. checkpoint-50/tokenizer.json +3 -0
  31. checkpoint-50/tokenizer_config.json +183 -0
  32. checkpoint-50/trainer_state.json +534 -0
  33. checkpoint-50/training_args.bin +3 -0
  34. checkpoint-50/vocab.json +0 -0
  35. config.json +69 -0
  36. generation_config.json +11 -0
  37. lora_weights/README.md +209 -0
  38. lora_weights/adapter_config.json +42 -0
  39. lora_weights/adapter_model.safetensors +3 -0
  40. merges.txt +0 -0
  41. model-00001-of-00009.safetensors +3 -0
  42. model-00002-of-00009.safetensors +3 -0
  43. model-00003-of-00009.safetensors +3 -0
  44. model-00004-of-00009.safetensors +3 -0
  45. model-00005-of-00009.safetensors +3 -0
  46. model-00006-of-00009.safetensors +3 -0
  47. model-00007-of-00009.safetensors +3 -0
  48. model-00008-of-00009.safetensors +3 -0
  49. model-00009-of-00009.safetensors +3 -0
  50. model.safetensors.index.json +419 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openai/gpt-oss-20b
3
+ library_name: transformers
4
+ model_name: outputs
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for outputs
13
+
14
+ This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="None", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.24.0
38
+ - Transformers: 4.57.0.dev0
39
+ - Pytorch: 2.8.0+cu129
40
+ - Datasets: 4.2.0
41
+ - Tokenizers: 0.22.1
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {#-
2
+ In addition to the normal inputs of `messages` and `tools`, this template also accepts the
3
+ following kwargs:
4
+ - "builtin_tools": A list, can contain "browser" and/or "python".
5
+ - "model_identity": A string that optionally describes the model identity.
6
+ - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
7
+ #}
8
+
9
+ {#- Tool Definition Rendering ============================================== #}
10
+ {%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
11
+ {%- if param_spec.type == "array" -%}
12
+ {%- if param_spec['items'] -%}
13
+ {%- if param_spec['items']['type'] == "string" -%}
14
+ {{- "string[]" }}
15
+ {%- elif param_spec['items']['type'] == "number" -%}
16
+ {{- "number[]" }}
17
+ {%- elif param_spec['items']['type'] == "integer" -%}
18
+ {{- "number[]" }}
19
+ {%- elif param_spec['items']['type'] == "boolean" -%}
20
+ {{- "boolean[]" }}
21
+ {%- else -%}
22
+ {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
23
+ {%- if inner_type == "object | object" or inner_type|length > 50 -%}
24
+ {{- "any[]" }}
25
+ {%- else -%}
26
+ {{- inner_type + "[]" }}
27
+ {%- endif -%}
28
+ {%- endif -%}
29
+ {%- if param_spec.nullable -%}
30
+ {{- " | null" }}
31
+ {%- endif -%}
32
+ {%- else -%}
33
+ {{- "any[]" }}
34
+ {%- if param_spec.nullable -%}
35
+ {{- " | null" }}
36
+ {%- endif -%}
37
+ {%- endif -%}
38
+ {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
39
+ {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
40
+ {%- if param_spec.type | length > 1 -%}
41
+ {{- param_spec.type | join(" | ") }}
42
+ {%- else -%}
43
+ {{- param_spec.type[0] }}
44
+ {%- endif -%}
45
+ {%- elif param_spec.oneOf -%}
46
+ {#- Handle oneOf schemas - check for complex unions and fallback to any #}
47
+ {%- set has_object_variants = false -%}
48
+ {%- for variant in param_spec.oneOf -%}
49
+ {%- if variant.type == "object" -%}
50
+ {%- set has_object_variants = true -%}
51
+ {%- endif -%}
52
+ {%- endfor -%}
53
+ {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
54
+ {{- "any" }}
55
+ {%- else -%}
56
+ {%- for variant in param_spec.oneOf -%}
57
+ {{- render_typescript_type(variant, required_params) -}}
58
+ {%- if variant.description %}
59
+ {{- "// " + variant.description }}
60
+ {%- endif -%}
61
+ {%- if variant.default is defined %}
62
+ {{ "// default: " + variant.default|tojson }}
63
+ {%- endif -%}
64
+ {%- if not loop.last %}
65
+ {{- " | " }}
66
+ {% endif -%}
67
+ {%- endfor -%}
68
+ {%- endif -%}
69
+ {%- elif param_spec.type == "string" -%}
70
+ {%- if param_spec.enum -%}
71
+ {{- '"' + param_spec.enum|join('" | "') + '"' -}}
72
+ {%- else -%}
73
+ {{- "string" }}
74
+ {%- if param_spec.nullable %}
75
+ {{- " | null" }}
76
+ {%- endif -%}
77
+ {%- endif -%}
78
+ {%- elif param_spec.type == "number" -%}
79
+ {{- "number" }}
80
+ {%- elif param_spec.type == "integer" -%}
81
+ {{- "number" }}
82
+ {%- elif param_spec.type == "boolean" -%}
83
+ {{- "boolean" }}
84
+
85
+ {%- elif param_spec.type == "object" -%}
86
+ {%- if param_spec.properties -%}
87
+ {{- "{\n" }}
88
+ {%- for prop_name, prop_spec in param_spec.properties.items() -%}
89
+ {{- prop_name -}}
90
+ {%- if prop_name not in (param_spec.required or []) -%}
91
+ {{- "?" }}
92
+ {%- endif -%}
93
+ {{- ": " }}
94
+ {{ render_typescript_type(prop_spec, param_spec.required or []) }}
95
+ {%- if not loop.last -%}
96
+ {{-", " }}
97
+ {%- endif -%}
98
+ {%- endfor -%}
99
+ {{- "}" }}
100
+ {%- else -%}
101
+ {{- "object" }}
102
+ {%- endif -%}
103
+ {%- else -%}
104
+ {{- "any" }}
105
+ {%- endif -%}
106
+ {%- endmacro -%}
107
+
108
+ {%- macro render_tool_namespace(namespace_name, tools) -%}
109
+ {{- "## " + namespace_name + "\n\n" }}
110
+ {{- "namespace " + namespace_name + " {\n\n" }}
111
+ {%- for tool in tools %}
112
+ {%- set tool = tool.function %}
113
+ {{- "// " + tool.description + "\n" }}
114
+ {{- "type "+ tool.name + " = " }}
115
+ {%- if tool.parameters and tool.parameters.properties %}
116
+ {{- "(_: {\n" }}
117
+ {%- for param_name, param_spec in tool.parameters.properties.items() %}
118
+ {%- if param_spec.description %}
119
+ {{- "// " + param_spec.description + "\n" }}
120
+ {%- endif %}
121
+ {{- param_name }}
122
+ {%- if param_name not in (tool.parameters.required or []) -%}
123
+ {{- "?" }}
124
+ {%- endif -%}
125
+ {{- ": " }}
126
+ {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
127
+ {%- if param_spec.default is defined -%}
128
+ {%- if param_spec.enum %}
129
+ {{- ", // default: " + param_spec.default }}
130
+ {%- elif param_spec.oneOf %}
131
+ {{- "// default: " + param_spec.default }}
132
+ {%- else %}
133
+ {{- ", // default: " + param_spec.default|tojson }}
134
+ {%- endif -%}
135
+ {%- endif -%}
136
+ {%- if not loop.last %}
137
+ {{- ",\n" }}
138
+ {%- else %}
139
+ {{- ",\n" }}
140
+ {%- endif -%}
141
+ {%- endfor %}
142
+ {{- "}) => any;\n\n" }}
143
+ {%- else -%}
144
+ {{- "() => any;\n\n" }}
145
+ {%- endif -%}
146
+ {%- endfor %}
147
+ {{- "} // namespace " + namespace_name }}
148
+ {%- endmacro -%}
149
+
150
+ {%- macro render_builtin_tools(browser_tool, python_tool) -%}
151
+ {%- if browser_tool %}
152
+ {{- "## browser\n\n" }}
153
+ {{- "// Tool for browsing.\n" }}
154
+ {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
155
+ {{- "// Cite information from the tool using the following format:\n" }}
156
+ {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
157
+ {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
158
+ {{- "// sources=web (default: web)\n" }}
159
+ {{- "namespace browser {\n\n" }}
160
+ {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
161
+ {{- "type search = (_: {\n" }}
162
+ {{- "query: string,\n" }}
163
+ {{- "topn?: number, // default: 10\n" }}
164
+ {{- "source?: string,\n" }}
165
+ {{- "}) => any;\n\n" }}
166
+ {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
167
+ {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
168
+ {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
169
+ {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
170
+ {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
171
+ {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
172
+ {{- "type open = (_: {\n" }}
173
+ {{- "id?: number | string, // default: -1\n" }}
174
+ {{- "cursor?: number, // default: -1\n" }}
175
+ {{- "loc?: number, // default: -1\n" }}
176
+ {{- "num_lines?: number, // default: -1\n" }}
177
+ {{- "view_source?: boolean, // default: false\n" }}
178
+ {{- "source?: string,\n" }}
179
+ {{- "}) => any;\n\n" }}
180
+ {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
181
+ {{- "type find = (_: {\n" }}
182
+ {{- "pattern: string,\n" }}
183
+ {{- "cursor?: number, // default: -1\n" }}
184
+ {{- "}) => any;\n\n" }}
185
+ {{- "} // namespace browser\n\n" }}
186
+ {%- endif -%}
187
+
188
+ {%- if python_tool %}
189
+ {{- "## python\n\n" }}
190
+ {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
191
+ {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
192
+ {%- endif -%}
193
+ {%- endmacro -%}
194
+
195
+ {#- System Message Construction ============================================ #}
196
+ {%- macro build_system_message() -%}
197
+ {%- if model_identity is not defined %}
198
+ {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
199
+ {%- endif %}
200
+ {{- model_identity + "\n" }}
201
+ {{- "Knowledge cutoff: 2024-06\n" }}
202
+ {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
203
+ {%- if reasoning_effort is not defined %}
204
+ {%- set reasoning_effort = "medium" %}
205
+ {%- endif %}
206
+ {{- "Reasoning: " + reasoning_effort + "\n\n" }}
207
+ {%- if builtin_tools %}
208
+ {{- "# Tools\n\n" }}
209
+ {%- set available_builtin_tools = namespace(browser=false, python=false) %}
210
+ {%- for tool in builtin_tools %}
211
+ {%- if tool == "browser" %}
212
+ {%- set available_builtin_tools.browser = true %}
213
+ {%- elif tool == "python" %}
214
+ {%- set available_builtin_tools.python = true %}
215
+ {%- endif %}
216
+ {%- endfor %}
217
+ {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
218
+ {%- endif -%}
219
+ {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
220
+ {%- if tools -%}
221
+ {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
222
+ {%- endif -%}
223
+ {%- endmacro -%}
224
+
225
+ {#- Main Template Logic ================================================= #}
226
+ {#- Set defaults #}
227
+
228
+ {#- Render system message #}
229
+ {{- "<|start|>system<|message|>" }}
230
+ {{- build_system_message() }}
231
+ {{- "<|end|>" }}
232
+
233
+ {#- Extract developer message #}
234
+ {%- if messages[0].role == "developer" or messages[0].role == "system" %}
235
+ {%- set developer_message = messages[0].content %}
236
+ {%- set loop_messages = messages[1:] %}
237
+ {%- else %}
238
+ {%- set developer_message = "" %}
239
+ {%- set loop_messages = messages %}
240
+ {%- endif %}
241
+
242
+ {#- Render developer message #}
243
+ {%- if developer_message or tools %}
244
+ {{- "<|start|>developer<|message|>" }}
245
+ {%- if developer_message %}
246
+ {{- "# Instructions\n\n" }}
247
+ {{- developer_message }}
248
+ {{- "\n\n" }}
249
+ {%- endif %}
250
+ {%- if tools -%}
251
+ {{- "# Tools\n\n" }}
252
+ {{- render_tool_namespace("functions", tools) }}
253
+ {%- endif -%}
254
+ {{- "<|end|>" }}
255
+ {%- endif %}
256
+
257
+ {#- Render messages #}
258
+ {%- set last_tool_call = namespace(name=none) %}
259
+ {%- for message in loop_messages -%}
260
+ {#- At this point only assistant/user/tool messages should remain #}
261
+ {%- if message.role == 'assistant' -%}
262
+ {#- Checks to ensure the messages are being passed in the format we expect #}
263
+ {%- if "content" in message %}
264
+ {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
265
+ {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
266
+ {%- endif %}
267
+ {%- endif %}
268
+ {%- if "thinking" in message %}
269
+ {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
270
+ {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
271
+ {%- endif %}
272
+ {%- endif %}
273
+ {%- if "tool_calls" in message %}
274
+ {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
275
+ {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
276
+ {#- when we render CoT/analysis messages in inference. #}
277
+ {%- set future_final_message = namespace(found=false) %}
278
+ {%- for future_message in loop_messages[loop.index:] %}
279
+ {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
280
+ {%- set future_final_message.found = true %}
281
+ {%- endif %}
282
+ {%- endfor %}
283
+ {#- We assume max 1 tool call per message, and so we infer the tool call name #}
284
+ {#- in "tool" messages from the most recent assistant tool call name #}
285
+ {%- set tool_call = message.tool_calls[0] %}
286
+ {%- if tool_call.function %}
287
+ {%- set tool_call = tool_call.function %}
288
+ {%- endif %}
289
+ {%- if message.content and message.thinking %}
290
+ {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
291
+ {%- elif message.content and not future_final_message.found %}
292
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
293
+ {%- elif message.thinking and not future_final_message.found %}
294
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
295
+ {%- endif %}
296
+ {{- "<|start|>assistant to=" }}
297
+ {{- "functions." + tool_call.name + "<|channel|>commentary " }}
298
+ {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
299
+ {{- tool_call.arguments|tojson }}
300
+ {{- "<|call|>" }}
301
+ {%- set last_tool_call.name = tool_call.name %}
302
+ {%- elif loop.last and not add_generation_prompt %}
303
+ {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
304
+ {#- This is a situation that should only occur in training, never in inference. #}
305
+ {%- if "thinking" in message %}
306
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
307
+ {%- endif %}
308
+ {#- <|return|> indicates the end of generation, but <|end|> does not #}
309
+ {#- <|return|> should never be an input to the model, but we include it as the final token #}
310
+ {#- when training, so the model learns to emit it. #}
311
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
312
+ {%- else %}
313
+ {#- CoT is dropped during all previous turns, so we never render it for inference #}
314
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
315
+ {%- set last_tool_call.name = none %}
316
+ {%- endif %}
317
+ {%- elif message.role == 'tool' -%}
318
+ {%- if last_tool_call.name is none %}
319
+ {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
320
+ {%- endif %}
321
+ {{- "<|start|>functions." + last_tool_call.name }}
322
+ {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
323
+ {%- elif message.role == 'user' -%}
324
+ {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
325
+ {%- endif -%}
326
+ {%- endfor -%}
327
+
328
+ {#- Generation prompt #}
329
+ {%- if add_generation_prompt -%}
330
+ <|start|>assistant
331
+ {%- endif -%}
checkpoint-300/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-7B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 64,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "v_proj",
29
+ "o_proj",
30
+ "q_proj",
31
+ "k_proj",
32
+ "down_proj",
33
+ "up_proj",
34
+ "gate_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bd493654b196ece7e5697a186a971485c7a5edfd9a9f9bdcc446d31d01784d
3
+ size 645975704
checkpoint-300/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-300/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-300/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcdbff5c0b18f69a32415e63f46cedd84dc449061240416429db5a60c3bfd75d
3
+ size 1292182139
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47aad30eba6947da47bec58af0eabbba394fed1fbffd0477fedd282ad31f3bc5
3
+ size 14645
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15d3d1b8bb19162d239033d431d77f4eba28beb04ec2c0ba04b41fbc223a133
3
+ size 1465
checkpoint-300/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-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,3034 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 15.0,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.3481858372688293,
14
+ "epoch": 0.050955414012738856,
15
+ "grad_norm": 0.42022356390953064,
16
+ "learning_rate": 0.0,
17
+ "loss": 1.5404,
18
+ "mean_token_accuracy": 0.6100348308682442,
19
+ "num_tokens": 16370.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 1.2509200274944305,
24
+ "epoch": 0.10191082802547771,
25
+ "grad_norm": 0.37541937828063965,
26
+ "learning_rate": 4e-05,
27
+ "loss": 1.4171,
28
+ "mean_token_accuracy": 0.637866273522377,
29
+ "num_tokens": 32126.0,
30
+ "step": 2
31
+ },
32
+ {
33
+ "entropy": 1.2236506044864655,
34
+ "epoch": 0.15286624203821655,
35
+ "grad_norm": 0.3010457754135132,
36
+ "learning_rate": 8e-05,
37
+ "loss": 1.3236,
38
+ "mean_token_accuracy": 0.6549251675605774,
39
+ "num_tokens": 48510.0,
40
+ "step": 3
41
+ },
42
+ {
43
+ "entropy": 1.3142070770263672,
44
+ "epoch": 0.20382165605095542,
45
+ "grad_norm": 0.2625364661216736,
46
+ "learning_rate": 0.00012,
47
+ "loss": 1.3343,
48
+ "mean_token_accuracy": 0.6495203450322151,
49
+ "num_tokens": 64106.0,
50
+ "step": 4
51
+ },
52
+ {
53
+ "entropy": 1.3711989670991898,
54
+ "epoch": 0.25477707006369427,
55
+ "grad_norm": 0.2332204282283783,
56
+ "learning_rate": 0.00016,
57
+ "loss": 1.3073,
58
+ "mean_token_accuracy": 0.654352568089962,
59
+ "num_tokens": 80490.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "entropy": 1.30281962454319,
64
+ "epoch": 0.3057324840764331,
65
+ "grad_norm": 0.27727022767066956,
66
+ "learning_rate": 0.0002,
67
+ "loss": 1.1383,
68
+ "mean_token_accuracy": 0.6825252249836922,
69
+ "num_tokens": 96874.0,
70
+ "step": 6
71
+ },
72
+ {
73
+ "entropy": 1.440766528248787,
74
+ "epoch": 0.35668789808917195,
75
+ "grad_norm": 0.38116148114204407,
76
+ "learning_rate": 0.0001993220338983051,
77
+ "loss": 1.2144,
78
+ "mean_token_accuracy": 0.6650549918413162,
79
+ "num_tokens": 113258.0,
80
+ "step": 7
81
+ },
82
+ {
83
+ "entropy": 1.2435247004032135,
84
+ "epoch": 0.40764331210191085,
85
+ "grad_norm": 0.27608051896095276,
86
+ "learning_rate": 0.00019864406779661017,
87
+ "loss": 1.1114,
88
+ "mean_token_accuracy": 0.6855753660202026,
89
+ "num_tokens": 129642.0,
90
+ "step": 8
91
+ },
92
+ {
93
+ "entropy": 1.2537222802639008,
94
+ "epoch": 0.4585987261146497,
95
+ "grad_norm": 0.23021401464939117,
96
+ "learning_rate": 0.00019796610169491526,
97
+ "loss": 1.1577,
98
+ "mean_token_accuracy": 0.676470473408699,
99
+ "num_tokens": 145665.0,
100
+ "step": 9
101
+ },
102
+ {
103
+ "entropy": 1.1785454452037811,
104
+ "epoch": 0.5095541401273885,
105
+ "grad_norm": 0.2424541562795639,
106
+ "learning_rate": 0.00019728813559322035,
107
+ "loss": 1.1131,
108
+ "mean_token_accuracy": 0.6807782724499702,
109
+ "num_tokens": 161676.0,
110
+ "step": 10
111
+ },
112
+ {
113
+ "entropy": 1.1859825029969215,
114
+ "epoch": 0.5605095541401274,
115
+ "grad_norm": 0.23673631250858307,
116
+ "learning_rate": 0.00019661016949152545,
117
+ "loss": 1.1231,
118
+ "mean_token_accuracy": 0.6809910237789154,
119
+ "num_tokens": 178060.0,
120
+ "step": 11
121
+ },
122
+ {
123
+ "entropy": 1.199895717203617,
124
+ "epoch": 0.6114649681528662,
125
+ "grad_norm": 0.22655269503593445,
126
+ "learning_rate": 0.0001959322033898305,
127
+ "loss": 1.1237,
128
+ "mean_token_accuracy": 0.6825583502650261,
129
+ "num_tokens": 193801.0,
130
+ "step": 12
131
+ },
132
+ {
133
+ "entropy": 1.1316778659820557,
134
+ "epoch": 0.6624203821656051,
135
+ "grad_norm": 0.1964697539806366,
136
+ "learning_rate": 0.0001952542372881356,
137
+ "loss": 1.0177,
138
+ "mean_token_accuracy": 0.7018924430012703,
139
+ "num_tokens": 210117.0,
140
+ "step": 13
141
+ },
142
+ {
143
+ "entropy": 1.2201827466487885,
144
+ "epoch": 0.7133757961783439,
145
+ "grad_norm": 0.2558380961418152,
146
+ "learning_rate": 0.0001945762711864407,
147
+ "loss": 1.1021,
148
+ "mean_token_accuracy": 0.6867032945156097,
149
+ "num_tokens": 226501.0,
150
+ "step": 14
151
+ },
152
+ {
153
+ "entropy": 1.2256827503442764,
154
+ "epoch": 0.7643312101910829,
155
+ "grad_norm": 0.24053122103214264,
156
+ "learning_rate": 0.0001938983050847458,
157
+ "loss": 1.0771,
158
+ "mean_token_accuracy": 0.6895216032862663,
159
+ "num_tokens": 242576.0,
160
+ "step": 15
161
+ },
162
+ {
163
+ "entropy": 1.1773390918970108,
164
+ "epoch": 0.8152866242038217,
165
+ "grad_norm": 0.23696200549602509,
166
+ "learning_rate": 0.00019322033898305085,
167
+ "loss": 1.0436,
168
+ "mean_token_accuracy": 0.7001483887434006,
169
+ "num_tokens": 258960.0,
170
+ "step": 16
171
+ },
172
+ {
173
+ "entropy": 1.2502182573080063,
174
+ "epoch": 0.8662420382165605,
175
+ "grad_norm": 0.2583620250225067,
176
+ "learning_rate": 0.00019254237288135595,
177
+ "loss": 1.0969,
178
+ "mean_token_accuracy": 0.6846700087189674,
179
+ "num_tokens": 275344.0,
180
+ "step": 17
181
+ },
182
+ {
183
+ "entropy": 1.1538116410374641,
184
+ "epoch": 0.9171974522292994,
185
+ "grad_norm": 0.22091548144817352,
186
+ "learning_rate": 0.000191864406779661,
187
+ "loss": 1.0384,
188
+ "mean_token_accuracy": 0.7043633460998535,
189
+ "num_tokens": 291212.0,
190
+ "step": 18
191
+ },
192
+ {
193
+ "entropy": 1.0872942060232162,
194
+ "epoch": 0.9681528662420382,
195
+ "grad_norm": 0.21255861222743988,
196
+ "learning_rate": 0.0001911864406779661,
197
+ "loss": 1.0042,
198
+ "mean_token_accuracy": 0.7119970843195915,
199
+ "num_tokens": 307596.0,
200
+ "step": 19
201
+ },
202
+ {
203
+ "entropy": 1.079186463356018,
204
+ "epoch": 1.0,
205
+ "grad_norm": 0.2622547149658203,
206
+ "learning_rate": 0.0001905084745762712,
207
+ "loss": 0.9877,
208
+ "mean_token_accuracy": 0.7082325220108032,
209
+ "num_tokens": 316575.0,
210
+ "step": 20
211
+ },
212
+ {
213
+ "entropy": 1.042311891913414,
214
+ "epoch": 1.0509554140127388,
215
+ "grad_norm": 0.2054571956396103,
216
+ "learning_rate": 0.0001898305084745763,
217
+ "loss": 0.9347,
218
+ "mean_token_accuracy": 0.7204505205154419,
219
+ "num_tokens": 332686.0,
220
+ "step": 21
221
+ },
222
+ {
223
+ "entropy": 1.0129416584968567,
224
+ "epoch": 1.1019108280254777,
225
+ "grad_norm": 0.20944714546203613,
226
+ "learning_rate": 0.00018915254237288136,
227
+ "loss": 0.8911,
228
+ "mean_token_accuracy": 0.7332312241196632,
229
+ "num_tokens": 349070.0,
230
+ "step": 22
231
+ },
232
+ {
233
+ "entropy": 1.0294566750526428,
234
+ "epoch": 1.1528662420382165,
235
+ "grad_norm": 0.21608634293079376,
236
+ "learning_rate": 0.00018847457627118645,
237
+ "loss": 0.936,
238
+ "mean_token_accuracy": 0.7302276790142059,
239
+ "num_tokens": 365454.0,
240
+ "step": 23
241
+ },
242
+ {
243
+ "entropy": 1.0530632957816124,
244
+ "epoch": 1.2038216560509554,
245
+ "grad_norm": 0.2166907787322998,
246
+ "learning_rate": 0.00018779661016949151,
247
+ "loss": 0.9256,
248
+ "mean_token_accuracy": 0.7271289154887199,
249
+ "num_tokens": 381498.0,
250
+ "step": 24
251
+ },
252
+ {
253
+ "entropy": 1.0419923067092896,
254
+ "epoch": 1.2547770700636942,
255
+ "grad_norm": 0.2031186819076538,
256
+ "learning_rate": 0.00018711864406779663,
257
+ "loss": 0.9173,
258
+ "mean_token_accuracy": 0.7247356176376343,
259
+ "num_tokens": 397882.0,
260
+ "step": 25
261
+ },
262
+ {
263
+ "entropy": 0.9017334207892418,
264
+ "epoch": 1.305732484076433,
265
+ "grad_norm": 0.2247246950864792,
266
+ "learning_rate": 0.0001864406779661017,
267
+ "loss": 0.8218,
268
+ "mean_token_accuracy": 0.750381663441658,
269
+ "num_tokens": 414252.0,
270
+ "step": 26
271
+ },
272
+ {
273
+ "entropy": 0.9545145109295845,
274
+ "epoch": 1.356687898089172,
275
+ "grad_norm": 0.22306284308433533,
276
+ "learning_rate": 0.0001857627118644068,
277
+ "loss": 0.8353,
278
+ "mean_token_accuracy": 0.745391808450222,
279
+ "num_tokens": 430333.0,
280
+ "step": 27
281
+ },
282
+ {
283
+ "entropy": 1.007826380431652,
284
+ "epoch": 1.4076433121019107,
285
+ "grad_norm": 0.2460908591747284,
286
+ "learning_rate": 0.00018508474576271186,
287
+ "loss": 0.894,
288
+ "mean_token_accuracy": 0.7268281579017639,
289
+ "num_tokens": 445716.0,
290
+ "step": 28
291
+ },
292
+ {
293
+ "entropy": 0.9371664151549339,
294
+ "epoch": 1.4585987261146496,
295
+ "grad_norm": 0.2315070778131485,
296
+ "learning_rate": 0.00018440677966101695,
297
+ "loss": 0.8582,
298
+ "mean_token_accuracy": 0.744682066142559,
299
+ "num_tokens": 462100.0,
300
+ "step": 29
301
+ },
302
+ {
303
+ "entropy": 0.9967339187860489,
304
+ "epoch": 1.5095541401273884,
305
+ "grad_norm": 0.24030983448028564,
306
+ "learning_rate": 0.00018372881355932204,
307
+ "loss": 0.8878,
308
+ "mean_token_accuracy": 0.7294926047325134,
309
+ "num_tokens": 478484.0,
310
+ "step": 30
311
+ },
312
+ {
313
+ "entropy": 0.9289672449231148,
314
+ "epoch": 1.5605095541401273,
315
+ "grad_norm": 0.24277092516422272,
316
+ "learning_rate": 0.00018305084745762714,
317
+ "loss": 0.8019,
318
+ "mean_token_accuracy": 0.7570356875658035,
319
+ "num_tokens": 494353.0,
320
+ "step": 31
321
+ },
322
+ {
323
+ "entropy": 1.0442854911088943,
324
+ "epoch": 1.611464968152866,
325
+ "grad_norm": 0.24407894909381866,
326
+ "learning_rate": 0.0001823728813559322,
327
+ "loss": 0.9474,
328
+ "mean_token_accuracy": 0.718492366373539,
329
+ "num_tokens": 510669.0,
330
+ "step": 32
331
+ },
332
+ {
333
+ "entropy": 0.9737825468182564,
334
+ "epoch": 1.662420382165605,
335
+ "grad_norm": 0.23990698158740997,
336
+ "learning_rate": 0.0001816949152542373,
337
+ "loss": 0.8649,
338
+ "mean_token_accuracy": 0.7393911480903625,
339
+ "num_tokens": 526692.0,
340
+ "step": 33
341
+ },
342
+ {
343
+ "entropy": 0.9364971444010735,
344
+ "epoch": 1.7133757961783438,
345
+ "grad_norm": 0.25242283940315247,
346
+ "learning_rate": 0.00018101694915254239,
347
+ "loss": 0.8594,
348
+ "mean_token_accuracy": 0.7426017448306084,
349
+ "num_tokens": 542767.0,
350
+ "step": 34
351
+ },
352
+ {
353
+ "entropy": 0.9076659008860588,
354
+ "epoch": 1.7643312101910829,
355
+ "grad_norm": 0.24069900810718536,
356
+ "learning_rate": 0.00018033898305084748,
357
+ "loss": 0.7971,
358
+ "mean_token_accuracy": 0.7580301761627197,
359
+ "num_tokens": 559151.0,
360
+ "step": 35
361
+ },
362
+ {
363
+ "entropy": 0.9450107514858246,
364
+ "epoch": 1.8152866242038217,
365
+ "grad_norm": 0.2449842095375061,
366
+ "learning_rate": 0.00017966101694915257,
367
+ "loss": 0.8106,
368
+ "mean_token_accuracy": 0.751865841448307,
369
+ "num_tokens": 575298.0,
370
+ "step": 36
371
+ },
372
+ {
373
+ "entropy": 0.9835781082510948,
374
+ "epoch": 1.8662420382165605,
375
+ "grad_norm": 0.26215094327926636,
376
+ "learning_rate": 0.00017898305084745764,
377
+ "loss": 0.8635,
378
+ "mean_token_accuracy": 0.7387464940547943,
379
+ "num_tokens": 591682.0,
380
+ "step": 37
381
+ },
382
+ {
383
+ "entropy": 0.996803492307663,
384
+ "epoch": 1.9171974522292994,
385
+ "grad_norm": 0.26561757922172546,
386
+ "learning_rate": 0.00017830508474576273,
387
+ "loss": 0.8834,
388
+ "mean_token_accuracy": 0.7345194965600967,
389
+ "num_tokens": 608066.0,
390
+ "step": 38
391
+ },
392
+ {
393
+ "entropy": 0.9412061348557472,
394
+ "epoch": 1.9681528662420382,
395
+ "grad_norm": 0.2681407630443573,
396
+ "learning_rate": 0.0001776271186440678,
397
+ "loss": 0.8378,
398
+ "mean_token_accuracy": 0.7482910975813866,
399
+ "num_tokens": 623934.0,
400
+ "step": 39
401
+ },
402
+ {
403
+ "entropy": 0.8333677649497986,
404
+ "epoch": 2.0,
405
+ "grad_norm": 0.3134506046772003,
406
+ "learning_rate": 0.0001769491525423729,
407
+ "loss": 0.7475,
408
+ "mean_token_accuracy": 0.7668535470962524,
409
+ "num_tokens": 633150.0,
410
+ "step": 40
411
+ },
412
+ {
413
+ "entropy": 0.9032419994473457,
414
+ "epoch": 2.050955414012739,
415
+ "grad_norm": 0.2786886990070343,
416
+ "learning_rate": 0.00017627118644067798,
417
+ "loss": 0.6645,
418
+ "mean_token_accuracy": 0.7967495918273926,
419
+ "num_tokens": 649534.0,
420
+ "step": 41
421
+ },
422
+ {
423
+ "entropy": 0.8636530712246895,
424
+ "epoch": 2.1019108280254777,
425
+ "grad_norm": 0.27957314252853394,
426
+ "learning_rate": 0.00017559322033898307,
427
+ "loss": 0.6314,
428
+ "mean_token_accuracy": 0.8060957714915276,
429
+ "num_tokens": 665403.0,
430
+ "step": 42
431
+ },
432
+ {
433
+ "entropy": 0.8624916896224022,
434
+ "epoch": 2.1528662420382165,
435
+ "grad_norm": 0.2938512861728668,
436
+ "learning_rate": 0.00017491525423728814,
437
+ "loss": 0.6799,
438
+ "mean_token_accuracy": 0.790034182369709,
439
+ "num_tokens": 681447.0,
440
+ "step": 43
441
+ },
442
+ {
443
+ "entropy": 0.7863286510109901,
444
+ "epoch": 2.2038216560509554,
445
+ "grad_norm": 0.3072890341281891,
446
+ "learning_rate": 0.00017423728813559323,
447
+ "loss": 0.647,
448
+ "mean_token_accuracy": 0.7969771400094032,
449
+ "num_tokens": 697831.0,
450
+ "step": 44
451
+ },
452
+ {
453
+ "entropy": 0.7100256532430649,
454
+ "epoch": 2.254777070063694,
455
+ "grad_norm": 0.3542580008506775,
456
+ "learning_rate": 0.0001735593220338983,
457
+ "loss": 0.6337,
458
+ "mean_token_accuracy": 0.8022638335824013,
459
+ "num_tokens": 714215.0,
460
+ "step": 45
461
+ },
462
+ {
463
+ "entropy": 0.716219499707222,
464
+ "epoch": 2.305732484076433,
465
+ "grad_norm": 0.39583054184913635,
466
+ "learning_rate": 0.00017288135593220342,
467
+ "loss": 0.6277,
468
+ "mean_token_accuracy": 0.8007404282689095,
469
+ "num_tokens": 730585.0,
470
+ "step": 46
471
+ },
472
+ {
473
+ "entropy": 0.7219437435269356,
474
+ "epoch": 2.356687898089172,
475
+ "grad_norm": 0.3591735363006592,
476
+ "learning_rate": 0.00017220338983050848,
477
+ "loss": 0.634,
478
+ "mean_token_accuracy": 0.8042735084891319,
479
+ "num_tokens": 746901.0,
480
+ "step": 47
481
+ },
482
+ {
483
+ "entropy": 0.7401451990008354,
484
+ "epoch": 2.4076433121019107,
485
+ "grad_norm": 0.34251025319099426,
486
+ "learning_rate": 0.00017152542372881357,
487
+ "loss": 0.6275,
488
+ "mean_token_accuracy": 0.8064323589205742,
489
+ "num_tokens": 763285.0,
490
+ "step": 48
491
+ },
492
+ {
493
+ "entropy": 0.7539378255605698,
494
+ "epoch": 2.4585987261146496,
495
+ "grad_norm": 0.3110820949077606,
496
+ "learning_rate": 0.00017084745762711864,
497
+ "loss": 0.5985,
498
+ "mean_token_accuracy": 0.8130116537213326,
499
+ "num_tokens": 779041.0,
500
+ "step": 49
501
+ },
502
+ {
503
+ "entropy": 0.7710842117667198,
504
+ "epoch": 2.5095541401273884,
505
+ "grad_norm": 0.3228455185890198,
506
+ "learning_rate": 0.00017016949152542373,
507
+ "loss": 0.5966,
508
+ "mean_token_accuracy": 0.8146229013800621,
509
+ "num_tokens": 795064.0,
510
+ "step": 50
511
+ },
512
+ {
513
+ "entropy": 0.7773924395442009,
514
+ "epoch": 2.5605095541401273,
515
+ "grad_norm": 0.3367364704608917,
516
+ "learning_rate": 0.00016949152542372882,
517
+ "loss": 0.5938,
518
+ "mean_token_accuracy": 0.8128385469317436,
519
+ "num_tokens": 811448.0,
520
+ "step": 51
521
+ },
522
+ {
523
+ "entropy": 0.7728712856769562,
524
+ "epoch": 2.611464968152866,
525
+ "grad_norm": 0.35927024483680725,
526
+ "learning_rate": 0.00016881355932203392,
527
+ "loss": 0.6354,
528
+ "mean_token_accuracy": 0.8013699352741241,
529
+ "num_tokens": 827459.0,
530
+ "step": 52
531
+ },
532
+ {
533
+ "entropy": 0.7718184515833855,
534
+ "epoch": 2.662420382165605,
535
+ "grad_norm": 0.3391318619251251,
536
+ "learning_rate": 0.00016813559322033898,
537
+ "loss": 0.6334,
538
+ "mean_token_accuracy": 0.8047890961170197,
539
+ "num_tokens": 843327.0,
540
+ "step": 53
541
+ },
542
+ {
543
+ "entropy": 0.7653945237398148,
544
+ "epoch": 2.713375796178344,
545
+ "grad_norm": 0.35930103063583374,
546
+ "learning_rate": 0.00016745762711864408,
547
+ "loss": 0.6198,
548
+ "mean_token_accuracy": 0.8065511807799339,
549
+ "num_tokens": 859402.0,
550
+ "step": 54
551
+ },
552
+ {
553
+ "entropy": 0.7647791504859924,
554
+ "epoch": 2.7643312101910826,
555
+ "grad_norm": 0.3643956482410431,
556
+ "learning_rate": 0.00016677966101694914,
557
+ "loss": 0.6315,
558
+ "mean_token_accuracy": 0.8033340945839882,
559
+ "num_tokens": 875786.0,
560
+ "step": 55
561
+ },
562
+ {
563
+ "entropy": 0.7234460189938545,
564
+ "epoch": 2.8152866242038215,
565
+ "grad_norm": 0.3637371361255646,
566
+ "learning_rate": 0.00016610169491525423,
567
+ "loss": 0.6047,
568
+ "mean_token_accuracy": 0.8084925785660744,
569
+ "num_tokens": 892170.0,
570
+ "step": 56
571
+ },
572
+ {
573
+ "entropy": 0.7029176577925682,
574
+ "epoch": 2.8662420382165603,
575
+ "grad_norm": 0.41221824288368225,
576
+ "learning_rate": 0.00016542372881355933,
577
+ "loss": 0.6028,
578
+ "mean_token_accuracy": 0.8094355836510658,
579
+ "num_tokens": 908554.0,
580
+ "step": 57
581
+ },
582
+ {
583
+ "entropy": 0.8026896864175797,
584
+ "epoch": 2.917197452229299,
585
+ "grad_norm": 0.40634164214134216,
586
+ "learning_rate": 0.00016474576271186442,
587
+ "loss": 0.6841,
588
+ "mean_token_accuracy": 0.7903437316417694,
589
+ "num_tokens": 924362.0,
590
+ "step": 58
591
+ },
592
+ {
593
+ "entropy": 0.7678564339876175,
594
+ "epoch": 2.968152866242038,
595
+ "grad_norm": 0.3688332438468933,
596
+ "learning_rate": 0.00016406779661016948,
597
+ "loss": 0.6375,
598
+ "mean_token_accuracy": 0.8057018518447876,
599
+ "num_tokens": 940746.0,
600
+ "step": 59
601
+ },
602
+ {
603
+ "entropy": 0.7260988593101502,
604
+ "epoch": 3.0,
605
+ "grad_norm": 0.4596911668777466,
606
+ "learning_rate": 0.00016338983050847458,
607
+ "loss": 0.608,
608
+ "mean_token_accuracy": 0.8153721690177917,
609
+ "num_tokens": 949725.0,
610
+ "step": 60
611
+ },
612
+ {
613
+ "entropy": 0.7356696203351021,
614
+ "epoch": 3.050955414012739,
615
+ "grad_norm": 0.39724084734916687,
616
+ "learning_rate": 0.00016271186440677967,
617
+ "loss": 0.4432,
618
+ "mean_token_accuracy": 0.8702359348535538,
619
+ "num_tokens": 966109.0,
620
+ "step": 61
621
+ },
622
+ {
623
+ "entropy": 0.7380152717232704,
624
+ "epoch": 3.1019108280254777,
625
+ "grad_norm": 0.38238734006881714,
626
+ "learning_rate": 0.00016203389830508476,
627
+ "loss": 0.4427,
628
+ "mean_token_accuracy": 0.8688767999410629,
629
+ "num_tokens": 982132.0,
630
+ "step": 62
631
+ },
632
+ {
633
+ "entropy": 0.6648666933178902,
634
+ "epoch": 3.1528662420382165,
635
+ "grad_norm": 0.3744766414165497,
636
+ "learning_rate": 0.00016135593220338985,
637
+ "loss": 0.4303,
638
+ "mean_token_accuracy": 0.8702655509114265,
639
+ "num_tokens": 998516.0,
640
+ "step": 63
641
+ },
642
+ {
643
+ "entropy": 0.5741898603737354,
644
+ "epoch": 3.2038216560509554,
645
+ "grad_norm": 0.38260239362716675,
646
+ "learning_rate": 0.00016067796610169492,
647
+ "loss": 0.3882,
648
+ "mean_token_accuracy": 0.877837598323822,
649
+ "num_tokens": 1014900.0,
650
+ "step": 64
651
+ },
652
+ {
653
+ "entropy": 0.594137117266655,
654
+ "epoch": 3.254777070063694,
655
+ "grad_norm": 0.4781484007835388,
656
+ "learning_rate": 0.00016,
657
+ "loss": 0.4123,
658
+ "mean_token_accuracy": 0.8714389055967331,
659
+ "num_tokens": 1030353.0,
660
+ "step": 65
661
+ },
662
+ {
663
+ "entropy": 0.49363305792212486,
664
+ "epoch": 3.305732484076433,
665
+ "grad_norm": 0.43986085057258606,
666
+ "learning_rate": 0.00015932203389830508,
667
+ "loss": 0.3587,
668
+ "mean_token_accuracy": 0.8876991271972656,
669
+ "num_tokens": 1046737.0,
670
+ "step": 66
671
+ },
672
+ {
673
+ "entropy": 0.5222570262849331,
674
+ "epoch": 3.356687898089172,
675
+ "grad_norm": 0.5446242094039917,
676
+ "learning_rate": 0.0001586440677966102,
677
+ "loss": 0.4049,
678
+ "mean_token_accuracy": 0.8768400251865387,
679
+ "num_tokens": 1062022.0,
680
+ "step": 67
681
+ },
682
+ {
683
+ "entropy": 0.5206106752157211,
684
+ "epoch": 3.4076433121019107,
685
+ "grad_norm": 0.5299471616744995,
686
+ "learning_rate": 0.00015796610169491526,
687
+ "loss": 0.4241,
688
+ "mean_token_accuracy": 0.8641180545091629,
689
+ "num_tokens": 1078406.0,
690
+ "step": 68
691
+ },
692
+ {
693
+ "entropy": 0.518733087927103,
694
+ "epoch": 3.4585987261146496,
695
+ "grad_norm": 0.5972740650177002,
696
+ "learning_rate": 0.00015728813559322036,
697
+ "loss": 0.4115,
698
+ "mean_token_accuracy": 0.8688035756349564,
699
+ "num_tokens": 1094436.0,
700
+ "step": 69
701
+ },
702
+ {
703
+ "entropy": 0.5547057241201401,
704
+ "epoch": 3.5095541401273884,
705
+ "grad_norm": 0.4489477276802063,
706
+ "learning_rate": 0.00015661016949152542,
707
+ "loss": 0.404,
708
+ "mean_token_accuracy": 0.8720321208238602,
709
+ "num_tokens": 1110820.0,
710
+ "step": 70
711
+ },
712
+ {
713
+ "entropy": 0.5842308104038239,
714
+ "epoch": 3.5605095541401273,
715
+ "grad_norm": 0.44466689229011536,
716
+ "learning_rate": 0.00015593220338983051,
717
+ "loss": 0.3898,
718
+ "mean_token_accuracy": 0.8796258941292763,
719
+ "num_tokens": 1126967.0,
720
+ "step": 71
721
+ },
722
+ {
723
+ "entropy": 0.5873496159911156,
724
+ "epoch": 3.611464968152866,
725
+ "grad_norm": 0.45185112953186035,
726
+ "learning_rate": 0.0001552542372881356,
727
+ "loss": 0.3966,
728
+ "mean_token_accuracy": 0.8762336745858192,
729
+ "num_tokens": 1143042.0,
730
+ "step": 72
731
+ },
732
+ {
733
+ "entropy": 0.5752235390245914,
734
+ "epoch": 3.662420382165605,
735
+ "grad_norm": 0.40973153710365295,
736
+ "learning_rate": 0.0001545762711864407,
737
+ "loss": 0.3858,
738
+ "mean_token_accuracy": 0.8801640048623085,
739
+ "num_tokens": 1159426.0,
740
+ "step": 73
741
+ },
742
+ {
743
+ "entropy": 0.5780553109943867,
744
+ "epoch": 3.713375796178344,
745
+ "grad_norm": 0.4268912374973297,
746
+ "learning_rate": 0.00015389830508474577,
747
+ "loss": 0.3839,
748
+ "mean_token_accuracy": 0.8774776384234428,
749
+ "num_tokens": 1175810.0,
750
+ "step": 74
751
+ },
752
+ {
753
+ "entropy": 0.6104332208633423,
754
+ "epoch": 3.7643312101910826,
755
+ "grad_norm": 0.46141061186790466,
756
+ "learning_rate": 0.00015322033898305086,
757
+ "loss": 0.4187,
758
+ "mean_token_accuracy": 0.8688839823007584,
759
+ "num_tokens": 1191821.0,
760
+ "step": 75
761
+ },
762
+ {
763
+ "entropy": 0.6029752381145954,
764
+ "epoch": 3.8152866242038215,
765
+ "grad_norm": 0.43786218762397766,
766
+ "learning_rate": 0.00015254237288135592,
767
+ "loss": 0.416,
768
+ "mean_token_accuracy": 0.8730273470282555,
769
+ "num_tokens": 1208205.0,
770
+ "step": 76
771
+ },
772
+ {
773
+ "entropy": 0.549268014729023,
774
+ "epoch": 3.8662420382165603,
775
+ "grad_norm": 0.4513143301010132,
776
+ "learning_rate": 0.00015186440677966102,
777
+ "loss": 0.3974,
778
+ "mean_token_accuracy": 0.8771107047796249,
779
+ "num_tokens": 1224589.0,
780
+ "step": 77
781
+ },
782
+ {
783
+ "entropy": 0.5441488139331341,
784
+ "epoch": 3.917197452229299,
785
+ "grad_norm": 0.46811601519584656,
786
+ "learning_rate": 0.0001511864406779661,
787
+ "loss": 0.4154,
788
+ "mean_token_accuracy": 0.8654165118932724,
789
+ "num_tokens": 1240973.0,
790
+ "step": 78
791
+ },
792
+ {
793
+ "entropy": 0.5493720956146717,
794
+ "epoch": 3.968152866242038,
795
+ "grad_norm": 0.44944748282432556,
796
+ "learning_rate": 0.0001505084745762712,
797
+ "loss": 0.4034,
798
+ "mean_token_accuracy": 0.8696450367569923,
799
+ "num_tokens": 1257084.0,
800
+ "step": 79
801
+ },
802
+ {
803
+ "entropy": 0.5232674360275269,
804
+ "epoch": 4.0,
805
+ "grad_norm": 0.6509364247322083,
806
+ "learning_rate": 0.00014983050847457627,
807
+ "loss": 0.382,
808
+ "mean_token_accuracy": 0.8761990904808045,
809
+ "num_tokens": 1266300.0,
810
+ "step": 80
811
+ },
812
+ {
813
+ "entropy": 0.47885553166270256,
814
+ "epoch": 4.050955414012739,
815
+ "grad_norm": 0.3760603368282318,
816
+ "learning_rate": 0.00014915254237288136,
817
+ "loss": 0.2536,
818
+ "mean_token_accuracy": 0.9295564144849777,
819
+ "num_tokens": 1282684.0,
820
+ "step": 81
821
+ },
822
+ {
823
+ "entropy": 0.48514579981565475,
824
+ "epoch": 4.101910828025478,
825
+ "grad_norm": 0.41000157594680786,
826
+ "learning_rate": 0.00014847457627118645,
827
+ "loss": 0.2466,
828
+ "mean_token_accuracy": 0.9299841672182083,
829
+ "num_tokens": 1298131.0,
830
+ "step": 82
831
+ },
832
+ {
833
+ "entropy": 0.4603138528764248,
834
+ "epoch": 4.1528662420382165,
835
+ "grad_norm": 0.4120670557022095,
836
+ "learning_rate": 0.00014779661016949154,
837
+ "loss": 0.2421,
838
+ "mean_token_accuracy": 0.9294634088873863,
839
+ "num_tokens": 1314515.0,
840
+ "step": 83
841
+ },
842
+ {
843
+ "entropy": 0.45813342928886414,
844
+ "epoch": 4.203821656050955,
845
+ "grad_norm": 0.4626755714416504,
846
+ "learning_rate": 0.0001471186440677966,
847
+ "loss": 0.2564,
848
+ "mean_token_accuracy": 0.9251118749380112,
849
+ "num_tokens": 1330265.0,
850
+ "step": 84
851
+ },
852
+ {
853
+ "entropy": 0.44495610520243645,
854
+ "epoch": 4.254777070063694,
855
+ "grad_norm": 0.44884416460990906,
856
+ "learning_rate": 0.0001464406779661017,
857
+ "loss": 0.2521,
858
+ "mean_token_accuracy": 0.9254637137055397,
859
+ "num_tokens": 1346649.0,
860
+ "step": 85
861
+ },
862
+ {
863
+ "entropy": 0.4175037741661072,
864
+ "epoch": 4.305732484076433,
865
+ "grad_norm": 0.46599075198173523,
866
+ "learning_rate": 0.00014576271186440677,
867
+ "loss": 0.2359,
868
+ "mean_token_accuracy": 0.9287681803107262,
869
+ "num_tokens": 1363033.0,
870
+ "step": 86
871
+ },
872
+ {
873
+ "entropy": 0.3893379382789135,
874
+ "epoch": 4.356687898089172,
875
+ "grad_norm": 0.4749402105808258,
876
+ "learning_rate": 0.00014508474576271186,
877
+ "loss": 0.2318,
878
+ "mean_token_accuracy": 0.928847424685955,
879
+ "num_tokens": 1379417.0,
880
+ "step": 87
881
+ },
882
+ {
883
+ "entropy": 0.38882919400930405,
884
+ "epoch": 4.407643312101911,
885
+ "grad_norm": 0.5757173299789429,
886
+ "learning_rate": 0.00014440677966101695,
887
+ "loss": 0.2428,
888
+ "mean_token_accuracy": 0.9265876188874245,
889
+ "num_tokens": 1395550.0,
890
+ "step": 88
891
+ },
892
+ {
893
+ "entropy": 0.3952750638127327,
894
+ "epoch": 4.45859872611465,
895
+ "grad_norm": 0.461063414812088,
896
+ "learning_rate": 0.00014372881355932205,
897
+ "loss": 0.2315,
898
+ "mean_token_accuracy": 0.9281129166483879,
899
+ "num_tokens": 1411418.0,
900
+ "step": 89
901
+ },
902
+ {
903
+ "entropy": 0.4219426065683365,
904
+ "epoch": 4.509554140127388,
905
+ "grad_norm": 0.6616204977035522,
906
+ "learning_rate": 0.00014305084745762714,
907
+ "loss": 0.2723,
908
+ "mean_token_accuracy": 0.9186402186751366,
909
+ "num_tokens": 1427802.0,
910
+ "step": 90
911
+ },
912
+ {
913
+ "entropy": 0.3946552649140358,
914
+ "epoch": 4.560509554140127,
915
+ "grad_norm": 0.5001639723777771,
916
+ "learning_rate": 0.0001423728813559322,
917
+ "loss": 0.2342,
918
+ "mean_token_accuracy": 0.9264548048377037,
919
+ "num_tokens": 1444186.0,
920
+ "step": 91
921
+ },
922
+ {
923
+ "entropy": 0.3841370493173599,
924
+ "epoch": 4.611464968152866,
925
+ "grad_norm": 0.513782262802124,
926
+ "learning_rate": 0.0001416949152542373,
927
+ "loss": 0.2234,
928
+ "mean_token_accuracy": 0.9312374666333199,
929
+ "num_tokens": 1460570.0,
930
+ "step": 92
931
+ },
932
+ {
933
+ "entropy": 0.4142785668373108,
934
+ "epoch": 4.662420382165605,
935
+ "grad_norm": 0.57405686378479,
936
+ "learning_rate": 0.0001410169491525424,
937
+ "loss": 0.2387,
938
+ "mean_token_accuracy": 0.9266747310757637,
939
+ "num_tokens": 1476954.0,
940
+ "step": 93
941
+ },
942
+ {
943
+ "entropy": 0.40532124042510986,
944
+ "epoch": 4.713375796178344,
945
+ "grad_norm": 0.46338939666748047,
946
+ "learning_rate": 0.00014033898305084748,
947
+ "loss": 0.2242,
948
+ "mean_token_accuracy": 0.9350497350096703,
949
+ "num_tokens": 1492662.0,
950
+ "step": 94
951
+ },
952
+ {
953
+ "entropy": 0.4392712004482746,
954
+ "epoch": 4.764331210191083,
955
+ "grad_norm": 0.44444721937179565,
956
+ "learning_rate": 0.00013966101694915255,
957
+ "loss": 0.2493,
958
+ "mean_token_accuracy": 0.9251364171504974,
959
+ "num_tokens": 1508191.0,
960
+ "step": 95
961
+ },
962
+ {
963
+ "entropy": 0.4355561286211014,
964
+ "epoch": 4.8152866242038215,
965
+ "grad_norm": 0.6919573545455933,
966
+ "learning_rate": 0.00013898305084745764,
967
+ "loss": 0.2784,
968
+ "mean_token_accuracy": 0.9153470247983932,
969
+ "num_tokens": 1524575.0,
970
+ "step": 96
971
+ },
972
+ {
973
+ "entropy": 0.42629534751176834,
974
+ "epoch": 4.86624203821656,
975
+ "grad_norm": 0.48309773206710815,
976
+ "learning_rate": 0.0001383050847457627,
977
+ "loss": 0.2451,
978
+ "mean_token_accuracy": 0.9251194447278976,
979
+ "num_tokens": 1540891.0,
980
+ "step": 97
981
+ },
982
+ {
983
+ "entropy": 0.43248729407787323,
984
+ "epoch": 4.917197452229299,
985
+ "grad_norm": 0.45119330286979675,
986
+ "learning_rate": 0.0001376271186440678,
987
+ "loss": 0.2419,
988
+ "mean_token_accuracy": 0.9283814057707787,
989
+ "num_tokens": 1557275.0,
990
+ "step": 98
991
+ },
992
+ {
993
+ "entropy": 0.43973976373672485,
994
+ "epoch": 4.968152866242038,
995
+ "grad_norm": 0.4691547155380249,
996
+ "learning_rate": 0.0001369491525423729,
997
+ "loss": 0.2527,
998
+ "mean_token_accuracy": 0.9239722490310669,
999
+ "num_tokens": 1573659.0,
1000
+ "step": 99
1001
+ },
1002
+ {
1003
+ "entropy": 0.4433164715766907,
1004
+ "epoch": 5.0,
1005
+ "grad_norm": 0.7236930131912231,
1006
+ "learning_rate": 0.00013627118644067798,
1007
+ "loss": 0.2708,
1008
+ "mean_token_accuracy": 0.918548333644867,
1009
+ "num_tokens": 1582875.0,
1010
+ "step": 100
1011
+ },
1012
+ {
1013
+ "entropy": 0.34633738547563553,
1014
+ "epoch": 5.050955414012739,
1015
+ "grad_norm": 0.33959242701530457,
1016
+ "learning_rate": 0.00013559322033898305,
1017
+ "loss": 0.1452,
1018
+ "mean_token_accuracy": 0.963602103292942,
1019
+ "num_tokens": 1599259.0,
1020
+ "step": 101
1021
+ },
1022
+ {
1023
+ "entropy": 0.3849232979118824,
1024
+ "epoch": 5.101910828025478,
1025
+ "grad_norm": 0.44738227128982544,
1026
+ "learning_rate": 0.00013491525423728814,
1027
+ "loss": 0.1612,
1028
+ "mean_token_accuracy": 0.9605535492300987,
1029
+ "num_tokens": 1615643.0,
1030
+ "step": 102
1031
+ },
1032
+ {
1033
+ "entropy": 0.3427181765437126,
1034
+ "epoch": 5.1528662420382165,
1035
+ "grad_norm": 0.5047619342803955,
1036
+ "learning_rate": 0.0001342372881355932,
1037
+ "loss": 0.1552,
1038
+ "mean_token_accuracy": 0.9561429843306541,
1039
+ "num_tokens": 1632013.0,
1040
+ "step": 103
1041
+ },
1042
+ {
1043
+ "entropy": 0.3299499414861202,
1044
+ "epoch": 5.203821656050955,
1045
+ "grad_norm": 0.39201250672340393,
1046
+ "learning_rate": 0.00013355932203389833,
1047
+ "loss": 0.1377,
1048
+ "mean_token_accuracy": 0.9647994339466095,
1049
+ "num_tokens": 1648397.0,
1050
+ "step": 104
1051
+ },
1052
+ {
1053
+ "entropy": 0.31782786548137665,
1054
+ "epoch": 5.254777070063694,
1055
+ "grad_norm": 0.5107133388519287,
1056
+ "learning_rate": 0.0001328813559322034,
1057
+ "loss": 0.1561,
1058
+ "mean_token_accuracy": 0.9557145461440086,
1059
+ "num_tokens": 1664713.0,
1060
+ "step": 105
1061
+ },
1062
+ {
1063
+ "entropy": 0.30781830847263336,
1064
+ "epoch": 5.305732484076433,
1065
+ "grad_norm": 0.4927469789981842,
1066
+ "learning_rate": 0.00013220338983050849,
1067
+ "loss": 0.1469,
1068
+ "mean_token_accuracy": 0.9573208466172218,
1069
+ "num_tokens": 1680451.0,
1070
+ "step": 106
1071
+ },
1072
+ {
1073
+ "entropy": 0.29482175409793854,
1074
+ "epoch": 5.356687898089172,
1075
+ "grad_norm": 0.47950249910354614,
1076
+ "learning_rate": 0.00013152542372881355,
1077
+ "loss": 0.134,
1078
+ "mean_token_accuracy": 0.96302530169487,
1079
+ "num_tokens": 1696835.0,
1080
+ "step": 107
1081
+ },
1082
+ {
1083
+ "entropy": 0.3074999451637268,
1084
+ "epoch": 5.407643312101911,
1085
+ "grad_norm": 0.6049532890319824,
1086
+ "learning_rate": 0.00013084745762711864,
1087
+ "loss": 0.1514,
1088
+ "mean_token_accuracy": 0.953678622841835,
1089
+ "num_tokens": 1713219.0,
1090
+ "step": 108
1091
+ },
1092
+ {
1093
+ "entropy": 0.29727265425026417,
1094
+ "epoch": 5.45859872611465,
1095
+ "grad_norm": 0.4694285988807678,
1096
+ "learning_rate": 0.00013016949152542374,
1097
+ "loss": 0.1361,
1098
+ "mean_token_accuracy": 0.9609672874212265,
1099
+ "num_tokens": 1729263.0,
1100
+ "step": 109
1101
+ },
1102
+ {
1103
+ "entropy": 0.3285507708787918,
1104
+ "epoch": 5.509554140127388,
1105
+ "grad_norm": 0.46858081221580505,
1106
+ "learning_rate": 0.00012949152542372883,
1107
+ "loss": 0.1477,
1108
+ "mean_token_accuracy": 0.9602150619029999,
1109
+ "num_tokens": 1745647.0,
1110
+ "step": 110
1111
+ },
1112
+ {
1113
+ "entropy": 0.31142256781458855,
1114
+ "epoch": 5.560509554140127,
1115
+ "grad_norm": 0.4510185122489929,
1116
+ "learning_rate": 0.0001288135593220339,
1117
+ "loss": 0.1516,
1118
+ "mean_token_accuracy": 0.9559924080967903,
1119
+ "num_tokens": 1762031.0,
1120
+ "step": 111
1121
+ },
1122
+ {
1123
+ "entropy": 0.29558346793055534,
1124
+ "epoch": 5.611464968152866,
1125
+ "grad_norm": 0.4283140301704407,
1126
+ "learning_rate": 0.000128135593220339,
1127
+ "loss": 0.1308,
1128
+ "mean_token_accuracy": 0.9620353132486343,
1129
+ "num_tokens": 1778415.0,
1130
+ "step": 112
1131
+ },
1132
+ {
1133
+ "entropy": 0.33179714903235435,
1134
+ "epoch": 5.662420382165605,
1135
+ "grad_norm": 0.5021042227745056,
1136
+ "learning_rate": 0.00012745762711864405,
1137
+ "loss": 0.16,
1138
+ "mean_token_accuracy": 0.9551054015755653,
1139
+ "num_tokens": 1793768.0,
1140
+ "step": 113
1141
+ },
1142
+ {
1143
+ "entropy": 0.31468261033296585,
1144
+ "epoch": 5.713375796178344,
1145
+ "grad_norm": 0.4006524682044983,
1146
+ "learning_rate": 0.00012677966101694917,
1147
+ "loss": 0.1411,
1148
+ "mean_token_accuracy": 0.962010994553566,
1149
+ "num_tokens": 1810152.0,
1150
+ "step": 114
1151
+ },
1152
+ {
1153
+ "entropy": 0.32593148201704025,
1154
+ "epoch": 5.764331210191083,
1155
+ "grad_norm": 0.43213579058647156,
1156
+ "learning_rate": 0.00012610169491525426,
1157
+ "loss": 0.1533,
1158
+ "mean_token_accuracy": 0.9591230899095535,
1159
+ "num_tokens": 1826536.0,
1160
+ "step": 115
1161
+ },
1162
+ {
1163
+ "entropy": 0.33078752644360065,
1164
+ "epoch": 5.8152866242038215,
1165
+ "grad_norm": 0.44711190462112427,
1166
+ "learning_rate": 0.00012542372881355933,
1167
+ "loss": 0.1468,
1168
+ "mean_token_accuracy": 0.959298774600029,
1169
+ "num_tokens": 1842250.0,
1170
+ "step": 116
1171
+ },
1172
+ {
1173
+ "entropy": 0.32063932716846466,
1174
+ "epoch": 5.86624203821656,
1175
+ "grad_norm": 0.4965178072452545,
1176
+ "learning_rate": 0.00012474576271186442,
1177
+ "loss": 0.1502,
1178
+ "mean_token_accuracy": 0.9585834592580795,
1179
+ "num_tokens": 1857769.0,
1180
+ "step": 117
1181
+ },
1182
+ {
1183
+ "entropy": 0.31165121495723724,
1184
+ "epoch": 5.917197452229299,
1185
+ "grad_norm": 0.49228012561798096,
1186
+ "learning_rate": 0.0001240677966101695,
1187
+ "loss": 0.1586,
1188
+ "mean_token_accuracy": 0.9569637924432755,
1189
+ "num_tokens": 1874153.0,
1190
+ "step": 118
1191
+ },
1192
+ {
1193
+ "entropy": 0.30535227805376053,
1194
+ "epoch": 5.968152866242038,
1195
+ "grad_norm": 0.4432555139064789,
1196
+ "learning_rate": 0.00012338983050847458,
1197
+ "loss": 0.1359,
1198
+ "mean_token_accuracy": 0.9641127064824104,
1199
+ "num_tokens": 1890537.0,
1200
+ "step": 119
1201
+ },
1202
+ {
1203
+ "entropy": 0.28426828384399416,
1204
+ "epoch": 6.0,
1205
+ "grad_norm": 0.4886658191680908,
1206
+ "learning_rate": 0.00012271186440677967,
1207
+ "loss": 0.1239,
1208
+ "mean_token_accuracy": 0.9645166516304016,
1209
+ "num_tokens": 1899450.0,
1210
+ "step": 120
1211
+ },
1212
+ {
1213
+ "entropy": 0.27130062878131866,
1214
+ "epoch": 6.050955414012739,
1215
+ "grad_norm": 0.3076384663581848,
1216
+ "learning_rate": 0.00012203389830508477,
1217
+ "loss": 0.0791,
1218
+ "mean_token_accuracy": 0.9847517609596252,
1219
+ "num_tokens": 1915834.0,
1220
+ "step": 121
1221
+ },
1222
+ {
1223
+ "entropy": 0.25769038312137127,
1224
+ "epoch": 6.101910828025478,
1225
+ "grad_norm": 0.3248060941696167,
1226
+ "learning_rate": 0.00012135593220338983,
1227
+ "loss": 0.0855,
1228
+ "mean_token_accuracy": 0.9826889634132385,
1229
+ "num_tokens": 1932218.0,
1230
+ "step": 122
1231
+ },
1232
+ {
1233
+ "entropy": 0.2626284286379814,
1234
+ "epoch": 6.1528662420382165,
1235
+ "grad_norm": 0.33836546540260315,
1236
+ "learning_rate": 0.00012067796610169492,
1237
+ "loss": 0.0783,
1238
+ "mean_token_accuracy": 0.9843145906925201,
1239
+ "num_tokens": 1947992.0,
1240
+ "step": 123
1241
+ },
1242
+ {
1243
+ "entropy": 0.25033274479210377,
1244
+ "epoch": 6.203821656050955,
1245
+ "grad_norm": 0.3555228114128113,
1246
+ "learning_rate": 0.00012,
1247
+ "loss": 0.0856,
1248
+ "mean_token_accuracy": 0.9805334359407425,
1249
+ "num_tokens": 1964376.0,
1250
+ "step": 124
1251
+ },
1252
+ {
1253
+ "entropy": 0.2594117093831301,
1254
+ "epoch": 6.254777070063694,
1255
+ "grad_norm": 0.3466283082962036,
1256
+ "learning_rate": 0.0001193220338983051,
1257
+ "loss": 0.0866,
1258
+ "mean_token_accuracy": 0.9796433374285698,
1259
+ "num_tokens": 1980760.0,
1260
+ "step": 125
1261
+ },
1262
+ {
1263
+ "entropy": 0.2532740030437708,
1264
+ "epoch": 6.305732484076433,
1265
+ "grad_norm": 0.3873954713344574,
1266
+ "learning_rate": 0.00011864406779661017,
1267
+ "loss": 0.0888,
1268
+ "mean_token_accuracy": 0.9801652058959007,
1269
+ "num_tokens": 1997130.0,
1270
+ "step": 126
1271
+ },
1272
+ {
1273
+ "entropy": 0.2388041988015175,
1274
+ "epoch": 6.356687898089172,
1275
+ "grad_norm": 0.3720211088657379,
1276
+ "learning_rate": 0.00011796610169491527,
1277
+ "loss": 0.0801,
1278
+ "mean_token_accuracy": 0.981012374162674,
1279
+ "num_tokens": 2013514.0,
1280
+ "step": 127
1281
+ },
1282
+ {
1283
+ "entropy": 0.22601926513016224,
1284
+ "epoch": 6.407643312101911,
1285
+ "grad_norm": 0.42567574977874756,
1286
+ "learning_rate": 0.00011728813559322033,
1287
+ "loss": 0.0884,
1288
+ "mean_token_accuracy": 0.9771610125899315,
1289
+ "num_tokens": 2029898.0,
1290
+ "step": 128
1291
+ },
1292
+ {
1293
+ "entropy": 0.241213021799922,
1294
+ "epoch": 6.45859872611465,
1295
+ "grad_norm": 0.39269620180130005,
1296
+ "learning_rate": 0.00011661016949152544,
1297
+ "loss": 0.0829,
1298
+ "mean_token_accuracy": 0.979632280766964,
1299
+ "num_tokens": 2046282.0,
1300
+ "step": 129
1301
+ },
1302
+ {
1303
+ "entropy": 0.23457833379507065,
1304
+ "epoch": 6.509554140127388,
1305
+ "grad_norm": 0.40059277415275574,
1306
+ "learning_rate": 0.0001159322033898305,
1307
+ "loss": 0.0846,
1308
+ "mean_token_accuracy": 0.9801751151680946,
1309
+ "num_tokens": 2062084.0,
1310
+ "step": 130
1311
+ },
1312
+ {
1313
+ "entropy": 0.2504513543099165,
1314
+ "epoch": 6.560509554140127,
1315
+ "grad_norm": 0.38298025727272034,
1316
+ "learning_rate": 0.0001152542372881356,
1317
+ "loss": 0.0814,
1318
+ "mean_token_accuracy": 0.980772852897644,
1319
+ "num_tokens": 2078097.0,
1320
+ "step": 131
1321
+ },
1322
+ {
1323
+ "entropy": 0.2271766308695078,
1324
+ "epoch": 6.611464968152866,
1325
+ "grad_norm": 0.31705358624458313,
1326
+ "learning_rate": 0.00011457627118644068,
1327
+ "loss": 0.0695,
1328
+ "mean_token_accuracy": 0.9833817705512047,
1329
+ "num_tokens": 2094141.0,
1330
+ "step": 132
1331
+ },
1332
+ {
1333
+ "entropy": 0.24483878165483475,
1334
+ "epoch": 6.662420382165605,
1335
+ "grad_norm": 0.346872478723526,
1336
+ "learning_rate": 0.00011389830508474577,
1337
+ "loss": 0.0844,
1338
+ "mean_token_accuracy": 0.9803112000226974,
1339
+ "num_tokens": 2110525.0,
1340
+ "step": 133
1341
+ },
1342
+ {
1343
+ "entropy": 0.24256090261042118,
1344
+ "epoch": 6.713375796178344,
1345
+ "grad_norm": 0.3615415096282959,
1346
+ "learning_rate": 0.00011322033898305085,
1347
+ "loss": 0.0847,
1348
+ "mean_token_accuracy": 0.9810795113444328,
1349
+ "num_tokens": 2126394.0,
1350
+ "step": 134
1351
+ },
1352
+ {
1353
+ "entropy": 0.2385116182267666,
1354
+ "epoch": 6.764331210191083,
1355
+ "grad_norm": 0.36627471446990967,
1356
+ "learning_rate": 0.00011254237288135594,
1357
+ "loss": 0.0798,
1358
+ "mean_token_accuracy": 0.9812560752034187,
1359
+ "num_tokens": 2142417.0,
1360
+ "step": 135
1361
+ },
1362
+ {
1363
+ "entropy": 0.23489636927843094,
1364
+ "epoch": 6.8152866242038215,
1365
+ "grad_norm": 0.3386026918888092,
1366
+ "learning_rate": 0.00011186440677966102,
1367
+ "loss": 0.0793,
1368
+ "mean_token_accuracy": 0.9815322011709213,
1369
+ "num_tokens": 2158801.0,
1370
+ "step": 136
1371
+ },
1372
+ {
1373
+ "entropy": 0.2517122123390436,
1374
+ "epoch": 6.86624203821656,
1375
+ "grad_norm": 0.3319648504257202,
1376
+ "learning_rate": 0.00011118644067796611,
1377
+ "loss": 0.0834,
1378
+ "mean_token_accuracy": 0.9808342307806015,
1379
+ "num_tokens": 2174557.0,
1380
+ "step": 137
1381
+ },
1382
+ {
1383
+ "entropy": 0.21653795056045055,
1384
+ "epoch": 6.917197452229299,
1385
+ "grad_norm": 0.3044669032096863,
1386
+ "learning_rate": 0.00011050847457627118,
1387
+ "loss": 0.0671,
1388
+ "mean_token_accuracy": 0.9844768345355988,
1389
+ "num_tokens": 2190425.0,
1390
+ "step": 138
1391
+ },
1392
+ {
1393
+ "entropy": 0.2155477125197649,
1394
+ "epoch": 6.968152866242038,
1395
+ "grad_norm": 0.3357236683368683,
1396
+ "learning_rate": 0.00010983050847457627,
1397
+ "loss": 0.0737,
1398
+ "mean_token_accuracy": 0.9834475293755531,
1399
+ "num_tokens": 2206809.0,
1400
+ "step": 139
1401
+ },
1402
+ {
1403
+ "entropy": 0.2226566791534424,
1404
+ "epoch": 7.0,
1405
+ "grad_norm": 0.45016321539878845,
1406
+ "learning_rate": 0.00010915254237288135,
1407
+ "loss": 0.0773,
1408
+ "mean_token_accuracy": 0.9805417537689209,
1409
+ "num_tokens": 2216025.0,
1410
+ "step": 140
1411
+ },
1412
+ {
1413
+ "entropy": 0.19488166272640228,
1414
+ "epoch": 7.050955414012739,
1415
+ "grad_norm": 0.22016853094100952,
1416
+ "learning_rate": 0.00010847457627118644,
1417
+ "loss": 0.0432,
1418
+ "mean_token_accuracy": 0.9938134476542473,
1419
+ "num_tokens": 2232409.0,
1420
+ "step": 141
1421
+ },
1422
+ {
1423
+ "entropy": 0.21024399995803833,
1424
+ "epoch": 7.101910828025478,
1425
+ "grad_norm": 0.25993385910987854,
1426
+ "learning_rate": 0.00010779661016949153,
1427
+ "loss": 0.0493,
1428
+ "mean_token_accuracy": 0.9914661943912506,
1429
+ "num_tokens": 2248779.0,
1430
+ "step": 142
1431
+ },
1432
+ {
1433
+ "entropy": 0.19661536812782288,
1434
+ "epoch": 7.1528662420382165,
1435
+ "grad_norm": 0.23448358476161957,
1436
+ "learning_rate": 0.00010711864406779661,
1437
+ "loss": 0.0427,
1438
+ "mean_token_accuracy": 0.994029700756073,
1439
+ "num_tokens": 2265163.0,
1440
+ "step": 143
1441
+ },
1442
+ {
1443
+ "entropy": 0.19229250587522984,
1444
+ "epoch": 7.203821656050955,
1445
+ "grad_norm": 0.23268407583236694,
1446
+ "learning_rate": 0.0001064406779661017,
1447
+ "loss": 0.0444,
1448
+ "mean_token_accuracy": 0.9925731718540192,
1449
+ "num_tokens": 2281547.0,
1450
+ "step": 144
1451
+ },
1452
+ {
1453
+ "entropy": 0.1830152403563261,
1454
+ "epoch": 7.254777070063694,
1455
+ "grad_norm": 0.26999878883361816,
1456
+ "learning_rate": 0.00010576271186440679,
1457
+ "loss": 0.0434,
1458
+ "mean_token_accuracy": 0.9930359646677971,
1459
+ "num_tokens": 2297622.0,
1460
+ "step": 145
1461
+ },
1462
+ {
1463
+ "entropy": 0.19611400365829468,
1464
+ "epoch": 7.305732484076433,
1465
+ "grad_norm": 0.24712666869163513,
1466
+ "learning_rate": 0.00010508474576271188,
1467
+ "loss": 0.0466,
1468
+ "mean_token_accuracy": 0.9918844103813171,
1469
+ "num_tokens": 2313120.0,
1470
+ "step": 146
1471
+ },
1472
+ {
1473
+ "entropy": 0.19746861048042774,
1474
+ "epoch": 7.356687898089172,
1475
+ "grad_norm": 0.2552828788757324,
1476
+ "learning_rate": 0.00010440677966101696,
1477
+ "loss": 0.0467,
1478
+ "mean_token_accuracy": 0.991991437971592,
1479
+ "num_tokens": 2328870.0,
1480
+ "step": 147
1481
+ },
1482
+ {
1483
+ "entropy": 0.17946216836571693,
1484
+ "epoch": 7.407643312101911,
1485
+ "grad_norm": 0.2574717402458191,
1486
+ "learning_rate": 0.00010372881355932205,
1487
+ "loss": 0.0471,
1488
+ "mean_token_accuracy": 0.9908664375543594,
1489
+ "num_tokens": 2345254.0,
1490
+ "step": 148
1491
+ },
1492
+ {
1493
+ "entropy": 0.1869801040738821,
1494
+ "epoch": 7.45859872611465,
1495
+ "grad_norm": 0.3232134282588959,
1496
+ "learning_rate": 0.00010305084745762712,
1497
+ "loss": 0.0482,
1498
+ "mean_token_accuracy": 0.9902735576033592,
1499
+ "num_tokens": 2361638.0,
1500
+ "step": 149
1501
+ },
1502
+ {
1503
+ "entropy": 0.18208733573555946,
1504
+ "epoch": 7.509554140127388,
1505
+ "grad_norm": 0.2782075107097626,
1506
+ "learning_rate": 0.00010237288135593222,
1507
+ "loss": 0.0429,
1508
+ "mean_token_accuracy": 0.9918385148048401,
1509
+ "num_tokens": 2377649.0,
1510
+ "step": 150
1511
+ },
1512
+ {
1513
+ "entropy": 0.1766122207045555,
1514
+ "epoch": 7.560509554140127,
1515
+ "grad_norm": 0.2637811005115509,
1516
+ "learning_rate": 0.00010169491525423729,
1517
+ "loss": 0.0386,
1518
+ "mean_token_accuracy": 0.9930592477321625,
1519
+ "num_tokens": 2393693.0,
1520
+ "step": 151
1521
+ },
1522
+ {
1523
+ "entropy": 0.18536034412682056,
1524
+ "epoch": 7.611464968152866,
1525
+ "grad_norm": 0.2969140112400055,
1526
+ "learning_rate": 0.00010101694915254238,
1527
+ "loss": 0.0484,
1528
+ "mean_token_accuracy": 0.9912179261445999,
1529
+ "num_tokens": 2409561.0,
1530
+ "step": 152
1531
+ },
1532
+ {
1533
+ "entropy": 0.1679281499236822,
1534
+ "epoch": 7.662420382165605,
1535
+ "grad_norm": 0.27921634912490845,
1536
+ "learning_rate": 0.00010033898305084746,
1537
+ "loss": 0.0396,
1538
+ "mean_token_accuracy": 0.9927029833197594,
1539
+ "num_tokens": 2425945.0,
1540
+ "step": 153
1541
+ },
1542
+ {
1543
+ "entropy": 0.1875128336250782,
1544
+ "epoch": 7.713375796178344,
1545
+ "grad_norm": 0.2692323923110962,
1546
+ "learning_rate": 9.966101694915255e-05,
1547
+ "loss": 0.0411,
1548
+ "mean_token_accuracy": 0.9918234646320343,
1549
+ "num_tokens": 2441701.0,
1550
+ "step": 154
1551
+ },
1552
+ {
1553
+ "entropy": 0.17189276590943336,
1554
+ "epoch": 7.764331210191083,
1555
+ "grad_norm": 0.24035243690013885,
1556
+ "learning_rate": 9.898305084745763e-05,
1557
+ "loss": 0.0384,
1558
+ "mean_token_accuracy": 0.9931274279952049,
1559
+ "num_tokens": 2458085.0,
1560
+ "step": 155
1561
+ },
1562
+ {
1563
+ "entropy": 0.16816619411110878,
1564
+ "epoch": 7.8152866242038215,
1565
+ "grad_norm": 0.23464734852313995,
1566
+ "learning_rate": 9.830508474576272e-05,
1567
+ "loss": 0.0378,
1568
+ "mean_token_accuracy": 0.9941559284925461,
1569
+ "num_tokens": 2474469.0,
1570
+ "step": 156
1571
+ },
1572
+ {
1573
+ "entropy": 0.17040574364364147,
1574
+ "epoch": 7.86624203821656,
1575
+ "grad_norm": 0.2753109037876129,
1576
+ "learning_rate": 9.76271186440678e-05,
1577
+ "loss": 0.0408,
1578
+ "mean_token_accuracy": 0.9930224418640137,
1579
+ "num_tokens": 2490853.0,
1580
+ "step": 157
1581
+ },
1582
+ {
1583
+ "entropy": 0.17619120329618454,
1584
+ "epoch": 7.917197452229299,
1585
+ "grad_norm": 0.28378522396087646,
1586
+ "learning_rate": 9.69491525423729e-05,
1587
+ "loss": 0.0429,
1588
+ "mean_token_accuracy": 0.9916679263114929,
1589
+ "num_tokens": 2507237.0,
1590
+ "step": 158
1591
+ },
1592
+ {
1593
+ "entropy": 0.18376159109175205,
1594
+ "epoch": 7.968152866242038,
1595
+ "grad_norm": 0.25075170397758484,
1596
+ "learning_rate": 9.627118644067797e-05,
1597
+ "loss": 0.0409,
1598
+ "mean_token_accuracy": 0.9928998127579689,
1599
+ "num_tokens": 2523384.0,
1600
+ "step": 159
1601
+ },
1602
+ {
1603
+ "entropy": 0.16814205944538116,
1604
+ "epoch": 8.0,
1605
+ "grad_norm": 0.2868243455886841,
1606
+ "learning_rate": 9.559322033898305e-05,
1607
+ "loss": 0.039,
1608
+ "mean_token_accuracy": 0.9940619587898254,
1609
+ "num_tokens": 2532600.0,
1610
+ "step": 160
1611
+ },
1612
+ {
1613
+ "entropy": 0.16274571232497692,
1614
+ "epoch": 8.050955414012739,
1615
+ "grad_norm": 0.14176861941814423,
1616
+ "learning_rate": 9.491525423728815e-05,
1617
+ "loss": 0.0254,
1618
+ "mean_token_accuracy": 0.9974143728613853,
1619
+ "num_tokens": 2548984.0,
1620
+ "step": 161
1621
+ },
1622
+ {
1623
+ "entropy": 0.15707932971417904,
1624
+ "epoch": 8.101910828025478,
1625
+ "grad_norm": 0.14470599591732025,
1626
+ "learning_rate": 9.423728813559322e-05,
1627
+ "loss": 0.0236,
1628
+ "mean_token_accuracy": 0.9979943335056305,
1629
+ "num_tokens": 2565368.0,
1630
+ "step": 162
1631
+ },
1632
+ {
1633
+ "entropy": 0.15231047943234444,
1634
+ "epoch": 8.152866242038217,
1635
+ "grad_norm": 0.15325938165187836,
1636
+ "learning_rate": 9.355932203389832e-05,
1637
+ "loss": 0.0242,
1638
+ "mean_token_accuracy": 0.9976884126663208,
1639
+ "num_tokens": 2581752.0,
1640
+ "step": 163
1641
+ },
1642
+ {
1643
+ "entropy": 0.16208907216787338,
1644
+ "epoch": 8.203821656050955,
1645
+ "grad_norm": 0.17481264472007751,
1646
+ "learning_rate": 9.28813559322034e-05,
1647
+ "loss": 0.0257,
1648
+ "mean_token_accuracy": 0.9974030405282974,
1649
+ "num_tokens": 2598136.0,
1650
+ "step": 164
1651
+ },
1652
+ {
1653
+ "entropy": 0.15740813314914703,
1654
+ "epoch": 8.254777070063694,
1655
+ "grad_norm": 0.1707678586244583,
1656
+ "learning_rate": 9.220338983050847e-05,
1657
+ "loss": 0.0255,
1658
+ "mean_token_accuracy": 0.9970719814300537,
1659
+ "num_tokens": 2614147.0,
1660
+ "step": 165
1661
+ },
1662
+ {
1663
+ "entropy": 0.1630783099681139,
1664
+ "epoch": 8.305732484076433,
1665
+ "grad_norm": 0.17213749885559082,
1666
+ "learning_rate": 9.152542372881357e-05,
1667
+ "loss": 0.0262,
1668
+ "mean_token_accuracy": 0.9976739212870598,
1669
+ "num_tokens": 2630190.0,
1670
+ "step": 166
1671
+ },
1672
+ {
1673
+ "entropy": 0.16571603156626225,
1674
+ "epoch": 8.356687898089172,
1675
+ "grad_norm": 0.1789257526397705,
1676
+ "learning_rate": 9.084745762711865e-05,
1677
+ "loss": 0.0259,
1678
+ "mean_token_accuracy": 0.9970768317580223,
1679
+ "num_tokens": 2645931.0,
1680
+ "step": 167
1681
+ },
1682
+ {
1683
+ "entropy": 0.15572900883853436,
1684
+ "epoch": 8.40764331210191,
1685
+ "grad_norm": 0.1874908059835434,
1686
+ "learning_rate": 9.016949152542374e-05,
1687
+ "loss": 0.0255,
1688
+ "mean_token_accuracy": 0.9973345398902893,
1689
+ "num_tokens": 2662315.0,
1690
+ "step": 168
1691
+ },
1692
+ {
1693
+ "entropy": 0.1498353499919176,
1694
+ "epoch": 8.45859872611465,
1695
+ "grad_norm": 0.20052368938922882,
1696
+ "learning_rate": 8.949152542372882e-05,
1697
+ "loss": 0.0236,
1698
+ "mean_token_accuracy": 0.9972066730260849,
1699
+ "num_tokens": 2678153.0,
1700
+ "step": 169
1701
+ },
1702
+ {
1703
+ "entropy": 0.14614599663764238,
1704
+ "epoch": 8.509554140127388,
1705
+ "grad_norm": 0.17338193953037262,
1706
+ "learning_rate": 8.88135593220339e-05,
1707
+ "loss": 0.0254,
1708
+ "mean_token_accuracy": 0.9967966079711914,
1709
+ "num_tokens": 2694537.0,
1710
+ "step": 170
1711
+ },
1712
+ {
1713
+ "entropy": 0.16034340485930443,
1714
+ "epoch": 8.560509554140127,
1715
+ "grad_norm": 0.2193768173456192,
1716
+ "learning_rate": 8.813559322033899e-05,
1717
+ "loss": 0.0294,
1718
+ "mean_token_accuracy": 0.9959402531385422,
1719
+ "num_tokens": 2710406.0,
1720
+ "step": 171
1721
+ },
1722
+ {
1723
+ "entropy": 0.1384358825162053,
1724
+ "epoch": 8.611464968152866,
1725
+ "grad_norm": 0.18264280259609222,
1726
+ "learning_rate": 8.745762711864407e-05,
1727
+ "loss": 0.0222,
1728
+ "mean_token_accuracy": 0.9968310818076134,
1729
+ "num_tokens": 2726790.0,
1730
+ "step": 172
1731
+ },
1732
+ {
1733
+ "entropy": 0.13634015154093504,
1734
+ "epoch": 8.662420382165605,
1735
+ "grad_norm": 0.22209401428699493,
1736
+ "learning_rate": 8.677966101694915e-05,
1737
+ "loss": 0.0252,
1738
+ "mean_token_accuracy": 0.9960110113024712,
1739
+ "num_tokens": 2743160.0,
1740
+ "step": 173
1741
+ },
1742
+ {
1743
+ "entropy": 0.1479941438883543,
1744
+ "epoch": 8.713375796178344,
1745
+ "grad_norm": 0.2538638412952423,
1746
+ "learning_rate": 8.610169491525424e-05,
1747
+ "loss": 0.0287,
1748
+ "mean_token_accuracy": 0.9960155114531517,
1749
+ "num_tokens": 2759028.0,
1750
+ "step": 174
1751
+ },
1752
+ {
1753
+ "entropy": 0.15019258111715317,
1754
+ "epoch": 8.764331210191083,
1755
+ "grad_norm": 0.1906321942806244,
1756
+ "learning_rate": 8.542372881355932e-05,
1757
+ "loss": 0.0225,
1758
+ "mean_token_accuracy": 0.9977850168943405,
1759
+ "num_tokens": 2775412.0,
1760
+ "step": 175
1761
+ },
1762
+ {
1763
+ "entropy": 0.15425540879368782,
1764
+ "epoch": 8.815286624203821,
1765
+ "grad_norm": 0.1589612066745758,
1766
+ "learning_rate": 8.474576271186441e-05,
1767
+ "loss": 0.022,
1768
+ "mean_token_accuracy": 0.9976635351777077,
1769
+ "num_tokens": 2790807.0,
1770
+ "step": 176
1771
+ },
1772
+ {
1773
+ "entropy": 0.14349912479519844,
1774
+ "epoch": 8.86624203821656,
1775
+ "grad_norm": 0.19421131908893585,
1776
+ "learning_rate": 8.406779661016949e-05,
1777
+ "loss": 0.0235,
1778
+ "mean_token_accuracy": 0.9972120821475983,
1779
+ "num_tokens": 2807191.0,
1780
+ "step": 177
1781
+ },
1782
+ {
1783
+ "entropy": 0.13660633098334074,
1784
+ "epoch": 8.9171974522293,
1785
+ "grad_norm": 0.1643456220626831,
1786
+ "learning_rate": 8.338983050847457e-05,
1787
+ "loss": 0.0209,
1788
+ "mean_token_accuracy": 0.9972153529524803,
1789
+ "num_tokens": 2823575.0,
1790
+ "step": 178
1791
+ },
1792
+ {
1793
+ "entropy": 0.14072524290531874,
1794
+ "epoch": 8.968152866242038,
1795
+ "grad_norm": 0.20266622304916382,
1796
+ "learning_rate": 8.271186440677966e-05,
1797
+ "loss": 0.0267,
1798
+ "mean_token_accuracy": 0.9961338341236115,
1799
+ "num_tokens": 2839959.0,
1800
+ "step": 179
1801
+ },
1802
+ {
1803
+ "entropy": 0.1358090877532959,
1804
+ "epoch": 9.0,
1805
+ "grad_norm": 0.20919552445411682,
1806
+ "learning_rate": 8.203389830508474e-05,
1807
+ "loss": 0.0206,
1808
+ "mean_token_accuracy": 0.9980488061904907,
1809
+ "num_tokens": 2849175.0,
1810
+ "step": 180
1811
+ },
1812
+ {
1813
+ "entropy": 0.1502374578267336,
1814
+ "epoch": 9.050955414012739,
1815
+ "grad_norm": 0.09697608649730682,
1816
+ "learning_rate": 8.135593220338983e-05,
1817
+ "loss": 0.017,
1818
+ "mean_token_accuracy": 0.9991338849067688,
1819
+ "num_tokens": 2864741.0,
1820
+ "step": 181
1821
+ },
1822
+ {
1823
+ "entropy": 0.131621690467,
1824
+ "epoch": 9.101910828025478,
1825
+ "grad_norm": 0.09774398058652878,
1826
+ "learning_rate": 8.067796610169493e-05,
1827
+ "loss": 0.0138,
1828
+ "mean_token_accuracy": 0.9994169324636459,
1829
+ "num_tokens": 2881125.0,
1830
+ "step": 182
1831
+ },
1832
+ {
1833
+ "entropy": 0.14369910676032305,
1834
+ "epoch": 9.152866242038217,
1835
+ "grad_norm": 0.11493105441331863,
1836
+ "learning_rate": 8e-05,
1837
+ "loss": 0.0194,
1838
+ "mean_token_accuracy": 0.9986832365393639,
1839
+ "num_tokens": 2896867.0,
1840
+ "step": 183
1841
+ },
1842
+ {
1843
+ "entropy": 0.13094604760408401,
1844
+ "epoch": 9.203821656050955,
1845
+ "grad_norm": 0.11127211898565292,
1846
+ "learning_rate": 7.93220338983051e-05,
1847
+ "loss": 0.0154,
1848
+ "mean_token_accuracy": 0.9990357309579849,
1849
+ "num_tokens": 2913251.0,
1850
+ "step": 184
1851
+ },
1852
+ {
1853
+ "entropy": 0.14038352109491825,
1854
+ "epoch": 9.254777070063694,
1855
+ "grad_norm": 0.08400645852088928,
1856
+ "learning_rate": 7.864406779661018e-05,
1857
+ "loss": 0.0138,
1858
+ "mean_token_accuracy": 0.9998054951429367,
1859
+ "num_tokens": 2929274.0,
1860
+ "step": 185
1861
+ },
1862
+ {
1863
+ "entropy": 0.12506767269223928,
1864
+ "epoch": 9.305732484076433,
1865
+ "grad_norm": 0.23133188486099243,
1866
+ "learning_rate": 7.796610169491526e-05,
1867
+ "loss": 0.0195,
1868
+ "mean_token_accuracy": 0.9976899400353432,
1869
+ "num_tokens": 2945658.0,
1870
+ "step": 186
1871
+ },
1872
+ {
1873
+ "entropy": 0.12773161567747593,
1874
+ "epoch": 9.356687898089172,
1875
+ "grad_norm": 0.09952336549758911,
1876
+ "learning_rate": 7.728813559322035e-05,
1877
+ "loss": 0.0144,
1878
+ "mean_token_accuracy": 0.9993524551391602,
1879
+ "num_tokens": 2962042.0,
1880
+ "step": 187
1881
+ },
1882
+ {
1883
+ "entropy": 0.13072299119085073,
1884
+ "epoch": 9.40764331210191,
1885
+ "grad_norm": 0.10790853202342987,
1886
+ "learning_rate": 7.661016949152543e-05,
1887
+ "loss": 0.0135,
1888
+ "mean_token_accuracy": 0.9991421699523926,
1889
+ "num_tokens": 2978117.0,
1890
+ "step": 188
1891
+ },
1892
+ {
1893
+ "entropy": 0.1242481516674161,
1894
+ "epoch": 9.45859872611465,
1895
+ "grad_norm": 0.1122814416885376,
1896
+ "learning_rate": 7.593220338983051e-05,
1897
+ "loss": 0.0133,
1898
+ "mean_token_accuracy": 0.9989665970206261,
1899
+ "num_tokens": 2994433.0,
1900
+ "step": 189
1901
+ },
1902
+ {
1903
+ "entropy": 0.13957257848232985,
1904
+ "epoch": 9.509554140127388,
1905
+ "grad_norm": 0.10560327023267746,
1906
+ "learning_rate": 7.52542372881356e-05,
1907
+ "loss": 0.0147,
1908
+ "mean_token_accuracy": 0.999118261039257,
1909
+ "num_tokens": 3010580.0,
1910
+ "step": 190
1911
+ },
1912
+ {
1913
+ "entropy": 0.1291163843125105,
1914
+ "epoch": 9.560509554140127,
1915
+ "grad_norm": 0.10222429037094116,
1916
+ "learning_rate": 7.457627118644068e-05,
1917
+ "loss": 0.0153,
1918
+ "mean_token_accuracy": 0.9986425712704659,
1919
+ "num_tokens": 3026964.0,
1920
+ "step": 191
1921
+ },
1922
+ {
1923
+ "entropy": 0.12281094025820494,
1924
+ "epoch": 9.611464968152866,
1925
+ "grad_norm": 0.11164791136980057,
1926
+ "learning_rate": 7.389830508474577e-05,
1927
+ "loss": 0.0135,
1928
+ "mean_token_accuracy": 0.9989040344953537,
1929
+ "num_tokens": 3043348.0,
1930
+ "step": 192
1931
+ },
1932
+ {
1933
+ "entropy": 0.13303168211132288,
1934
+ "epoch": 9.662420382165605,
1935
+ "grad_norm": 0.13216403126716614,
1936
+ "learning_rate": 7.322033898305085e-05,
1937
+ "loss": 0.0166,
1938
+ "mean_token_accuracy": 0.9990960881114006,
1939
+ "num_tokens": 3059216.0,
1940
+ "step": 193
1941
+ },
1942
+ {
1943
+ "entropy": 0.12154316995292902,
1944
+ "epoch": 9.713375796178344,
1945
+ "grad_norm": 0.11085794121026993,
1946
+ "learning_rate": 7.254237288135593e-05,
1947
+ "loss": 0.0129,
1948
+ "mean_token_accuracy": 0.9989554509520531,
1949
+ "num_tokens": 3075600.0,
1950
+ "step": 194
1951
+ },
1952
+ {
1953
+ "entropy": 0.12221709545701742,
1954
+ "epoch": 9.764331210191083,
1955
+ "grad_norm": 0.09001041948795319,
1956
+ "learning_rate": 7.186440677966102e-05,
1957
+ "loss": 0.0132,
1958
+ "mean_token_accuracy": 0.999326765537262,
1959
+ "num_tokens": 3091644.0,
1960
+ "step": 195
1961
+ },
1962
+ {
1963
+ "entropy": 0.12168204598128796,
1964
+ "epoch": 9.815286624203821,
1965
+ "grad_norm": 0.16245830059051514,
1966
+ "learning_rate": 7.11864406779661e-05,
1967
+ "loss": 0.0155,
1968
+ "mean_token_accuracy": 0.9988898932933807,
1969
+ "num_tokens": 3107655.0,
1970
+ "step": 196
1971
+ },
1972
+ {
1973
+ "entropy": 0.11974250618368387,
1974
+ "epoch": 9.86624203821656,
1975
+ "grad_norm": 0.15768024325370789,
1976
+ "learning_rate": 7.05084745762712e-05,
1977
+ "loss": 0.0157,
1978
+ "mean_token_accuracy": 0.9990957900881767,
1979
+ "num_tokens": 3124039.0,
1980
+ "step": 197
1981
+ },
1982
+ {
1983
+ "entropy": 0.13452547043561935,
1984
+ "epoch": 9.9171974522293,
1985
+ "grad_norm": 0.11966739594936371,
1986
+ "learning_rate": 6.983050847457627e-05,
1987
+ "loss": 0.0154,
1988
+ "mean_token_accuracy": 0.9989514648914337,
1989
+ "num_tokens": 3140150.0,
1990
+ "step": 198
1991
+ },
1992
+ {
1993
+ "entropy": 0.1197445448487997,
1994
+ "epoch": 9.968152866242038,
1995
+ "grad_norm": 0.12122300267219543,
1996
+ "learning_rate": 6.915254237288135e-05,
1997
+ "loss": 0.0144,
1998
+ "mean_token_accuracy": 0.999027393758297,
1999
+ "num_tokens": 3156534.0,
2000
+ "step": 199
2001
+ },
2002
+ {
2003
+ "entropy": 0.11745601445436478,
2004
+ "epoch": 10.0,
2005
+ "grad_norm": 0.12567812204360962,
2006
+ "learning_rate": 6.847457627118645e-05,
2007
+ "loss": 0.0128,
2008
+ "mean_token_accuracy": 0.9989682912826539,
2009
+ "num_tokens": 3165750.0,
2010
+ "step": 200
2011
+ },
2012
+ {
2013
+ "entropy": 0.12042893003672361,
2014
+ "epoch": 10.050955414012739,
2015
+ "grad_norm": 0.0663767158985138,
2016
+ "learning_rate": 6.779661016949152e-05,
2017
+ "loss": 0.0108,
2018
+ "mean_token_accuracy": 0.9996045753359795,
2019
+ "num_tokens": 3181897.0,
2020
+ "step": 201
2021
+ },
2022
+ {
2023
+ "entropy": 0.11832231562584639,
2024
+ "epoch": 10.101910828025478,
2025
+ "grad_norm": 0.07664559781551361,
2026
+ "learning_rate": 6.71186440677966e-05,
2027
+ "loss": 0.0108,
2028
+ "mean_token_accuracy": 0.999675951898098,
2029
+ "num_tokens": 3198281.0,
2030
+ "step": 202
2031
+ },
2032
+ {
2033
+ "entropy": 0.124271041713655,
2034
+ "epoch": 10.152866242038217,
2035
+ "grad_norm": 0.09082630276679993,
2036
+ "learning_rate": 6.64406779661017e-05,
2037
+ "loss": 0.0123,
2038
+ "mean_token_accuracy": 0.999231606721878,
2039
+ "num_tokens": 3214292.0,
2040
+ "step": 203
2041
+ },
2042
+ {
2043
+ "entropy": 0.12200119253247976,
2044
+ "epoch": 10.203821656050955,
2045
+ "grad_norm": 0.13074713945388794,
2046
+ "learning_rate": 6.576271186440678e-05,
2047
+ "loss": 0.0117,
2048
+ "mean_token_accuracy": 0.9990891143679619,
2049
+ "num_tokens": 3229708.0,
2050
+ "step": 204
2051
+ },
2052
+ {
2053
+ "entropy": 0.11397830117493868,
2054
+ "epoch": 10.254777070063694,
2055
+ "grad_norm": 0.08310648053884506,
2056
+ "learning_rate": 6.508474576271187e-05,
2057
+ "loss": 0.0113,
2058
+ "mean_token_accuracy": 0.9991616681218147,
2059
+ "num_tokens": 3246092.0,
2060
+ "step": 205
2061
+ },
2062
+ {
2063
+ "entropy": 0.1141798933967948,
2064
+ "epoch": 10.305732484076433,
2065
+ "grad_norm": 0.05808615684509277,
2066
+ "learning_rate": 6.440677966101695e-05,
2067
+ "loss": 0.0086,
2068
+ "mean_token_accuracy": 0.9996744319796562,
2069
+ "num_tokens": 3262476.0,
2070
+ "step": 206
2071
+ },
2072
+ {
2073
+ "entropy": 0.11953330133110285,
2074
+ "epoch": 10.356687898089172,
2075
+ "grad_norm": 0.179758682847023,
2076
+ "learning_rate": 6.372881355932203e-05,
2077
+ "loss": 0.0184,
2078
+ "mean_token_accuracy": 0.998580165207386,
2079
+ "num_tokens": 3278499.0,
2080
+ "step": 207
2081
+ },
2082
+ {
2083
+ "entropy": 0.11975150462239981,
2084
+ "epoch": 10.40764331210191,
2085
+ "grad_norm": 0.09039207547903061,
2086
+ "learning_rate": 6.305084745762713e-05,
2087
+ "loss": 0.0114,
2088
+ "mean_token_accuracy": 0.9994799271225929,
2089
+ "num_tokens": 3294883.0,
2090
+ "step": 208
2091
+ },
2092
+ {
2093
+ "entropy": 0.12320903595536947,
2094
+ "epoch": 10.45859872611465,
2095
+ "grad_norm": 0.05162489041686058,
2096
+ "learning_rate": 6.237288135593221e-05,
2097
+ "loss": 0.0102,
2098
+ "mean_token_accuracy": 0.9998693540692329,
2099
+ "num_tokens": 3311267.0,
2100
+ "step": 209
2101
+ },
2102
+ {
2103
+ "entropy": 0.10688549000769854,
2104
+ "epoch": 10.509554140127388,
2105
+ "grad_norm": 0.06506083160638809,
2106
+ "learning_rate": 6.169491525423729e-05,
2107
+ "loss": 0.0088,
2108
+ "mean_token_accuracy": 0.9997412338852882,
2109
+ "num_tokens": 3327651.0,
2110
+ "step": 210
2111
+ },
2112
+ {
2113
+ "entropy": 0.10415452346205711,
2114
+ "epoch": 10.560509554140127,
2115
+ "grad_norm": 0.06173918396234512,
2116
+ "learning_rate": 6.101694915254238e-05,
2117
+ "loss": 0.0087,
2118
+ "mean_token_accuracy": 0.9996152892708778,
2119
+ "num_tokens": 3344035.0,
2120
+ "step": 211
2121
+ },
2122
+ {
2123
+ "entropy": 0.11600155290216208,
2124
+ "epoch": 10.611464968152866,
2125
+ "grad_norm": 0.050665903836488724,
2126
+ "learning_rate": 6.033898305084746e-05,
2127
+ "loss": 0.0096,
2128
+ "mean_token_accuracy": 0.9998079538345337,
2129
+ "num_tokens": 3360419.0,
2130
+ "step": 212
2131
+ },
2132
+ {
2133
+ "entropy": 0.10566186718642712,
2134
+ "epoch": 10.662420382165605,
2135
+ "grad_norm": 0.07954474538564682,
2136
+ "learning_rate": 5.966101694915255e-05,
2137
+ "loss": 0.0097,
2138
+ "mean_token_accuracy": 0.9996142834424973,
2139
+ "num_tokens": 3376789.0,
2140
+ "step": 213
2141
+ },
2142
+ {
2143
+ "entropy": 0.11559769324958324,
2144
+ "epoch": 10.713375796178344,
2145
+ "grad_norm": 0.09305853396654129,
2146
+ "learning_rate": 5.8983050847457634e-05,
2147
+ "loss": 0.0107,
2148
+ "mean_token_accuracy": 0.9994818046689034,
2149
+ "num_tokens": 3393173.0,
2150
+ "step": 214
2151
+ },
2152
+ {
2153
+ "entropy": 0.11908081825822592,
2154
+ "epoch": 10.764331210191083,
2155
+ "grad_norm": 0.04667564108967781,
2156
+ "learning_rate": 5.830508474576272e-05,
2157
+ "loss": 0.0094,
2158
+ "mean_token_accuracy": 0.999924786388874,
2159
+ "num_tokens": 3408769.0,
2160
+ "step": 215
2161
+ },
2162
+ {
2163
+ "entropy": 0.1183215007185936,
2164
+ "epoch": 10.815286624203821,
2165
+ "grad_norm": 0.04595829173922539,
2166
+ "learning_rate": 5.76271186440678e-05,
2167
+ "loss": 0.0093,
2168
+ "mean_token_accuracy": 0.9997801333665848,
2169
+ "num_tokens": 3424473.0,
2170
+ "step": 216
2171
+ },
2172
+ {
2173
+ "entropy": 0.1201422717422247,
2174
+ "epoch": 10.86624203821656,
2175
+ "grad_norm": 0.06230077147483826,
2176
+ "learning_rate": 5.6949152542372884e-05,
2177
+ "loss": 0.0099,
2178
+ "mean_token_accuracy": 0.9996102750301361,
2179
+ "num_tokens": 3440341.0,
2180
+ "step": 217
2181
+ },
2182
+ {
2183
+ "entropy": 0.11482239048928022,
2184
+ "epoch": 10.9171974522293,
2185
+ "grad_norm": 0.05606631562113762,
2186
+ "learning_rate": 5.627118644067797e-05,
2187
+ "loss": 0.0103,
2188
+ "mean_token_accuracy": 0.9998069554567337,
2189
+ "num_tokens": 3456725.0,
2190
+ "step": 218
2191
+ },
2192
+ {
2193
+ "entropy": 0.11935457587242126,
2194
+ "epoch": 10.968152866242038,
2195
+ "grad_norm": 0.07897260040044785,
2196
+ "learning_rate": 5.5593220338983056e-05,
2197
+ "loss": 0.0101,
2198
+ "mean_token_accuracy": 0.999412514269352,
2199
+ "num_tokens": 3473109.0,
2200
+ "step": 219
2201
+ },
2202
+ {
2203
+ "entropy": 0.11128216087818146,
2204
+ "epoch": 11.0,
2205
+ "grad_norm": 0.0996818020939827,
2206
+ "learning_rate": 5.4915254237288135e-05,
2207
+ "loss": 0.0091,
2208
+ "mean_token_accuracy": 0.999491286277771,
2209
+ "num_tokens": 3482325.0,
2210
+ "step": 220
2211
+ },
2212
+ {
2213
+ "entropy": 0.11160805076360703,
2214
+ "epoch": 11.050955414012739,
2215
+ "grad_norm": 0.05367226526141167,
2216
+ "learning_rate": 5.423728813559322e-05,
2217
+ "loss": 0.0088,
2218
+ "mean_token_accuracy": 0.9997417852282524,
2219
+ "num_tokens": 3498709.0,
2220
+ "step": 221
2221
+ },
2222
+ {
2223
+ "entropy": 0.1070787301287055,
2224
+ "epoch": 11.101910828025478,
2225
+ "grad_norm": 0.05334122106432915,
2226
+ "learning_rate": 5.355932203389831e-05,
2227
+ "loss": 0.0082,
2228
+ "mean_token_accuracy": 0.9998068884015083,
2229
+ "num_tokens": 3515093.0,
2230
+ "step": 222
2231
+ },
2232
+ {
2233
+ "entropy": 0.10628996696323156,
2234
+ "epoch": 11.152866242038217,
2235
+ "grad_norm": 0.055135585367679596,
2236
+ "learning_rate": 5.288135593220339e-05,
2237
+ "loss": 0.008,
2238
+ "mean_token_accuracy": 0.9998051300644875,
2239
+ "num_tokens": 3531477.0,
2240
+ "step": 223
2241
+ },
2242
+ {
2243
+ "entropy": 0.10990262683480978,
2244
+ "epoch": 11.203821656050955,
2245
+ "grad_norm": 0.03518820181488991,
2246
+ "learning_rate": 5.220338983050848e-05,
2247
+ "loss": 0.0072,
2248
+ "mean_token_accuracy": 1.0,
2249
+ "num_tokens": 3547861.0,
2250
+ "step": 224
2251
+ },
2252
+ {
2253
+ "entropy": 0.10836105886846781,
2254
+ "epoch": 11.254777070063694,
2255
+ "grad_norm": 0.0368078239262104,
2256
+ "learning_rate": 5.152542372881356e-05,
2257
+ "loss": 0.0075,
2258
+ "mean_token_accuracy": 0.9999355971813202,
2259
+ "num_tokens": 3564245.0,
2260
+ "step": 225
2261
+ },
2262
+ {
2263
+ "entropy": 0.1082956362515688,
2264
+ "epoch": 11.305732484076433,
2265
+ "grad_norm": 0.03756461665034294,
2266
+ "learning_rate": 5.0847457627118643e-05,
2267
+ "loss": 0.0075,
2268
+ "mean_token_accuracy": 0.9999363869428635,
2269
+ "num_tokens": 3579752.0,
2270
+ "step": 226
2271
+ },
2272
+ {
2273
+ "entropy": 0.10948039591312408,
2274
+ "epoch": 11.356687898089172,
2275
+ "grad_norm": 0.04509361833333969,
2276
+ "learning_rate": 5.016949152542373e-05,
2277
+ "loss": 0.0081,
2278
+ "mean_token_accuracy": 0.9998712986707687,
2279
+ "num_tokens": 3596136.0,
2280
+ "step": 227
2281
+ },
2282
+ {
2283
+ "entropy": 0.1059270715340972,
2284
+ "epoch": 11.40764331210191,
2285
+ "grad_norm": 0.047251664102077484,
2286
+ "learning_rate": 4.9491525423728815e-05,
2287
+ "loss": 0.008,
2288
+ "mean_token_accuracy": 0.9997420459985733,
2289
+ "num_tokens": 3612520.0,
2290
+ "step": 228
2291
+ },
2292
+ {
2293
+ "entropy": 0.11516531370580196,
2294
+ "epoch": 11.45859872611465,
2295
+ "grad_norm": 0.04376146197319031,
2296
+ "learning_rate": 4.88135593220339e-05,
2297
+ "loss": 0.0095,
2298
+ "mean_token_accuracy": 0.9995211735367775,
2299
+ "num_tokens": 3628322.0,
2300
+ "step": 229
2301
+ },
2302
+ {
2303
+ "entropy": 0.10558972507715225,
2304
+ "epoch": 11.509554140127388,
2305
+ "grad_norm": 0.13402560353279114,
2306
+ "learning_rate": 4.813559322033899e-05,
2307
+ "loss": 0.0114,
2308
+ "mean_token_accuracy": 0.9990246370434761,
2309
+ "num_tokens": 3644333.0,
2310
+ "step": 230
2311
+ },
2312
+ {
2313
+ "entropy": 0.10923876147717237,
2314
+ "epoch": 11.560509554140127,
2315
+ "grad_norm": 0.040236614644527435,
2316
+ "learning_rate": 4.745762711864407e-05,
2317
+ "loss": 0.0074,
2318
+ "mean_token_accuracy": 0.9999355301260948,
2319
+ "num_tokens": 3660717.0,
2320
+ "step": 231
2321
+ },
2322
+ {
2323
+ "entropy": 0.10896432586014271,
2324
+ "epoch": 11.611464968152866,
2325
+ "grad_norm": 0.17227506637573242,
2326
+ "learning_rate": 4.677966101694916e-05,
2327
+ "loss": 0.0083,
2328
+ "mean_token_accuracy": 0.9997416883707047,
2329
+ "num_tokens": 3677101.0,
2330
+ "step": 232
2331
+ },
2332
+ {
2333
+ "entropy": 0.10140051785856485,
2334
+ "epoch": 11.662420382165605,
2335
+ "grad_norm": 0.03426056727766991,
2336
+ "learning_rate": 4.610169491525424e-05,
2337
+ "loss": 0.0067,
2338
+ "mean_token_accuracy": 0.999934658408165,
2339
+ "num_tokens": 3693248.0,
2340
+ "step": 233
2341
+ },
2342
+ {
2343
+ "entropy": 0.11477772425860167,
2344
+ "epoch": 11.713375796178344,
2345
+ "grad_norm": 0.043852221220731735,
2346
+ "learning_rate": 4.542372881355932e-05,
2347
+ "loss": 0.0083,
2348
+ "mean_token_accuracy": 0.9997580200433731,
2349
+ "num_tokens": 3708777.0,
2350
+ "step": 234
2351
+ },
2352
+ {
2353
+ "entropy": 0.1119665578007698,
2354
+ "epoch": 11.764331210191083,
2355
+ "grad_norm": 0.03210538625717163,
2356
+ "learning_rate": 4.474576271186441e-05,
2357
+ "loss": 0.007,
2358
+ "mean_token_accuracy": 0.9998657628893852,
2359
+ "num_tokens": 3725161.0,
2360
+ "step": 235
2361
+ },
2362
+ {
2363
+ "entropy": 0.10569995269179344,
2364
+ "epoch": 11.815286624203821,
2365
+ "grad_norm": 0.033930789679288864,
2366
+ "learning_rate": 4.4067796610169495e-05,
2367
+ "loss": 0.0077,
2368
+ "mean_token_accuracy": 1.0,
2369
+ "num_tokens": 3741531.0,
2370
+ "step": 236
2371
+ },
2372
+ {
2373
+ "entropy": 0.10806028544902802,
2374
+ "epoch": 11.86624203821656,
2375
+ "grad_norm": 0.0338793508708477,
2376
+ "learning_rate": 4.3389830508474574e-05,
2377
+ "loss": 0.0074,
2378
+ "mean_token_accuracy": 0.999867282807827,
2379
+ "num_tokens": 3757847.0,
2380
+ "step": 237
2381
+ },
2382
+ {
2383
+ "entropy": 0.10707560367882252,
2384
+ "epoch": 11.9171974522293,
2385
+ "grad_norm": 0.03882453218102455,
2386
+ "learning_rate": 4.271186440677966e-05,
2387
+ "loss": 0.0071,
2388
+ "mean_token_accuracy": 0.9999340698122978,
2389
+ "num_tokens": 3774231.0,
2390
+ "step": 238
2391
+ },
2392
+ {
2393
+ "entropy": 0.10312746185809374,
2394
+ "epoch": 11.968152866242038,
2395
+ "grad_norm": 0.043584294617176056,
2396
+ "learning_rate": 4.2033898305084746e-05,
2397
+ "loss": 0.0068,
2398
+ "mean_token_accuracy": 1.0,
2399
+ "num_tokens": 3790312.0,
2400
+ "step": 239
2401
+ },
2402
+ {
2403
+ "entropy": 0.11070414036512374,
2404
+ "epoch": 12.0,
2405
+ "grad_norm": 0.045331358909606934,
2406
+ "learning_rate": 4.135593220338983e-05,
2407
+ "loss": 0.0079,
2408
+ "mean_token_accuracy": 1.0,
2409
+ "num_tokens": 3798900.0,
2410
+ "step": 240
2411
+ },
2412
+ {
2413
+ "entropy": 0.10184395220130682,
2414
+ "epoch": 12.050955414012739,
2415
+ "grad_norm": 0.026744039729237556,
2416
+ "learning_rate": 4.067796610169492e-05,
2417
+ "loss": 0.0059,
2418
+ "mean_token_accuracy": 1.0,
2419
+ "num_tokens": 3814769.0,
2420
+ "step": 241
2421
+ },
2422
+ {
2423
+ "entropy": 0.10635124333202839,
2424
+ "epoch": 12.101910828025478,
2425
+ "grad_norm": 0.028835609555244446,
2426
+ "learning_rate": 4e-05,
2427
+ "loss": 0.0065,
2428
+ "mean_token_accuracy": 0.99993547052145,
2429
+ "num_tokens": 3831153.0,
2430
+ "step": 242
2431
+ },
2432
+ {
2433
+ "entropy": 0.10043890587985516,
2434
+ "epoch": 12.152866242038217,
2435
+ "grad_norm": 0.04694792628288269,
2436
+ "learning_rate": 3.932203389830509e-05,
2437
+ "loss": 0.0082,
2438
+ "mean_token_accuracy": 0.9998090639710426,
2439
+ "num_tokens": 3847537.0,
2440
+ "step": 243
2441
+ },
2442
+ {
2443
+ "entropy": 0.10733645875006914,
2444
+ "epoch": 12.203821656050955,
2445
+ "grad_norm": 0.026845334097743034,
2446
+ "learning_rate": 3.8644067796610175e-05,
2447
+ "loss": 0.0068,
2448
+ "mean_token_accuracy": 0.9999350681900978,
2449
+ "num_tokens": 3863921.0,
2450
+ "step": 244
2451
+ },
2452
+ {
2453
+ "entropy": 0.09936889354139566,
2454
+ "epoch": 12.254777070063694,
2455
+ "grad_norm": 0.03058328479528427,
2456
+ "learning_rate": 3.7966101694915254e-05,
2457
+ "loss": 0.0069,
2458
+ "mean_token_accuracy": 0.9997949451208115,
2459
+ "num_tokens": 3879635.0,
2460
+ "step": 245
2461
+ },
2462
+ {
2463
+ "entropy": 0.10591370053589344,
2464
+ "epoch": 12.305732484076433,
2465
+ "grad_norm": 0.028634637594223022,
2466
+ "learning_rate": 3.728813559322034e-05,
2467
+ "loss": 0.007,
2468
+ "mean_token_accuracy": 1.0,
2469
+ "num_tokens": 3896019.0,
2470
+ "step": 246
2471
+ },
2472
+ {
2473
+ "entropy": 0.10039967019110918,
2474
+ "epoch": 12.356687898089172,
2475
+ "grad_norm": 0.028052492067217827,
2476
+ "learning_rate": 3.6610169491525426e-05,
2477
+ "loss": 0.0064,
2478
+ "mean_token_accuracy": 1.0,
2479
+ "num_tokens": 3912403.0,
2480
+ "step": 247
2481
+ },
2482
+ {
2483
+ "entropy": 0.10025474335998297,
2484
+ "epoch": 12.40764331210191,
2485
+ "grad_norm": 0.02830340526998043,
2486
+ "learning_rate": 3.593220338983051e-05,
2487
+ "loss": 0.0063,
2488
+ "mean_token_accuracy": 0.9998716190457344,
2489
+ "num_tokens": 3928787.0,
2490
+ "step": 248
2491
+ },
2492
+ {
2493
+ "entropy": 0.10644072014838457,
2494
+ "epoch": 12.45859872611465,
2495
+ "grad_norm": 0.02761429361999035,
2496
+ "learning_rate": 3.52542372881356e-05,
2497
+ "loss": 0.0068,
2498
+ "mean_token_accuracy": 1.0,
2499
+ "num_tokens": 3944898.0,
2500
+ "step": 249
2501
+ },
2502
+ {
2503
+ "entropy": 0.1037906389683485,
2504
+ "epoch": 12.509554140127388,
2505
+ "grad_norm": 0.03129090368747711,
2506
+ "learning_rate": 3.4576271186440676e-05,
2507
+ "loss": 0.007,
2508
+ "mean_token_accuracy": 0.9999349936842918,
2509
+ "num_tokens": 3961282.0,
2510
+ "step": 250
2511
+ },
2512
+ {
2513
+ "entropy": 0.10302811488509178,
2514
+ "epoch": 12.560509554140127,
2515
+ "grad_norm": 0.026480698958039284,
2516
+ "learning_rate": 3.389830508474576e-05,
2517
+ "loss": 0.0067,
2518
+ "mean_token_accuracy": 1.0,
2519
+ "num_tokens": 3977652.0,
2520
+ "step": 251
2521
+ },
2522
+ {
2523
+ "entropy": 0.10825122147798538,
2524
+ "epoch": 12.611464968152866,
2525
+ "grad_norm": 0.029188238084316254,
2526
+ "learning_rate": 3.322033898305085e-05,
2527
+ "loss": 0.0072,
2528
+ "mean_token_accuracy": 0.999933548271656,
2529
+ "num_tokens": 3994036.0,
2530
+ "step": 252
2531
+ },
2532
+ {
2533
+ "entropy": 0.10613303910940886,
2534
+ "epoch": 12.662420382165605,
2535
+ "grad_norm": 0.028023159131407738,
2536
+ "learning_rate": 3.2542372881355934e-05,
2537
+ "loss": 0.0066,
2538
+ "mean_token_accuracy": 1.0,
2539
+ "num_tokens": 4008991.0,
2540
+ "step": 253
2541
+ },
2542
+ {
2543
+ "entropy": 0.11473400145769119,
2544
+ "epoch": 12.713375796178344,
2545
+ "grad_norm": 0.027821091935038567,
2546
+ "learning_rate": 3.186440677966101e-05,
2547
+ "loss": 0.0063,
2548
+ "mean_token_accuracy": 1.0,
2549
+ "num_tokens": 4024407.0,
2550
+ "step": 254
2551
+ },
2552
+ {
2553
+ "entropy": 0.10935076046735048,
2554
+ "epoch": 12.764331210191083,
2555
+ "grad_norm": 0.031338147819042206,
2556
+ "learning_rate": 3.1186440677966106e-05,
2557
+ "loss": 0.0067,
2558
+ "mean_token_accuracy": 0.9999353662133217,
2559
+ "num_tokens": 4040791.0,
2560
+ "step": 255
2561
+ },
2562
+ {
2563
+ "entropy": 0.10937976185232401,
2564
+ "epoch": 12.815286624203821,
2565
+ "grad_norm": 0.029371492564678192,
2566
+ "learning_rate": 3.050847457627119e-05,
2567
+ "loss": 0.007,
2568
+ "mean_token_accuracy": 0.9998026117682457,
2569
+ "num_tokens": 4057107.0,
2570
+ "step": 256
2571
+ },
2572
+ {
2573
+ "entropy": 0.10393634624779224,
2574
+ "epoch": 12.86624203821656,
2575
+ "grad_norm": 0.027899138629436493,
2576
+ "learning_rate": 2.9830508474576274e-05,
2577
+ "loss": 0.0064,
2578
+ "mean_token_accuracy": 0.9999347925186157,
2579
+ "num_tokens": 4073491.0,
2580
+ "step": 257
2581
+ },
2582
+ {
2583
+ "entropy": 0.10141265112906694,
2584
+ "epoch": 12.9171974522293,
2585
+ "grad_norm": 0.028487876057624817,
2586
+ "learning_rate": 2.915254237288136e-05,
2587
+ "loss": 0.0065,
2588
+ "mean_token_accuracy": 1.0,
2589
+ "num_tokens": 4089875.0,
2590
+ "step": 258
2591
+ },
2592
+ {
2593
+ "entropy": 0.0965907471254468,
2594
+ "epoch": 12.968152866242038,
2595
+ "grad_norm": 0.028266245499253273,
2596
+ "learning_rate": 2.8474576271186442e-05,
2597
+ "loss": 0.0067,
2598
+ "mean_token_accuracy": 0.9998710304498672,
2599
+ "num_tokens": 4106259.0,
2600
+ "step": 259
2601
+ },
2602
+ {
2603
+ "entropy": 0.10284970700740814,
2604
+ "epoch": 13.0,
2605
+ "grad_norm": 0.03353312984108925,
2606
+ "learning_rate": 2.7796610169491528e-05,
2607
+ "loss": 0.0052,
2608
+ "mean_token_accuracy": 1.0,
2609
+ "num_tokens": 4115475.0,
2610
+ "step": 260
2611
+ },
2612
+ {
2613
+ "entropy": 0.10281004942953587,
2614
+ "epoch": 13.050955414012739,
2615
+ "grad_norm": 0.02671942301094532,
2616
+ "learning_rate": 2.711864406779661e-05,
2617
+ "loss": 0.0062,
2618
+ "mean_token_accuracy": 0.9998715296387672,
2619
+ "num_tokens": 4131231.0,
2620
+ "step": 261
2621
+ },
2622
+ {
2623
+ "entropy": 0.10125970002263784,
2624
+ "epoch": 13.101910828025478,
2625
+ "grad_norm": 0.025036444887518883,
2626
+ "learning_rate": 2.6440677966101696e-05,
2627
+ "loss": 0.006,
2628
+ "mean_token_accuracy": 0.9999360293149948,
2629
+ "num_tokens": 4147601.0,
2630
+ "step": 262
2631
+ },
2632
+ {
2633
+ "entropy": 0.09949134290218353,
2634
+ "epoch": 13.152866242038217,
2635
+ "grad_norm": 0.02558460272848606,
2636
+ "learning_rate": 2.576271186440678e-05,
2637
+ "loss": 0.006,
2638
+ "mean_token_accuracy": 1.0,
2639
+ "num_tokens": 4163985.0,
2640
+ "step": 263
2641
+ },
2642
+ {
2643
+ "entropy": 0.09930670354515314,
2644
+ "epoch": 13.203821656050955,
2645
+ "grad_norm": 0.026054522022604942,
2646
+ "learning_rate": 2.5084745762711865e-05,
2647
+ "loss": 0.0067,
2648
+ "mean_token_accuracy": 1.0,
2649
+ "num_tokens": 4180369.0,
2650
+ "step": 264
2651
+ },
2652
+ {
2653
+ "entropy": 0.10627400875091553,
2654
+ "epoch": 13.254777070063694,
2655
+ "grad_norm": 0.026049450039863586,
2656
+ "learning_rate": 2.440677966101695e-05,
2657
+ "loss": 0.0063,
2658
+ "mean_token_accuracy": 0.999923825263977,
2659
+ "num_tokens": 4196083.0,
2660
+ "step": 265
2661
+ },
2662
+ {
2663
+ "entropy": 0.09930684044957161,
2664
+ "epoch": 13.305732484076433,
2665
+ "grad_norm": 0.024473560974001884,
2666
+ "learning_rate": 2.3728813559322036e-05,
2667
+ "loss": 0.0059,
2668
+ "mean_token_accuracy": 0.999931126832962,
2669
+ "num_tokens": 4212399.0,
2670
+ "step": 266
2671
+ },
2672
+ {
2673
+ "entropy": 0.10002897586673498,
2674
+ "epoch": 13.356687898089172,
2675
+ "grad_norm": 0.025572266429662704,
2676
+ "learning_rate": 2.305084745762712e-05,
2677
+ "loss": 0.0058,
2678
+ "mean_token_accuracy": 1.0,
2679
+ "num_tokens": 4228783.0,
2680
+ "step": 267
2681
+ },
2682
+ {
2683
+ "entropy": 0.10443572327494621,
2684
+ "epoch": 13.40764331210191,
2685
+ "grad_norm": 0.02436634711921215,
2686
+ "learning_rate": 2.2372881355932205e-05,
2687
+ "loss": 0.0058,
2688
+ "mean_token_accuracy": 1.0,
2689
+ "num_tokens": 4244827.0,
2690
+ "step": 268
2691
+ },
2692
+ {
2693
+ "entropy": 0.09615321457386017,
2694
+ "epoch": 13.45859872611465,
2695
+ "grad_norm": 0.025177955627441406,
2696
+ "learning_rate": 2.1694915254237287e-05,
2697
+ "loss": 0.0056,
2698
+ "mean_token_accuracy": 0.9999350979924202,
2699
+ "num_tokens": 4261211.0,
2700
+ "step": 269
2701
+ },
2702
+ {
2703
+ "entropy": 0.10436165984719992,
2704
+ "epoch": 13.509554140127388,
2705
+ "grad_norm": 0.02651069685816765,
2706
+ "learning_rate": 2.1016949152542373e-05,
2707
+ "loss": 0.007,
2708
+ "mean_token_accuracy": 0.9998708888888359,
2709
+ "num_tokens": 4277292.0,
2710
+ "step": 270
2711
+ },
2712
+ {
2713
+ "entropy": 0.09940579812973738,
2714
+ "epoch": 13.560509554140127,
2715
+ "grad_norm": 0.024446485564112663,
2716
+ "learning_rate": 2.033898305084746e-05,
2717
+ "loss": 0.0058,
2718
+ "mean_token_accuracy": 1.0,
2719
+ "num_tokens": 4293676.0,
2720
+ "step": 271
2721
+ },
2722
+ {
2723
+ "entropy": 0.1089943777769804,
2724
+ "epoch": 13.611464968152866,
2725
+ "grad_norm": 0.027576526626944542,
2726
+ "learning_rate": 1.9661016949152545e-05,
2727
+ "loss": 0.0071,
2728
+ "mean_token_accuracy": 0.9999209865927696,
2729
+ "num_tokens": 4309171.0,
2730
+ "step": 272
2731
+ },
2732
+ {
2733
+ "entropy": 0.09422466903924942,
2734
+ "epoch": 13.662420382165605,
2735
+ "grad_norm": 0.024253997951745987,
2736
+ "learning_rate": 1.8983050847457627e-05,
2737
+ "loss": 0.0056,
2738
+ "mean_token_accuracy": 0.9999356642365456,
2739
+ "num_tokens": 4325555.0,
2740
+ "step": 273
2741
+ },
2742
+ {
2743
+ "entropy": 0.10771417059004307,
2744
+ "epoch": 13.713375796178344,
2745
+ "grad_norm": 0.024483634158968925,
2746
+ "learning_rate": 1.8305084745762713e-05,
2747
+ "loss": 0.0058,
2748
+ "mean_token_accuracy": 1.0,
2749
+ "num_tokens": 4341424.0,
2750
+ "step": 274
2751
+ },
2752
+ {
2753
+ "entropy": 0.1011097515001893,
2754
+ "epoch": 13.764331210191083,
2755
+ "grad_norm": 0.02411043830215931,
2756
+ "learning_rate": 1.76271186440678e-05,
2757
+ "loss": 0.0056,
2758
+ "mean_token_accuracy": 0.9999353364109993,
2759
+ "num_tokens": 4357808.0,
2760
+ "step": 275
2761
+ },
2762
+ {
2763
+ "entropy": 0.0979408985003829,
2764
+ "epoch": 13.815286624203821,
2765
+ "grad_norm": 0.03372422233223915,
2766
+ "learning_rate": 1.694915254237288e-05,
2767
+ "loss": 0.0068,
2768
+ "mean_token_accuracy": 0.999871663749218,
2769
+ "num_tokens": 4374192.0,
2770
+ "step": 276
2771
+ },
2772
+ {
2773
+ "entropy": 0.10360954143106937,
2774
+ "epoch": 13.86624203821656,
2775
+ "grad_norm": 0.02556852251291275,
2776
+ "learning_rate": 1.6271186440677967e-05,
2777
+ "loss": 0.0064,
2778
+ "mean_token_accuracy": 1.0,
2779
+ "num_tokens": 4390303.0,
2780
+ "step": 277
2781
+ },
2782
+ {
2783
+ "entropy": 0.09622267633676529,
2784
+ "epoch": 13.9171974522293,
2785
+ "grad_norm": 0.02323872037231922,
2786
+ "learning_rate": 1.5593220338983053e-05,
2787
+ "loss": 0.0053,
2788
+ "mean_token_accuracy": 1.0,
2789
+ "num_tokens": 4406687.0,
2790
+ "step": 278
2791
+ },
2792
+ {
2793
+ "entropy": 0.10244499053806067,
2794
+ "epoch": 13.968152866242038,
2795
+ "grad_norm": 0.025733351707458496,
2796
+ "learning_rate": 1.4915254237288137e-05,
2797
+ "loss": 0.0059,
2798
+ "mean_token_accuracy": 1.0,
2799
+ "num_tokens": 4423071.0,
2800
+ "step": 279
2801
+ },
2802
+ {
2803
+ "entropy": 0.11494807302951812,
2804
+ "epoch": 14.0,
2805
+ "grad_norm": 0.034636951982975006,
2806
+ "learning_rate": 1.4237288135593221e-05,
2807
+ "loss": 0.0061,
2808
+ "mean_token_accuracy": 1.0,
2809
+ "num_tokens": 4432050.0,
2810
+ "step": 280
2811
+ },
2812
+ {
2813
+ "entropy": 0.09753070399165154,
2814
+ "epoch": 14.050955414012739,
2815
+ "grad_norm": 0.022641047835350037,
2816
+ "learning_rate": 1.3559322033898305e-05,
2817
+ "loss": 0.0055,
2818
+ "mean_token_accuracy": 1.0,
2819
+ "num_tokens": 4448434.0,
2820
+ "step": 281
2821
+ },
2822
+ {
2823
+ "entropy": 0.08915799483656883,
2824
+ "epoch": 14.101910828025478,
2825
+ "grad_norm": 0.021472405642271042,
2826
+ "learning_rate": 1.288135593220339e-05,
2827
+ "loss": 0.0047,
2828
+ "mean_token_accuracy": 1.0,
2829
+ "num_tokens": 4464818.0,
2830
+ "step": 282
2831
+ },
2832
+ {
2833
+ "entropy": 0.09933264553546906,
2834
+ "epoch": 14.152866242038217,
2835
+ "grad_norm": 0.02268746867775917,
2836
+ "learning_rate": 1.2203389830508475e-05,
2837
+ "loss": 0.0056,
2838
+ "mean_token_accuracy": 1.0,
2839
+ "num_tokens": 4481202.0,
2840
+ "step": 283
2841
+ },
2842
+ {
2843
+ "entropy": 0.10949048679322004,
2844
+ "epoch": 14.203821656050955,
2845
+ "grad_norm": 0.02363019995391369,
2846
+ "learning_rate": 1.152542372881356e-05,
2847
+ "loss": 0.0057,
2848
+ "mean_token_accuracy": 1.0,
2849
+ "num_tokens": 4497586.0,
2850
+ "step": 284
2851
+ },
2852
+ {
2853
+ "entropy": 0.09538892284035683,
2854
+ "epoch": 14.254777070063694,
2855
+ "grad_norm": 0.02280281111598015,
2856
+ "learning_rate": 1.0847457627118644e-05,
2857
+ "loss": 0.0056,
2858
+ "mean_token_accuracy": 0.9999348297715187,
2859
+ "num_tokens": 4513970.0,
2860
+ "step": 285
2861
+ },
2862
+ {
2863
+ "entropy": 0.09355007391422987,
2864
+ "epoch": 14.305732484076433,
2865
+ "grad_norm": 0.024101026356220245,
2866
+ "learning_rate": 1.016949152542373e-05,
2867
+ "loss": 0.0058,
2868
+ "mean_token_accuracy": 1.0,
2869
+ "num_tokens": 4530117.0,
2870
+ "step": 286
2871
+ },
2872
+ {
2873
+ "entropy": 0.09671080578118563,
2874
+ "epoch": 14.356687898089172,
2875
+ "grad_norm": 0.024017931893467903,
2876
+ "learning_rate": 9.491525423728814e-06,
2877
+ "loss": 0.0058,
2878
+ "mean_token_accuracy": 1.0,
2879
+ "num_tokens": 4546128.0,
2880
+ "step": 287
2881
+ },
2882
+ {
2883
+ "entropy": 0.10226992424577475,
2884
+ "epoch": 14.40764331210191,
2885
+ "grad_norm": 0.024143729358911514,
2886
+ "learning_rate": 8.8135593220339e-06,
2887
+ "loss": 0.0057,
2888
+ "mean_token_accuracy": 1.0,
2889
+ "num_tokens": 4562512.0,
2890
+ "step": 288
2891
+ },
2892
+ {
2893
+ "entropy": 0.09842728730291128,
2894
+ "epoch": 14.45859872611465,
2895
+ "grad_norm": 0.022391093894839287,
2896
+ "learning_rate": 8.135593220338983e-06,
2897
+ "loss": 0.0054,
2898
+ "mean_token_accuracy": 1.0,
2899
+ "num_tokens": 4578896.0,
2900
+ "step": 289
2901
+ },
2902
+ {
2903
+ "entropy": 0.09875787049531937,
2904
+ "epoch": 14.509554140127388,
2905
+ "grad_norm": 0.036525625735521317,
2906
+ "learning_rate": 7.4576271186440685e-06,
2907
+ "loss": 0.0068,
2908
+ "mean_token_accuracy": 0.9998043775558472,
2909
+ "num_tokens": 4595212.0,
2910
+ "step": 290
2911
+ },
2912
+ {
2913
+ "entropy": 0.10088277515023947,
2914
+ "epoch": 14.560509554140127,
2915
+ "grad_norm": 0.024536944925785065,
2916
+ "learning_rate": 6.779661016949153e-06,
2917
+ "loss": 0.0061,
2918
+ "mean_token_accuracy": 0.9999360293149948,
2919
+ "num_tokens": 4611323.0,
2920
+ "step": 291
2921
+ },
2922
+ {
2923
+ "entropy": 0.09735479392111301,
2924
+ "epoch": 14.611464968152866,
2925
+ "grad_norm": 0.024319127202033997,
2926
+ "learning_rate": 6.101694915254238e-06,
2927
+ "loss": 0.0056,
2928
+ "mean_token_accuracy": 0.999872088432312,
2929
+ "num_tokens": 4627191.0,
2930
+ "step": 292
2931
+ },
2932
+ {
2933
+ "entropy": 0.1000251853838563,
2934
+ "epoch": 14.662420382165605,
2935
+ "grad_norm": 0.025493454188108444,
2936
+ "learning_rate": 5.423728813559322e-06,
2937
+ "loss": 0.0066,
2938
+ "mean_token_accuracy": 1.0,
2939
+ "num_tokens": 4643575.0,
2940
+ "step": 293
2941
+ },
2942
+ {
2943
+ "entropy": 0.10344643983989954,
2944
+ "epoch": 14.713375796178344,
2945
+ "grad_norm": 0.025770332664251328,
2946
+ "learning_rate": 4.745762711864407e-06,
2947
+ "loss": 0.0066,
2948
+ "mean_token_accuracy": 0.9999344870448112,
2949
+ "num_tokens": 4659959.0,
2950
+ "step": 294
2951
+ },
2952
+ {
2953
+ "entropy": 0.1049768216907978,
2954
+ "epoch": 14.764331210191083,
2955
+ "grad_norm": 0.023523753508925438,
2956
+ "learning_rate": 4.067796610169492e-06,
2957
+ "loss": 0.0057,
2958
+ "mean_token_accuracy": 1.0,
2959
+ "num_tokens": 4675982.0,
2960
+ "step": 295
2961
+ },
2962
+ {
2963
+ "entropy": 0.10388771630823612,
2964
+ "epoch": 14.815286624203821,
2965
+ "grad_norm": 0.023833539336919785,
2966
+ "learning_rate": 3.3898305084745763e-06,
2967
+ "loss": 0.0055,
2968
+ "mean_token_accuracy": 1.0,
2969
+ "num_tokens": 4691837.0,
2970
+ "step": 296
2971
+ },
2972
+ {
2973
+ "entropy": 0.10857217479497194,
2974
+ "epoch": 14.86624203821656,
2975
+ "grad_norm": 0.023440934717655182,
2976
+ "learning_rate": 2.711864406779661e-06,
2977
+ "loss": 0.0057,
2978
+ "mean_token_accuracy": 1.0,
2979
+ "num_tokens": 4707881.0,
2980
+ "step": 297
2981
+ },
2982
+ {
2983
+ "entropy": 0.10144319850951433,
2984
+ "epoch": 14.9171974522293,
2985
+ "grad_norm": 0.02377854287624359,
2986
+ "learning_rate": 2.033898305084746e-06,
2987
+ "loss": 0.0058,
2988
+ "mean_token_accuracy": 0.9999219700694084,
2989
+ "num_tokens": 4723956.0,
2990
+ "step": 298
2991
+ },
2992
+ {
2993
+ "entropy": 0.10537906363606453,
2994
+ "epoch": 14.968152866242038,
2995
+ "grad_norm": 0.024843264371156693,
2996
+ "learning_rate": 1.3559322033898304e-06,
2997
+ "loss": 0.006,
2998
+ "mean_token_accuracy": 1.0,
2999
+ "num_tokens": 4740037.0,
3000
+ "step": 299
3001
+ },
3002
+ {
3003
+ "entropy": 0.12200375497341157,
3004
+ "epoch": 15.0,
3005
+ "grad_norm": 0.03387058898806572,
3006
+ "learning_rate": 6.779661016949152e-07,
3007
+ "loss": 0.006,
3008
+ "mean_token_accuracy": 1.0,
3009
+ "num_tokens": 4748625.0,
3010
+ "step": 300
3011
+ }
3012
+ ],
3013
+ "logging_steps": 1,
3014
+ "max_steps": 300,
3015
+ "num_input_tokens_seen": 0,
3016
+ "num_train_epochs": 15,
3017
+ "save_steps": 500,
3018
+ "stateful_callbacks": {
3019
+ "TrainerControl": {
3020
+ "args": {
3021
+ "should_epoch_stop": false,
3022
+ "should_evaluate": false,
3023
+ "should_log": false,
3024
+ "should_save": true,
3025
+ "should_training_stop": true
3026
+ },
3027
+ "attributes": {}
3028
+ }
3029
+ },
3030
+ "total_flos": 2.0845431402464256e+17,
3031
+ "train_batch_size": 2,
3032
+ "trial_name": null,
3033
+ "trial_params": null
3034
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077b87357be7e3347a59817bffdd5639168ab5f567cc54f95f4792a1bea59bab
3
+ size 5713
checkpoint-300/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openai/gpt-oss-20b
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:openai/gpt-oss-20b
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai/gpt-oss-20b",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 64,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "gate_proj",
29
+ "k_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "v_proj",
33
+ "q_proj",
34
+ "o_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-50/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66588ad755f746ec82e0bf0290eb4b80f1792e714636a26ab0cc88500df86f08
3
+ size 127427864
checkpoint-50/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-50/chat_template.jinja ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {#-
2
+ In addition to the normal inputs of `messages` and `tools`, this template also accepts the
3
+ following kwargs:
4
+ - "builtin_tools": A list, can contain "browser" and/or "python".
5
+ - "model_identity": A string that optionally describes the model identity.
6
+ - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
7
+ #}
8
+
9
+ {#- Tool Definition Rendering ============================================== #}
10
+ {%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
11
+ {%- if param_spec.type == "array" -%}
12
+ {%- if param_spec['items'] -%}
13
+ {%- if param_spec['items']['type'] == "string" -%}
14
+ {{- "string[]" }}
15
+ {%- elif param_spec['items']['type'] == "number" -%}
16
+ {{- "number[]" }}
17
+ {%- elif param_spec['items']['type'] == "integer" -%}
18
+ {{- "number[]" }}
19
+ {%- elif param_spec['items']['type'] == "boolean" -%}
20
+ {{- "boolean[]" }}
21
+ {%- else -%}
22
+ {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
23
+ {%- if inner_type == "object | object" or inner_type|length > 50 -%}
24
+ {{- "any[]" }}
25
+ {%- else -%}
26
+ {{- inner_type + "[]" }}
27
+ {%- endif -%}
28
+ {%- endif -%}
29
+ {%- if param_spec.nullable -%}
30
+ {{- " | null" }}
31
+ {%- endif -%}
32
+ {%- else -%}
33
+ {{- "any[]" }}
34
+ {%- if param_spec.nullable -%}
35
+ {{- " | null" }}
36
+ {%- endif -%}
37
+ {%- endif -%}
38
+ {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
39
+ {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
40
+ {%- if param_spec.type | length > 1 -%}
41
+ {{- param_spec.type | join(" | ") }}
42
+ {%- else -%}
43
+ {{- param_spec.type[0] }}
44
+ {%- endif -%}
45
+ {%- elif param_spec.oneOf -%}
46
+ {#- Handle oneOf schemas - check for complex unions and fallback to any #}
47
+ {%- set has_object_variants = false -%}
48
+ {%- for variant in param_spec.oneOf -%}
49
+ {%- if variant.type == "object" -%}
50
+ {%- set has_object_variants = true -%}
51
+ {%- endif -%}
52
+ {%- endfor -%}
53
+ {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
54
+ {{- "any" }}
55
+ {%- else -%}
56
+ {%- for variant in param_spec.oneOf -%}
57
+ {{- render_typescript_type(variant, required_params) -}}
58
+ {%- if variant.description %}
59
+ {{- "// " + variant.description }}
60
+ {%- endif -%}
61
+ {%- if variant.default is defined %}
62
+ {{ "// default: " + variant.default|tojson }}
63
+ {%- endif -%}
64
+ {%- if not loop.last %}
65
+ {{- " | " }}
66
+ {% endif -%}
67
+ {%- endfor -%}
68
+ {%- endif -%}
69
+ {%- elif param_spec.type == "string" -%}
70
+ {%- if param_spec.enum -%}
71
+ {{- '"' + param_spec.enum|join('" | "') + '"' -}}
72
+ {%- else -%}
73
+ {{- "string" }}
74
+ {%- if param_spec.nullable %}
75
+ {{- " | null" }}
76
+ {%- endif -%}
77
+ {%- endif -%}
78
+ {%- elif param_spec.type == "number" -%}
79
+ {{- "number" }}
80
+ {%- elif param_spec.type == "integer" -%}
81
+ {{- "number" }}
82
+ {%- elif param_spec.type == "boolean" -%}
83
+ {{- "boolean" }}
84
+
85
+ {%- elif param_spec.type == "object" -%}
86
+ {%- if param_spec.properties -%}
87
+ {{- "{\n" }}
88
+ {%- for prop_name, prop_spec in param_spec.properties.items() -%}
89
+ {{- prop_name -}}
90
+ {%- if prop_name not in (param_spec.required or []) -%}
91
+ {{- "?" }}
92
+ {%- endif -%}
93
+ {{- ": " }}
94
+ {{ render_typescript_type(prop_spec, param_spec.required or []) }}
95
+ {%- if not loop.last -%}
96
+ {{-", " }}
97
+ {%- endif -%}
98
+ {%- endfor -%}
99
+ {{- "}" }}
100
+ {%- else -%}
101
+ {{- "object" }}
102
+ {%- endif -%}
103
+ {%- else -%}
104
+ {{- "any" }}
105
+ {%- endif -%}
106
+ {%- endmacro -%}
107
+
108
+ {%- macro render_tool_namespace(namespace_name, tools) -%}
109
+ {{- "## " + namespace_name + "\n\n" }}
110
+ {{- "namespace " + namespace_name + " {\n\n" }}
111
+ {%- for tool in tools %}
112
+ {%- set tool = tool.function %}
113
+ {{- "// " + tool.description + "\n" }}
114
+ {{- "type "+ tool.name + " = " }}
115
+ {%- if tool.parameters and tool.parameters.properties %}
116
+ {{- "(_: {\n" }}
117
+ {%- for param_name, param_spec in tool.parameters.properties.items() %}
118
+ {%- if param_spec.description %}
119
+ {{- "// " + param_spec.description + "\n" }}
120
+ {%- endif %}
121
+ {{- param_name }}
122
+ {%- if param_name not in (tool.parameters.required or []) -%}
123
+ {{- "?" }}
124
+ {%- endif -%}
125
+ {{- ": " }}
126
+ {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
127
+ {%- if param_spec.default is defined -%}
128
+ {%- if param_spec.enum %}
129
+ {{- ", // default: " + param_spec.default }}
130
+ {%- elif param_spec.oneOf %}
131
+ {{- "// default: " + param_spec.default }}
132
+ {%- else %}
133
+ {{- ", // default: " + param_spec.default|tojson }}
134
+ {%- endif -%}
135
+ {%- endif -%}
136
+ {%- if not loop.last %}
137
+ {{- ",\n" }}
138
+ {%- else %}
139
+ {{- ",\n" }}
140
+ {%- endif -%}
141
+ {%- endfor %}
142
+ {{- "}) => any;\n\n" }}
143
+ {%- else -%}
144
+ {{- "() => any;\n\n" }}
145
+ {%- endif -%}
146
+ {%- endfor %}
147
+ {{- "} // namespace " + namespace_name }}
148
+ {%- endmacro -%}
149
+
150
+ {%- macro render_builtin_tools(browser_tool, python_tool) -%}
151
+ {%- if browser_tool %}
152
+ {{- "## browser\n\n" }}
153
+ {{- "// Tool for browsing.\n" }}
154
+ {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
155
+ {{- "// Cite information from the tool using the following format:\n" }}
156
+ {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
157
+ {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
158
+ {{- "// sources=web (default: web)\n" }}
159
+ {{- "namespace browser {\n\n" }}
160
+ {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
161
+ {{- "type search = (_: {\n" }}
162
+ {{- "query: string,\n" }}
163
+ {{- "topn?: number, // default: 10\n" }}
164
+ {{- "source?: string,\n" }}
165
+ {{- "}) => any;\n\n" }}
166
+ {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
167
+ {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
168
+ {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
169
+ {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
170
+ {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
171
+ {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
172
+ {{- "type open = (_: {\n" }}
173
+ {{- "id?: number | string, // default: -1\n" }}
174
+ {{- "cursor?: number, // default: -1\n" }}
175
+ {{- "loc?: number, // default: -1\n" }}
176
+ {{- "num_lines?: number, // default: -1\n" }}
177
+ {{- "view_source?: boolean, // default: false\n" }}
178
+ {{- "source?: string,\n" }}
179
+ {{- "}) => any;\n\n" }}
180
+ {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
181
+ {{- "type find = (_: {\n" }}
182
+ {{- "pattern: string,\n" }}
183
+ {{- "cursor?: number, // default: -1\n" }}
184
+ {{- "}) => any;\n\n" }}
185
+ {{- "} // namespace browser\n\n" }}
186
+ {%- endif -%}
187
+
188
+ {%- if python_tool %}
189
+ {{- "## python\n\n" }}
190
+ {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
191
+ {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
192
+ {%- endif -%}
193
+ {%- endmacro -%}
194
+
195
+ {#- System Message Construction ============================================ #}
196
+ {%- macro build_system_message() -%}
197
+ {%- if model_identity is not defined %}
198
+ {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
199
+ {%- endif %}
200
+ {{- model_identity + "\n" }}
201
+ {{- "Knowledge cutoff: 2024-06\n" }}
202
+ {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
203
+ {%- if reasoning_effort is not defined %}
204
+ {%- set reasoning_effort = "medium" %}
205
+ {%- endif %}
206
+ {{- "Reasoning: " + reasoning_effort + "\n\n" }}
207
+ {%- if builtin_tools %}
208
+ {{- "# Tools\n\n" }}
209
+ {%- set available_builtin_tools = namespace(browser=false, python=false) %}
210
+ {%- for tool in builtin_tools %}
211
+ {%- if tool == "browser" %}
212
+ {%- set available_builtin_tools.browser = true %}
213
+ {%- elif tool == "python" %}
214
+ {%- set available_builtin_tools.python = true %}
215
+ {%- endif %}
216
+ {%- endfor %}
217
+ {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
218
+ {%- endif -%}
219
+ {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
220
+ {%- if tools -%}
221
+ {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
222
+ {%- endif -%}
223
+ {%- endmacro -%}
224
+
225
+ {#- Main Template Logic ================================================= #}
226
+ {#- Set defaults #}
227
+
228
+ {#- Render system message #}
229
+ {{- "<|start|>system<|message|>" }}
230
+ {{- build_system_message() }}
231
+ {{- "<|end|>" }}
232
+
233
+ {#- Extract developer message #}
234
+ {%- if messages[0].role == "developer" or messages[0].role == "system" %}
235
+ {%- set developer_message = messages[0].content %}
236
+ {%- set loop_messages = messages[1:] %}
237
+ {%- else %}
238
+ {%- set developer_message = "" %}
239
+ {%- set loop_messages = messages %}
240
+ {%- endif %}
241
+
242
+ {#- Render developer message #}
243
+ {%- if developer_message or tools %}
244
+ {{- "<|start|>developer<|message|>" }}
245
+ {%- if developer_message %}
246
+ {{- "# Instructions\n\n" }}
247
+ {{- developer_message }}
248
+ {{- "\n\n" }}
249
+ {%- endif %}
250
+ {%- if tools -%}
251
+ {{- "# Tools\n\n" }}
252
+ {{- render_tool_namespace("functions", tools) }}
253
+ {%- endif -%}
254
+ {{- "<|end|>" }}
255
+ {%- endif %}
256
+
257
+ {#- Render messages #}
258
+ {%- set last_tool_call = namespace(name=none) %}
259
+ {%- for message in loop_messages -%}
260
+ {#- At this point only assistant/user/tool messages should remain #}
261
+ {%- if message.role == 'assistant' -%}
262
+ {#- Checks to ensure the messages are being passed in the format we expect #}
263
+ {%- if "content" in message %}
264
+ {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
265
+ {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
266
+ {%- endif %}
267
+ {%- endif %}
268
+ {%- if "thinking" in message %}
269
+ {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
270
+ {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
271
+ {%- endif %}
272
+ {%- endif %}
273
+ {%- if "tool_calls" in message %}
274
+ {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
275
+ {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
276
+ {#- when we render CoT/analysis messages in inference. #}
277
+ {%- set future_final_message = namespace(found=false) %}
278
+ {%- for future_message in loop_messages[loop.index:] %}
279
+ {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
280
+ {%- set future_final_message.found = true %}
281
+ {%- endif %}
282
+ {%- endfor %}
283
+ {#- We assume max 1 tool call per message, and so we infer the tool call name #}
284
+ {#- in "tool" messages from the most recent assistant tool call name #}
285
+ {%- set tool_call = message.tool_calls[0] %}
286
+ {%- if tool_call.function %}
287
+ {%- set tool_call = tool_call.function %}
288
+ {%- endif %}
289
+ {%- if message.content and message.thinking %}
290
+ {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
291
+ {%- elif message.content and not future_final_message.found %}
292
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
293
+ {%- elif message.thinking and not future_final_message.found %}
294
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
295
+ {%- endif %}
296
+ {{- "<|start|>assistant to=" }}
297
+ {{- "functions." + tool_call.name + "<|channel|>commentary " }}
298
+ {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
299
+ {{- tool_call.arguments|tojson }}
300
+ {{- "<|call|>" }}
301
+ {%- set last_tool_call.name = tool_call.name %}
302
+ {%- elif loop.last and not add_generation_prompt %}
303
+ {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
304
+ {#- This is a situation that should only occur in training, never in inference. #}
305
+ {%- if "thinking" in message %}
306
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
307
+ {%- endif %}
308
+ {#- <|return|> indicates the end of generation, but <|end|> does not #}
309
+ {#- <|return|> should never be an input to the model, but we include it as the final token #}
310
+ {#- when training, so the model learns to emit it. #}
311
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
312
+ {%- else %}
313
+ {#- CoT is dropped during all previous turns, so we never render it for inference #}
314
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
315
+ {%- set last_tool_call.name = none %}
316
+ {%- endif %}
317
+ {%- elif message.role == 'tool' -%}
318
+ {%- if last_tool_call.name is none %}
319
+ {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
320
+ {%- endif %}
321
+ {{- "<|start|>functions." + last_tool_call.name }}
322
+ {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
323
+ {%- elif message.role == 'user' -%}
324
+ {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
325
+ {%- endif -%}
326
+ {%- endfor -%}
327
+
328
+ {#- Generation prompt #}
329
+ {%- if add_generation_prompt -%}
330
+ <|start|>assistant
331
+ {%- endif -%}
checkpoint-50/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc98fa817f50d692279c3d572238544cc5a8db37aa382cbfc89c607a1788f657
3
+ size 254968907
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d74f24ff40c66479cca4bb3cf7148fba593ccfeb7f3603d6f962430abd8d57
3
+ size 14645
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31edc2a2bbce91c1e6afed681e5dc14966c375f87f735113b40ed0fe4d96a219
3
+ size 1465
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|return|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-50/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
3
+ size 27868174
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "199998": {
4
+ "content": "<|startoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "199999": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "200000": {
20
+ "content": "<|reserved_200000|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "200001": {
28
+ "content": "<|reserved_200001|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "200002": {
36
+ "content": "<|return|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "200003": {
44
+ "content": "<|constrain|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "200004": {
52
+ "content": "<|reserved_200004|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "200005": {
60
+ "content": "<|channel|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "200006": {
68
+ "content": "<|start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "200007": {
76
+ "content": "<|end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "200008": {
84
+ "content": "<|message|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "200009": {
92
+ "content": "<|reserved_200009|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "200010": {
100
+ "content": "<|reserved_200010|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "200011": {
108
+ "content": "<|reserved_200011|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "200012": {
116
+ "content": "<|call|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "200013": {
124
+ "content": "<|reserved_200013|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "200014": {
132
+ "content": "<|reserved_200014|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "200015": {
140
+ "content": "<|reserved_200015|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "200016": {
148
+ "content": "<|reserved_200016|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "200017": {
156
+ "content": "<|reserved_200017|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "200018": {
164
+ "content": "<|endofprompt|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ }
171
+ },
172
+ "bos_token": "<|startoftext|>",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "<|return|>",
175
+ "extra_special_tokens": {},
176
+ "model_input_names": [
177
+ "input_ids",
178
+ "attention_mask"
179
+ ],
180
+ "model_max_length": 1000000000000000019884624838656,
181
+ "pad_token": "<|endoftext|>",
182
+ "tokenizer_class": "PreTrainedTokenizerFast"
183
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.255591054313099,
6
+ "eval_steps": 500,
7
+ "global_step": 50,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.3369140625,
14
+ "epoch": 0.025559105431309903,
15
+ "grad_norm": 2.3105356693267822,
16
+ "learning_rate": 0.0,
17
+ "loss": 1.087,
18
+ "mean_token_accuracy": 0.701034776866436,
19
+ "num_tokens": 6906.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 1.23681640625,
24
+ "epoch": 0.051118210862619806,
25
+ "grad_norm": 2.381164312362671,
26
+ "learning_rate": 4e-05,
27
+ "loss": 0.9348,
28
+ "mean_token_accuracy": 0.7362930178642273,
29
+ "num_tokens": 14418.0,
30
+ "step": 2
31
+ },
32
+ {
33
+ "entropy": 1.0859375,
34
+ "epoch": 0.07667731629392971,
35
+ "grad_norm": 1.7778037786483765,
36
+ "learning_rate": 8e-05,
37
+ "loss": 0.8803,
38
+ "mean_token_accuracy": 0.7567353323101997,
39
+ "num_tokens": 22610.0,
40
+ "step": 3
41
+ },
42
+ {
43
+ "entropy": 1.14208984375,
44
+ "epoch": 0.10223642172523961,
45
+ "grad_norm": 1.4184125661849976,
46
+ "learning_rate": 0.00012,
47
+ "loss": 0.7839,
48
+ "mean_token_accuracy": 0.7793847769498825,
49
+ "num_tokens": 30802.0,
50
+ "step": 4
51
+ },
52
+ {
53
+ "entropy": 1.06689453125,
54
+ "epoch": 0.12779552715654952,
55
+ "grad_norm": 1.1998612880706787,
56
+ "learning_rate": 0.00016,
57
+ "loss": 0.7794,
58
+ "mean_token_accuracy": 0.7751764059066772,
59
+ "num_tokens": 38994.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "entropy": 1.06884765625,
64
+ "epoch": 0.15335463258785942,
65
+ "grad_norm": 3.067514181137085,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.8615,
68
+ "mean_token_accuracy": 0.7497537210583687,
69
+ "num_tokens": 47186.0,
70
+ "step": 6
71
+ },
72
+ {
73
+ "entropy": 1.0419921875,
74
+ "epoch": 0.17891373801916932,
75
+ "grad_norm": 3.843412399291992,
76
+ "learning_rate": 0.00019555555555555556,
77
+ "loss": 0.9073,
78
+ "mean_token_accuracy": 0.7386935651302338,
79
+ "num_tokens": 55157.0,
80
+ "step": 7
81
+ },
82
+ {
83
+ "entropy": 0.935546875,
84
+ "epoch": 0.20447284345047922,
85
+ "grad_norm": 2.127117156982422,
86
+ "learning_rate": 0.00019111111111111114,
87
+ "loss": 0.7947,
88
+ "mean_token_accuracy": 0.7617381662130356,
89
+ "num_tokens": 62915.0,
90
+ "step": 8
91
+ },
92
+ {
93
+ "entropy": 1.13232421875,
94
+ "epoch": 0.23003194888178913,
95
+ "grad_norm": 1.4348453283309937,
96
+ "learning_rate": 0.0001866666666666667,
97
+ "loss": 0.8575,
98
+ "mean_token_accuracy": 0.7442174553871155,
99
+ "num_tokens": 70290.0,
100
+ "step": 9
101
+ },
102
+ {
103
+ "entropy": 1.1875,
104
+ "epoch": 0.25559105431309903,
105
+ "grad_norm": 0.9306125044822693,
106
+ "learning_rate": 0.00018222222222222224,
107
+ "loss": 0.9053,
108
+ "mean_token_accuracy": 0.7269261628389359,
109
+ "num_tokens": 77189.0,
110
+ "step": 10
111
+ },
112
+ {
113
+ "entropy": 0.7666015625,
114
+ "epoch": 0.28115015974440893,
115
+ "grad_norm": 0.6212925910949707,
116
+ "learning_rate": 0.00017777777777777779,
117
+ "loss": 0.5573,
118
+ "mean_token_accuracy": 0.8304020240902901,
119
+ "num_tokens": 85381.0,
120
+ "step": 11
121
+ },
122
+ {
123
+ "entropy": 0.871337890625,
124
+ "epoch": 0.30670926517571884,
125
+ "grad_norm": 0.6617708802223206,
126
+ "learning_rate": 0.00017333333333333334,
127
+ "loss": 0.6777,
128
+ "mean_token_accuracy": 0.7921964526176453,
129
+ "num_tokens": 93217.0,
130
+ "step": 12
131
+ },
132
+ {
133
+ "entropy": 0.91796875,
134
+ "epoch": 0.33226837060702874,
135
+ "grad_norm": 0.6723743081092834,
136
+ "learning_rate": 0.00016888888888888889,
137
+ "loss": 0.7622,
138
+ "mean_token_accuracy": 0.765856072306633,
139
+ "num_tokens": 100949.0,
140
+ "step": 13
141
+ },
142
+ {
143
+ "entropy": 0.8798828125,
144
+ "epoch": 0.35782747603833864,
145
+ "grad_norm": 0.6261276602745056,
146
+ "learning_rate": 0.00016444444444444444,
147
+ "loss": 0.7665,
148
+ "mean_token_accuracy": 0.7666892483830452,
149
+ "num_tokens": 108686.0,
150
+ "step": 14
151
+ },
152
+ {
153
+ "entropy": 0.97998046875,
154
+ "epoch": 0.38338658146964855,
155
+ "grad_norm": 0.6475221514701843,
156
+ "learning_rate": 0.00016,
157
+ "loss": 0.8913,
158
+ "mean_token_accuracy": 0.7170633375644684,
159
+ "num_tokens": 115992.0,
160
+ "step": 15
161
+ },
162
+ {
163
+ "entropy": 0.780517578125,
164
+ "epoch": 0.40894568690095845,
165
+ "grad_norm": 0.4886324405670166,
166
+ "learning_rate": 0.00015555555555555556,
167
+ "loss": 0.6722,
168
+ "mean_token_accuracy": 0.7949602380394936,
169
+ "num_tokens": 124184.0,
170
+ "step": 16
171
+ },
172
+ {
173
+ "entropy": 0.82666015625,
174
+ "epoch": 0.43450479233226835,
175
+ "grad_norm": 0.45082569122314453,
176
+ "learning_rate": 0.0001511111111111111,
177
+ "loss": 0.6955,
178
+ "mean_token_accuracy": 0.7882104143500328,
179
+ "num_tokens": 132376.0,
180
+ "step": 17
181
+ },
182
+ {
183
+ "entropy": 0.7724609375,
184
+ "epoch": 0.46006389776357826,
185
+ "grad_norm": 0.5022221207618713,
186
+ "learning_rate": 0.00014666666666666666,
187
+ "loss": 0.6556,
188
+ "mean_token_accuracy": 0.7958140671253204,
189
+ "num_tokens": 140568.0,
190
+ "step": 18
191
+ },
192
+ {
193
+ "entropy": 0.553955078125,
194
+ "epoch": 0.48562300319488816,
195
+ "grad_norm": 0.4155460000038147,
196
+ "learning_rate": 0.00014222222222222224,
197
+ "loss": 0.458,
198
+ "mean_token_accuracy": 0.8605139404535294,
199
+ "num_tokens": 148760.0,
200
+ "step": 19
201
+ },
202
+ {
203
+ "entropy": 0.814453125,
204
+ "epoch": 0.5111821086261981,
205
+ "grad_norm": 0.6609243750572205,
206
+ "learning_rate": 0.0001377777777777778,
207
+ "loss": 0.7756,
208
+ "mean_token_accuracy": 0.7634661719202995,
209
+ "num_tokens": 156158.0,
210
+ "step": 20
211
+ },
212
+ {
213
+ "entropy": 0.738037109375,
214
+ "epoch": 0.536741214057508,
215
+ "grad_norm": 0.5830342173576355,
216
+ "learning_rate": 0.00013333333333333334,
217
+ "loss": 0.7332,
218
+ "mean_token_accuracy": 0.7767216190695763,
219
+ "num_tokens": 164214.0,
220
+ "step": 21
221
+ },
222
+ {
223
+ "entropy": 0.68359375,
224
+ "epoch": 0.5623003194888179,
225
+ "grad_norm": 0.4524409770965576,
226
+ "learning_rate": 0.00012888888888888892,
227
+ "loss": 0.6408,
228
+ "mean_token_accuracy": 0.8016774877905846,
229
+ "num_tokens": 172167.0,
230
+ "step": 22
231
+ },
232
+ {
233
+ "entropy": 0.8681640625,
234
+ "epoch": 0.5878594249201278,
235
+ "grad_norm": 0.4371228516101837,
236
+ "learning_rate": 0.00012444444444444444,
237
+ "loss": 0.7977,
238
+ "mean_token_accuracy": 0.7557996660470963,
239
+ "num_tokens": 179926.0,
240
+ "step": 23
241
+ },
242
+ {
243
+ "entropy": 0.726806640625,
244
+ "epoch": 0.6134185303514377,
245
+ "grad_norm": 0.4200146496295929,
246
+ "learning_rate": 0.00012,
247
+ "loss": 0.6229,
248
+ "mean_token_accuracy": 0.8095021098852158,
249
+ "num_tokens": 188118.0,
250
+ "step": 24
251
+ },
252
+ {
253
+ "entropy": 0.865234375,
254
+ "epoch": 0.6389776357827476,
255
+ "grad_norm": 0.46773526072502136,
256
+ "learning_rate": 0.00011555555555555555,
257
+ "loss": 0.7052,
258
+ "mean_token_accuracy": 0.77592733502388,
259
+ "num_tokens": 195613.0,
260
+ "step": 25
261
+ },
262
+ {
263
+ "entropy": 0.80078125,
264
+ "epoch": 0.6645367412140575,
265
+ "grad_norm": 0.42418503761291504,
266
+ "learning_rate": 0.00011111111111111112,
267
+ "loss": 0.6926,
268
+ "mean_token_accuracy": 0.7816073298454285,
269
+ "num_tokens": 203805.0,
270
+ "step": 26
271
+ },
272
+ {
273
+ "entropy": 0.752685546875,
274
+ "epoch": 0.6900958466453674,
275
+ "grad_norm": 0.3921058475971222,
276
+ "learning_rate": 0.00010666666666666667,
277
+ "loss": 0.5513,
278
+ "mean_token_accuracy": 0.8219155222177505,
279
+ "num_tokens": 211183.0,
280
+ "step": 27
281
+ },
282
+ {
283
+ "entropy": 0.7596435546875,
284
+ "epoch": 0.7156549520766773,
285
+ "grad_norm": 0.41568854451179504,
286
+ "learning_rate": 0.00010222222222222222,
287
+ "loss": 0.6115,
288
+ "mean_token_accuracy": 0.8116571307182312,
289
+ "num_tokens": 218666.0,
290
+ "step": 28
291
+ },
292
+ {
293
+ "entropy": 0.717529296875,
294
+ "epoch": 0.7412140575079872,
295
+ "grad_norm": 0.39525139331817627,
296
+ "learning_rate": 9.777777777777778e-05,
297
+ "loss": 0.5978,
298
+ "mean_token_accuracy": 0.8129823505878448,
299
+ "num_tokens": 226858.0,
300
+ "step": 29
301
+ },
302
+ {
303
+ "entropy": 0.729248046875,
304
+ "epoch": 0.7667731629392971,
305
+ "grad_norm": 0.38765206933021545,
306
+ "learning_rate": 9.333333333333334e-05,
307
+ "loss": 0.578,
308
+ "mean_token_accuracy": 0.8145338892936707,
309
+ "num_tokens": 234618.0,
310
+ "step": 30
311
+ },
312
+ {
313
+ "entropy": 0.78564453125,
314
+ "epoch": 0.792332268370607,
315
+ "grad_norm": 0.48644062876701355,
316
+ "learning_rate": 8.888888888888889e-05,
317
+ "loss": 0.7218,
318
+ "mean_token_accuracy": 0.77530936896801,
319
+ "num_tokens": 242810.0,
320
+ "step": 31
321
+ },
322
+ {
323
+ "entropy": 0.7998046875,
324
+ "epoch": 0.8178913738019169,
325
+ "grad_norm": 0.4270438551902771,
326
+ "learning_rate": 8.444444444444444e-05,
327
+ "loss": 0.7347,
328
+ "mean_token_accuracy": 0.769258588552475,
329
+ "num_tokens": 251002.0,
330
+ "step": 32
331
+ },
332
+ {
333
+ "entropy": 0.7529296875,
334
+ "epoch": 0.8434504792332268,
335
+ "grad_norm": 0.4402211308479309,
336
+ "learning_rate": 8e-05,
337
+ "loss": 0.6393,
338
+ "mean_token_accuracy": 0.8079103901982307,
339
+ "num_tokens": 258948.0,
340
+ "step": 33
341
+ },
342
+ {
343
+ "entropy": 0.647216796875,
344
+ "epoch": 0.8690095846645367,
345
+ "grad_norm": 0.42324361205101013,
346
+ "learning_rate": 7.555555555555556e-05,
347
+ "loss": 0.4934,
348
+ "mean_token_accuracy": 0.8280825689435005,
349
+ "num_tokens": 266397.0,
350
+ "step": 34
351
+ },
352
+ {
353
+ "entropy": 0.8359375,
354
+ "epoch": 0.8945686900958466,
355
+ "grad_norm": 0.47273099422454834,
356
+ "learning_rate": 7.111111111111112e-05,
357
+ "loss": 0.7317,
358
+ "mean_token_accuracy": 0.7696092054247856,
359
+ "num_tokens": 273244.0,
360
+ "step": 35
361
+ },
362
+ {
363
+ "entropy": 0.774169921875,
364
+ "epoch": 0.9201277955271565,
365
+ "grad_norm": 0.40159478783607483,
366
+ "learning_rate": 6.666666666666667e-05,
367
+ "loss": 0.5951,
368
+ "mean_token_accuracy": 0.8139322251081467,
369
+ "num_tokens": 280724.0,
370
+ "step": 36
371
+ },
372
+ {
373
+ "entropy": 0.65966796875,
374
+ "epoch": 0.9456869009584664,
375
+ "grad_norm": 0.38593849539756775,
376
+ "learning_rate": 6.222222222222222e-05,
377
+ "loss": 0.5762,
378
+ "mean_token_accuracy": 0.8153740167617798,
379
+ "num_tokens": 288703.0,
380
+ "step": 37
381
+ },
382
+ {
383
+ "entropy": 0.7236328125,
384
+ "epoch": 0.9712460063897763,
385
+ "grad_norm": 0.4029550850391388,
386
+ "learning_rate": 5.7777777777777776e-05,
387
+ "loss": 0.6262,
388
+ "mean_token_accuracy": 0.8032189607620239,
389
+ "num_tokens": 296736.0,
390
+ "step": 38
391
+ },
392
+ {
393
+ "entropy": 0.695068359375,
394
+ "epoch": 0.9968051118210862,
395
+ "grad_norm": 0.4444594085216522,
396
+ "learning_rate": 5.333333333333333e-05,
397
+ "loss": 0.6218,
398
+ "mean_token_accuracy": 0.8159564882516861,
399
+ "num_tokens": 304425.0,
400
+ "step": 39
401
+ },
402
+ {
403
+ "entropy": 0.90234375,
404
+ "epoch": 1.0,
405
+ "grad_norm": 1.3549686670303345,
406
+ "learning_rate": 4.888888888888889e-05,
407
+ "loss": 0.8577,
408
+ "mean_token_accuracy": 0.725623607635498,
409
+ "num_tokens": 305449.0,
410
+ "step": 40
411
+ },
412
+ {
413
+ "entropy": 0.79345703125,
414
+ "epoch": 1.0255591054313098,
415
+ "grad_norm": 0.4474547207355499,
416
+ "learning_rate": 4.4444444444444447e-05,
417
+ "loss": 0.6887,
418
+ "mean_token_accuracy": 0.7809437215328217,
419
+ "num_tokens": 313242.0,
420
+ "step": 41
421
+ },
422
+ {
423
+ "entropy": 0.7763671875,
424
+ "epoch": 1.0511182108626198,
425
+ "grad_norm": 0.4416673481464386,
426
+ "learning_rate": 4e-05,
427
+ "loss": 0.6635,
428
+ "mean_token_accuracy": 0.7911219000816345,
429
+ "num_tokens": 320751.0,
430
+ "step": 42
431
+ },
432
+ {
433
+ "entropy": 0.81494140625,
434
+ "epoch": 1.0766773162939298,
435
+ "grad_norm": 0.4539318382740021,
436
+ "learning_rate": 3.555555555555556e-05,
437
+ "loss": 0.6578,
438
+ "mean_token_accuracy": 0.7916175723075867,
439
+ "num_tokens": 328943.0,
440
+ "step": 43
441
+ },
442
+ {
443
+ "entropy": 0.86474609375,
444
+ "epoch": 1.1022364217252396,
445
+ "grad_norm": 0.40605172514915466,
446
+ "learning_rate": 3.111111111111111e-05,
447
+ "loss": 0.7085,
448
+ "mean_token_accuracy": 0.7670398578047752,
449
+ "num_tokens": 336515.0,
450
+ "step": 44
451
+ },
452
+ {
453
+ "entropy": 0.69775390625,
454
+ "epoch": 1.1277955271565494,
455
+ "grad_norm": 0.3975476026535034,
456
+ "learning_rate": 2.6666666666666667e-05,
457
+ "loss": 0.4933,
458
+ "mean_token_accuracy": 0.8318949267268181,
459
+ "num_tokens": 343984.0,
460
+ "step": 45
461
+ },
462
+ {
463
+ "entropy": 0.791259765625,
464
+ "epoch": 1.1533546325878594,
465
+ "grad_norm": 0.4187847673892975,
466
+ "learning_rate": 2.2222222222222223e-05,
467
+ "loss": 0.6253,
468
+ "mean_token_accuracy": 0.8081694170832634,
469
+ "num_tokens": 351464.0,
470
+ "step": 46
471
+ },
472
+ {
473
+ "entropy": 0.703857421875,
474
+ "epoch": 1.1789137380191694,
475
+ "grad_norm": 0.35935476422309875,
476
+ "learning_rate": 1.777777777777778e-05,
477
+ "loss": 0.5352,
478
+ "mean_token_accuracy": 0.811345063149929,
479
+ "num_tokens": 358913.0,
480
+ "step": 47
481
+ },
482
+ {
483
+ "entropy": 0.84765625,
484
+ "epoch": 1.2044728434504792,
485
+ "grad_norm": 0.4173986315727234,
486
+ "learning_rate": 1.3333333333333333e-05,
487
+ "loss": 0.7239,
488
+ "mean_token_accuracy": 0.7771043181419373,
489
+ "num_tokens": 366672.0,
490
+ "step": 48
491
+ },
492
+ {
493
+ "entropy": 0.69775390625,
494
+ "epoch": 1.230031948881789,
495
+ "grad_norm": 0.37685781717300415,
496
+ "learning_rate": 8.88888888888889e-06,
497
+ "loss": 0.6163,
498
+ "mean_token_accuracy": 0.8031821772456169,
499
+ "num_tokens": 374864.0,
500
+ "step": 49
501
+ },
502
+ {
503
+ "entropy": 0.71435546875,
504
+ "epoch": 1.255591054313099,
505
+ "grad_norm": 0.38702356815338135,
506
+ "learning_rate": 4.444444444444445e-06,
507
+ "loss": 0.6231,
508
+ "mean_token_accuracy": 0.806434653699398,
509
+ "num_tokens": 383056.0,
510
+ "step": 50
511
+ }
512
+ ],
513
+ "logging_steps": 1,
514
+ "max_steps": 50,
515
+ "num_input_tokens_seen": 0,
516
+ "num_train_epochs": 2,
517
+ "save_steps": 500,
518
+ "stateful_callbacks": {
519
+ "TrainerControl": {
520
+ "args": {
521
+ "should_epoch_stop": false,
522
+ "should_evaluate": false,
523
+ "should_log": false,
524
+ "should_save": true,
525
+ "should_training_stop": true
526
+ },
527
+ "attributes": {}
528
+ }
529
+ },
530
+ "total_flos": 4.681129927486464e+16,
531
+ "train_batch_size": 1,
532
+ "trial_name": null,
533
+ "trial_params": null
534
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef7111ffab0c1452afe643559792e51d9a4120b16dfea8d8982a1087a6cfc9d
3
+ size 5713
checkpoint-50/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 199998,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 200002,
10
+ "experts_per_token": 4,
11
+ "head_dim": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2880,
14
+ "initial_context_length": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2880,
17
+ "layer_types": [
18
+ "sliding_attention",
19
+ "full_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "model_type": "gpt_oss",
45
+ "num_attention_heads": 64,
46
+ "num_experts_per_tok": 4,
47
+ "num_hidden_layers": 24,
48
+ "num_key_value_heads": 8,
49
+ "num_local_experts": 32,
50
+ "output_router_logits": false,
51
+ "pad_token_id": 199999,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "beta_fast": 32.0,
55
+ "beta_slow": 1.0,
56
+ "factor": 32.0,
57
+ "original_max_position_embeddings": 4096,
58
+ "rope_type": "yarn",
59
+ "truncate": false
60
+ },
61
+ "rope_theta": 150000,
62
+ "router_aux_loss_coef": 0.9,
63
+ "sliding_window": 128,
64
+ "swiglu_limit": 7.0,
65
+ "tie_word_embeddings": false,
66
+ "transformers_version": "4.57.0.dev0",
67
+ "use_cache": true,
68
+ "vocab_size": 201088
69
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999,
7
+ 200012
8
+ ],
9
+ "pad_token_id": 199999,
10
+ "transformers_version": "4.57.0.dev0"
11
+ }
lora_weights/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openai/gpt-oss-20b
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:openai/gpt-oss-20b
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
lora_weights/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai/gpt-oss-20b",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 64,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "gate_proj",
29
+ "k_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "v_proj",
33
+ "q_proj",
34
+ "o_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
lora_weights/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66588ad755f746ec82e0bf0290eb4b80f1792e714636a26ab0cc88500df86f08
3
+ size 127427864
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49feabd467741ee98df04ca370476960ec368100e3c7ed7039c26ef993c00c73
3
+ size 4504304664
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1c751af0255e029aa68af79619a560898c3cda96525727d049040aa549472a
3
+ size 4939127656
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d793c8bf80427c1ebcd4d5c55938115a0a2638b53309c7bf072b0b56c44a5e
3
+ size 4939127656
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d87f482f3fe66643efb6ba83da3500f9927ee55e0d4e48bb3239a90d17258a
3
+ size 4939127680
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59e45b0b11d6b7f46583d937b0f7acb2abddd3c3cbc00669984c1e1048bd2d8
3
+ size 4939127704
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c3782f811fc251321743a09600ce9ecdad594de5e427f0c9703d14df8482b4
3
+ size 4939127704
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82654433ea16dbaf46e1e064593d6d4660134d0465b91934f2a0e9de8b7b8a59
3
+ size 4939127704
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d470fc83b0675251ff1a91ab87d2e21e0892b57bbd5efb610b229eea604d74ca
3
+ size 4939127704
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1951ff65d233bcb7f50485d294cced6497b8e0d9707f57087912fc2352492e
3
+ size 2751362856
model.safetensors.index.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 20914757184,
4
+ "total_size": 41829514368
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00009-of-00009.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
24
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
25
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
27
+ "model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
28
+ "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
29
+ "model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
30
+ "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
31
+ "model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
32
+ "model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
33
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
34
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
35
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
36
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
37
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
38
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
39
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
40
+ "model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
41
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
42
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
43
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
44
+ "model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
45
+ "model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
46
+ "model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
47
+ "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
48
+ "model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
49
+ "model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
50
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
51
+ "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
52
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
53
+ "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
54
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
55
+ "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
56
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
57
+ "model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
58
+ "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
59
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
60
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
61
+ "model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
62
+ "model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
63
+ "model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
64
+ "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
65
+ "model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
66
+ "model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
67
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
68
+ "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
69
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
70
+ "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
71
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
72
+ "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
73
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
74
+ "model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
75
+ "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
76
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
77
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
78
+ "model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
79
+ "model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
80
+ "model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
81
+ "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
82
+ "model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
83
+ "model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
84
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
85
+ "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
86
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
87
+ "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
88
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
89
+ "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
90
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
91
+ "model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
92
+ "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
93
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
94
+ "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
95
+ "model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
96
+ "model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
97
+ "model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
98
+ "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
99
+ "model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
100
+ "model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
101
+ "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
102
+ "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
103
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
104
+ "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
105
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
106
+ "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
107
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
108
+ "model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
109
+ "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
110
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
111
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
112
+ "model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
113
+ "model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
114
+ "model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
115
+ "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
116
+ "model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
117
+ "model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
118
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
119
+ "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
120
+ "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
121
+ "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
122
+ "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
123
+ "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
124
+ "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
125
+ "model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
126
+ "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
127
+ "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
128
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
129
+ "model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
130
+ "model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
131
+ "model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
132
+ "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
133
+ "model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
134
+ "model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
135
+ "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
136
+ "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
137
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
138
+ "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
139
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
140
+ "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
141
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
142
+ "model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
143
+ "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
144
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
145
+ "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
146
+ "model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
147
+ "model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
148
+ "model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
149
+ "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
150
+ "model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
151
+ "model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
152
+ "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
153
+ "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
154
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
155
+ "model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
156
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
157
+ "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
158
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
159
+ "model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
160
+ "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
161
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
162
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
163
+ "model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
164
+ "model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
165
+ "model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
166
+ "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
167
+ "model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
168
+ "model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
169
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
170
+ "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
171
+ "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
172
+ "model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
173
+ "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
174
+ "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
175
+ "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
176
+ "model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
177
+ "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
178
+ "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
179
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
180
+ "model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
181
+ "model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
182
+ "model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
183
+ "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
184
+ "model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
185
+ "model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
186
+ "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
187
+ "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
188
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
189
+ "model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
190
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
191
+ "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
192
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
193
+ "model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
194
+ "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
195
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
196
+ "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
197
+ "model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
198
+ "model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
199
+ "model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
200
+ "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
201
+ "model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
202
+ "model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
203
+ "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
204
+ "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
205
+ "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
206
+ "model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
207
+ "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
208
+ "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
209
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
210
+ "model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
211
+ "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
212
+ "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
213
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
214
+ "model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
215
+ "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
216
+ "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
217
+ "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
218
+ "model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
219
+ "model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
220
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
221
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
222
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
223
+ "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
224
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
225
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
226
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
227
+ "model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
228
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
229
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
230
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
231
+ "model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
232
+ "model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
233
+ "model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
234
+ "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
235
+ "model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
236
+ "model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
237
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
238
+ "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
239
+ "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
240
+ "model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
241
+ "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
242
+ "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
243
+ "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
244
+ "model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
245
+ "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
246
+ "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
247
+ "model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
248
+ "model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
249
+ "model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
250
+ "model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
251
+ "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
252
+ "model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
253
+ "model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
254
+ "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
255
+ "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
256
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
257
+ "model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
258
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
259
+ "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
260
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
261
+ "model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
262
+ "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
263
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
264
+ "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
265
+ "model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
266
+ "model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
267
+ "model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
268
+ "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
269
+ "model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
270
+ "model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
271
+ "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
272
+ "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
273
+ "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
274
+ "model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
275
+ "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
276
+ "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
277
+ "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
278
+ "model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
279
+ "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
280
+ "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
281
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
282
+ "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
283
+ "model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
284
+ "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
285
+ "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
286
+ "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
287
+ "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
288
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
289
+ "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
290
+ "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
291
+ "model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
292
+ "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
293
+ "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
294
+ "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
295
+ "model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
296
+ "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
297
+ "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
298
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
299
+ "model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
300
+ "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
301
+ "model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
302
+ "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
303
+ "model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
304
+ "model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
305
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
306
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
307
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
308
+ "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
309
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
310
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
311
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
312
+ "model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
313
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
314
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
315
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
316
+ "model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
317
+ "model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
318
+ "model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
319
+ "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
320
+ "model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
321
+ "model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
322
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
323
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
324
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
325
+ "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
326
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
327
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
328
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
329
+ "model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
330
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
331
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
332
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
333
+ "model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
334
+ "model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
335
+ "model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
336
+ "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
337
+ "model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
338
+ "model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
339
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
340
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
341
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
342
+ "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
343
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
344
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
345
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
346
+ "model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
347
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
348
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
349
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
350
+ "model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
351
+ "model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
352
+ "model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
353
+ "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
354
+ "model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
355
+ "model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
356
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
357
+ "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
358
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
359
+ "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
360
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
361
+ "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
362
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
363
+ "model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
364
+ "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
365
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
366
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
367
+ "model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
368
+ "model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
369
+ "model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
370
+ "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
371
+ "model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
372
+ "model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
373
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
374
+ "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
375
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
376
+ "model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
377
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
378
+ "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
379
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
380
+ "model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
381
+ "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
384
+ "model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
385
+ "model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
386
+ "model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
387
+ "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
388
+ "model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
389
+ "model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
390
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
391
+ "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
392
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
393
+ "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
394
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
395
+ "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
396
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
397
+ "model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
398
+ "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
399
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
400
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
401
+ "model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
402
+ "model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
403
+ "model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
404
+ "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
405
+ "model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
406
+ "model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
407
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
408
+ "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
409
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
410
+ "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
411
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
412
+ "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
413
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
414
+ "model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
415
+ "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
416
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
417
+ "model.norm.weight": "model-00009-of-00009.safetensors"
418
+ }
419
+ }