jlov7 commited on
Commit
1e6e409
·
verified ·
1 Parent(s): 6d2d49f

Upload fine-tuned SmolLM3 function-calling adapter (100% success rate)

Browse files
Files changed (41) hide show
  1. .gitattributes +3 -0
  2. README.md +207 -0
  3. adapter_config.json +41 -0
  4. adapter_model.safetensors +3 -0
  5. chat_template.jinja +94 -0
  6. checkpoint-660/README.md +207 -0
  7. checkpoint-660/adapter_config.json +41 -0
  8. checkpoint-660/adapter_model.safetensors +3 -0
  9. checkpoint-660/chat_template.jinja +94 -0
  10. checkpoint-660/optimizer.pt +3 -0
  11. checkpoint-660/rng_state.pth +3 -0
  12. checkpoint-660/scheduler.pt +3 -0
  13. checkpoint-660/special_tokens_map.json +16 -0
  14. checkpoint-660/tokenizer.json +3 -0
  15. checkpoint-660/tokenizer_config.json +2064 -0
  16. checkpoint-660/trainer_state.json +2344 -0
  17. checkpoint-660/training_args.bin +3 -0
  18. checkpoint-670/README.md +207 -0
  19. checkpoint-670/adapter_config.json +41 -0
  20. checkpoint-670/adapter_model.safetensors +3 -0
  21. checkpoint-670/chat_template.jinja +94 -0
  22. checkpoint-670/optimizer.pt +3 -0
  23. checkpoint-670/rng_state.pth +3 -0
  24. checkpoint-670/scheduler.pt +3 -0
  25. checkpoint-670/special_tokens_map.json +16 -0
  26. checkpoint-670/tokenizer.json +3 -0
  27. checkpoint-670/tokenizer_config.json +2064 -0
  28. checkpoint-670/trainer_state.json +2379 -0
  29. checkpoint-670/training_args.bin +3 -0
  30. optimizer.pt +3 -0
  31. rng_state.pth +3 -0
  32. runs/Jul21_18-43-33_Jasons-MacBook-Pro.local/events.out.tfevents.1753119814.Jasons-MacBook-Pro.local.87971.0 +3 -0
  33. runs/Jul21_18-48-03_Jasons-MacBook-Pro.local/events.out.tfevents.1753120084.Jasons-MacBook-Pro.local.90405.0 +3 -0
  34. runs/Jul21_18-52-37_Jasons-MacBook-Pro.local/events.out.tfevents.1753120358.Jasons-MacBook-Pro.local.94516.0 +3 -0
  35. runs/Jul21_19-07-35_Jasons-MacBook-Pro.local/events.out.tfevents.1753121256.Jasons-MacBook-Pro.local.99650.0 +3 -0
  36. scheduler.pt +3 -0
  37. special_tokens_map.json +16 -0
  38. tokenizer.json +3 -0
  39. tokenizer_config.json +2064 -0
  40. trainer_state.json +2379 -0
  41. training_args.bin +3 -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-660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-670/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM3-3B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM3-3B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.16.0
adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM3-3B",
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": 16,
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": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "k_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "o_proj",
32
+ "down_proj",
33
+ "q_proj",
34
+ "gate_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_qalora": false,
40
+ "use_rslora": false
41
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3458fc95dd76c973d77067a8b1bba3b9ef30b3abf188c05ccfcef00e2aedf0
3
+ size 60523464
chat_template.jinja ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# ───── defaults ───── #}
2
+ {%- if enable_thinking is not defined -%}
3
+ {%- set enable_thinking = true -%}
4
+ {%- endif -%}
5
+
6
+ {# ───── reasoning mode ───── #}
7
+ {%- if enable_thinking -%}
8
+ {%- set reasoning_mode = "/think" -%}
9
+ {%- else -%}
10
+ {%- set reasoning_mode = "/no_think" -%}
11
+ {%- endif -%}
12
+
13
+ {# ───── header (system message) ───── #}
14
+ {{- "<|im_start|>system\n" -}}
15
+
16
+ {%- if messages[0].role == "system" -%}
17
+ {%- set system_message = messages[0].content -%}
18
+ {%- if "/no_think" in system_message -%}
19
+ {%- set reasoning_mode = "/no_think" -%}
20
+ {%- elif "/think" in system_message -%}
21
+ {%- set reasoning_mode = "/think" -%}
22
+ {%- endif -%}
23
+ {%- set custom_instructions = system_message.replace("/no_think", "").replace("/think", "").rstrip() -%}
24
+ {%- endif -%}
25
+
26
+ {%- if "/system_override" in system_message -%}
27
+ {{- custom_instructions.replace("/system_override", "").rstrip() -}}
28
+ {{- "<|im_end|>\n" -}}
29
+ {%- else -%}
30
+ {{- "## Metadata\n\n" -}}
31
+ {{- "Knowledge Cutoff Date: June 2025\n" -}}
32
+ {%- set today = strftime_now("%d %B %Y") -%}
33
+ {{- "Today Date: " ~ today ~ "\n" -}}
34
+ {{- "Reasoning Mode: " + reasoning_mode + "\n\n" -}}
35
+
36
+ {{- "## Custom Instructions\n\n" -}}
37
+ {%- if custom_instructions -%}
38
+ {{- custom_instructions + "\n\n" -}}
39
+ {%- elif reasoning_mode == "/think" -%}
40
+ {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: <think> Thought section </think> Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion.\n\n" -}}
41
+ {%- else -%}
42
+ {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face.\n\n" -}}
43
+ {%- endif -%}
44
+
45
+ {%- if xml_tools or python_tools or tools -%}
46
+ {{- "### Tools\n\n" -}}
47
+ {%- if xml_tools or tools -%}
48
+ {%- if tools -%}
49
+ {%- set xml_tools = tools -%}
50
+ {%- endif -%}
51
+ {%- set ns = namespace(xml_tool_string="You may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n") -%}
52
+ {%- for tool in xml_tools[:] -%} {# The slicing makes sure that xml_tools is a list #}
53
+ {%- set ns.xml_tool_string = ns.xml_tool_string ~ (tool | string) ~ "\n" -%}
54
+ {%- endfor -%}
55
+ {%- set xml_tool_string = ns.xml_tool_string + "</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>" -%}
56
+ {{- xml_tool_string -}}
57
+ {%- endif -%}
58
+ {%- if python_tools -%}
59
+ {%- set ns = namespace(python_tool_string="When you send a message containing Python code between '<code>' and '</code>' tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output to continued reasoning in an agentic loop.\n\nYou can use the following tools in your python code like regular functions:\n<tools>\n") -%}
60
+ {%- for tool in python_tools[:] -%} {# The slicing makes sure that python_tools is a list #}
61
+ {%- set ns.python_tool_string = ns.python_tool_string ~ (tool | string) ~ "\n" -%}
62
+ {%- endfor -%}
63
+ {%- set python_tool_string = ns.python_tool_string + "</tools>\n\nThe state persists between code executions: so variables that you define in one step are still available thereafter." -%}
64
+ {{- python_tool_string -}}
65
+ {%- endif -%}
66
+ {{- "\n\n" -}}
67
+ {{- "<|im_end|>\n" -}}
68
+ {%- endif -%}
69
+ {%- endif -%}
70
+ {# ───── main loop ───── #}
71
+ {%- for message in messages -%}
72
+ {%- set content = message.content if message.content is string else "" -%}
73
+ {%- if message.role == "user" -%}
74
+ {{ "<|im_start|>" + message.role + "\n" + content + "<|im_end|>\n" }}
75
+ {%- elif message.role == "assistant" -%}
76
+ {% generation %}
77
+ {%- if reasoning_mode == "/think" -%}
78
+ {{ "<|im_start|>assistant\n" + content.lstrip("\n") + "<|im_end|>\n" }}
79
+ {%- else -%}
80
+ {{ "<|im_start|>assistant\n" + "<think>\n\n</think>\n" + content.lstrip("\n") + "<|im_end|>\n" }}
81
+ {%- endif -%}
82
+ {% endgeneration %}
83
+ {%- elif message.role == "tool" -%}
84
+ {{ "<|im_start|>" + "user\n" + content + "<|im_end|>\n" }}
85
+ {%- endif -%}
86
+ {%- endfor -%}
87
+ {# ───── generation prompt ───── #}
88
+ {%- if add_generation_prompt -%}
89
+ {%- if reasoning_mode == "/think" -%}
90
+ {{ "<|im_start|>assistant\n" }}
91
+ {%- else -%}
92
+ {{ "<|im_start|>assistant\n" + "<think>\n\n</think>\n" }}
93
+ {%- endif -%}
94
+ {%- endif -%}
checkpoint-660/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM3-3B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM3-3B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.16.0
checkpoint-660/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM3-3B",
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": 16,
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": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "k_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "o_proj",
32
+ "down_proj",
33
+ "q_proj",
34
+ "gate_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_qalora": false,
40
+ "use_rslora": false
41
+ }
checkpoint-660/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db3f4ec07af778ae153eb7539140ea1ecd76e428fab32091e57a857202be1e8
3
+ size 60523464
checkpoint-660/chat_template.jinja ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# ───── defaults ───── #}
2
+ {%- if enable_thinking is not defined -%}
3
+ {%- set enable_thinking = true -%}
4
+ {%- endif -%}
5
+
6
+ {# ───── reasoning mode ───── #}
7
+ {%- if enable_thinking -%}
8
+ {%- set reasoning_mode = "/think" -%}
9
+ {%- else -%}
10
+ {%- set reasoning_mode = "/no_think" -%}
11
+ {%- endif -%}
12
+
13
+ {# ───── header (system message) ───── #}
14
+ {{- "<|im_start|>system\n" -}}
15
+
16
+ {%- if messages[0].role == "system" -%}
17
+ {%- set system_message = messages[0].content -%}
18
+ {%- if "/no_think" in system_message -%}
19
+ {%- set reasoning_mode = "/no_think" -%}
20
+ {%- elif "/think" in system_message -%}
21
+ {%- set reasoning_mode = "/think" -%}
22
+ {%- endif -%}
23
+ {%- set custom_instructions = system_message.replace("/no_think", "").replace("/think", "").rstrip() -%}
24
+ {%- endif -%}
25
+
26
+ {%- if "/system_override" in system_message -%}
27
+ {{- custom_instructions.replace("/system_override", "").rstrip() -}}
28
+ {{- "<|im_end|>\n" -}}
29
+ {%- else -%}
30
+ {{- "## Metadata\n\n" -}}
31
+ {{- "Knowledge Cutoff Date: June 2025\n" -}}
32
+ {%- set today = strftime_now("%d %B %Y") -%}
33
+ {{- "Today Date: " ~ today ~ "\n" -}}
34
+ {{- "Reasoning Mode: " + reasoning_mode + "\n\n" -}}
35
+
36
+ {{- "## Custom Instructions\n\n" -}}
37
+ {%- if custom_instructions -%}
38
+ {{- custom_instructions + "\n\n" -}}
39
+ {%- elif reasoning_mode == "/think" -%}
40
+ {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: <think> Thought section </think> Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion.\n\n" -}}
41
+ {%- else -%}
42
+ {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face.\n\n" -}}
43
+ {%- endif -%}
44
+
45
+ {%- if xml_tools or python_tools or tools -%}
46
+ {{- "### Tools\n\n" -}}
47
+ {%- if xml_tools or tools -%}
48
+ {%- if tools -%}
49
+ {%- set xml_tools = tools -%}
50
+ {%- endif -%}
51
+ {%- set ns = namespace(xml_tool_string="You may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n") -%}
52
+ {%- for tool in xml_tools[:] -%} {# The slicing makes sure that xml_tools is a list #}
53
+ {%- set ns.xml_tool_string = ns.xml_tool_string ~ (tool | string) ~ "\n" -%}
54
+ {%- endfor -%}
55
+ {%- set xml_tool_string = ns.xml_tool_string + "</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>" -%}
56
+ {{- xml_tool_string -}}
57
+ {%- endif -%}
58
+ {%- if python_tools -%}
59
+ {%- set ns = namespace(python_tool_string="When you send a message containing Python code between '<code>' and '</code>' tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output to continued reasoning in an agentic loop.\n\nYou can use the following tools in your python code like regular functions:\n<tools>\n") -%}
60
+ {%- for tool in python_tools[:] -%} {# The slicing makes sure that python_tools is a list #}
61
+ {%- set ns.python_tool_string = ns.python_tool_string ~ (tool | string) ~ "\n" -%}
62
+ {%- endfor -%}
63
+ {%- set python_tool_string = ns.python_tool_string + "</tools>\n\nThe state persists between code executions: so variables that you define in one step are still available thereafter." -%}
64
+ {{- python_tool_string -}}
65
+ {%- endif -%}
66
+ {{- "\n\n" -}}
67
+ {{- "<|im_end|>\n" -}}
68
+ {%- endif -%}
69
+ {%- endif -%}
70
+ {# ───── main loop ───── #}
71
+ {%- for message in messages -%}
72
+ {%- set content = message.content if message.content is string else "" -%}
73
+ {%- if message.role == "user" -%}
74
+ {{ "<|im_start|>" + message.role + "\n" + content + "<|im_end|>\n" }}
75
+ {%- elif message.role == "assistant" -%}
76
+ {% generation %}
77
+ {%- if reasoning_mode == "/think" -%}
78
+ {{ "<|im_start|>assistant\n" + content.lstrip("\n") + "<|im_end|>\n" }}
79
+ {%- else -%}
80
+ {{ "<|im_start|>assistant\n" + "<think>\n\n</think>\n" + content.lstrip("\n") + "<|im_end|>\n" }}
81
+ {%- endif -%}
82
+ {% endgeneration %}
83
+ {%- elif message.role == "tool" -%}
84
+ {{ "<|im_start|>" + "user\n" + content + "<|im_end|>\n" }}
85
+ {%- endif -%}
86
+ {%- endfor -%}
87
+ {# ───── generation prompt ───── #}
88
+ {%- if add_generation_prompt -%}
89
+ {%- if reasoning_mode == "/think" -%}
90
+ {{ "<|im_start|>assistant\n" }}
91
+ {%- else -%}
92
+ {{ "<|im_start|>assistant\n" + "<think>\n\n</think>\n" }}
93
+ {%- endif -%}
94
+ {%- endif -%}
checkpoint-660/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aade52639963b04c8415d6dbd38c79b2b4bb115d0359097a6abd2b302ab6645
3
+ size 121324555
checkpoint-660/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53538b67fc8658d85f3bae341f21061961843a7ee32995c942b7f9de93f80df8
3
+ size 14391
checkpoint-660/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3d5d4bca1c24a5c187613724df652b6fcd83aa3fc7cdf21bb8a2faf66ab878
3
+ size 1465
checkpoint-660/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|im_end|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-660/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea5a8ce6451543cb0af4d08ccae7e2187ad41a68c571706a34ddf33b89add59
3
+ size 17208917
checkpoint-660/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<think>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "</think>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|im_start|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|im_end|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<tool_response>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<tool_call>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</tool_call>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<code>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</code>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": null,
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|im_end|>",
2055
+ "extra_special_tokens": {},
2056
+ "fast": false,
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|im_end|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-660/trainer_state.json ADDED
@@ -0,0 +1,2344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 9.853932584269662,
6
+ "eval_steps": 500,
7
+ "global_step": 660,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0299625468164794,
14
+ "grad_norm": 3.7318975925445557,
15
+ "learning_rate": 5e-06,
16
+ "loss": 1.6973,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.0599250936329588,
21
+ "grad_norm": 3.4212851524353027,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 1.6821,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.0898876404494382,
28
+ "grad_norm": 2.5065758228302,
29
+ "learning_rate": 2.5e-05,
30
+ "loss": 1.4689,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.1198501872659176,
35
+ "grad_norm": 2.081493854522705,
36
+ "learning_rate": 3.5e-05,
37
+ "loss": 1.411,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.149812734082397,
42
+ "grad_norm": 2.0012290477752686,
43
+ "learning_rate": 4.5e-05,
44
+ "loss": 1.1681,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.1797752808988764,
49
+ "grad_norm": 1.9056272506713867,
50
+ "learning_rate": 4.992424242424243e-05,
51
+ "loss": 0.9463,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.20973782771535582,
56
+ "grad_norm": 2.0275352001190186,
57
+ "learning_rate": 4.9772727272727275e-05,
58
+ "loss": 0.8338,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.2397003745318352,
63
+ "grad_norm": 1.6332467794418335,
64
+ "learning_rate": 4.962121212121213e-05,
65
+ "loss": 0.6327,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.2696629213483146,
70
+ "grad_norm": 1.3445727825164795,
71
+ "learning_rate": 4.946969696969697e-05,
72
+ "loss": 0.4954,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.299625468164794,
77
+ "grad_norm": 0.9636670351028442,
78
+ "learning_rate": 4.931818181818182e-05,
79
+ "loss": 0.3803,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.3295880149812734,
84
+ "grad_norm": 0.4598312973976135,
85
+ "learning_rate": 4.9166666666666665e-05,
86
+ "loss": 0.3355,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.3595505617977528,
91
+ "grad_norm": 0.6035417318344116,
92
+ "learning_rate": 4.901515151515152e-05,
93
+ "loss": 0.3144,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.3895131086142322,
98
+ "grad_norm": 0.48754820227622986,
99
+ "learning_rate": 4.886363636363637e-05,
100
+ "loss": 0.2577,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.41947565543071164,
105
+ "grad_norm": 0.5186039805412292,
106
+ "learning_rate": 4.8712121212121216e-05,
107
+ "loss": 0.2478,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.449438202247191,
112
+ "grad_norm": 0.6087205410003662,
113
+ "learning_rate": 4.856060606060606e-05,
114
+ "loss": 0.2272,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.4794007490636704,
119
+ "grad_norm": 0.8594069480895996,
120
+ "learning_rate": 4.840909090909091e-05,
121
+ "loss": 0.1992,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.5093632958801498,
126
+ "grad_norm": 0.6205722093582153,
127
+ "learning_rate": 4.825757575757576e-05,
128
+ "loss": 0.1631,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.5393258426966292,
133
+ "grad_norm": 0.4654604196548462,
134
+ "learning_rate": 4.810606060606061e-05,
135
+ "loss": 0.1629,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.5692883895131086,
140
+ "grad_norm": 0.9451954364776611,
141
+ "learning_rate": 4.795454545454546e-05,
142
+ "loss": 0.1814,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.599250936329588,
147
+ "grad_norm": 0.4229886829853058,
148
+ "learning_rate": 4.7803030303030304e-05,
149
+ "loss": 0.14,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.6292134831460674,
154
+ "grad_norm": 0.43104586005210876,
155
+ "learning_rate": 4.765151515151515e-05,
156
+ "loss": 0.1495,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.6591760299625468,
161
+ "grad_norm": 0.48881301283836365,
162
+ "learning_rate": 4.75e-05,
163
+ "loss": 0.0983,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.6891385767790262,
168
+ "grad_norm": 0.3992343544960022,
169
+ "learning_rate": 4.7348484848484855e-05,
170
+ "loss": 0.0893,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.7191011235955056,
175
+ "grad_norm": 0.4501804709434509,
176
+ "learning_rate": 4.71969696969697e-05,
177
+ "loss": 0.092,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.7490636704119851,
182
+ "grad_norm": 0.576210081577301,
183
+ "learning_rate": 4.704545454545455e-05,
184
+ "loss": 0.0741,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.7790262172284644,
189
+ "grad_norm": 0.4083947241306305,
190
+ "learning_rate": 4.689393939393939e-05,
191
+ "loss": 0.0572,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.8089887640449438,
196
+ "grad_norm": 0.5864295363426208,
197
+ "learning_rate": 4.6742424242424245e-05,
198
+ "loss": 0.0769,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.8389513108614233,
203
+ "grad_norm": 0.7252892851829529,
204
+ "learning_rate": 4.659090909090909e-05,
205
+ "loss": 0.0619,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.8689138576779026,
210
+ "grad_norm": 0.42146825790405273,
211
+ "learning_rate": 4.6439393939393944e-05,
212
+ "loss": 0.0384,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.898876404494382,
217
+ "grad_norm": 0.593726634979248,
218
+ "learning_rate": 4.628787878787879e-05,
219
+ "loss": 0.052,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.9288389513108615,
224
+ "grad_norm": 0.5652066469192505,
225
+ "learning_rate": 4.6136363636363635e-05,
226
+ "loss": 0.0468,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.9588014981273408,
231
+ "grad_norm": 0.28684931993484497,
232
+ "learning_rate": 4.598484848484849e-05,
233
+ "loss": 0.0295,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.9887640449438202,
238
+ "grad_norm": 0.2981000244617462,
239
+ "learning_rate": 4.5833333333333334e-05,
240
+ "loss": 0.032,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 1.0149812734082397,
245
+ "grad_norm": 0.48514777421951294,
246
+ "learning_rate": 4.5681818181818186e-05,
247
+ "loss": 0.0506,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 1.0449438202247192,
252
+ "grad_norm": 0.32234543561935425,
253
+ "learning_rate": 4.553030303030303e-05,
254
+ "loss": 0.0318,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 1.0749063670411985,
259
+ "grad_norm": 0.38080576062202454,
260
+ "learning_rate": 4.5378787878787885e-05,
261
+ "loss": 0.0258,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 1.104868913857678,
266
+ "grad_norm": 0.3635996878147125,
267
+ "learning_rate": 4.522727272727273e-05,
268
+ "loss": 0.037,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 1.1348314606741572,
273
+ "grad_norm": 0.42449885606765747,
274
+ "learning_rate": 4.5075757575757577e-05,
275
+ "loss": 0.0393,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 1.1647940074906367,
280
+ "grad_norm": 0.5858486890792847,
281
+ "learning_rate": 4.492424242424242e-05,
282
+ "loss": 0.0207,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 1.1947565543071161,
287
+ "grad_norm": 0.24009667336940765,
288
+ "learning_rate": 4.4772727272727275e-05,
289
+ "loss": 0.0189,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 1.2247191011235956,
294
+ "grad_norm": 0.21841216087341309,
295
+ "learning_rate": 4.462121212121213e-05,
296
+ "loss": 0.0173,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 1.2546816479400749,
301
+ "grad_norm": 0.34650227427482605,
302
+ "learning_rate": 4.4469696969696973e-05,
303
+ "loss": 0.0311,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 1.2846441947565543,
308
+ "grad_norm": 0.3726528584957123,
309
+ "learning_rate": 4.431818181818182e-05,
310
+ "loss": 0.0272,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 1.3146067415730336,
315
+ "grad_norm": 0.2907704710960388,
316
+ "learning_rate": 4.4166666666666665e-05,
317
+ "loss": 0.0235,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 1.344569288389513,
322
+ "grad_norm": 0.21228495240211487,
323
+ "learning_rate": 4.401515151515152e-05,
324
+ "loss": 0.0206,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 1.3745318352059925,
329
+ "grad_norm": 0.2763824462890625,
330
+ "learning_rate": 4.386363636363637e-05,
331
+ "loss": 0.0222,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 1.404494382022472,
336
+ "grad_norm": 0.2596808969974518,
337
+ "learning_rate": 4.3712121212121216e-05,
338
+ "loss": 0.0171,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 1.4344569288389513,
343
+ "grad_norm": 0.36683645844459534,
344
+ "learning_rate": 4.356060606060606e-05,
345
+ "loss": 0.0213,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 1.4644194756554307,
350
+ "grad_norm": 0.25381800532341003,
351
+ "learning_rate": 4.340909090909091e-05,
352
+ "loss": 0.0149,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 1.49438202247191,
357
+ "grad_norm": 0.4874545633792877,
358
+ "learning_rate": 4.325757575757576e-05,
359
+ "loss": 0.0235,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 1.5243445692883895,
364
+ "grad_norm": 0.35136911273002625,
365
+ "learning_rate": 4.3106060606060606e-05,
366
+ "loss": 0.0186,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 1.554307116104869,
371
+ "grad_norm": 0.3259860873222351,
372
+ "learning_rate": 4.295454545454546e-05,
373
+ "loss": 0.0228,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 1.5842696629213484,
378
+ "grad_norm": 0.24276824295520782,
379
+ "learning_rate": 4.2803030303030305e-05,
380
+ "loss": 0.0147,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 1.6142322097378277,
385
+ "grad_norm": 0.4493170976638794,
386
+ "learning_rate": 4.265151515151515e-05,
387
+ "loss": 0.0152,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 1.6441947565543071,
392
+ "grad_norm": 0.4474326968193054,
393
+ "learning_rate": 4.25e-05,
394
+ "loss": 0.0199,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 1.6741573033707864,
399
+ "grad_norm": 0.229719340801239,
400
+ "learning_rate": 4.234848484848485e-05,
401
+ "loss": 0.0166,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 1.7041198501872659,
406
+ "grad_norm": 0.2303067445755005,
407
+ "learning_rate": 4.21969696969697e-05,
408
+ "loss": 0.017,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 1.7340823970037453,
413
+ "grad_norm": 0.24925805628299713,
414
+ "learning_rate": 4.204545454545455e-05,
415
+ "loss": 0.0147,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 1.7640449438202248,
420
+ "grad_norm": 0.18361054360866547,
421
+ "learning_rate": 4.189393939393939e-05,
422
+ "loss": 0.0191,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 1.7940074906367043,
427
+ "grad_norm": 0.2936908006668091,
428
+ "learning_rate": 4.1742424242424246e-05,
429
+ "loss": 0.0189,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 1.8239700374531835,
434
+ "grad_norm": 0.2073887437582016,
435
+ "learning_rate": 4.159090909090909e-05,
436
+ "loss": 0.0171,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 1.8539325842696628,
441
+ "grad_norm": 0.3212382197380066,
442
+ "learning_rate": 4.143939393939394e-05,
443
+ "loss": 0.0204,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 1.8838951310861423,
448
+ "grad_norm": 0.1888497769832611,
449
+ "learning_rate": 4.128787878787879e-05,
450
+ "loss": 0.0201,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 1.9138576779026217,
455
+ "grad_norm": 0.18828518688678741,
456
+ "learning_rate": 4.113636363636364e-05,
457
+ "loss": 0.0179,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 1.9438202247191012,
462
+ "grad_norm": 0.22073791921138763,
463
+ "learning_rate": 4.098484848484849e-05,
464
+ "loss": 0.02,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 1.9737827715355807,
469
+ "grad_norm": 0.23251274228096008,
470
+ "learning_rate": 4.0833333333333334e-05,
471
+ "loss": 0.0184,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 2.0,
476
+ "grad_norm": 0.2079184651374817,
477
+ "learning_rate": 4.068181818181818e-05,
478
+ "loss": 0.0192,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 2.0299625468164795,
483
+ "grad_norm": 0.21343930065631866,
484
+ "learning_rate": 4.053030303030303e-05,
485
+ "loss": 0.0166,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 2.059925093632959,
490
+ "grad_norm": 0.2166517972946167,
491
+ "learning_rate": 4.0378787878787885e-05,
492
+ "loss": 0.0159,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 2.0898876404494384,
497
+ "grad_norm": 0.17601799964904785,
498
+ "learning_rate": 4.022727272727273e-05,
499
+ "loss": 0.0157,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 2.1198501872659175,
504
+ "grad_norm": 0.292283296585083,
505
+ "learning_rate": 4.007575757575758e-05,
506
+ "loss": 0.0214,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 2.149812734082397,
511
+ "grad_norm": 0.2258112132549286,
512
+ "learning_rate": 3.992424242424242e-05,
513
+ "loss": 0.0184,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 2.1797752808988764,
518
+ "grad_norm": 0.15815454721450806,
519
+ "learning_rate": 3.9772727272727275e-05,
520
+ "loss": 0.017,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 2.209737827715356,
525
+ "grad_norm": 0.26803699135780334,
526
+ "learning_rate": 3.962121212121213e-05,
527
+ "loss": 0.0182,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 2.2397003745318353,
532
+ "grad_norm": 0.2198362499475479,
533
+ "learning_rate": 3.9469696969696974e-05,
534
+ "loss": 0.0167,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 2.2696629213483144,
539
+ "grad_norm": 0.201346293091774,
540
+ "learning_rate": 3.931818181818182e-05,
541
+ "loss": 0.0161,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 2.299625468164794,
546
+ "grad_norm": 0.22819150984287262,
547
+ "learning_rate": 3.9166666666666665e-05,
548
+ "loss": 0.015,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 2.3295880149812733,
553
+ "grad_norm": 0.2712112069129944,
554
+ "learning_rate": 3.901515151515152e-05,
555
+ "loss": 0.0163,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 2.359550561797753,
560
+ "grad_norm": 0.19178956747055054,
561
+ "learning_rate": 3.8863636363636364e-05,
562
+ "loss": 0.0163,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 2.3895131086142323,
567
+ "grad_norm": 0.1914001852273941,
568
+ "learning_rate": 3.8712121212121217e-05,
569
+ "loss": 0.0168,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 2.4194756554307117,
574
+ "grad_norm": 0.1301780492067337,
575
+ "learning_rate": 3.856060606060606e-05,
576
+ "loss": 0.0151,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 2.449438202247191,
581
+ "grad_norm": 0.22975341975688934,
582
+ "learning_rate": 3.840909090909091e-05,
583
+ "loss": 0.0171,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 2.4794007490636703,
588
+ "grad_norm": 0.2856428623199463,
589
+ "learning_rate": 3.825757575757576e-05,
590
+ "loss": 0.0182,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 2.5093632958801497,
595
+ "grad_norm": 0.22180147469043732,
596
+ "learning_rate": 3.810606060606061e-05,
597
+ "loss": 0.0164,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 2.539325842696629,
602
+ "grad_norm": 0.18585917353630066,
603
+ "learning_rate": 3.795454545454545e-05,
604
+ "loss": 0.0175,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 2.5692883895131087,
609
+ "grad_norm": 0.21161819994449615,
610
+ "learning_rate": 3.7803030303030305e-05,
611
+ "loss": 0.0149,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 2.599250936329588,
616
+ "grad_norm": 0.14073120057582855,
617
+ "learning_rate": 3.765151515151516e-05,
618
+ "loss": 0.0143,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 2.629213483146067,
623
+ "grad_norm": 0.1988099217414856,
624
+ "learning_rate": 3.7500000000000003e-05,
625
+ "loss": 0.0155,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 2.6591760299625467,
630
+ "grad_norm": 0.17829206585884094,
631
+ "learning_rate": 3.734848484848485e-05,
632
+ "loss": 0.0172,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 2.689138576779026,
637
+ "grad_norm": 0.25729623436927795,
638
+ "learning_rate": 3.7196969696969695e-05,
639
+ "loss": 0.0161,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 2.7191011235955056,
644
+ "grad_norm": 0.15630777180194855,
645
+ "learning_rate": 3.704545454545455e-05,
646
+ "loss": 0.0161,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 2.749063670411985,
651
+ "grad_norm": 0.10787078738212585,
652
+ "learning_rate": 3.68939393939394e-05,
653
+ "loss": 0.0139,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 2.7790262172284645,
658
+ "grad_norm": 0.11183971166610718,
659
+ "learning_rate": 3.6742424242424246e-05,
660
+ "loss": 0.0142,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 2.808988764044944,
665
+ "grad_norm": 0.3003017008304596,
666
+ "learning_rate": 3.659090909090909e-05,
667
+ "loss": 0.0201,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 2.8389513108614235,
672
+ "grad_norm": 0.15837068855762482,
673
+ "learning_rate": 3.643939393939394e-05,
674
+ "loss": 0.014,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 2.8689138576779025,
679
+ "grad_norm": 0.15499652922153473,
680
+ "learning_rate": 3.628787878787879e-05,
681
+ "loss": 0.0166,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 2.898876404494382,
686
+ "grad_norm": 0.166601300239563,
687
+ "learning_rate": 3.613636363636364e-05,
688
+ "loss": 0.0136,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 2.9288389513108615,
693
+ "grad_norm": 0.23306916654109955,
694
+ "learning_rate": 3.598484848484849e-05,
695
+ "loss": 0.0145,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 2.958801498127341,
700
+ "grad_norm": 0.23148281872272491,
701
+ "learning_rate": 3.5833333333333335e-05,
702
+ "loss": 0.0166,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 2.98876404494382,
707
+ "grad_norm": 0.2514810562133789,
708
+ "learning_rate": 3.568181818181818e-05,
709
+ "loss": 0.0197,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 3.0149812734082397,
714
+ "grad_norm": 0.15844318270683289,
715
+ "learning_rate": 3.553030303030303e-05,
716
+ "loss": 0.0127,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 3.044943820224719,
721
+ "grad_norm": 0.15709055960178375,
722
+ "learning_rate": 3.537878787878788e-05,
723
+ "loss": 0.0144,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 3.0749063670411987,
728
+ "grad_norm": 0.21092790365219116,
729
+ "learning_rate": 3.522727272727273e-05,
730
+ "loss": 0.0174,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 3.1048689138576777,
735
+ "grad_norm": 0.22406940162181854,
736
+ "learning_rate": 3.507575757575758e-05,
737
+ "loss": 0.0151,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 3.134831460674157,
742
+ "grad_norm": 0.17414535582065582,
743
+ "learning_rate": 3.492424242424242e-05,
744
+ "loss": 0.0159,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 3.1647940074906367,
749
+ "grad_norm": 0.1722804456949234,
750
+ "learning_rate": 3.4772727272727276e-05,
751
+ "loss": 0.0146,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 3.194756554307116,
756
+ "grad_norm": 0.26471957564353943,
757
+ "learning_rate": 3.462121212121212e-05,
758
+ "loss": 0.0157,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 3.2247191011235956,
763
+ "grad_norm": 0.13862167298793793,
764
+ "learning_rate": 3.4469696969696974e-05,
765
+ "loss": 0.0137,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 3.254681647940075,
770
+ "grad_norm": 0.24047966301441193,
771
+ "learning_rate": 3.431818181818182e-05,
772
+ "loss": 0.017,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 3.284644194756554,
777
+ "grad_norm": 0.1237376257777214,
778
+ "learning_rate": 3.4166666666666666e-05,
779
+ "loss": 0.0151,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 3.3146067415730336,
784
+ "grad_norm": 0.15304620563983917,
785
+ "learning_rate": 3.401515151515152e-05,
786
+ "loss": 0.0155,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 3.344569288389513,
791
+ "grad_norm": 0.15872317552566528,
792
+ "learning_rate": 3.3863636363636364e-05,
793
+ "loss": 0.0147,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 3.3745318352059925,
798
+ "grad_norm": 0.18952298164367676,
799
+ "learning_rate": 3.371212121212121e-05,
800
+ "loss": 0.0154,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 3.404494382022472,
805
+ "grad_norm": 0.21287596225738525,
806
+ "learning_rate": 3.356060606060606e-05,
807
+ "loss": 0.0166,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 3.4344569288389515,
812
+ "grad_norm": 0.19477762281894684,
813
+ "learning_rate": 3.3409090909090915e-05,
814
+ "loss": 0.0167,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 3.464419475655431,
819
+ "grad_norm": 0.1801714450120926,
820
+ "learning_rate": 3.325757575757576e-05,
821
+ "loss": 0.0145,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 3.49438202247191,
826
+ "grad_norm": 0.14180026948451996,
827
+ "learning_rate": 3.310606060606061e-05,
828
+ "loss": 0.0138,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 3.5243445692883895,
833
+ "grad_norm": 0.21012850105762482,
834
+ "learning_rate": 3.295454545454545e-05,
835
+ "loss": 0.0165,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 3.554307116104869,
840
+ "grad_norm": 0.1273059993982315,
841
+ "learning_rate": 3.2803030303030305e-05,
842
+ "loss": 0.0148,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 3.5842696629213484,
847
+ "grad_norm": 0.13745197653770447,
848
+ "learning_rate": 3.265151515151516e-05,
849
+ "loss": 0.0137,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 3.6142322097378274,
854
+ "grad_norm": 0.19960223138332367,
855
+ "learning_rate": 3.2500000000000004e-05,
856
+ "loss": 0.0178,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 3.644194756554307,
861
+ "grad_norm": 0.21453413367271423,
862
+ "learning_rate": 3.234848484848485e-05,
863
+ "loss": 0.0156,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 3.6741573033707864,
868
+ "grad_norm": 0.17091749608516693,
869
+ "learning_rate": 3.2196969696969696e-05,
870
+ "loss": 0.0157,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 3.704119850187266,
875
+ "grad_norm": 0.15684160590171814,
876
+ "learning_rate": 3.204545454545455e-05,
877
+ "loss": 0.0148,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 3.7340823970037453,
882
+ "grad_norm": 0.15323583781719208,
883
+ "learning_rate": 3.18939393939394e-05,
884
+ "loss": 0.015,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 3.764044943820225,
889
+ "grad_norm": 0.13383668661117554,
890
+ "learning_rate": 3.174242424242425e-05,
891
+ "loss": 0.0154,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 3.7940074906367043,
896
+ "grad_norm": 0.15054528415203094,
897
+ "learning_rate": 3.159090909090909e-05,
898
+ "loss": 0.0153,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 3.8239700374531838,
903
+ "grad_norm": 0.10618451982736588,
904
+ "learning_rate": 3.143939393939394e-05,
905
+ "loss": 0.0131,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 3.853932584269663,
910
+ "grad_norm": 0.20882849395275116,
911
+ "learning_rate": 3.128787878787879e-05,
912
+ "loss": 0.019,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 3.8838951310861423,
917
+ "grad_norm": 0.19676630198955536,
918
+ "learning_rate": 3.113636363636364e-05,
919
+ "loss": 0.0164,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 3.9138576779026217,
924
+ "grad_norm": 0.10724353790283203,
925
+ "learning_rate": 3.098484848484849e-05,
926
+ "loss": 0.0145,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 3.943820224719101,
931
+ "grad_norm": 0.11003574728965759,
932
+ "learning_rate": 3.0833333333333335e-05,
933
+ "loss": 0.0153,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 3.9737827715355807,
938
+ "grad_norm": 0.10973632335662842,
939
+ "learning_rate": 3.068181818181818e-05,
940
+ "loss": 0.0131,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 4.0,
945
+ "grad_norm": 0.21611331403255463,
946
+ "learning_rate": 3.0530303030303034e-05,
947
+ "loss": 0.0184,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 4.0299625468164795,
952
+ "grad_norm": 0.11275507509708405,
953
+ "learning_rate": 3.037878787878788e-05,
954
+ "loss": 0.0159,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 4.059925093632959,
959
+ "grad_norm": 0.182546004652977,
960
+ "learning_rate": 3.0227272727272725e-05,
961
+ "loss": 0.0143,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 4.089887640449438,
966
+ "grad_norm": 0.11307963728904724,
967
+ "learning_rate": 3.0075757575757578e-05,
968
+ "loss": 0.014,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 4.119850187265918,
973
+ "grad_norm": 0.13171932101249695,
974
+ "learning_rate": 2.9924242424242427e-05,
975
+ "loss": 0.0159,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 4.149812734082397,
980
+ "grad_norm": 0.2185821682214737,
981
+ "learning_rate": 2.9772727272727273e-05,
982
+ "loss": 0.0158,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 4.179775280898877,
987
+ "grad_norm": 0.1575690507888794,
988
+ "learning_rate": 2.9621212121212122e-05,
989
+ "loss": 0.0168,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 4.209737827715355,
994
+ "grad_norm": 0.1727718561887741,
995
+ "learning_rate": 2.9469696969696968e-05,
996
+ "loss": 0.0154,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 4.239700374531835,
1001
+ "grad_norm": 0.13435468077659607,
1002
+ "learning_rate": 2.9318181818181817e-05,
1003
+ "loss": 0.0165,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 4.269662921348314,
1008
+ "grad_norm": 0.15063047409057617,
1009
+ "learning_rate": 2.916666666666667e-05,
1010
+ "loss": 0.0173,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 4.299625468164794,
1015
+ "grad_norm": 0.12659698724746704,
1016
+ "learning_rate": 2.901515151515152e-05,
1017
+ "loss": 0.0152,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 4.329588014981273,
1022
+ "grad_norm": 0.19473259150981903,
1023
+ "learning_rate": 2.8863636363636365e-05,
1024
+ "loss": 0.016,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 4.359550561797753,
1029
+ "grad_norm": 0.1952139437198639,
1030
+ "learning_rate": 2.8712121212121214e-05,
1031
+ "loss": 0.0164,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 4.389513108614232,
1036
+ "grad_norm": 0.15907561779022217,
1037
+ "learning_rate": 2.856060606060606e-05,
1038
+ "loss": 0.0126,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 4.419475655430712,
1043
+ "grad_norm": 0.197600319981575,
1044
+ "learning_rate": 2.8409090909090912e-05,
1045
+ "loss": 0.0166,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 4.449438202247191,
1050
+ "grad_norm": 0.09373123943805695,
1051
+ "learning_rate": 2.825757575757576e-05,
1052
+ "loss": 0.016,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 4.479400749063671,
1057
+ "grad_norm": 0.14290565252304077,
1058
+ "learning_rate": 2.8106060606060607e-05,
1059
+ "loss": 0.0172,
1060
+ "step": 300
1061
+ },
1062
+ {
1063
+ "epoch": 4.50936329588015,
1064
+ "grad_norm": 0.1223093792796135,
1065
+ "learning_rate": 2.7954545454545457e-05,
1066
+ "loss": 0.0157,
1067
+ "step": 302
1068
+ },
1069
+ {
1070
+ "epoch": 4.539325842696629,
1071
+ "grad_norm": 0.11388926208019257,
1072
+ "learning_rate": 2.7803030303030303e-05,
1073
+ "loss": 0.015,
1074
+ "step": 304
1075
+ },
1076
+ {
1077
+ "epoch": 4.569288389513108,
1078
+ "grad_norm": 0.10850539058446884,
1079
+ "learning_rate": 2.7651515151515152e-05,
1080
+ "loss": 0.0166,
1081
+ "step": 306
1082
+ },
1083
+ {
1084
+ "epoch": 4.599250936329588,
1085
+ "grad_norm": 0.13963742554187775,
1086
+ "learning_rate": 2.7500000000000004e-05,
1087
+ "loss": 0.0158,
1088
+ "step": 308
1089
+ },
1090
+ {
1091
+ "epoch": 4.629213483146067,
1092
+ "grad_norm": 0.15747179090976715,
1093
+ "learning_rate": 2.734848484848485e-05,
1094
+ "loss": 0.0144,
1095
+ "step": 310
1096
+ },
1097
+ {
1098
+ "epoch": 4.659176029962547,
1099
+ "grad_norm": 0.1513000726699829,
1100
+ "learning_rate": 2.71969696969697e-05,
1101
+ "loss": 0.0164,
1102
+ "step": 312
1103
+ },
1104
+ {
1105
+ "epoch": 4.689138576779026,
1106
+ "grad_norm": 0.14622750878334045,
1107
+ "learning_rate": 2.7045454545454545e-05,
1108
+ "loss": 0.016,
1109
+ "step": 314
1110
+ },
1111
+ {
1112
+ "epoch": 4.719101123595506,
1113
+ "grad_norm": 0.1300605684518814,
1114
+ "learning_rate": 2.6893939393939394e-05,
1115
+ "loss": 0.0158,
1116
+ "step": 316
1117
+ },
1118
+ {
1119
+ "epoch": 4.749063670411985,
1120
+ "grad_norm": 0.1521446704864502,
1121
+ "learning_rate": 2.674242424242424e-05,
1122
+ "loss": 0.0139,
1123
+ "step": 318
1124
+ },
1125
+ {
1126
+ "epoch": 4.7790262172284645,
1127
+ "grad_norm": 0.13343091309070587,
1128
+ "learning_rate": 2.6590909090909093e-05,
1129
+ "loss": 0.0141,
1130
+ "step": 320
1131
+ },
1132
+ {
1133
+ "epoch": 4.808988764044944,
1134
+ "grad_norm": 0.1171831339597702,
1135
+ "learning_rate": 2.6439393939393942e-05,
1136
+ "loss": 0.0129,
1137
+ "step": 322
1138
+ },
1139
+ {
1140
+ "epoch": 4.8389513108614235,
1141
+ "grad_norm": 0.10482454299926758,
1142
+ "learning_rate": 2.6287878787878788e-05,
1143
+ "loss": 0.0115,
1144
+ "step": 324
1145
+ },
1146
+ {
1147
+ "epoch": 4.868913857677903,
1148
+ "grad_norm": 0.13335193693637848,
1149
+ "learning_rate": 2.6136363636363637e-05,
1150
+ "loss": 0.0155,
1151
+ "step": 326
1152
+ },
1153
+ {
1154
+ "epoch": 4.898876404494382,
1155
+ "grad_norm": 0.1327083259820938,
1156
+ "learning_rate": 2.5984848484848483e-05,
1157
+ "loss": 0.0154,
1158
+ "step": 328
1159
+ },
1160
+ {
1161
+ "epoch": 4.928838951310862,
1162
+ "grad_norm": 0.15616530179977417,
1163
+ "learning_rate": 2.5833333333333336e-05,
1164
+ "loss": 0.0186,
1165
+ "step": 330
1166
+ },
1167
+ {
1168
+ "epoch": 4.9588014981273405,
1169
+ "grad_norm": 0.1196502074599266,
1170
+ "learning_rate": 2.5681818181818185e-05,
1171
+ "loss": 0.0151,
1172
+ "step": 332
1173
+ },
1174
+ {
1175
+ "epoch": 4.98876404494382,
1176
+ "grad_norm": 0.11737090349197388,
1177
+ "learning_rate": 2.553030303030303e-05,
1178
+ "loss": 0.013,
1179
+ "step": 334
1180
+ },
1181
+ {
1182
+ "epoch": 5.01498127340824,
1183
+ "grad_norm": 0.14445465803146362,
1184
+ "learning_rate": 2.537878787878788e-05,
1185
+ "loss": 0.0134,
1186
+ "step": 336
1187
+ },
1188
+ {
1189
+ "epoch": 5.044943820224719,
1190
+ "grad_norm": 0.10734406858682632,
1191
+ "learning_rate": 2.5227272727272726e-05,
1192
+ "loss": 0.0138,
1193
+ "step": 338
1194
+ },
1195
+ {
1196
+ "epoch": 5.074906367041199,
1197
+ "grad_norm": 0.11528757214546204,
1198
+ "learning_rate": 2.5075757575757575e-05,
1199
+ "loss": 0.013,
1200
+ "step": 340
1201
+ },
1202
+ {
1203
+ "epoch": 5.104868913857678,
1204
+ "grad_norm": 0.17952029407024384,
1205
+ "learning_rate": 2.4924242424242424e-05,
1206
+ "loss": 0.0152,
1207
+ "step": 342
1208
+ },
1209
+ {
1210
+ "epoch": 5.134831460674158,
1211
+ "grad_norm": 0.12444639205932617,
1212
+ "learning_rate": 2.4772727272727277e-05,
1213
+ "loss": 0.0148,
1214
+ "step": 344
1215
+ },
1216
+ {
1217
+ "epoch": 5.164794007490637,
1218
+ "grad_norm": 0.12819650769233704,
1219
+ "learning_rate": 2.4621212121212123e-05,
1220
+ "loss": 0.0146,
1221
+ "step": 346
1222
+ },
1223
+ {
1224
+ "epoch": 5.194756554307116,
1225
+ "grad_norm": 0.13396833837032318,
1226
+ "learning_rate": 2.4469696969696972e-05,
1227
+ "loss": 0.0175,
1228
+ "step": 348
1229
+ },
1230
+ {
1231
+ "epoch": 5.224719101123595,
1232
+ "grad_norm": 0.1286836415529251,
1233
+ "learning_rate": 2.431818181818182e-05,
1234
+ "loss": 0.0144,
1235
+ "step": 350
1236
+ },
1237
+ {
1238
+ "epoch": 5.254681647940075,
1239
+ "grad_norm": 0.12591804563999176,
1240
+ "learning_rate": 2.4166666666666667e-05,
1241
+ "loss": 0.0167,
1242
+ "step": 352
1243
+ },
1244
+ {
1245
+ "epoch": 5.284644194756554,
1246
+ "grad_norm": 0.12226350605487823,
1247
+ "learning_rate": 2.4015151515151516e-05,
1248
+ "loss": 0.0133,
1249
+ "step": 354
1250
+ },
1251
+ {
1252
+ "epoch": 5.314606741573034,
1253
+ "grad_norm": 0.10504593700170517,
1254
+ "learning_rate": 2.3863636363636365e-05,
1255
+ "loss": 0.0135,
1256
+ "step": 356
1257
+ },
1258
+ {
1259
+ "epoch": 5.344569288389513,
1260
+ "grad_norm": 0.1078866645693779,
1261
+ "learning_rate": 2.3712121212121214e-05,
1262
+ "loss": 0.0147,
1263
+ "step": 358
1264
+ },
1265
+ {
1266
+ "epoch": 5.3745318352059925,
1267
+ "grad_norm": 0.28363969922065735,
1268
+ "learning_rate": 2.356060606060606e-05,
1269
+ "loss": 0.0156,
1270
+ "step": 360
1271
+ },
1272
+ {
1273
+ "epoch": 5.404494382022472,
1274
+ "grad_norm": 0.1177087053656578,
1275
+ "learning_rate": 2.340909090909091e-05,
1276
+ "loss": 0.0138,
1277
+ "step": 362
1278
+ },
1279
+ {
1280
+ "epoch": 5.4344569288389515,
1281
+ "grad_norm": 0.16584421694278717,
1282
+ "learning_rate": 2.325757575757576e-05,
1283
+ "loss": 0.0179,
1284
+ "step": 364
1285
+ },
1286
+ {
1287
+ "epoch": 5.464419475655431,
1288
+ "grad_norm": 0.10715971887111664,
1289
+ "learning_rate": 2.3106060606060605e-05,
1290
+ "loss": 0.0144,
1291
+ "step": 366
1292
+ },
1293
+ {
1294
+ "epoch": 5.49438202247191,
1295
+ "grad_norm": 0.11904123425483704,
1296
+ "learning_rate": 2.2954545454545457e-05,
1297
+ "loss": 0.0133,
1298
+ "step": 368
1299
+ },
1300
+ {
1301
+ "epoch": 5.52434456928839,
1302
+ "grad_norm": 0.19020037353038788,
1303
+ "learning_rate": 2.2803030303030303e-05,
1304
+ "loss": 0.0178,
1305
+ "step": 370
1306
+ },
1307
+ {
1308
+ "epoch": 5.554307116104869,
1309
+ "grad_norm": 0.1367521733045578,
1310
+ "learning_rate": 2.2651515151515152e-05,
1311
+ "loss": 0.0155,
1312
+ "step": 372
1313
+ },
1314
+ {
1315
+ "epoch": 5.584269662921348,
1316
+ "grad_norm": 0.12585178017616272,
1317
+ "learning_rate": 2.25e-05,
1318
+ "loss": 0.0143,
1319
+ "step": 374
1320
+ },
1321
+ {
1322
+ "epoch": 5.614232209737827,
1323
+ "grad_norm": 0.20084144175052643,
1324
+ "learning_rate": 2.234848484848485e-05,
1325
+ "loss": 0.0178,
1326
+ "step": 376
1327
+ },
1328
+ {
1329
+ "epoch": 5.644194756554307,
1330
+ "grad_norm": 0.12197957187891006,
1331
+ "learning_rate": 2.21969696969697e-05,
1332
+ "loss": 0.0142,
1333
+ "step": 378
1334
+ },
1335
+ {
1336
+ "epoch": 5.674157303370786,
1337
+ "grad_norm": 0.11580586433410645,
1338
+ "learning_rate": 2.2045454545454546e-05,
1339
+ "loss": 0.0158,
1340
+ "step": 380
1341
+ },
1342
+ {
1343
+ "epoch": 5.704119850187266,
1344
+ "grad_norm": 0.1596754640340805,
1345
+ "learning_rate": 2.1893939393939395e-05,
1346
+ "loss": 0.0153,
1347
+ "step": 382
1348
+ },
1349
+ {
1350
+ "epoch": 5.734082397003745,
1351
+ "grad_norm": 0.11820989102125168,
1352
+ "learning_rate": 2.1742424242424244e-05,
1353
+ "loss": 0.0133,
1354
+ "step": 384
1355
+ },
1356
+ {
1357
+ "epoch": 5.764044943820225,
1358
+ "grad_norm": 0.1528993546962738,
1359
+ "learning_rate": 2.1590909090909093e-05,
1360
+ "loss": 0.0131,
1361
+ "step": 386
1362
+ },
1363
+ {
1364
+ "epoch": 5.794007490636704,
1365
+ "grad_norm": 0.15335053205490112,
1366
+ "learning_rate": 2.143939393939394e-05,
1367
+ "loss": 0.0188,
1368
+ "step": 388
1369
+ },
1370
+ {
1371
+ "epoch": 5.823970037453184,
1372
+ "grad_norm": 0.13823996484279633,
1373
+ "learning_rate": 2.128787878787879e-05,
1374
+ "loss": 0.0156,
1375
+ "step": 390
1376
+ },
1377
+ {
1378
+ "epoch": 5.853932584269663,
1379
+ "grad_norm": 0.11527912318706512,
1380
+ "learning_rate": 2.1136363636363638e-05,
1381
+ "loss": 0.0156,
1382
+ "step": 392
1383
+ },
1384
+ {
1385
+ "epoch": 5.883895131086143,
1386
+ "grad_norm": 0.09302780777215958,
1387
+ "learning_rate": 2.0984848484848483e-05,
1388
+ "loss": 0.0144,
1389
+ "step": 394
1390
+ },
1391
+ {
1392
+ "epoch": 5.913857677902621,
1393
+ "grad_norm": 0.1214398592710495,
1394
+ "learning_rate": 2.0833333333333336e-05,
1395
+ "loss": 0.0137,
1396
+ "step": 396
1397
+ },
1398
+ {
1399
+ "epoch": 5.943820224719101,
1400
+ "grad_norm": 0.17180432379245758,
1401
+ "learning_rate": 2.0681818181818182e-05,
1402
+ "loss": 0.0158,
1403
+ "step": 398
1404
+ },
1405
+ {
1406
+ "epoch": 5.97378277153558,
1407
+ "grad_norm": 0.13470757007598877,
1408
+ "learning_rate": 2.053030303030303e-05,
1409
+ "loss": 0.016,
1410
+ "step": 400
1411
+ },
1412
+ {
1413
+ "epoch": 6.0,
1414
+ "grad_norm": 0.12095994502305984,
1415
+ "learning_rate": 2.037878787878788e-05,
1416
+ "loss": 0.0136,
1417
+ "step": 402
1418
+ },
1419
+ {
1420
+ "epoch": 6.0299625468164795,
1421
+ "grad_norm": 0.13292968273162842,
1422
+ "learning_rate": 2.022727272727273e-05,
1423
+ "loss": 0.0146,
1424
+ "step": 404
1425
+ },
1426
+ {
1427
+ "epoch": 6.059925093632959,
1428
+ "grad_norm": 0.143639475107193,
1429
+ "learning_rate": 2.0075757575757575e-05,
1430
+ "loss": 0.0159,
1431
+ "step": 406
1432
+ },
1433
+ {
1434
+ "epoch": 6.089887640449438,
1435
+ "grad_norm": 0.13313822448253632,
1436
+ "learning_rate": 1.9924242424242425e-05,
1437
+ "loss": 0.017,
1438
+ "step": 408
1439
+ },
1440
+ {
1441
+ "epoch": 6.119850187265918,
1442
+ "grad_norm": 0.17898374795913696,
1443
+ "learning_rate": 1.9772727272727274e-05,
1444
+ "loss": 0.0162,
1445
+ "step": 410
1446
+ },
1447
+ {
1448
+ "epoch": 6.149812734082397,
1449
+ "grad_norm": 0.12149132043123245,
1450
+ "learning_rate": 1.962121212121212e-05,
1451
+ "loss": 0.0143,
1452
+ "step": 412
1453
+ },
1454
+ {
1455
+ "epoch": 6.179775280898877,
1456
+ "grad_norm": 0.12255310267210007,
1457
+ "learning_rate": 1.9469696969696972e-05,
1458
+ "loss": 0.0148,
1459
+ "step": 414
1460
+ },
1461
+ {
1462
+ "epoch": 6.209737827715355,
1463
+ "grad_norm": 0.17352508008480072,
1464
+ "learning_rate": 1.9318181818181818e-05,
1465
+ "loss": 0.0153,
1466
+ "step": 416
1467
+ },
1468
+ {
1469
+ "epoch": 6.239700374531835,
1470
+ "grad_norm": 0.15836010873317719,
1471
+ "learning_rate": 1.9166666666666667e-05,
1472
+ "loss": 0.0152,
1473
+ "step": 418
1474
+ },
1475
+ {
1476
+ "epoch": 6.269662921348314,
1477
+ "grad_norm": 0.13117386400699615,
1478
+ "learning_rate": 1.9015151515151516e-05,
1479
+ "loss": 0.0131,
1480
+ "step": 420
1481
+ },
1482
+ {
1483
+ "epoch": 6.299625468164794,
1484
+ "grad_norm": 0.09744709730148315,
1485
+ "learning_rate": 1.8863636363636362e-05,
1486
+ "loss": 0.0133,
1487
+ "step": 422
1488
+ },
1489
+ {
1490
+ "epoch": 6.329588014981273,
1491
+ "grad_norm": 0.11249203234910965,
1492
+ "learning_rate": 1.8712121212121215e-05,
1493
+ "loss": 0.0137,
1494
+ "step": 424
1495
+ },
1496
+ {
1497
+ "epoch": 6.359550561797753,
1498
+ "grad_norm": 0.14073345065116882,
1499
+ "learning_rate": 1.856060606060606e-05,
1500
+ "loss": 0.0158,
1501
+ "step": 426
1502
+ },
1503
+ {
1504
+ "epoch": 6.389513108614232,
1505
+ "grad_norm": 0.19942159950733185,
1506
+ "learning_rate": 1.840909090909091e-05,
1507
+ "loss": 0.0179,
1508
+ "step": 428
1509
+ },
1510
+ {
1511
+ "epoch": 6.419475655430712,
1512
+ "grad_norm": 0.12104730308055878,
1513
+ "learning_rate": 1.825757575757576e-05,
1514
+ "loss": 0.0143,
1515
+ "step": 430
1516
+ },
1517
+ {
1518
+ "epoch": 6.449438202247191,
1519
+ "grad_norm": 0.12874731421470642,
1520
+ "learning_rate": 1.810606060606061e-05,
1521
+ "loss": 0.0147,
1522
+ "step": 432
1523
+ },
1524
+ {
1525
+ "epoch": 6.479400749063671,
1526
+ "grad_norm": 0.09665031731128693,
1527
+ "learning_rate": 1.7954545454545454e-05,
1528
+ "loss": 0.0126,
1529
+ "step": 434
1530
+ },
1531
+ {
1532
+ "epoch": 6.50936329588015,
1533
+ "grad_norm": 0.22135666012763977,
1534
+ "learning_rate": 1.7803030303030303e-05,
1535
+ "loss": 0.0162,
1536
+ "step": 436
1537
+ },
1538
+ {
1539
+ "epoch": 6.539325842696629,
1540
+ "grad_norm": 0.12249334901571274,
1541
+ "learning_rate": 1.7651515151515153e-05,
1542
+ "loss": 0.013,
1543
+ "step": 438
1544
+ },
1545
+ {
1546
+ "epoch": 6.569288389513108,
1547
+ "grad_norm": 0.15929952263832092,
1548
+ "learning_rate": 1.75e-05,
1549
+ "loss": 0.0144,
1550
+ "step": 440
1551
+ },
1552
+ {
1553
+ "epoch": 6.599250936329588,
1554
+ "grad_norm": 0.116636261343956,
1555
+ "learning_rate": 1.734848484848485e-05,
1556
+ "loss": 0.0136,
1557
+ "step": 442
1558
+ },
1559
+ {
1560
+ "epoch": 6.629213483146067,
1561
+ "grad_norm": 0.26052579283714294,
1562
+ "learning_rate": 1.7196969696969697e-05,
1563
+ "loss": 0.0167,
1564
+ "step": 444
1565
+ },
1566
+ {
1567
+ "epoch": 6.659176029962547,
1568
+ "grad_norm": 0.16209331154823303,
1569
+ "learning_rate": 1.7045454545454546e-05,
1570
+ "loss": 0.0152,
1571
+ "step": 446
1572
+ },
1573
+ {
1574
+ "epoch": 6.689138576779026,
1575
+ "grad_norm": 0.11612333357334137,
1576
+ "learning_rate": 1.6893939393939395e-05,
1577
+ "loss": 0.0153,
1578
+ "step": 448
1579
+ },
1580
+ {
1581
+ "epoch": 6.719101123595506,
1582
+ "grad_norm": 0.092486672103405,
1583
+ "learning_rate": 1.674242424242424e-05,
1584
+ "loss": 0.0133,
1585
+ "step": 450
1586
+ },
1587
+ {
1588
+ "epoch": 6.749063670411985,
1589
+ "grad_norm": 0.10298772156238556,
1590
+ "learning_rate": 1.6590909090909094e-05,
1591
+ "loss": 0.0136,
1592
+ "step": 452
1593
+ },
1594
+ {
1595
+ "epoch": 6.7790262172284645,
1596
+ "grad_norm": 0.13439835608005524,
1597
+ "learning_rate": 1.643939393939394e-05,
1598
+ "loss": 0.016,
1599
+ "step": 454
1600
+ },
1601
+ {
1602
+ "epoch": 6.808988764044944,
1603
+ "grad_norm": 0.14403583109378815,
1604
+ "learning_rate": 1.628787878787879e-05,
1605
+ "loss": 0.014,
1606
+ "step": 456
1607
+ },
1608
+ {
1609
+ "epoch": 6.8389513108614235,
1610
+ "grad_norm": 0.1841178834438324,
1611
+ "learning_rate": 1.6136363636363638e-05,
1612
+ "loss": 0.0149,
1613
+ "step": 458
1614
+ },
1615
+ {
1616
+ "epoch": 6.868913857677903,
1617
+ "grad_norm": 0.09390496462583542,
1618
+ "learning_rate": 1.5984848484848487e-05,
1619
+ "loss": 0.0141,
1620
+ "step": 460
1621
+ },
1622
+ {
1623
+ "epoch": 6.898876404494382,
1624
+ "grad_norm": 0.16365155577659607,
1625
+ "learning_rate": 1.5833333333333333e-05,
1626
+ "loss": 0.0157,
1627
+ "step": 462
1628
+ },
1629
+ {
1630
+ "epoch": 6.928838951310862,
1631
+ "grad_norm": 0.1577712446451187,
1632
+ "learning_rate": 1.5681818181818182e-05,
1633
+ "loss": 0.0141,
1634
+ "step": 464
1635
+ },
1636
+ {
1637
+ "epoch": 6.9588014981273405,
1638
+ "grad_norm": 0.173916295170784,
1639
+ "learning_rate": 1.553030303030303e-05,
1640
+ "loss": 0.0157,
1641
+ "step": 466
1642
+ },
1643
+ {
1644
+ "epoch": 6.98876404494382,
1645
+ "grad_norm": 0.16699424386024475,
1646
+ "learning_rate": 1.5378787878787877e-05,
1647
+ "loss": 0.0169,
1648
+ "step": 468
1649
+ },
1650
+ {
1651
+ "epoch": 7.01498127340824,
1652
+ "grad_norm": 0.12708672881126404,
1653
+ "learning_rate": 1.5227272727272728e-05,
1654
+ "loss": 0.0142,
1655
+ "step": 470
1656
+ },
1657
+ {
1658
+ "epoch": 7.044943820224719,
1659
+ "grad_norm": 0.15440689027309418,
1660
+ "learning_rate": 1.5075757575757576e-05,
1661
+ "loss": 0.0158,
1662
+ "step": 472
1663
+ },
1664
+ {
1665
+ "epoch": 7.074906367041199,
1666
+ "grad_norm": 0.1230991929769516,
1667
+ "learning_rate": 1.4924242424242423e-05,
1668
+ "loss": 0.0136,
1669
+ "step": 474
1670
+ },
1671
+ {
1672
+ "epoch": 7.104868913857678,
1673
+ "grad_norm": 0.21653351187705994,
1674
+ "learning_rate": 1.4772727272727274e-05,
1675
+ "loss": 0.0159,
1676
+ "step": 476
1677
+ },
1678
+ {
1679
+ "epoch": 7.134831460674158,
1680
+ "grad_norm": 0.1883053332567215,
1681
+ "learning_rate": 1.4621212121212122e-05,
1682
+ "loss": 0.0155,
1683
+ "step": 478
1684
+ },
1685
+ {
1686
+ "epoch": 7.164794007490637,
1687
+ "grad_norm": 0.22849740087985992,
1688
+ "learning_rate": 1.446969696969697e-05,
1689
+ "loss": 0.0171,
1690
+ "step": 480
1691
+ },
1692
+ {
1693
+ "epoch": 7.194756554307116,
1694
+ "grad_norm": 0.12744282186031342,
1695
+ "learning_rate": 1.431818181818182e-05,
1696
+ "loss": 0.0142,
1697
+ "step": 482
1698
+ },
1699
+ {
1700
+ "epoch": 7.224719101123595,
1701
+ "grad_norm": 0.09133846312761307,
1702
+ "learning_rate": 1.4166666666666668e-05,
1703
+ "loss": 0.0133,
1704
+ "step": 484
1705
+ },
1706
+ {
1707
+ "epoch": 7.254681647940075,
1708
+ "grad_norm": 0.13602511584758759,
1709
+ "learning_rate": 1.4015151515151515e-05,
1710
+ "loss": 0.014,
1711
+ "step": 486
1712
+ },
1713
+ {
1714
+ "epoch": 7.284644194756554,
1715
+ "grad_norm": 0.13092727959156036,
1716
+ "learning_rate": 1.3863636363636364e-05,
1717
+ "loss": 0.0149,
1718
+ "step": 488
1719
+ },
1720
+ {
1721
+ "epoch": 7.314606741573034,
1722
+ "grad_norm": 0.12762710452079773,
1723
+ "learning_rate": 1.3712121212121212e-05,
1724
+ "loss": 0.0143,
1725
+ "step": 490
1726
+ },
1727
+ {
1728
+ "epoch": 7.344569288389513,
1729
+ "grad_norm": 0.12416286021471024,
1730
+ "learning_rate": 1.3560606060606063e-05,
1731
+ "loss": 0.0145,
1732
+ "step": 492
1733
+ },
1734
+ {
1735
+ "epoch": 7.3745318352059925,
1736
+ "grad_norm": 0.145538792014122,
1737
+ "learning_rate": 1.340909090909091e-05,
1738
+ "loss": 0.0145,
1739
+ "step": 494
1740
+ },
1741
+ {
1742
+ "epoch": 7.404494382022472,
1743
+ "grad_norm": 0.11264869570732117,
1744
+ "learning_rate": 1.3257575757575758e-05,
1745
+ "loss": 0.0156,
1746
+ "step": 496
1747
+ },
1748
+ {
1749
+ "epoch": 7.4344569288389515,
1750
+ "grad_norm": 0.10543698072433472,
1751
+ "learning_rate": 1.3106060606060607e-05,
1752
+ "loss": 0.0141,
1753
+ "step": 498
1754
+ },
1755
+ {
1756
+ "epoch": 7.464419475655431,
1757
+ "grad_norm": 0.1221228539943695,
1758
+ "learning_rate": 1.2954545454545455e-05,
1759
+ "loss": 0.0146,
1760
+ "step": 500
1761
+ },
1762
+ {
1763
+ "epoch": 7.49438202247191,
1764
+ "grad_norm": 0.12155947834253311,
1765
+ "learning_rate": 1.2803030303030302e-05,
1766
+ "loss": 0.0141,
1767
+ "step": 502
1768
+ },
1769
+ {
1770
+ "epoch": 7.52434456928839,
1771
+ "grad_norm": 0.12504641711711884,
1772
+ "learning_rate": 1.2651515151515153e-05,
1773
+ "loss": 0.0128,
1774
+ "step": 504
1775
+ },
1776
+ {
1777
+ "epoch": 7.554307116104869,
1778
+ "grad_norm": 0.11169607192277908,
1779
+ "learning_rate": 1.25e-05,
1780
+ "loss": 0.0128,
1781
+ "step": 506
1782
+ },
1783
+ {
1784
+ "epoch": 7.584269662921348,
1785
+ "grad_norm": 0.1285315901041031,
1786
+ "learning_rate": 1.234848484848485e-05,
1787
+ "loss": 0.0161,
1788
+ "step": 508
1789
+ },
1790
+ {
1791
+ "epoch": 7.614232209737827,
1792
+ "grad_norm": 0.10635136067867279,
1793
+ "learning_rate": 1.2196969696969697e-05,
1794
+ "loss": 0.0149,
1795
+ "step": 510
1796
+ },
1797
+ {
1798
+ "epoch": 7.644194756554307,
1799
+ "grad_norm": 0.11686955392360687,
1800
+ "learning_rate": 1.2045454545454547e-05,
1801
+ "loss": 0.0138,
1802
+ "step": 512
1803
+ },
1804
+ {
1805
+ "epoch": 7.674157303370786,
1806
+ "grad_norm": 0.08601470291614532,
1807
+ "learning_rate": 1.1893939393939394e-05,
1808
+ "loss": 0.0131,
1809
+ "step": 514
1810
+ },
1811
+ {
1812
+ "epoch": 7.704119850187266,
1813
+ "grad_norm": 0.0880078673362732,
1814
+ "learning_rate": 1.1742424242424243e-05,
1815
+ "loss": 0.0131,
1816
+ "step": 516
1817
+ },
1818
+ {
1819
+ "epoch": 7.734082397003745,
1820
+ "grad_norm": 0.15093624591827393,
1821
+ "learning_rate": 1.159090909090909e-05,
1822
+ "loss": 0.0162,
1823
+ "step": 518
1824
+ },
1825
+ {
1826
+ "epoch": 7.764044943820225,
1827
+ "grad_norm": 0.11285064369440079,
1828
+ "learning_rate": 1.143939393939394e-05,
1829
+ "loss": 0.015,
1830
+ "step": 520
1831
+ },
1832
+ {
1833
+ "epoch": 7.794007490636704,
1834
+ "grad_norm": 0.10577835887670517,
1835
+ "learning_rate": 1.128787878787879e-05,
1836
+ "loss": 0.0132,
1837
+ "step": 522
1838
+ },
1839
+ {
1840
+ "epoch": 7.823970037453184,
1841
+ "grad_norm": 0.19718210399150848,
1842
+ "learning_rate": 1.1136363636363637e-05,
1843
+ "loss": 0.0143,
1844
+ "step": 524
1845
+ },
1846
+ {
1847
+ "epoch": 7.853932584269663,
1848
+ "grad_norm": 0.13446953892707825,
1849
+ "learning_rate": 1.0984848484848486e-05,
1850
+ "loss": 0.0157,
1851
+ "step": 526
1852
+ },
1853
+ {
1854
+ "epoch": 7.883895131086143,
1855
+ "grad_norm": 0.12463881075382233,
1856
+ "learning_rate": 1.0833333333333334e-05,
1857
+ "loss": 0.015,
1858
+ "step": 528
1859
+ },
1860
+ {
1861
+ "epoch": 7.913857677902621,
1862
+ "grad_norm": 0.13918359577655792,
1863
+ "learning_rate": 1.0681818181818181e-05,
1864
+ "loss": 0.0124,
1865
+ "step": 530
1866
+ },
1867
+ {
1868
+ "epoch": 7.943820224719101,
1869
+ "grad_norm": 0.1380302906036377,
1870
+ "learning_rate": 1.053030303030303e-05,
1871
+ "loss": 0.014,
1872
+ "step": 532
1873
+ },
1874
+ {
1875
+ "epoch": 7.97378277153558,
1876
+ "grad_norm": 0.14899957180023193,
1877
+ "learning_rate": 1.037878787878788e-05,
1878
+ "loss": 0.0175,
1879
+ "step": 534
1880
+ },
1881
+ {
1882
+ "epoch": 8.0,
1883
+ "grad_norm": 0.11646629869937897,
1884
+ "learning_rate": 1.0227272727272729e-05,
1885
+ "loss": 0.0145,
1886
+ "step": 536
1887
+ },
1888
+ {
1889
+ "epoch": 8.02996254681648,
1890
+ "grad_norm": 0.14022769033908844,
1891
+ "learning_rate": 1.0075757575757576e-05,
1892
+ "loss": 0.0121,
1893
+ "step": 538
1894
+ },
1895
+ {
1896
+ "epoch": 8.059925093632959,
1897
+ "grad_norm": 0.15053826570510864,
1898
+ "learning_rate": 9.924242424242425e-06,
1899
+ "loss": 0.0157,
1900
+ "step": 540
1901
+ },
1902
+ {
1903
+ "epoch": 8.089887640449438,
1904
+ "grad_norm": 0.11895288527011871,
1905
+ "learning_rate": 9.772727272727273e-06,
1906
+ "loss": 0.0141,
1907
+ "step": 542
1908
+ },
1909
+ {
1910
+ "epoch": 8.119850187265918,
1911
+ "grad_norm": 0.11707016080617905,
1912
+ "learning_rate": 9.62121212121212e-06,
1913
+ "loss": 0.0145,
1914
+ "step": 544
1915
+ },
1916
+ {
1917
+ "epoch": 8.149812734082397,
1918
+ "grad_norm": 0.10449573397636414,
1919
+ "learning_rate": 9.46969696969697e-06,
1920
+ "loss": 0.0146,
1921
+ "step": 546
1922
+ },
1923
+ {
1924
+ "epoch": 8.179775280898877,
1925
+ "grad_norm": 0.13925935328006744,
1926
+ "learning_rate": 9.318181818181819e-06,
1927
+ "loss": 0.014,
1928
+ "step": 548
1929
+ },
1930
+ {
1931
+ "epoch": 8.209737827715356,
1932
+ "grad_norm": 0.12868592143058777,
1933
+ "learning_rate": 9.166666666666666e-06,
1934
+ "loss": 0.0138,
1935
+ "step": 550
1936
+ },
1937
+ {
1938
+ "epoch": 8.239700374531836,
1939
+ "grad_norm": 0.11764951050281525,
1940
+ "learning_rate": 9.015151515151516e-06,
1941
+ "loss": 0.0147,
1942
+ "step": 552
1943
+ },
1944
+ {
1945
+ "epoch": 8.269662921348315,
1946
+ "grad_norm": 0.21383918821811676,
1947
+ "learning_rate": 8.863636363636365e-06,
1948
+ "loss": 0.0134,
1949
+ "step": 554
1950
+ },
1951
+ {
1952
+ "epoch": 8.299625468164795,
1953
+ "grad_norm": 0.14592906832695007,
1954
+ "learning_rate": 8.712121212121212e-06,
1955
+ "loss": 0.0151,
1956
+ "step": 556
1957
+ },
1958
+ {
1959
+ "epoch": 8.329588014981274,
1960
+ "grad_norm": 0.1377759724855423,
1961
+ "learning_rate": 8.56060606060606e-06,
1962
+ "loss": 0.0138,
1963
+ "step": 558
1964
+ },
1965
+ {
1966
+ "epoch": 8.359550561797754,
1967
+ "grad_norm": 0.15097083151340485,
1968
+ "learning_rate": 8.409090909090909e-06,
1969
+ "loss": 0.013,
1970
+ "step": 560
1971
+ },
1972
+ {
1973
+ "epoch": 8.389513108614231,
1974
+ "grad_norm": 0.1862707883119583,
1975
+ "learning_rate": 8.257575757575758e-06,
1976
+ "loss": 0.0119,
1977
+ "step": 562
1978
+ },
1979
+ {
1980
+ "epoch": 8.41947565543071,
1981
+ "grad_norm": 0.19083456695079803,
1982
+ "learning_rate": 8.106060606060606e-06,
1983
+ "loss": 0.0175,
1984
+ "step": 564
1985
+ },
1986
+ {
1987
+ "epoch": 8.44943820224719,
1988
+ "grad_norm": 0.18206746876239777,
1989
+ "learning_rate": 7.954545454545455e-06,
1990
+ "loss": 0.0153,
1991
+ "step": 566
1992
+ },
1993
+ {
1994
+ "epoch": 8.47940074906367,
1995
+ "grad_norm": 0.1560777872800827,
1996
+ "learning_rate": 7.803030303030304e-06,
1997
+ "loss": 0.0142,
1998
+ "step": 568
1999
+ },
2000
+ {
2001
+ "epoch": 8.50936329588015,
2002
+ "grad_norm": 0.11597474664449692,
2003
+ "learning_rate": 7.651515151515152e-06,
2004
+ "loss": 0.015,
2005
+ "step": 570
2006
+ },
2007
+ {
2008
+ "epoch": 8.539325842696629,
2009
+ "grad_norm": 0.14232860505580902,
2010
+ "learning_rate": 7.5e-06,
2011
+ "loss": 0.0154,
2012
+ "step": 572
2013
+ },
2014
+ {
2015
+ "epoch": 8.569288389513108,
2016
+ "grad_norm": 0.12590251863002777,
2017
+ "learning_rate": 7.3484848484848486e-06,
2018
+ "loss": 0.0141,
2019
+ "step": 574
2020
+ },
2021
+ {
2022
+ "epoch": 8.599250936329588,
2023
+ "grad_norm": 0.161521315574646,
2024
+ "learning_rate": 7.196969696969698e-06,
2025
+ "loss": 0.0152,
2026
+ "step": 576
2027
+ },
2028
+ {
2029
+ "epoch": 8.629213483146067,
2030
+ "grad_norm": 0.12818320095539093,
2031
+ "learning_rate": 7.045454545454545e-06,
2032
+ "loss": 0.0133,
2033
+ "step": 578
2034
+ },
2035
+ {
2036
+ "epoch": 8.659176029962547,
2037
+ "grad_norm": 0.10711938887834549,
2038
+ "learning_rate": 6.8939393939393945e-06,
2039
+ "loss": 0.0143,
2040
+ "step": 580
2041
+ },
2042
+ {
2043
+ "epoch": 8.689138576779026,
2044
+ "grad_norm": 0.11545701324939728,
2045
+ "learning_rate": 6.742424242424243e-06,
2046
+ "loss": 0.0153,
2047
+ "step": 582
2048
+ },
2049
+ {
2050
+ "epoch": 8.719101123595506,
2051
+ "grad_norm": 0.15045291185379028,
2052
+ "learning_rate": 6.59090909090909e-06,
2053
+ "loss": 0.0133,
2054
+ "step": 584
2055
+ },
2056
+ {
2057
+ "epoch": 8.749063670411985,
2058
+ "grad_norm": 0.1033000648021698,
2059
+ "learning_rate": 6.43939393939394e-06,
2060
+ "loss": 0.0145,
2061
+ "step": 586
2062
+ },
2063
+ {
2064
+ "epoch": 8.779026217228465,
2065
+ "grad_norm": 0.16855841875076294,
2066
+ "learning_rate": 6.287878787878789e-06,
2067
+ "loss": 0.0152,
2068
+ "step": 588
2069
+ },
2070
+ {
2071
+ "epoch": 8.808988764044944,
2072
+ "grad_norm": 0.11125820875167847,
2073
+ "learning_rate": 6.136363636363636e-06,
2074
+ "loss": 0.0143,
2075
+ "step": 590
2076
+ },
2077
+ {
2078
+ "epoch": 8.838951310861423,
2079
+ "grad_norm": 0.11163821816444397,
2080
+ "learning_rate": 5.984848484848485e-06,
2081
+ "loss": 0.0143,
2082
+ "step": 592
2083
+ },
2084
+ {
2085
+ "epoch": 8.868913857677903,
2086
+ "grad_norm": 0.11566553264856339,
2087
+ "learning_rate": 5.833333333333334e-06,
2088
+ "loss": 0.0142,
2089
+ "step": 594
2090
+ },
2091
+ {
2092
+ "epoch": 8.898876404494382,
2093
+ "grad_norm": 0.11087555438280106,
2094
+ "learning_rate": 5.681818181818182e-06,
2095
+ "loss": 0.0148,
2096
+ "step": 596
2097
+ },
2098
+ {
2099
+ "epoch": 8.928838951310862,
2100
+ "grad_norm": 0.1234087273478508,
2101
+ "learning_rate": 5.530303030303031e-06,
2102
+ "loss": 0.0156,
2103
+ "step": 598
2104
+ },
2105
+ {
2106
+ "epoch": 8.958801498127341,
2107
+ "grad_norm": 0.18318650126457214,
2108
+ "learning_rate": 5.378787878787879e-06,
2109
+ "loss": 0.0145,
2110
+ "step": 600
2111
+ },
2112
+ {
2113
+ "epoch": 8.98876404494382,
2114
+ "grad_norm": 0.09113040566444397,
2115
+ "learning_rate": 5.2272727272727274e-06,
2116
+ "loss": 0.0132,
2117
+ "step": 602
2118
+ },
2119
+ {
2120
+ "epoch": 9.014981273408239,
2121
+ "grad_norm": 0.10578633099794388,
2122
+ "learning_rate": 5.075757575757576e-06,
2123
+ "loss": 0.0143,
2124
+ "step": 604
2125
+ },
2126
+ {
2127
+ "epoch": 9.044943820224718,
2128
+ "grad_norm": 0.15693627297878265,
2129
+ "learning_rate": 4.924242424242424e-06,
2130
+ "loss": 0.015,
2131
+ "step": 606
2132
+ },
2133
+ {
2134
+ "epoch": 9.074906367041198,
2135
+ "grad_norm": 0.1018158420920372,
2136
+ "learning_rate": 4.772727272727273e-06,
2137
+ "loss": 0.0139,
2138
+ "step": 608
2139
+ },
2140
+ {
2141
+ "epoch": 9.104868913857677,
2142
+ "grad_norm": 0.17492976784706116,
2143
+ "learning_rate": 4.621212121212122e-06,
2144
+ "loss": 0.0156,
2145
+ "step": 610
2146
+ },
2147
+ {
2148
+ "epoch": 9.134831460674157,
2149
+ "grad_norm": 0.11221963167190552,
2150
+ "learning_rate": 4.46969696969697e-06,
2151
+ "loss": 0.0152,
2152
+ "step": 612
2153
+ },
2154
+ {
2155
+ "epoch": 9.164794007490636,
2156
+ "grad_norm": 0.12558336555957794,
2157
+ "learning_rate": 4.3181818181818185e-06,
2158
+ "loss": 0.0143,
2159
+ "step": 614
2160
+ },
2161
+ {
2162
+ "epoch": 9.194756554307116,
2163
+ "grad_norm": 0.11668603867292404,
2164
+ "learning_rate": 4.166666666666667e-06,
2165
+ "loss": 0.0127,
2166
+ "step": 616
2167
+ },
2168
+ {
2169
+ "epoch": 9.224719101123595,
2170
+ "grad_norm": 0.14164716005325317,
2171
+ "learning_rate": 4.015151515151515e-06,
2172
+ "loss": 0.0155,
2173
+ "step": 618
2174
+ },
2175
+ {
2176
+ "epoch": 9.254681647940075,
2177
+ "grad_norm": 0.12440814077854156,
2178
+ "learning_rate": 3.863636363636364e-06,
2179
+ "loss": 0.0134,
2180
+ "step": 620
2181
+ },
2182
+ {
2183
+ "epoch": 9.284644194756554,
2184
+ "grad_norm": 0.14497360587120056,
2185
+ "learning_rate": 3.7121212121212124e-06,
2186
+ "loss": 0.0152,
2187
+ "step": 622
2188
+ },
2189
+ {
2190
+ "epoch": 9.314606741573034,
2191
+ "grad_norm": 0.13429833948612213,
2192
+ "learning_rate": 3.5606060606060608e-06,
2193
+ "loss": 0.015,
2194
+ "step": 624
2195
+ },
2196
+ {
2197
+ "epoch": 9.344569288389513,
2198
+ "grad_norm": 0.11680711805820465,
2199
+ "learning_rate": 3.409090909090909e-06,
2200
+ "loss": 0.0141,
2201
+ "step": 626
2202
+ },
2203
+ {
2204
+ "epoch": 9.374531835205993,
2205
+ "grad_norm": 0.141137033700943,
2206
+ "learning_rate": 3.257575757575758e-06,
2207
+ "loss": 0.0137,
2208
+ "step": 628
2209
+ },
2210
+ {
2211
+ "epoch": 9.404494382022472,
2212
+ "grad_norm": 0.11425523459911346,
2213
+ "learning_rate": 3.106060606060606e-06,
2214
+ "loss": 0.0153,
2215
+ "step": 630
2216
+ },
2217
+ {
2218
+ "epoch": 9.434456928838951,
2219
+ "grad_norm": 0.175795778632164,
2220
+ "learning_rate": 2.9545454545454547e-06,
2221
+ "loss": 0.0137,
2222
+ "step": 632
2223
+ },
2224
+ {
2225
+ "epoch": 9.464419475655431,
2226
+ "grad_norm": 0.21211205422878265,
2227
+ "learning_rate": 2.803030303030303e-06,
2228
+ "loss": 0.0145,
2229
+ "step": 634
2230
+ },
2231
+ {
2232
+ "epoch": 9.49438202247191,
2233
+ "grad_norm": 0.12809644639492035,
2234
+ "learning_rate": 2.651515151515152e-06,
2235
+ "loss": 0.0137,
2236
+ "step": 636
2237
+ },
2238
+ {
2239
+ "epoch": 9.52434456928839,
2240
+ "grad_norm": 0.1471203863620758,
2241
+ "learning_rate": 2.5e-06,
2242
+ "loss": 0.0122,
2243
+ "step": 638
2244
+ },
2245
+ {
2246
+ "epoch": 9.55430711610487,
2247
+ "grad_norm": 0.11589685082435608,
2248
+ "learning_rate": 2.3484848484848486e-06,
2249
+ "loss": 0.0137,
2250
+ "step": 640
2251
+ },
2252
+ {
2253
+ "epoch": 9.584269662921349,
2254
+ "grad_norm": 0.11537714302539825,
2255
+ "learning_rate": 2.196969696969697e-06,
2256
+ "loss": 0.0147,
2257
+ "step": 642
2258
+ },
2259
+ {
2260
+ "epoch": 9.614232209737828,
2261
+ "grad_norm": 0.10002223402261734,
2262
+ "learning_rate": 2.0454545454545457e-06,
2263
+ "loss": 0.0139,
2264
+ "step": 644
2265
+ },
2266
+ {
2267
+ "epoch": 9.644194756554308,
2268
+ "grad_norm": 0.1463649868965149,
2269
+ "learning_rate": 1.8939393939393941e-06,
2270
+ "loss": 0.0138,
2271
+ "step": 646
2272
+ },
2273
+ {
2274
+ "epoch": 9.674157303370787,
2275
+ "grad_norm": 0.15200403332710266,
2276
+ "learning_rate": 1.7424242424242427e-06,
2277
+ "loss": 0.0127,
2278
+ "step": 648
2279
+ },
2280
+ {
2281
+ "epoch": 9.704119850187267,
2282
+ "grad_norm": 0.1294555813074112,
2283
+ "learning_rate": 1.5909090909090908e-06,
2284
+ "loss": 0.013,
2285
+ "step": 650
2286
+ },
2287
+ {
2288
+ "epoch": 9.734082397003746,
2289
+ "grad_norm": 0.12834538519382477,
2290
+ "learning_rate": 1.4393939393939396e-06,
2291
+ "loss": 0.014,
2292
+ "step": 652
2293
+ },
2294
+ {
2295
+ "epoch": 9.764044943820224,
2296
+ "grad_norm": 0.16599954664707184,
2297
+ "learning_rate": 1.287878787878788e-06,
2298
+ "loss": 0.0153,
2299
+ "step": 654
2300
+ },
2301
+ {
2302
+ "epoch": 9.794007490636703,
2303
+ "grad_norm": 0.14348356425762177,
2304
+ "learning_rate": 1.1363636363636364e-06,
2305
+ "loss": 0.0145,
2306
+ "step": 656
2307
+ },
2308
+ {
2309
+ "epoch": 9.823970037453183,
2310
+ "grad_norm": 0.1504441797733307,
2311
+ "learning_rate": 9.848484848484847e-07,
2312
+ "loss": 0.0148,
2313
+ "step": 658
2314
+ },
2315
+ {
2316
+ "epoch": 9.853932584269662,
2317
+ "grad_norm": 0.12484189122915268,
2318
+ "learning_rate": 8.333333333333333e-07,
2319
+ "loss": 0.0156,
2320
+ "step": 660
2321
+ }
2322
+ ],
2323
+ "logging_steps": 2,
2324
+ "max_steps": 670,
2325
+ "num_input_tokens_seen": 0,
2326
+ "num_train_epochs": 10,
2327
+ "save_steps": 20,
2328
+ "stateful_callbacks": {
2329
+ "TrainerControl": {
2330
+ "args": {
2331
+ "should_epoch_stop": false,
2332
+ "should_evaluate": false,
2333
+ "should_log": false,
2334
+ "should_save": true,
2335
+ "should_training_stop": false
2336
+ },
2337
+ "attributes": {}
2338
+ }
2339
+ },
2340
+ "total_flos": 1.778197543133184e+16,
2341
+ "train_batch_size": 1,
2342
+ "trial_name": null,
2343
+ "trial_params": null
2344
+ }
checkpoint-660/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc984cd6b8e095021805ddd8e3c0a08d2950c17b15e17eebbeeaf65ff57c9fe
3
+ size 5777
checkpoint-670/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM3-3B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM3-3B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.16.0
checkpoint-670/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM3-3B",
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": 16,
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": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "k_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "o_proj",
32
+ "down_proj",
33
+ "q_proj",
34
+ "gate_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_qalora": false,
40
+ "use_rslora": false
41
+ }
checkpoint-670/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3458fc95dd76c973d77067a8b1bba3b9ef30b3abf188c05ccfcef00e2aedf0
3
+ size 60523464
checkpoint-670/chat_template.jinja ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# ───── defaults ───── #}
2
+ {%- if enable_thinking is not defined -%}
3
+ {%- set enable_thinking = true -%}
4
+ {%- endif -%}
5
+
6
+ {# ───── reasoning mode ───── #}
7
+ {%- if enable_thinking -%}
8
+ {%- set reasoning_mode = "/think" -%}
9
+ {%- else -%}
10
+ {%- set reasoning_mode = "/no_think" -%}
11
+ {%- endif -%}
12
+
13
+ {# ───── header (system message) ───── #}
14
+ {{- "<|im_start|>system\n" -}}
15
+
16
+ {%- if messages[0].role == "system" -%}
17
+ {%- set system_message = messages[0].content -%}
18
+ {%- if "/no_think" in system_message -%}
19
+ {%- set reasoning_mode = "/no_think" -%}
20
+ {%- elif "/think" in system_message -%}
21
+ {%- set reasoning_mode = "/think" -%}
22
+ {%- endif -%}
23
+ {%- set custom_instructions = system_message.replace("/no_think", "").replace("/think", "").rstrip() -%}
24
+ {%- endif -%}
25
+
26
+ {%- if "/system_override" in system_message -%}
27
+ {{- custom_instructions.replace("/system_override", "").rstrip() -}}
28
+ {{- "<|im_end|>\n" -}}
29
+ {%- else -%}
30
+ {{- "## Metadata\n\n" -}}
31
+ {{- "Knowledge Cutoff Date: June 2025\n" -}}
32
+ {%- set today = strftime_now("%d %B %Y") -%}
33
+ {{- "Today Date: " ~ today ~ "\n" -}}
34
+ {{- "Reasoning Mode: " + reasoning_mode + "\n\n" -}}
35
+
36
+ {{- "## Custom Instructions\n\n" -}}
37
+ {%- if custom_instructions -%}
38
+ {{- custom_instructions + "\n\n" -}}
39
+ {%- elif reasoning_mode == "/think" -%}
40
+ {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: <think> Thought section </think> Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion.\n\n" -}}
41
+ {%- else -%}
42
+ {{- "You are a helpful AI assistant named SmolLM, trained by Hugging Face.\n\n" -}}
43
+ {%- endif -%}
44
+
45
+ {%- if xml_tools or python_tools or tools -%}
46
+ {{- "### Tools\n\n" -}}
47
+ {%- if xml_tools or tools -%}
48
+ {%- if tools -%}
49
+ {%- set xml_tools = tools -%}
50
+ {%- endif -%}
51
+ {%- set ns = namespace(xml_tool_string="You may call one or more functions to assist with the user query.\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n") -%}
52
+ {%- for tool in xml_tools[:] -%} {# The slicing makes sure that xml_tools is a list #}
53
+ {%- set ns.xml_tool_string = ns.xml_tool_string ~ (tool | string) ~ "\n" -%}
54
+ {%- endfor -%}
55
+ {%- set xml_tool_string = ns.xml_tool_string + "</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>" -%}
56
+ {{- xml_tool_string -}}
57
+ {%- endif -%}
58
+ {%- if python_tools -%}
59
+ {%- set ns = namespace(python_tool_string="When you send a message containing Python code between '<code>' and '</code>' tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output to continued reasoning in an agentic loop.\n\nYou can use the following tools in your python code like regular functions:\n<tools>\n") -%}
60
+ {%- for tool in python_tools[:] -%} {# The slicing makes sure that python_tools is a list #}
61
+ {%- set ns.python_tool_string = ns.python_tool_string ~ (tool | string) ~ "\n" -%}
62
+ {%- endfor -%}
63
+ {%- set python_tool_string = ns.python_tool_string + "</tools>\n\nThe state persists between code executions: so variables that you define in one step are still available thereafter." -%}
64
+ {{- python_tool_string -}}
65
+ {%- endif -%}
66
+ {{- "\n\n" -}}
67
+ {{- "<|im_end|>\n" -}}
68
+ {%- endif -%}
69
+ {%- endif -%}
70
+ {# ───── main loop ───── #}
71
+ {%- for message in messages -%}
72
+ {%- set content = message.content if message.content is string else "" -%}
73
+ {%- if message.role == "user" -%}
74
+ {{ "<|im_start|>" + message.role + "\n" + content + "<|im_end|>\n" }}
75
+ {%- elif message.role == "assistant" -%}
76
+ {% generation %}
77
+ {%- if reasoning_mode == "/think" -%}
78
+ {{ "<|im_start|>assistant\n" + content.lstrip("\n") + "<|im_end|>\n" }}
79
+ {%- else -%}
80
+ {{ "<|im_start|>assistant\n" + "<think>\n\n</think>\n" + content.lstrip("\n") + "<|im_end|>\n" }}
81
+ {%- endif -%}
82
+ {% endgeneration %}
83
+ {%- elif message.role == "tool" -%}
84
+ {{ "<|im_start|>" + "user\n" + content + "<|im_end|>\n" }}
85
+ {%- endif -%}
86
+ {%- endfor -%}
87
+ {# ───── generation prompt ───── #}
88
+ {%- if add_generation_prompt -%}
89
+ {%- if reasoning_mode == "/think" -%}
90
+ {{ "<|im_start|>assistant\n" }}
91
+ {%- else -%}
92
+ {{ "<|im_start|>assistant\n" + "<think>\n\n</think>\n" }}
93
+ {%- endif -%}
94
+ {%- endif -%}
checkpoint-670/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7db42b9d1b6f573f9ac683f32e99e0626776178350b7906241ee4d2b4327c47
3
+ size 121324555
checkpoint-670/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53538b67fc8658d85f3bae341f21061961843a7ee32995c942b7f9de93f80df8
3
+ size 14391
checkpoint-670/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a423d2fcaea5cc7adde0c465a85784f7bb7eba6f2a5bfcf9be4f1f1ee9c0052e
3
+ size 1465
checkpoint-670/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|im_end|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-670/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea5a8ce6451543cb0af4d08ccae7e2187ad41a68c571706a34ddf33b89add59
3
+ size 17208917
checkpoint-670/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<think>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "</think>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|im_start|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|im_end|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<tool_response>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<tool_call>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</tool_call>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<code>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</code>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": null,
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|im_end|>",
2055
+ "extra_special_tokens": {},
2056
+ "fast": false,
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|im_end|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-670/trainer_state.json ADDED
@@ -0,0 +1,2379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 670,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0299625468164794,
14
+ "grad_norm": 3.7318975925445557,
15
+ "learning_rate": 5e-06,
16
+ "loss": 1.6973,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.0599250936329588,
21
+ "grad_norm": 3.4212851524353027,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 1.6821,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.0898876404494382,
28
+ "grad_norm": 2.5065758228302,
29
+ "learning_rate": 2.5e-05,
30
+ "loss": 1.4689,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.1198501872659176,
35
+ "grad_norm": 2.081493854522705,
36
+ "learning_rate": 3.5e-05,
37
+ "loss": 1.411,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.149812734082397,
42
+ "grad_norm": 2.0012290477752686,
43
+ "learning_rate": 4.5e-05,
44
+ "loss": 1.1681,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.1797752808988764,
49
+ "grad_norm": 1.9056272506713867,
50
+ "learning_rate": 4.992424242424243e-05,
51
+ "loss": 0.9463,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.20973782771535582,
56
+ "grad_norm": 2.0275352001190186,
57
+ "learning_rate": 4.9772727272727275e-05,
58
+ "loss": 0.8338,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.2397003745318352,
63
+ "grad_norm": 1.6332467794418335,
64
+ "learning_rate": 4.962121212121213e-05,
65
+ "loss": 0.6327,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.2696629213483146,
70
+ "grad_norm": 1.3445727825164795,
71
+ "learning_rate": 4.946969696969697e-05,
72
+ "loss": 0.4954,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.299625468164794,
77
+ "grad_norm": 0.9636670351028442,
78
+ "learning_rate": 4.931818181818182e-05,
79
+ "loss": 0.3803,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.3295880149812734,
84
+ "grad_norm": 0.4598312973976135,
85
+ "learning_rate": 4.9166666666666665e-05,
86
+ "loss": 0.3355,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.3595505617977528,
91
+ "grad_norm": 0.6035417318344116,
92
+ "learning_rate": 4.901515151515152e-05,
93
+ "loss": 0.3144,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.3895131086142322,
98
+ "grad_norm": 0.48754820227622986,
99
+ "learning_rate": 4.886363636363637e-05,
100
+ "loss": 0.2577,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.41947565543071164,
105
+ "grad_norm": 0.5186039805412292,
106
+ "learning_rate": 4.8712121212121216e-05,
107
+ "loss": 0.2478,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.449438202247191,
112
+ "grad_norm": 0.6087205410003662,
113
+ "learning_rate": 4.856060606060606e-05,
114
+ "loss": 0.2272,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.4794007490636704,
119
+ "grad_norm": 0.8594069480895996,
120
+ "learning_rate": 4.840909090909091e-05,
121
+ "loss": 0.1992,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.5093632958801498,
126
+ "grad_norm": 0.6205722093582153,
127
+ "learning_rate": 4.825757575757576e-05,
128
+ "loss": 0.1631,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.5393258426966292,
133
+ "grad_norm": 0.4654604196548462,
134
+ "learning_rate": 4.810606060606061e-05,
135
+ "loss": 0.1629,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.5692883895131086,
140
+ "grad_norm": 0.9451954364776611,
141
+ "learning_rate": 4.795454545454546e-05,
142
+ "loss": 0.1814,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.599250936329588,
147
+ "grad_norm": 0.4229886829853058,
148
+ "learning_rate": 4.7803030303030304e-05,
149
+ "loss": 0.14,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.6292134831460674,
154
+ "grad_norm": 0.43104586005210876,
155
+ "learning_rate": 4.765151515151515e-05,
156
+ "loss": 0.1495,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.6591760299625468,
161
+ "grad_norm": 0.48881301283836365,
162
+ "learning_rate": 4.75e-05,
163
+ "loss": 0.0983,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.6891385767790262,
168
+ "grad_norm": 0.3992343544960022,
169
+ "learning_rate": 4.7348484848484855e-05,
170
+ "loss": 0.0893,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.7191011235955056,
175
+ "grad_norm": 0.4501804709434509,
176
+ "learning_rate": 4.71969696969697e-05,
177
+ "loss": 0.092,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.7490636704119851,
182
+ "grad_norm": 0.576210081577301,
183
+ "learning_rate": 4.704545454545455e-05,
184
+ "loss": 0.0741,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.7790262172284644,
189
+ "grad_norm": 0.4083947241306305,
190
+ "learning_rate": 4.689393939393939e-05,
191
+ "loss": 0.0572,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.8089887640449438,
196
+ "grad_norm": 0.5864295363426208,
197
+ "learning_rate": 4.6742424242424245e-05,
198
+ "loss": 0.0769,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.8389513108614233,
203
+ "grad_norm": 0.7252892851829529,
204
+ "learning_rate": 4.659090909090909e-05,
205
+ "loss": 0.0619,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.8689138576779026,
210
+ "grad_norm": 0.42146825790405273,
211
+ "learning_rate": 4.6439393939393944e-05,
212
+ "loss": 0.0384,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.898876404494382,
217
+ "grad_norm": 0.593726634979248,
218
+ "learning_rate": 4.628787878787879e-05,
219
+ "loss": 0.052,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.9288389513108615,
224
+ "grad_norm": 0.5652066469192505,
225
+ "learning_rate": 4.6136363636363635e-05,
226
+ "loss": 0.0468,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.9588014981273408,
231
+ "grad_norm": 0.28684931993484497,
232
+ "learning_rate": 4.598484848484849e-05,
233
+ "loss": 0.0295,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.9887640449438202,
238
+ "grad_norm": 0.2981000244617462,
239
+ "learning_rate": 4.5833333333333334e-05,
240
+ "loss": 0.032,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 1.0149812734082397,
245
+ "grad_norm": 0.48514777421951294,
246
+ "learning_rate": 4.5681818181818186e-05,
247
+ "loss": 0.0506,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 1.0449438202247192,
252
+ "grad_norm": 0.32234543561935425,
253
+ "learning_rate": 4.553030303030303e-05,
254
+ "loss": 0.0318,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 1.0749063670411985,
259
+ "grad_norm": 0.38080576062202454,
260
+ "learning_rate": 4.5378787878787885e-05,
261
+ "loss": 0.0258,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 1.104868913857678,
266
+ "grad_norm": 0.3635996878147125,
267
+ "learning_rate": 4.522727272727273e-05,
268
+ "loss": 0.037,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 1.1348314606741572,
273
+ "grad_norm": 0.42449885606765747,
274
+ "learning_rate": 4.5075757575757577e-05,
275
+ "loss": 0.0393,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 1.1647940074906367,
280
+ "grad_norm": 0.5858486890792847,
281
+ "learning_rate": 4.492424242424242e-05,
282
+ "loss": 0.0207,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 1.1947565543071161,
287
+ "grad_norm": 0.24009667336940765,
288
+ "learning_rate": 4.4772727272727275e-05,
289
+ "loss": 0.0189,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 1.2247191011235956,
294
+ "grad_norm": 0.21841216087341309,
295
+ "learning_rate": 4.462121212121213e-05,
296
+ "loss": 0.0173,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 1.2546816479400749,
301
+ "grad_norm": 0.34650227427482605,
302
+ "learning_rate": 4.4469696969696973e-05,
303
+ "loss": 0.0311,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 1.2846441947565543,
308
+ "grad_norm": 0.3726528584957123,
309
+ "learning_rate": 4.431818181818182e-05,
310
+ "loss": 0.0272,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 1.3146067415730336,
315
+ "grad_norm": 0.2907704710960388,
316
+ "learning_rate": 4.4166666666666665e-05,
317
+ "loss": 0.0235,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 1.344569288389513,
322
+ "grad_norm": 0.21228495240211487,
323
+ "learning_rate": 4.401515151515152e-05,
324
+ "loss": 0.0206,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 1.3745318352059925,
329
+ "grad_norm": 0.2763824462890625,
330
+ "learning_rate": 4.386363636363637e-05,
331
+ "loss": 0.0222,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 1.404494382022472,
336
+ "grad_norm": 0.2596808969974518,
337
+ "learning_rate": 4.3712121212121216e-05,
338
+ "loss": 0.0171,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 1.4344569288389513,
343
+ "grad_norm": 0.36683645844459534,
344
+ "learning_rate": 4.356060606060606e-05,
345
+ "loss": 0.0213,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 1.4644194756554307,
350
+ "grad_norm": 0.25381800532341003,
351
+ "learning_rate": 4.340909090909091e-05,
352
+ "loss": 0.0149,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 1.49438202247191,
357
+ "grad_norm": 0.4874545633792877,
358
+ "learning_rate": 4.325757575757576e-05,
359
+ "loss": 0.0235,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 1.5243445692883895,
364
+ "grad_norm": 0.35136911273002625,
365
+ "learning_rate": 4.3106060606060606e-05,
366
+ "loss": 0.0186,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 1.554307116104869,
371
+ "grad_norm": 0.3259860873222351,
372
+ "learning_rate": 4.295454545454546e-05,
373
+ "loss": 0.0228,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 1.5842696629213484,
378
+ "grad_norm": 0.24276824295520782,
379
+ "learning_rate": 4.2803030303030305e-05,
380
+ "loss": 0.0147,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 1.6142322097378277,
385
+ "grad_norm": 0.4493170976638794,
386
+ "learning_rate": 4.265151515151515e-05,
387
+ "loss": 0.0152,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 1.6441947565543071,
392
+ "grad_norm": 0.4474326968193054,
393
+ "learning_rate": 4.25e-05,
394
+ "loss": 0.0199,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 1.6741573033707864,
399
+ "grad_norm": 0.229719340801239,
400
+ "learning_rate": 4.234848484848485e-05,
401
+ "loss": 0.0166,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 1.7041198501872659,
406
+ "grad_norm": 0.2303067445755005,
407
+ "learning_rate": 4.21969696969697e-05,
408
+ "loss": 0.017,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 1.7340823970037453,
413
+ "grad_norm": 0.24925805628299713,
414
+ "learning_rate": 4.204545454545455e-05,
415
+ "loss": 0.0147,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 1.7640449438202248,
420
+ "grad_norm": 0.18361054360866547,
421
+ "learning_rate": 4.189393939393939e-05,
422
+ "loss": 0.0191,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 1.7940074906367043,
427
+ "grad_norm": 0.2936908006668091,
428
+ "learning_rate": 4.1742424242424246e-05,
429
+ "loss": 0.0189,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 1.8239700374531835,
434
+ "grad_norm": 0.2073887437582016,
435
+ "learning_rate": 4.159090909090909e-05,
436
+ "loss": 0.0171,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 1.8539325842696628,
441
+ "grad_norm": 0.3212382197380066,
442
+ "learning_rate": 4.143939393939394e-05,
443
+ "loss": 0.0204,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 1.8838951310861423,
448
+ "grad_norm": 0.1888497769832611,
449
+ "learning_rate": 4.128787878787879e-05,
450
+ "loss": 0.0201,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 1.9138576779026217,
455
+ "grad_norm": 0.18828518688678741,
456
+ "learning_rate": 4.113636363636364e-05,
457
+ "loss": 0.0179,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 1.9438202247191012,
462
+ "grad_norm": 0.22073791921138763,
463
+ "learning_rate": 4.098484848484849e-05,
464
+ "loss": 0.02,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 1.9737827715355807,
469
+ "grad_norm": 0.23251274228096008,
470
+ "learning_rate": 4.0833333333333334e-05,
471
+ "loss": 0.0184,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 2.0,
476
+ "grad_norm": 0.2079184651374817,
477
+ "learning_rate": 4.068181818181818e-05,
478
+ "loss": 0.0192,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 2.0299625468164795,
483
+ "grad_norm": 0.21343930065631866,
484
+ "learning_rate": 4.053030303030303e-05,
485
+ "loss": 0.0166,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 2.059925093632959,
490
+ "grad_norm": 0.2166517972946167,
491
+ "learning_rate": 4.0378787878787885e-05,
492
+ "loss": 0.0159,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 2.0898876404494384,
497
+ "grad_norm": 0.17601799964904785,
498
+ "learning_rate": 4.022727272727273e-05,
499
+ "loss": 0.0157,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 2.1198501872659175,
504
+ "grad_norm": 0.292283296585083,
505
+ "learning_rate": 4.007575757575758e-05,
506
+ "loss": 0.0214,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 2.149812734082397,
511
+ "grad_norm": 0.2258112132549286,
512
+ "learning_rate": 3.992424242424242e-05,
513
+ "loss": 0.0184,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 2.1797752808988764,
518
+ "grad_norm": 0.15815454721450806,
519
+ "learning_rate": 3.9772727272727275e-05,
520
+ "loss": 0.017,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 2.209737827715356,
525
+ "grad_norm": 0.26803699135780334,
526
+ "learning_rate": 3.962121212121213e-05,
527
+ "loss": 0.0182,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 2.2397003745318353,
532
+ "grad_norm": 0.2198362499475479,
533
+ "learning_rate": 3.9469696969696974e-05,
534
+ "loss": 0.0167,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 2.2696629213483144,
539
+ "grad_norm": 0.201346293091774,
540
+ "learning_rate": 3.931818181818182e-05,
541
+ "loss": 0.0161,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 2.299625468164794,
546
+ "grad_norm": 0.22819150984287262,
547
+ "learning_rate": 3.9166666666666665e-05,
548
+ "loss": 0.015,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 2.3295880149812733,
553
+ "grad_norm": 0.2712112069129944,
554
+ "learning_rate": 3.901515151515152e-05,
555
+ "loss": 0.0163,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 2.359550561797753,
560
+ "grad_norm": 0.19178956747055054,
561
+ "learning_rate": 3.8863636363636364e-05,
562
+ "loss": 0.0163,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 2.3895131086142323,
567
+ "grad_norm": 0.1914001852273941,
568
+ "learning_rate": 3.8712121212121217e-05,
569
+ "loss": 0.0168,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 2.4194756554307117,
574
+ "grad_norm": 0.1301780492067337,
575
+ "learning_rate": 3.856060606060606e-05,
576
+ "loss": 0.0151,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 2.449438202247191,
581
+ "grad_norm": 0.22975341975688934,
582
+ "learning_rate": 3.840909090909091e-05,
583
+ "loss": 0.0171,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 2.4794007490636703,
588
+ "grad_norm": 0.2856428623199463,
589
+ "learning_rate": 3.825757575757576e-05,
590
+ "loss": 0.0182,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 2.5093632958801497,
595
+ "grad_norm": 0.22180147469043732,
596
+ "learning_rate": 3.810606060606061e-05,
597
+ "loss": 0.0164,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 2.539325842696629,
602
+ "grad_norm": 0.18585917353630066,
603
+ "learning_rate": 3.795454545454545e-05,
604
+ "loss": 0.0175,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 2.5692883895131087,
609
+ "grad_norm": 0.21161819994449615,
610
+ "learning_rate": 3.7803030303030305e-05,
611
+ "loss": 0.0149,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 2.599250936329588,
616
+ "grad_norm": 0.14073120057582855,
617
+ "learning_rate": 3.765151515151516e-05,
618
+ "loss": 0.0143,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 2.629213483146067,
623
+ "grad_norm": 0.1988099217414856,
624
+ "learning_rate": 3.7500000000000003e-05,
625
+ "loss": 0.0155,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 2.6591760299625467,
630
+ "grad_norm": 0.17829206585884094,
631
+ "learning_rate": 3.734848484848485e-05,
632
+ "loss": 0.0172,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 2.689138576779026,
637
+ "grad_norm": 0.25729623436927795,
638
+ "learning_rate": 3.7196969696969695e-05,
639
+ "loss": 0.0161,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 2.7191011235955056,
644
+ "grad_norm": 0.15630777180194855,
645
+ "learning_rate": 3.704545454545455e-05,
646
+ "loss": 0.0161,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 2.749063670411985,
651
+ "grad_norm": 0.10787078738212585,
652
+ "learning_rate": 3.68939393939394e-05,
653
+ "loss": 0.0139,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 2.7790262172284645,
658
+ "grad_norm": 0.11183971166610718,
659
+ "learning_rate": 3.6742424242424246e-05,
660
+ "loss": 0.0142,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 2.808988764044944,
665
+ "grad_norm": 0.3003017008304596,
666
+ "learning_rate": 3.659090909090909e-05,
667
+ "loss": 0.0201,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 2.8389513108614235,
672
+ "grad_norm": 0.15837068855762482,
673
+ "learning_rate": 3.643939393939394e-05,
674
+ "loss": 0.014,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 2.8689138576779025,
679
+ "grad_norm": 0.15499652922153473,
680
+ "learning_rate": 3.628787878787879e-05,
681
+ "loss": 0.0166,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 2.898876404494382,
686
+ "grad_norm": 0.166601300239563,
687
+ "learning_rate": 3.613636363636364e-05,
688
+ "loss": 0.0136,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 2.9288389513108615,
693
+ "grad_norm": 0.23306916654109955,
694
+ "learning_rate": 3.598484848484849e-05,
695
+ "loss": 0.0145,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 2.958801498127341,
700
+ "grad_norm": 0.23148281872272491,
701
+ "learning_rate": 3.5833333333333335e-05,
702
+ "loss": 0.0166,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 2.98876404494382,
707
+ "grad_norm": 0.2514810562133789,
708
+ "learning_rate": 3.568181818181818e-05,
709
+ "loss": 0.0197,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 3.0149812734082397,
714
+ "grad_norm": 0.15844318270683289,
715
+ "learning_rate": 3.553030303030303e-05,
716
+ "loss": 0.0127,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 3.044943820224719,
721
+ "grad_norm": 0.15709055960178375,
722
+ "learning_rate": 3.537878787878788e-05,
723
+ "loss": 0.0144,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 3.0749063670411987,
728
+ "grad_norm": 0.21092790365219116,
729
+ "learning_rate": 3.522727272727273e-05,
730
+ "loss": 0.0174,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 3.1048689138576777,
735
+ "grad_norm": 0.22406940162181854,
736
+ "learning_rate": 3.507575757575758e-05,
737
+ "loss": 0.0151,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 3.134831460674157,
742
+ "grad_norm": 0.17414535582065582,
743
+ "learning_rate": 3.492424242424242e-05,
744
+ "loss": 0.0159,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 3.1647940074906367,
749
+ "grad_norm": 0.1722804456949234,
750
+ "learning_rate": 3.4772727272727276e-05,
751
+ "loss": 0.0146,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 3.194756554307116,
756
+ "grad_norm": 0.26471957564353943,
757
+ "learning_rate": 3.462121212121212e-05,
758
+ "loss": 0.0157,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 3.2247191011235956,
763
+ "grad_norm": 0.13862167298793793,
764
+ "learning_rate": 3.4469696969696974e-05,
765
+ "loss": 0.0137,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 3.254681647940075,
770
+ "grad_norm": 0.24047966301441193,
771
+ "learning_rate": 3.431818181818182e-05,
772
+ "loss": 0.017,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 3.284644194756554,
777
+ "grad_norm": 0.1237376257777214,
778
+ "learning_rate": 3.4166666666666666e-05,
779
+ "loss": 0.0151,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 3.3146067415730336,
784
+ "grad_norm": 0.15304620563983917,
785
+ "learning_rate": 3.401515151515152e-05,
786
+ "loss": 0.0155,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 3.344569288389513,
791
+ "grad_norm": 0.15872317552566528,
792
+ "learning_rate": 3.3863636363636364e-05,
793
+ "loss": 0.0147,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 3.3745318352059925,
798
+ "grad_norm": 0.18952298164367676,
799
+ "learning_rate": 3.371212121212121e-05,
800
+ "loss": 0.0154,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 3.404494382022472,
805
+ "grad_norm": 0.21287596225738525,
806
+ "learning_rate": 3.356060606060606e-05,
807
+ "loss": 0.0166,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 3.4344569288389515,
812
+ "grad_norm": 0.19477762281894684,
813
+ "learning_rate": 3.3409090909090915e-05,
814
+ "loss": 0.0167,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 3.464419475655431,
819
+ "grad_norm": 0.1801714450120926,
820
+ "learning_rate": 3.325757575757576e-05,
821
+ "loss": 0.0145,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 3.49438202247191,
826
+ "grad_norm": 0.14180026948451996,
827
+ "learning_rate": 3.310606060606061e-05,
828
+ "loss": 0.0138,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 3.5243445692883895,
833
+ "grad_norm": 0.21012850105762482,
834
+ "learning_rate": 3.295454545454545e-05,
835
+ "loss": 0.0165,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 3.554307116104869,
840
+ "grad_norm": 0.1273059993982315,
841
+ "learning_rate": 3.2803030303030305e-05,
842
+ "loss": 0.0148,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 3.5842696629213484,
847
+ "grad_norm": 0.13745197653770447,
848
+ "learning_rate": 3.265151515151516e-05,
849
+ "loss": 0.0137,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 3.6142322097378274,
854
+ "grad_norm": 0.19960223138332367,
855
+ "learning_rate": 3.2500000000000004e-05,
856
+ "loss": 0.0178,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 3.644194756554307,
861
+ "grad_norm": 0.21453413367271423,
862
+ "learning_rate": 3.234848484848485e-05,
863
+ "loss": 0.0156,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 3.6741573033707864,
868
+ "grad_norm": 0.17091749608516693,
869
+ "learning_rate": 3.2196969696969696e-05,
870
+ "loss": 0.0157,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 3.704119850187266,
875
+ "grad_norm": 0.15684160590171814,
876
+ "learning_rate": 3.204545454545455e-05,
877
+ "loss": 0.0148,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 3.7340823970037453,
882
+ "grad_norm": 0.15323583781719208,
883
+ "learning_rate": 3.18939393939394e-05,
884
+ "loss": 0.015,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 3.764044943820225,
889
+ "grad_norm": 0.13383668661117554,
890
+ "learning_rate": 3.174242424242425e-05,
891
+ "loss": 0.0154,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 3.7940074906367043,
896
+ "grad_norm": 0.15054528415203094,
897
+ "learning_rate": 3.159090909090909e-05,
898
+ "loss": 0.0153,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 3.8239700374531838,
903
+ "grad_norm": 0.10618451982736588,
904
+ "learning_rate": 3.143939393939394e-05,
905
+ "loss": 0.0131,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 3.853932584269663,
910
+ "grad_norm": 0.20882849395275116,
911
+ "learning_rate": 3.128787878787879e-05,
912
+ "loss": 0.019,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 3.8838951310861423,
917
+ "grad_norm": 0.19676630198955536,
918
+ "learning_rate": 3.113636363636364e-05,
919
+ "loss": 0.0164,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 3.9138576779026217,
924
+ "grad_norm": 0.10724353790283203,
925
+ "learning_rate": 3.098484848484849e-05,
926
+ "loss": 0.0145,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 3.943820224719101,
931
+ "grad_norm": 0.11003574728965759,
932
+ "learning_rate": 3.0833333333333335e-05,
933
+ "loss": 0.0153,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 3.9737827715355807,
938
+ "grad_norm": 0.10973632335662842,
939
+ "learning_rate": 3.068181818181818e-05,
940
+ "loss": 0.0131,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 4.0,
945
+ "grad_norm": 0.21611331403255463,
946
+ "learning_rate": 3.0530303030303034e-05,
947
+ "loss": 0.0184,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 4.0299625468164795,
952
+ "grad_norm": 0.11275507509708405,
953
+ "learning_rate": 3.037878787878788e-05,
954
+ "loss": 0.0159,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 4.059925093632959,
959
+ "grad_norm": 0.182546004652977,
960
+ "learning_rate": 3.0227272727272725e-05,
961
+ "loss": 0.0143,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 4.089887640449438,
966
+ "grad_norm": 0.11307963728904724,
967
+ "learning_rate": 3.0075757575757578e-05,
968
+ "loss": 0.014,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 4.119850187265918,
973
+ "grad_norm": 0.13171932101249695,
974
+ "learning_rate": 2.9924242424242427e-05,
975
+ "loss": 0.0159,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 4.149812734082397,
980
+ "grad_norm": 0.2185821682214737,
981
+ "learning_rate": 2.9772727272727273e-05,
982
+ "loss": 0.0158,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 4.179775280898877,
987
+ "grad_norm": 0.1575690507888794,
988
+ "learning_rate": 2.9621212121212122e-05,
989
+ "loss": 0.0168,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 4.209737827715355,
994
+ "grad_norm": 0.1727718561887741,
995
+ "learning_rate": 2.9469696969696968e-05,
996
+ "loss": 0.0154,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 4.239700374531835,
1001
+ "grad_norm": 0.13435468077659607,
1002
+ "learning_rate": 2.9318181818181817e-05,
1003
+ "loss": 0.0165,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 4.269662921348314,
1008
+ "grad_norm": 0.15063047409057617,
1009
+ "learning_rate": 2.916666666666667e-05,
1010
+ "loss": 0.0173,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 4.299625468164794,
1015
+ "grad_norm": 0.12659698724746704,
1016
+ "learning_rate": 2.901515151515152e-05,
1017
+ "loss": 0.0152,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 4.329588014981273,
1022
+ "grad_norm": 0.19473259150981903,
1023
+ "learning_rate": 2.8863636363636365e-05,
1024
+ "loss": 0.016,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 4.359550561797753,
1029
+ "grad_norm": 0.1952139437198639,
1030
+ "learning_rate": 2.8712121212121214e-05,
1031
+ "loss": 0.0164,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 4.389513108614232,
1036
+ "grad_norm": 0.15907561779022217,
1037
+ "learning_rate": 2.856060606060606e-05,
1038
+ "loss": 0.0126,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 4.419475655430712,
1043
+ "grad_norm": 0.197600319981575,
1044
+ "learning_rate": 2.8409090909090912e-05,
1045
+ "loss": 0.0166,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 4.449438202247191,
1050
+ "grad_norm": 0.09373123943805695,
1051
+ "learning_rate": 2.825757575757576e-05,
1052
+ "loss": 0.016,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 4.479400749063671,
1057
+ "grad_norm": 0.14290565252304077,
1058
+ "learning_rate": 2.8106060606060607e-05,
1059
+ "loss": 0.0172,
1060
+ "step": 300
1061
+ },
1062
+ {
1063
+ "epoch": 4.50936329588015,
1064
+ "grad_norm": 0.1223093792796135,
1065
+ "learning_rate": 2.7954545454545457e-05,
1066
+ "loss": 0.0157,
1067
+ "step": 302
1068
+ },
1069
+ {
1070
+ "epoch": 4.539325842696629,
1071
+ "grad_norm": 0.11388926208019257,
1072
+ "learning_rate": 2.7803030303030303e-05,
1073
+ "loss": 0.015,
1074
+ "step": 304
1075
+ },
1076
+ {
1077
+ "epoch": 4.569288389513108,
1078
+ "grad_norm": 0.10850539058446884,
1079
+ "learning_rate": 2.7651515151515152e-05,
1080
+ "loss": 0.0166,
1081
+ "step": 306
1082
+ },
1083
+ {
1084
+ "epoch": 4.599250936329588,
1085
+ "grad_norm": 0.13963742554187775,
1086
+ "learning_rate": 2.7500000000000004e-05,
1087
+ "loss": 0.0158,
1088
+ "step": 308
1089
+ },
1090
+ {
1091
+ "epoch": 4.629213483146067,
1092
+ "grad_norm": 0.15747179090976715,
1093
+ "learning_rate": 2.734848484848485e-05,
1094
+ "loss": 0.0144,
1095
+ "step": 310
1096
+ },
1097
+ {
1098
+ "epoch": 4.659176029962547,
1099
+ "grad_norm": 0.1513000726699829,
1100
+ "learning_rate": 2.71969696969697e-05,
1101
+ "loss": 0.0164,
1102
+ "step": 312
1103
+ },
1104
+ {
1105
+ "epoch": 4.689138576779026,
1106
+ "grad_norm": 0.14622750878334045,
1107
+ "learning_rate": 2.7045454545454545e-05,
1108
+ "loss": 0.016,
1109
+ "step": 314
1110
+ },
1111
+ {
1112
+ "epoch": 4.719101123595506,
1113
+ "grad_norm": 0.1300605684518814,
1114
+ "learning_rate": 2.6893939393939394e-05,
1115
+ "loss": 0.0158,
1116
+ "step": 316
1117
+ },
1118
+ {
1119
+ "epoch": 4.749063670411985,
1120
+ "grad_norm": 0.1521446704864502,
1121
+ "learning_rate": 2.674242424242424e-05,
1122
+ "loss": 0.0139,
1123
+ "step": 318
1124
+ },
1125
+ {
1126
+ "epoch": 4.7790262172284645,
1127
+ "grad_norm": 0.13343091309070587,
1128
+ "learning_rate": 2.6590909090909093e-05,
1129
+ "loss": 0.0141,
1130
+ "step": 320
1131
+ },
1132
+ {
1133
+ "epoch": 4.808988764044944,
1134
+ "grad_norm": 0.1171831339597702,
1135
+ "learning_rate": 2.6439393939393942e-05,
1136
+ "loss": 0.0129,
1137
+ "step": 322
1138
+ },
1139
+ {
1140
+ "epoch": 4.8389513108614235,
1141
+ "grad_norm": 0.10482454299926758,
1142
+ "learning_rate": 2.6287878787878788e-05,
1143
+ "loss": 0.0115,
1144
+ "step": 324
1145
+ },
1146
+ {
1147
+ "epoch": 4.868913857677903,
1148
+ "grad_norm": 0.13335193693637848,
1149
+ "learning_rate": 2.6136363636363637e-05,
1150
+ "loss": 0.0155,
1151
+ "step": 326
1152
+ },
1153
+ {
1154
+ "epoch": 4.898876404494382,
1155
+ "grad_norm": 0.1327083259820938,
1156
+ "learning_rate": 2.5984848484848483e-05,
1157
+ "loss": 0.0154,
1158
+ "step": 328
1159
+ },
1160
+ {
1161
+ "epoch": 4.928838951310862,
1162
+ "grad_norm": 0.15616530179977417,
1163
+ "learning_rate": 2.5833333333333336e-05,
1164
+ "loss": 0.0186,
1165
+ "step": 330
1166
+ },
1167
+ {
1168
+ "epoch": 4.9588014981273405,
1169
+ "grad_norm": 0.1196502074599266,
1170
+ "learning_rate": 2.5681818181818185e-05,
1171
+ "loss": 0.0151,
1172
+ "step": 332
1173
+ },
1174
+ {
1175
+ "epoch": 4.98876404494382,
1176
+ "grad_norm": 0.11737090349197388,
1177
+ "learning_rate": 2.553030303030303e-05,
1178
+ "loss": 0.013,
1179
+ "step": 334
1180
+ },
1181
+ {
1182
+ "epoch": 5.01498127340824,
1183
+ "grad_norm": 0.14445465803146362,
1184
+ "learning_rate": 2.537878787878788e-05,
1185
+ "loss": 0.0134,
1186
+ "step": 336
1187
+ },
1188
+ {
1189
+ "epoch": 5.044943820224719,
1190
+ "grad_norm": 0.10734406858682632,
1191
+ "learning_rate": 2.5227272727272726e-05,
1192
+ "loss": 0.0138,
1193
+ "step": 338
1194
+ },
1195
+ {
1196
+ "epoch": 5.074906367041199,
1197
+ "grad_norm": 0.11528757214546204,
1198
+ "learning_rate": 2.5075757575757575e-05,
1199
+ "loss": 0.013,
1200
+ "step": 340
1201
+ },
1202
+ {
1203
+ "epoch": 5.104868913857678,
1204
+ "grad_norm": 0.17952029407024384,
1205
+ "learning_rate": 2.4924242424242424e-05,
1206
+ "loss": 0.0152,
1207
+ "step": 342
1208
+ },
1209
+ {
1210
+ "epoch": 5.134831460674158,
1211
+ "grad_norm": 0.12444639205932617,
1212
+ "learning_rate": 2.4772727272727277e-05,
1213
+ "loss": 0.0148,
1214
+ "step": 344
1215
+ },
1216
+ {
1217
+ "epoch": 5.164794007490637,
1218
+ "grad_norm": 0.12819650769233704,
1219
+ "learning_rate": 2.4621212121212123e-05,
1220
+ "loss": 0.0146,
1221
+ "step": 346
1222
+ },
1223
+ {
1224
+ "epoch": 5.194756554307116,
1225
+ "grad_norm": 0.13396833837032318,
1226
+ "learning_rate": 2.4469696969696972e-05,
1227
+ "loss": 0.0175,
1228
+ "step": 348
1229
+ },
1230
+ {
1231
+ "epoch": 5.224719101123595,
1232
+ "grad_norm": 0.1286836415529251,
1233
+ "learning_rate": 2.431818181818182e-05,
1234
+ "loss": 0.0144,
1235
+ "step": 350
1236
+ },
1237
+ {
1238
+ "epoch": 5.254681647940075,
1239
+ "grad_norm": 0.12591804563999176,
1240
+ "learning_rate": 2.4166666666666667e-05,
1241
+ "loss": 0.0167,
1242
+ "step": 352
1243
+ },
1244
+ {
1245
+ "epoch": 5.284644194756554,
1246
+ "grad_norm": 0.12226350605487823,
1247
+ "learning_rate": 2.4015151515151516e-05,
1248
+ "loss": 0.0133,
1249
+ "step": 354
1250
+ },
1251
+ {
1252
+ "epoch": 5.314606741573034,
1253
+ "grad_norm": 0.10504593700170517,
1254
+ "learning_rate": 2.3863636363636365e-05,
1255
+ "loss": 0.0135,
1256
+ "step": 356
1257
+ },
1258
+ {
1259
+ "epoch": 5.344569288389513,
1260
+ "grad_norm": 0.1078866645693779,
1261
+ "learning_rate": 2.3712121212121214e-05,
1262
+ "loss": 0.0147,
1263
+ "step": 358
1264
+ },
1265
+ {
1266
+ "epoch": 5.3745318352059925,
1267
+ "grad_norm": 0.28363969922065735,
1268
+ "learning_rate": 2.356060606060606e-05,
1269
+ "loss": 0.0156,
1270
+ "step": 360
1271
+ },
1272
+ {
1273
+ "epoch": 5.404494382022472,
1274
+ "grad_norm": 0.1177087053656578,
1275
+ "learning_rate": 2.340909090909091e-05,
1276
+ "loss": 0.0138,
1277
+ "step": 362
1278
+ },
1279
+ {
1280
+ "epoch": 5.4344569288389515,
1281
+ "grad_norm": 0.16584421694278717,
1282
+ "learning_rate": 2.325757575757576e-05,
1283
+ "loss": 0.0179,
1284
+ "step": 364
1285
+ },
1286
+ {
1287
+ "epoch": 5.464419475655431,
1288
+ "grad_norm": 0.10715971887111664,
1289
+ "learning_rate": 2.3106060606060605e-05,
1290
+ "loss": 0.0144,
1291
+ "step": 366
1292
+ },
1293
+ {
1294
+ "epoch": 5.49438202247191,
1295
+ "grad_norm": 0.11904123425483704,
1296
+ "learning_rate": 2.2954545454545457e-05,
1297
+ "loss": 0.0133,
1298
+ "step": 368
1299
+ },
1300
+ {
1301
+ "epoch": 5.52434456928839,
1302
+ "grad_norm": 0.19020037353038788,
1303
+ "learning_rate": 2.2803030303030303e-05,
1304
+ "loss": 0.0178,
1305
+ "step": 370
1306
+ },
1307
+ {
1308
+ "epoch": 5.554307116104869,
1309
+ "grad_norm": 0.1367521733045578,
1310
+ "learning_rate": 2.2651515151515152e-05,
1311
+ "loss": 0.0155,
1312
+ "step": 372
1313
+ },
1314
+ {
1315
+ "epoch": 5.584269662921348,
1316
+ "grad_norm": 0.12585178017616272,
1317
+ "learning_rate": 2.25e-05,
1318
+ "loss": 0.0143,
1319
+ "step": 374
1320
+ },
1321
+ {
1322
+ "epoch": 5.614232209737827,
1323
+ "grad_norm": 0.20084144175052643,
1324
+ "learning_rate": 2.234848484848485e-05,
1325
+ "loss": 0.0178,
1326
+ "step": 376
1327
+ },
1328
+ {
1329
+ "epoch": 5.644194756554307,
1330
+ "grad_norm": 0.12197957187891006,
1331
+ "learning_rate": 2.21969696969697e-05,
1332
+ "loss": 0.0142,
1333
+ "step": 378
1334
+ },
1335
+ {
1336
+ "epoch": 5.674157303370786,
1337
+ "grad_norm": 0.11580586433410645,
1338
+ "learning_rate": 2.2045454545454546e-05,
1339
+ "loss": 0.0158,
1340
+ "step": 380
1341
+ },
1342
+ {
1343
+ "epoch": 5.704119850187266,
1344
+ "grad_norm": 0.1596754640340805,
1345
+ "learning_rate": 2.1893939393939395e-05,
1346
+ "loss": 0.0153,
1347
+ "step": 382
1348
+ },
1349
+ {
1350
+ "epoch": 5.734082397003745,
1351
+ "grad_norm": 0.11820989102125168,
1352
+ "learning_rate": 2.1742424242424244e-05,
1353
+ "loss": 0.0133,
1354
+ "step": 384
1355
+ },
1356
+ {
1357
+ "epoch": 5.764044943820225,
1358
+ "grad_norm": 0.1528993546962738,
1359
+ "learning_rate": 2.1590909090909093e-05,
1360
+ "loss": 0.0131,
1361
+ "step": 386
1362
+ },
1363
+ {
1364
+ "epoch": 5.794007490636704,
1365
+ "grad_norm": 0.15335053205490112,
1366
+ "learning_rate": 2.143939393939394e-05,
1367
+ "loss": 0.0188,
1368
+ "step": 388
1369
+ },
1370
+ {
1371
+ "epoch": 5.823970037453184,
1372
+ "grad_norm": 0.13823996484279633,
1373
+ "learning_rate": 2.128787878787879e-05,
1374
+ "loss": 0.0156,
1375
+ "step": 390
1376
+ },
1377
+ {
1378
+ "epoch": 5.853932584269663,
1379
+ "grad_norm": 0.11527912318706512,
1380
+ "learning_rate": 2.1136363636363638e-05,
1381
+ "loss": 0.0156,
1382
+ "step": 392
1383
+ },
1384
+ {
1385
+ "epoch": 5.883895131086143,
1386
+ "grad_norm": 0.09302780777215958,
1387
+ "learning_rate": 2.0984848484848483e-05,
1388
+ "loss": 0.0144,
1389
+ "step": 394
1390
+ },
1391
+ {
1392
+ "epoch": 5.913857677902621,
1393
+ "grad_norm": 0.1214398592710495,
1394
+ "learning_rate": 2.0833333333333336e-05,
1395
+ "loss": 0.0137,
1396
+ "step": 396
1397
+ },
1398
+ {
1399
+ "epoch": 5.943820224719101,
1400
+ "grad_norm": 0.17180432379245758,
1401
+ "learning_rate": 2.0681818181818182e-05,
1402
+ "loss": 0.0158,
1403
+ "step": 398
1404
+ },
1405
+ {
1406
+ "epoch": 5.97378277153558,
1407
+ "grad_norm": 0.13470757007598877,
1408
+ "learning_rate": 2.053030303030303e-05,
1409
+ "loss": 0.016,
1410
+ "step": 400
1411
+ },
1412
+ {
1413
+ "epoch": 6.0,
1414
+ "grad_norm": 0.12095994502305984,
1415
+ "learning_rate": 2.037878787878788e-05,
1416
+ "loss": 0.0136,
1417
+ "step": 402
1418
+ },
1419
+ {
1420
+ "epoch": 6.0299625468164795,
1421
+ "grad_norm": 0.13292968273162842,
1422
+ "learning_rate": 2.022727272727273e-05,
1423
+ "loss": 0.0146,
1424
+ "step": 404
1425
+ },
1426
+ {
1427
+ "epoch": 6.059925093632959,
1428
+ "grad_norm": 0.143639475107193,
1429
+ "learning_rate": 2.0075757575757575e-05,
1430
+ "loss": 0.0159,
1431
+ "step": 406
1432
+ },
1433
+ {
1434
+ "epoch": 6.089887640449438,
1435
+ "grad_norm": 0.13313822448253632,
1436
+ "learning_rate": 1.9924242424242425e-05,
1437
+ "loss": 0.017,
1438
+ "step": 408
1439
+ },
1440
+ {
1441
+ "epoch": 6.119850187265918,
1442
+ "grad_norm": 0.17898374795913696,
1443
+ "learning_rate": 1.9772727272727274e-05,
1444
+ "loss": 0.0162,
1445
+ "step": 410
1446
+ },
1447
+ {
1448
+ "epoch": 6.149812734082397,
1449
+ "grad_norm": 0.12149132043123245,
1450
+ "learning_rate": 1.962121212121212e-05,
1451
+ "loss": 0.0143,
1452
+ "step": 412
1453
+ },
1454
+ {
1455
+ "epoch": 6.179775280898877,
1456
+ "grad_norm": 0.12255310267210007,
1457
+ "learning_rate": 1.9469696969696972e-05,
1458
+ "loss": 0.0148,
1459
+ "step": 414
1460
+ },
1461
+ {
1462
+ "epoch": 6.209737827715355,
1463
+ "grad_norm": 0.17352508008480072,
1464
+ "learning_rate": 1.9318181818181818e-05,
1465
+ "loss": 0.0153,
1466
+ "step": 416
1467
+ },
1468
+ {
1469
+ "epoch": 6.239700374531835,
1470
+ "grad_norm": 0.15836010873317719,
1471
+ "learning_rate": 1.9166666666666667e-05,
1472
+ "loss": 0.0152,
1473
+ "step": 418
1474
+ },
1475
+ {
1476
+ "epoch": 6.269662921348314,
1477
+ "grad_norm": 0.13117386400699615,
1478
+ "learning_rate": 1.9015151515151516e-05,
1479
+ "loss": 0.0131,
1480
+ "step": 420
1481
+ },
1482
+ {
1483
+ "epoch": 6.299625468164794,
1484
+ "grad_norm": 0.09744709730148315,
1485
+ "learning_rate": 1.8863636363636362e-05,
1486
+ "loss": 0.0133,
1487
+ "step": 422
1488
+ },
1489
+ {
1490
+ "epoch": 6.329588014981273,
1491
+ "grad_norm": 0.11249203234910965,
1492
+ "learning_rate": 1.8712121212121215e-05,
1493
+ "loss": 0.0137,
1494
+ "step": 424
1495
+ },
1496
+ {
1497
+ "epoch": 6.359550561797753,
1498
+ "grad_norm": 0.14073345065116882,
1499
+ "learning_rate": 1.856060606060606e-05,
1500
+ "loss": 0.0158,
1501
+ "step": 426
1502
+ },
1503
+ {
1504
+ "epoch": 6.389513108614232,
1505
+ "grad_norm": 0.19942159950733185,
1506
+ "learning_rate": 1.840909090909091e-05,
1507
+ "loss": 0.0179,
1508
+ "step": 428
1509
+ },
1510
+ {
1511
+ "epoch": 6.419475655430712,
1512
+ "grad_norm": 0.12104730308055878,
1513
+ "learning_rate": 1.825757575757576e-05,
1514
+ "loss": 0.0143,
1515
+ "step": 430
1516
+ },
1517
+ {
1518
+ "epoch": 6.449438202247191,
1519
+ "grad_norm": 0.12874731421470642,
1520
+ "learning_rate": 1.810606060606061e-05,
1521
+ "loss": 0.0147,
1522
+ "step": 432
1523
+ },
1524
+ {
1525
+ "epoch": 6.479400749063671,
1526
+ "grad_norm": 0.09665031731128693,
1527
+ "learning_rate": 1.7954545454545454e-05,
1528
+ "loss": 0.0126,
1529
+ "step": 434
1530
+ },
1531
+ {
1532
+ "epoch": 6.50936329588015,
1533
+ "grad_norm": 0.22135666012763977,
1534
+ "learning_rate": 1.7803030303030303e-05,
1535
+ "loss": 0.0162,
1536
+ "step": 436
1537
+ },
1538
+ {
1539
+ "epoch": 6.539325842696629,
1540
+ "grad_norm": 0.12249334901571274,
1541
+ "learning_rate": 1.7651515151515153e-05,
1542
+ "loss": 0.013,
1543
+ "step": 438
1544
+ },
1545
+ {
1546
+ "epoch": 6.569288389513108,
1547
+ "grad_norm": 0.15929952263832092,
1548
+ "learning_rate": 1.75e-05,
1549
+ "loss": 0.0144,
1550
+ "step": 440
1551
+ },
1552
+ {
1553
+ "epoch": 6.599250936329588,
1554
+ "grad_norm": 0.116636261343956,
1555
+ "learning_rate": 1.734848484848485e-05,
1556
+ "loss": 0.0136,
1557
+ "step": 442
1558
+ },
1559
+ {
1560
+ "epoch": 6.629213483146067,
1561
+ "grad_norm": 0.26052579283714294,
1562
+ "learning_rate": 1.7196969696969697e-05,
1563
+ "loss": 0.0167,
1564
+ "step": 444
1565
+ },
1566
+ {
1567
+ "epoch": 6.659176029962547,
1568
+ "grad_norm": 0.16209331154823303,
1569
+ "learning_rate": 1.7045454545454546e-05,
1570
+ "loss": 0.0152,
1571
+ "step": 446
1572
+ },
1573
+ {
1574
+ "epoch": 6.689138576779026,
1575
+ "grad_norm": 0.11612333357334137,
1576
+ "learning_rate": 1.6893939393939395e-05,
1577
+ "loss": 0.0153,
1578
+ "step": 448
1579
+ },
1580
+ {
1581
+ "epoch": 6.719101123595506,
1582
+ "grad_norm": 0.092486672103405,
1583
+ "learning_rate": 1.674242424242424e-05,
1584
+ "loss": 0.0133,
1585
+ "step": 450
1586
+ },
1587
+ {
1588
+ "epoch": 6.749063670411985,
1589
+ "grad_norm": 0.10298772156238556,
1590
+ "learning_rate": 1.6590909090909094e-05,
1591
+ "loss": 0.0136,
1592
+ "step": 452
1593
+ },
1594
+ {
1595
+ "epoch": 6.7790262172284645,
1596
+ "grad_norm": 0.13439835608005524,
1597
+ "learning_rate": 1.643939393939394e-05,
1598
+ "loss": 0.016,
1599
+ "step": 454
1600
+ },
1601
+ {
1602
+ "epoch": 6.808988764044944,
1603
+ "grad_norm": 0.14403583109378815,
1604
+ "learning_rate": 1.628787878787879e-05,
1605
+ "loss": 0.014,
1606
+ "step": 456
1607
+ },
1608
+ {
1609
+ "epoch": 6.8389513108614235,
1610
+ "grad_norm": 0.1841178834438324,
1611
+ "learning_rate": 1.6136363636363638e-05,
1612
+ "loss": 0.0149,
1613
+ "step": 458
1614
+ },
1615
+ {
1616
+ "epoch": 6.868913857677903,
1617
+ "grad_norm": 0.09390496462583542,
1618
+ "learning_rate": 1.5984848484848487e-05,
1619
+ "loss": 0.0141,
1620
+ "step": 460
1621
+ },
1622
+ {
1623
+ "epoch": 6.898876404494382,
1624
+ "grad_norm": 0.16365155577659607,
1625
+ "learning_rate": 1.5833333333333333e-05,
1626
+ "loss": 0.0157,
1627
+ "step": 462
1628
+ },
1629
+ {
1630
+ "epoch": 6.928838951310862,
1631
+ "grad_norm": 0.1577712446451187,
1632
+ "learning_rate": 1.5681818181818182e-05,
1633
+ "loss": 0.0141,
1634
+ "step": 464
1635
+ },
1636
+ {
1637
+ "epoch": 6.9588014981273405,
1638
+ "grad_norm": 0.173916295170784,
1639
+ "learning_rate": 1.553030303030303e-05,
1640
+ "loss": 0.0157,
1641
+ "step": 466
1642
+ },
1643
+ {
1644
+ "epoch": 6.98876404494382,
1645
+ "grad_norm": 0.16699424386024475,
1646
+ "learning_rate": 1.5378787878787877e-05,
1647
+ "loss": 0.0169,
1648
+ "step": 468
1649
+ },
1650
+ {
1651
+ "epoch": 7.01498127340824,
1652
+ "grad_norm": 0.12708672881126404,
1653
+ "learning_rate": 1.5227272727272728e-05,
1654
+ "loss": 0.0142,
1655
+ "step": 470
1656
+ },
1657
+ {
1658
+ "epoch": 7.044943820224719,
1659
+ "grad_norm": 0.15440689027309418,
1660
+ "learning_rate": 1.5075757575757576e-05,
1661
+ "loss": 0.0158,
1662
+ "step": 472
1663
+ },
1664
+ {
1665
+ "epoch": 7.074906367041199,
1666
+ "grad_norm": 0.1230991929769516,
1667
+ "learning_rate": 1.4924242424242423e-05,
1668
+ "loss": 0.0136,
1669
+ "step": 474
1670
+ },
1671
+ {
1672
+ "epoch": 7.104868913857678,
1673
+ "grad_norm": 0.21653351187705994,
1674
+ "learning_rate": 1.4772727272727274e-05,
1675
+ "loss": 0.0159,
1676
+ "step": 476
1677
+ },
1678
+ {
1679
+ "epoch": 7.134831460674158,
1680
+ "grad_norm": 0.1883053332567215,
1681
+ "learning_rate": 1.4621212121212122e-05,
1682
+ "loss": 0.0155,
1683
+ "step": 478
1684
+ },
1685
+ {
1686
+ "epoch": 7.164794007490637,
1687
+ "grad_norm": 0.22849740087985992,
1688
+ "learning_rate": 1.446969696969697e-05,
1689
+ "loss": 0.0171,
1690
+ "step": 480
1691
+ },
1692
+ {
1693
+ "epoch": 7.194756554307116,
1694
+ "grad_norm": 0.12744282186031342,
1695
+ "learning_rate": 1.431818181818182e-05,
1696
+ "loss": 0.0142,
1697
+ "step": 482
1698
+ },
1699
+ {
1700
+ "epoch": 7.224719101123595,
1701
+ "grad_norm": 0.09133846312761307,
1702
+ "learning_rate": 1.4166666666666668e-05,
1703
+ "loss": 0.0133,
1704
+ "step": 484
1705
+ },
1706
+ {
1707
+ "epoch": 7.254681647940075,
1708
+ "grad_norm": 0.13602511584758759,
1709
+ "learning_rate": 1.4015151515151515e-05,
1710
+ "loss": 0.014,
1711
+ "step": 486
1712
+ },
1713
+ {
1714
+ "epoch": 7.284644194756554,
1715
+ "grad_norm": 0.13092727959156036,
1716
+ "learning_rate": 1.3863636363636364e-05,
1717
+ "loss": 0.0149,
1718
+ "step": 488
1719
+ },
1720
+ {
1721
+ "epoch": 7.314606741573034,
1722
+ "grad_norm": 0.12762710452079773,
1723
+ "learning_rate": 1.3712121212121212e-05,
1724
+ "loss": 0.0143,
1725
+ "step": 490
1726
+ },
1727
+ {
1728
+ "epoch": 7.344569288389513,
1729
+ "grad_norm": 0.12416286021471024,
1730
+ "learning_rate": 1.3560606060606063e-05,
1731
+ "loss": 0.0145,
1732
+ "step": 492
1733
+ },
1734
+ {
1735
+ "epoch": 7.3745318352059925,
1736
+ "grad_norm": 0.145538792014122,
1737
+ "learning_rate": 1.340909090909091e-05,
1738
+ "loss": 0.0145,
1739
+ "step": 494
1740
+ },
1741
+ {
1742
+ "epoch": 7.404494382022472,
1743
+ "grad_norm": 0.11264869570732117,
1744
+ "learning_rate": 1.3257575757575758e-05,
1745
+ "loss": 0.0156,
1746
+ "step": 496
1747
+ },
1748
+ {
1749
+ "epoch": 7.4344569288389515,
1750
+ "grad_norm": 0.10543698072433472,
1751
+ "learning_rate": 1.3106060606060607e-05,
1752
+ "loss": 0.0141,
1753
+ "step": 498
1754
+ },
1755
+ {
1756
+ "epoch": 7.464419475655431,
1757
+ "grad_norm": 0.1221228539943695,
1758
+ "learning_rate": 1.2954545454545455e-05,
1759
+ "loss": 0.0146,
1760
+ "step": 500
1761
+ },
1762
+ {
1763
+ "epoch": 7.49438202247191,
1764
+ "grad_norm": 0.12155947834253311,
1765
+ "learning_rate": 1.2803030303030302e-05,
1766
+ "loss": 0.0141,
1767
+ "step": 502
1768
+ },
1769
+ {
1770
+ "epoch": 7.52434456928839,
1771
+ "grad_norm": 0.12504641711711884,
1772
+ "learning_rate": 1.2651515151515153e-05,
1773
+ "loss": 0.0128,
1774
+ "step": 504
1775
+ },
1776
+ {
1777
+ "epoch": 7.554307116104869,
1778
+ "grad_norm": 0.11169607192277908,
1779
+ "learning_rate": 1.25e-05,
1780
+ "loss": 0.0128,
1781
+ "step": 506
1782
+ },
1783
+ {
1784
+ "epoch": 7.584269662921348,
1785
+ "grad_norm": 0.1285315901041031,
1786
+ "learning_rate": 1.234848484848485e-05,
1787
+ "loss": 0.0161,
1788
+ "step": 508
1789
+ },
1790
+ {
1791
+ "epoch": 7.614232209737827,
1792
+ "grad_norm": 0.10635136067867279,
1793
+ "learning_rate": 1.2196969696969697e-05,
1794
+ "loss": 0.0149,
1795
+ "step": 510
1796
+ },
1797
+ {
1798
+ "epoch": 7.644194756554307,
1799
+ "grad_norm": 0.11686955392360687,
1800
+ "learning_rate": 1.2045454545454547e-05,
1801
+ "loss": 0.0138,
1802
+ "step": 512
1803
+ },
1804
+ {
1805
+ "epoch": 7.674157303370786,
1806
+ "grad_norm": 0.08601470291614532,
1807
+ "learning_rate": 1.1893939393939394e-05,
1808
+ "loss": 0.0131,
1809
+ "step": 514
1810
+ },
1811
+ {
1812
+ "epoch": 7.704119850187266,
1813
+ "grad_norm": 0.0880078673362732,
1814
+ "learning_rate": 1.1742424242424243e-05,
1815
+ "loss": 0.0131,
1816
+ "step": 516
1817
+ },
1818
+ {
1819
+ "epoch": 7.734082397003745,
1820
+ "grad_norm": 0.15093624591827393,
1821
+ "learning_rate": 1.159090909090909e-05,
1822
+ "loss": 0.0162,
1823
+ "step": 518
1824
+ },
1825
+ {
1826
+ "epoch": 7.764044943820225,
1827
+ "grad_norm": 0.11285064369440079,
1828
+ "learning_rate": 1.143939393939394e-05,
1829
+ "loss": 0.015,
1830
+ "step": 520
1831
+ },
1832
+ {
1833
+ "epoch": 7.794007490636704,
1834
+ "grad_norm": 0.10577835887670517,
1835
+ "learning_rate": 1.128787878787879e-05,
1836
+ "loss": 0.0132,
1837
+ "step": 522
1838
+ },
1839
+ {
1840
+ "epoch": 7.823970037453184,
1841
+ "grad_norm": 0.19718210399150848,
1842
+ "learning_rate": 1.1136363636363637e-05,
1843
+ "loss": 0.0143,
1844
+ "step": 524
1845
+ },
1846
+ {
1847
+ "epoch": 7.853932584269663,
1848
+ "grad_norm": 0.13446953892707825,
1849
+ "learning_rate": 1.0984848484848486e-05,
1850
+ "loss": 0.0157,
1851
+ "step": 526
1852
+ },
1853
+ {
1854
+ "epoch": 7.883895131086143,
1855
+ "grad_norm": 0.12463881075382233,
1856
+ "learning_rate": 1.0833333333333334e-05,
1857
+ "loss": 0.015,
1858
+ "step": 528
1859
+ },
1860
+ {
1861
+ "epoch": 7.913857677902621,
1862
+ "grad_norm": 0.13918359577655792,
1863
+ "learning_rate": 1.0681818181818181e-05,
1864
+ "loss": 0.0124,
1865
+ "step": 530
1866
+ },
1867
+ {
1868
+ "epoch": 7.943820224719101,
1869
+ "grad_norm": 0.1380302906036377,
1870
+ "learning_rate": 1.053030303030303e-05,
1871
+ "loss": 0.014,
1872
+ "step": 532
1873
+ },
1874
+ {
1875
+ "epoch": 7.97378277153558,
1876
+ "grad_norm": 0.14899957180023193,
1877
+ "learning_rate": 1.037878787878788e-05,
1878
+ "loss": 0.0175,
1879
+ "step": 534
1880
+ },
1881
+ {
1882
+ "epoch": 8.0,
1883
+ "grad_norm": 0.11646629869937897,
1884
+ "learning_rate": 1.0227272727272729e-05,
1885
+ "loss": 0.0145,
1886
+ "step": 536
1887
+ },
1888
+ {
1889
+ "epoch": 8.02996254681648,
1890
+ "grad_norm": 0.14022769033908844,
1891
+ "learning_rate": 1.0075757575757576e-05,
1892
+ "loss": 0.0121,
1893
+ "step": 538
1894
+ },
1895
+ {
1896
+ "epoch": 8.059925093632959,
1897
+ "grad_norm": 0.15053826570510864,
1898
+ "learning_rate": 9.924242424242425e-06,
1899
+ "loss": 0.0157,
1900
+ "step": 540
1901
+ },
1902
+ {
1903
+ "epoch": 8.089887640449438,
1904
+ "grad_norm": 0.11895288527011871,
1905
+ "learning_rate": 9.772727272727273e-06,
1906
+ "loss": 0.0141,
1907
+ "step": 542
1908
+ },
1909
+ {
1910
+ "epoch": 8.119850187265918,
1911
+ "grad_norm": 0.11707016080617905,
1912
+ "learning_rate": 9.62121212121212e-06,
1913
+ "loss": 0.0145,
1914
+ "step": 544
1915
+ },
1916
+ {
1917
+ "epoch": 8.149812734082397,
1918
+ "grad_norm": 0.10449573397636414,
1919
+ "learning_rate": 9.46969696969697e-06,
1920
+ "loss": 0.0146,
1921
+ "step": 546
1922
+ },
1923
+ {
1924
+ "epoch": 8.179775280898877,
1925
+ "grad_norm": 0.13925935328006744,
1926
+ "learning_rate": 9.318181818181819e-06,
1927
+ "loss": 0.014,
1928
+ "step": 548
1929
+ },
1930
+ {
1931
+ "epoch": 8.209737827715356,
1932
+ "grad_norm": 0.12868592143058777,
1933
+ "learning_rate": 9.166666666666666e-06,
1934
+ "loss": 0.0138,
1935
+ "step": 550
1936
+ },
1937
+ {
1938
+ "epoch": 8.239700374531836,
1939
+ "grad_norm": 0.11764951050281525,
1940
+ "learning_rate": 9.015151515151516e-06,
1941
+ "loss": 0.0147,
1942
+ "step": 552
1943
+ },
1944
+ {
1945
+ "epoch": 8.269662921348315,
1946
+ "grad_norm": 0.21383918821811676,
1947
+ "learning_rate": 8.863636363636365e-06,
1948
+ "loss": 0.0134,
1949
+ "step": 554
1950
+ },
1951
+ {
1952
+ "epoch": 8.299625468164795,
1953
+ "grad_norm": 0.14592906832695007,
1954
+ "learning_rate": 8.712121212121212e-06,
1955
+ "loss": 0.0151,
1956
+ "step": 556
1957
+ },
1958
+ {
1959
+ "epoch": 8.329588014981274,
1960
+ "grad_norm": 0.1377759724855423,
1961
+ "learning_rate": 8.56060606060606e-06,
1962
+ "loss": 0.0138,
1963
+ "step": 558
1964
+ },
1965
+ {
1966
+ "epoch": 8.359550561797754,
1967
+ "grad_norm": 0.15097083151340485,
1968
+ "learning_rate": 8.409090909090909e-06,
1969
+ "loss": 0.013,
1970
+ "step": 560
1971
+ },
1972
+ {
1973
+ "epoch": 8.389513108614231,
1974
+ "grad_norm": 0.1862707883119583,
1975
+ "learning_rate": 8.257575757575758e-06,
1976
+ "loss": 0.0119,
1977
+ "step": 562
1978
+ },
1979
+ {
1980
+ "epoch": 8.41947565543071,
1981
+ "grad_norm": 0.19083456695079803,
1982
+ "learning_rate": 8.106060606060606e-06,
1983
+ "loss": 0.0175,
1984
+ "step": 564
1985
+ },
1986
+ {
1987
+ "epoch": 8.44943820224719,
1988
+ "grad_norm": 0.18206746876239777,
1989
+ "learning_rate": 7.954545454545455e-06,
1990
+ "loss": 0.0153,
1991
+ "step": 566
1992
+ },
1993
+ {
1994
+ "epoch": 8.47940074906367,
1995
+ "grad_norm": 0.1560777872800827,
1996
+ "learning_rate": 7.803030303030304e-06,
1997
+ "loss": 0.0142,
1998
+ "step": 568
1999
+ },
2000
+ {
2001
+ "epoch": 8.50936329588015,
2002
+ "grad_norm": 0.11597474664449692,
2003
+ "learning_rate": 7.651515151515152e-06,
2004
+ "loss": 0.015,
2005
+ "step": 570
2006
+ },
2007
+ {
2008
+ "epoch": 8.539325842696629,
2009
+ "grad_norm": 0.14232860505580902,
2010
+ "learning_rate": 7.5e-06,
2011
+ "loss": 0.0154,
2012
+ "step": 572
2013
+ },
2014
+ {
2015
+ "epoch": 8.569288389513108,
2016
+ "grad_norm": 0.12590251863002777,
2017
+ "learning_rate": 7.3484848484848486e-06,
2018
+ "loss": 0.0141,
2019
+ "step": 574
2020
+ },
2021
+ {
2022
+ "epoch": 8.599250936329588,
2023
+ "grad_norm": 0.161521315574646,
2024
+ "learning_rate": 7.196969696969698e-06,
2025
+ "loss": 0.0152,
2026
+ "step": 576
2027
+ },
2028
+ {
2029
+ "epoch": 8.629213483146067,
2030
+ "grad_norm": 0.12818320095539093,
2031
+ "learning_rate": 7.045454545454545e-06,
2032
+ "loss": 0.0133,
2033
+ "step": 578
2034
+ },
2035
+ {
2036
+ "epoch": 8.659176029962547,
2037
+ "grad_norm": 0.10711938887834549,
2038
+ "learning_rate": 6.8939393939393945e-06,
2039
+ "loss": 0.0143,
2040
+ "step": 580
2041
+ },
2042
+ {
2043
+ "epoch": 8.689138576779026,
2044
+ "grad_norm": 0.11545701324939728,
2045
+ "learning_rate": 6.742424242424243e-06,
2046
+ "loss": 0.0153,
2047
+ "step": 582
2048
+ },
2049
+ {
2050
+ "epoch": 8.719101123595506,
2051
+ "grad_norm": 0.15045291185379028,
2052
+ "learning_rate": 6.59090909090909e-06,
2053
+ "loss": 0.0133,
2054
+ "step": 584
2055
+ },
2056
+ {
2057
+ "epoch": 8.749063670411985,
2058
+ "grad_norm": 0.1033000648021698,
2059
+ "learning_rate": 6.43939393939394e-06,
2060
+ "loss": 0.0145,
2061
+ "step": 586
2062
+ },
2063
+ {
2064
+ "epoch": 8.779026217228465,
2065
+ "grad_norm": 0.16855841875076294,
2066
+ "learning_rate": 6.287878787878789e-06,
2067
+ "loss": 0.0152,
2068
+ "step": 588
2069
+ },
2070
+ {
2071
+ "epoch": 8.808988764044944,
2072
+ "grad_norm": 0.11125820875167847,
2073
+ "learning_rate": 6.136363636363636e-06,
2074
+ "loss": 0.0143,
2075
+ "step": 590
2076
+ },
2077
+ {
2078
+ "epoch": 8.838951310861423,
2079
+ "grad_norm": 0.11163821816444397,
2080
+ "learning_rate": 5.984848484848485e-06,
2081
+ "loss": 0.0143,
2082
+ "step": 592
2083
+ },
2084
+ {
2085
+ "epoch": 8.868913857677903,
2086
+ "grad_norm": 0.11566553264856339,
2087
+ "learning_rate": 5.833333333333334e-06,
2088
+ "loss": 0.0142,
2089
+ "step": 594
2090
+ },
2091
+ {
2092
+ "epoch": 8.898876404494382,
2093
+ "grad_norm": 0.11087555438280106,
2094
+ "learning_rate": 5.681818181818182e-06,
2095
+ "loss": 0.0148,
2096
+ "step": 596
2097
+ },
2098
+ {
2099
+ "epoch": 8.928838951310862,
2100
+ "grad_norm": 0.1234087273478508,
2101
+ "learning_rate": 5.530303030303031e-06,
2102
+ "loss": 0.0156,
2103
+ "step": 598
2104
+ },
2105
+ {
2106
+ "epoch": 8.958801498127341,
2107
+ "grad_norm": 0.18318650126457214,
2108
+ "learning_rate": 5.378787878787879e-06,
2109
+ "loss": 0.0145,
2110
+ "step": 600
2111
+ },
2112
+ {
2113
+ "epoch": 8.98876404494382,
2114
+ "grad_norm": 0.09113040566444397,
2115
+ "learning_rate": 5.2272727272727274e-06,
2116
+ "loss": 0.0132,
2117
+ "step": 602
2118
+ },
2119
+ {
2120
+ "epoch": 9.014981273408239,
2121
+ "grad_norm": 0.10578633099794388,
2122
+ "learning_rate": 5.075757575757576e-06,
2123
+ "loss": 0.0143,
2124
+ "step": 604
2125
+ },
2126
+ {
2127
+ "epoch": 9.044943820224718,
2128
+ "grad_norm": 0.15693627297878265,
2129
+ "learning_rate": 4.924242424242424e-06,
2130
+ "loss": 0.015,
2131
+ "step": 606
2132
+ },
2133
+ {
2134
+ "epoch": 9.074906367041198,
2135
+ "grad_norm": 0.1018158420920372,
2136
+ "learning_rate": 4.772727272727273e-06,
2137
+ "loss": 0.0139,
2138
+ "step": 608
2139
+ },
2140
+ {
2141
+ "epoch": 9.104868913857677,
2142
+ "grad_norm": 0.17492976784706116,
2143
+ "learning_rate": 4.621212121212122e-06,
2144
+ "loss": 0.0156,
2145
+ "step": 610
2146
+ },
2147
+ {
2148
+ "epoch": 9.134831460674157,
2149
+ "grad_norm": 0.11221963167190552,
2150
+ "learning_rate": 4.46969696969697e-06,
2151
+ "loss": 0.0152,
2152
+ "step": 612
2153
+ },
2154
+ {
2155
+ "epoch": 9.164794007490636,
2156
+ "grad_norm": 0.12558336555957794,
2157
+ "learning_rate": 4.3181818181818185e-06,
2158
+ "loss": 0.0143,
2159
+ "step": 614
2160
+ },
2161
+ {
2162
+ "epoch": 9.194756554307116,
2163
+ "grad_norm": 0.11668603867292404,
2164
+ "learning_rate": 4.166666666666667e-06,
2165
+ "loss": 0.0127,
2166
+ "step": 616
2167
+ },
2168
+ {
2169
+ "epoch": 9.224719101123595,
2170
+ "grad_norm": 0.14164716005325317,
2171
+ "learning_rate": 4.015151515151515e-06,
2172
+ "loss": 0.0155,
2173
+ "step": 618
2174
+ },
2175
+ {
2176
+ "epoch": 9.254681647940075,
2177
+ "grad_norm": 0.12440814077854156,
2178
+ "learning_rate": 3.863636363636364e-06,
2179
+ "loss": 0.0134,
2180
+ "step": 620
2181
+ },
2182
+ {
2183
+ "epoch": 9.284644194756554,
2184
+ "grad_norm": 0.14497360587120056,
2185
+ "learning_rate": 3.7121212121212124e-06,
2186
+ "loss": 0.0152,
2187
+ "step": 622
2188
+ },
2189
+ {
2190
+ "epoch": 9.314606741573034,
2191
+ "grad_norm": 0.13429833948612213,
2192
+ "learning_rate": 3.5606060606060608e-06,
2193
+ "loss": 0.015,
2194
+ "step": 624
2195
+ },
2196
+ {
2197
+ "epoch": 9.344569288389513,
2198
+ "grad_norm": 0.11680711805820465,
2199
+ "learning_rate": 3.409090909090909e-06,
2200
+ "loss": 0.0141,
2201
+ "step": 626
2202
+ },
2203
+ {
2204
+ "epoch": 9.374531835205993,
2205
+ "grad_norm": 0.141137033700943,
2206
+ "learning_rate": 3.257575757575758e-06,
2207
+ "loss": 0.0137,
2208
+ "step": 628
2209
+ },
2210
+ {
2211
+ "epoch": 9.404494382022472,
2212
+ "grad_norm": 0.11425523459911346,
2213
+ "learning_rate": 3.106060606060606e-06,
2214
+ "loss": 0.0153,
2215
+ "step": 630
2216
+ },
2217
+ {
2218
+ "epoch": 9.434456928838951,
2219
+ "grad_norm": 0.175795778632164,
2220
+ "learning_rate": 2.9545454545454547e-06,
2221
+ "loss": 0.0137,
2222
+ "step": 632
2223
+ },
2224
+ {
2225
+ "epoch": 9.464419475655431,
2226
+ "grad_norm": 0.21211205422878265,
2227
+ "learning_rate": 2.803030303030303e-06,
2228
+ "loss": 0.0145,
2229
+ "step": 634
2230
+ },
2231
+ {
2232
+ "epoch": 9.49438202247191,
2233
+ "grad_norm": 0.12809644639492035,
2234
+ "learning_rate": 2.651515151515152e-06,
2235
+ "loss": 0.0137,
2236
+ "step": 636
2237
+ },
2238
+ {
2239
+ "epoch": 9.52434456928839,
2240
+ "grad_norm": 0.1471203863620758,
2241
+ "learning_rate": 2.5e-06,
2242
+ "loss": 0.0122,
2243
+ "step": 638
2244
+ },
2245
+ {
2246
+ "epoch": 9.55430711610487,
2247
+ "grad_norm": 0.11589685082435608,
2248
+ "learning_rate": 2.3484848484848486e-06,
2249
+ "loss": 0.0137,
2250
+ "step": 640
2251
+ },
2252
+ {
2253
+ "epoch": 9.584269662921349,
2254
+ "grad_norm": 0.11537714302539825,
2255
+ "learning_rate": 2.196969696969697e-06,
2256
+ "loss": 0.0147,
2257
+ "step": 642
2258
+ },
2259
+ {
2260
+ "epoch": 9.614232209737828,
2261
+ "grad_norm": 0.10002223402261734,
2262
+ "learning_rate": 2.0454545454545457e-06,
2263
+ "loss": 0.0139,
2264
+ "step": 644
2265
+ },
2266
+ {
2267
+ "epoch": 9.644194756554308,
2268
+ "grad_norm": 0.1463649868965149,
2269
+ "learning_rate": 1.8939393939393941e-06,
2270
+ "loss": 0.0138,
2271
+ "step": 646
2272
+ },
2273
+ {
2274
+ "epoch": 9.674157303370787,
2275
+ "grad_norm": 0.15200403332710266,
2276
+ "learning_rate": 1.7424242424242427e-06,
2277
+ "loss": 0.0127,
2278
+ "step": 648
2279
+ },
2280
+ {
2281
+ "epoch": 9.704119850187267,
2282
+ "grad_norm": 0.1294555813074112,
2283
+ "learning_rate": 1.5909090909090908e-06,
2284
+ "loss": 0.013,
2285
+ "step": 650
2286
+ },
2287
+ {
2288
+ "epoch": 9.734082397003746,
2289
+ "grad_norm": 0.12834538519382477,
2290
+ "learning_rate": 1.4393939393939396e-06,
2291
+ "loss": 0.014,
2292
+ "step": 652
2293
+ },
2294
+ {
2295
+ "epoch": 9.764044943820224,
2296
+ "grad_norm": 0.16599954664707184,
2297
+ "learning_rate": 1.287878787878788e-06,
2298
+ "loss": 0.0153,
2299
+ "step": 654
2300
+ },
2301
+ {
2302
+ "epoch": 9.794007490636703,
2303
+ "grad_norm": 0.14348356425762177,
2304
+ "learning_rate": 1.1363636363636364e-06,
2305
+ "loss": 0.0145,
2306
+ "step": 656
2307
+ },
2308
+ {
2309
+ "epoch": 9.823970037453183,
2310
+ "grad_norm": 0.1504441797733307,
2311
+ "learning_rate": 9.848484848484847e-07,
2312
+ "loss": 0.0148,
2313
+ "step": 658
2314
+ },
2315
+ {
2316
+ "epoch": 9.853932584269662,
2317
+ "grad_norm": 0.12484189122915268,
2318
+ "learning_rate": 8.333333333333333e-07,
2319
+ "loss": 0.0156,
2320
+ "step": 660
2321
+ },
2322
+ {
2323
+ "epoch": 9.883895131086142,
2324
+ "grad_norm": 0.17609864473342896,
2325
+ "learning_rate": 6.818181818181818e-07,
2326
+ "loss": 0.0154,
2327
+ "step": 662
2328
+ },
2329
+ {
2330
+ "epoch": 9.913857677902621,
2331
+ "grad_norm": 0.1843879073858261,
2332
+ "learning_rate": 5.303030303030304e-07,
2333
+ "loss": 0.0133,
2334
+ "step": 664
2335
+ },
2336
+ {
2337
+ "epoch": 9.9438202247191,
2338
+ "grad_norm": 0.145470529794693,
2339
+ "learning_rate": 3.787878787878788e-07,
2340
+ "loss": 0.0142,
2341
+ "step": 666
2342
+ },
2343
+ {
2344
+ "epoch": 9.97378277153558,
2345
+ "grad_norm": 0.13248123228549957,
2346
+ "learning_rate": 2.2727272727272726e-07,
2347
+ "loss": 0.0145,
2348
+ "step": 668
2349
+ },
2350
+ {
2351
+ "epoch": 10.0,
2352
+ "grad_norm": 0.18026700615882874,
2353
+ "learning_rate": 7.575757575757576e-08,
2354
+ "loss": 0.0139,
2355
+ "step": 670
2356
+ }
2357
+ ],
2358
+ "logging_steps": 2,
2359
+ "max_steps": 670,
2360
+ "num_input_tokens_seen": 0,
2361
+ "num_train_epochs": 10,
2362
+ "save_steps": 20,
2363
+ "stateful_callbacks": {
2364
+ "TrainerControl": {
2365
+ "args": {
2366
+ "should_epoch_stop": false,
2367
+ "should_evaluate": false,
2368
+ "should_log": false,
2369
+ "should_save": true,
2370
+ "should_training_stop": true
2371
+ },
2372
+ "attributes": {}
2373
+ }
2374
+ },
2375
+ "total_flos": 1.804222263410688e+16,
2376
+ "train_batch_size": 1,
2377
+ "trial_name": null,
2378
+ "trial_params": null
2379
+ }
checkpoint-670/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc984cd6b8e095021805ddd8e3c0a08d2950c17b15e17eebbeeaf65ff57c9fe
3
+ size 5777
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7db42b9d1b6f573f9ac683f32e99e0626776178350b7906241ee4d2b4327c47
3
+ size 121324555
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53538b67fc8658d85f3bae341f21061961843a7ee32995c942b7f9de93f80df8
3
+ size 14391
runs/Jul21_18-43-33_Jasons-MacBook-Pro.local/events.out.tfevents.1753119814.Jasons-MacBook-Pro.local.87971.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc9873d216c5fbd45b66fef3cfa546bb2c558700e0ccca4f54bd37a6a1b5130
3
+ size 6225
runs/Jul21_18-48-03_Jasons-MacBook-Pro.local/events.out.tfevents.1753120084.Jasons-MacBook-Pro.local.90405.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c29bd610aa4f4ce02106da5e57d1923532790032d56a358af1a5c6f9f36e15
3
+ size 8088
runs/Jul21_18-52-37_Jasons-MacBook-Pro.local/events.out.tfevents.1753120358.Jasons-MacBook-Pro.local.94516.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb7ae2508d5c279052f063d69db4f720f351e25916178117a0e969771b3822f
3
+ size 9744
runs/Jul21_19-07-35_Jasons-MacBook-Pro.local/events.out.tfevents.1753121256.Jasons-MacBook-Pro.local.99650.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d311b7554ec1a885ac64085006e34e97d35e6ab7c08a7c37b4219143961855
3
+ size 77012
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a423d2fcaea5cc7adde0c465a85784f7bb7eba6f2a5bfcf9be4f1f1ee9c0052e
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|im_end|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea5a8ce6451543cb0af4d08ccae7e2187ad41a68c571706a34ddf33b89add59
3
+ size 17208917
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<think>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "</think>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|im_start|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|im_end|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<tool_response>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<tool_call>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</tool_call>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<code>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</code>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": null,
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|im_end|>",
2055
+ "extra_special_tokens": {},
2056
+ "fast": false,
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|im_end|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,2379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 670,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0299625468164794,
14
+ "grad_norm": 3.7318975925445557,
15
+ "learning_rate": 5e-06,
16
+ "loss": 1.6973,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.0599250936329588,
21
+ "grad_norm": 3.4212851524353027,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 1.6821,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.0898876404494382,
28
+ "grad_norm": 2.5065758228302,
29
+ "learning_rate": 2.5e-05,
30
+ "loss": 1.4689,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.1198501872659176,
35
+ "grad_norm": 2.081493854522705,
36
+ "learning_rate": 3.5e-05,
37
+ "loss": 1.411,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.149812734082397,
42
+ "grad_norm": 2.0012290477752686,
43
+ "learning_rate": 4.5e-05,
44
+ "loss": 1.1681,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.1797752808988764,
49
+ "grad_norm": 1.9056272506713867,
50
+ "learning_rate": 4.992424242424243e-05,
51
+ "loss": 0.9463,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.20973782771535582,
56
+ "grad_norm": 2.0275352001190186,
57
+ "learning_rate": 4.9772727272727275e-05,
58
+ "loss": 0.8338,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.2397003745318352,
63
+ "grad_norm": 1.6332467794418335,
64
+ "learning_rate": 4.962121212121213e-05,
65
+ "loss": 0.6327,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.2696629213483146,
70
+ "grad_norm": 1.3445727825164795,
71
+ "learning_rate": 4.946969696969697e-05,
72
+ "loss": 0.4954,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.299625468164794,
77
+ "grad_norm": 0.9636670351028442,
78
+ "learning_rate": 4.931818181818182e-05,
79
+ "loss": 0.3803,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.3295880149812734,
84
+ "grad_norm": 0.4598312973976135,
85
+ "learning_rate": 4.9166666666666665e-05,
86
+ "loss": 0.3355,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.3595505617977528,
91
+ "grad_norm": 0.6035417318344116,
92
+ "learning_rate": 4.901515151515152e-05,
93
+ "loss": 0.3144,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.3895131086142322,
98
+ "grad_norm": 0.48754820227622986,
99
+ "learning_rate": 4.886363636363637e-05,
100
+ "loss": 0.2577,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.41947565543071164,
105
+ "grad_norm": 0.5186039805412292,
106
+ "learning_rate": 4.8712121212121216e-05,
107
+ "loss": 0.2478,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.449438202247191,
112
+ "grad_norm": 0.6087205410003662,
113
+ "learning_rate": 4.856060606060606e-05,
114
+ "loss": 0.2272,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.4794007490636704,
119
+ "grad_norm": 0.8594069480895996,
120
+ "learning_rate": 4.840909090909091e-05,
121
+ "loss": 0.1992,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.5093632958801498,
126
+ "grad_norm": 0.6205722093582153,
127
+ "learning_rate": 4.825757575757576e-05,
128
+ "loss": 0.1631,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.5393258426966292,
133
+ "grad_norm": 0.4654604196548462,
134
+ "learning_rate": 4.810606060606061e-05,
135
+ "loss": 0.1629,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.5692883895131086,
140
+ "grad_norm": 0.9451954364776611,
141
+ "learning_rate": 4.795454545454546e-05,
142
+ "loss": 0.1814,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.599250936329588,
147
+ "grad_norm": 0.4229886829853058,
148
+ "learning_rate": 4.7803030303030304e-05,
149
+ "loss": 0.14,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.6292134831460674,
154
+ "grad_norm": 0.43104586005210876,
155
+ "learning_rate": 4.765151515151515e-05,
156
+ "loss": 0.1495,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.6591760299625468,
161
+ "grad_norm": 0.48881301283836365,
162
+ "learning_rate": 4.75e-05,
163
+ "loss": 0.0983,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.6891385767790262,
168
+ "grad_norm": 0.3992343544960022,
169
+ "learning_rate": 4.7348484848484855e-05,
170
+ "loss": 0.0893,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.7191011235955056,
175
+ "grad_norm": 0.4501804709434509,
176
+ "learning_rate": 4.71969696969697e-05,
177
+ "loss": 0.092,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.7490636704119851,
182
+ "grad_norm": 0.576210081577301,
183
+ "learning_rate": 4.704545454545455e-05,
184
+ "loss": 0.0741,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.7790262172284644,
189
+ "grad_norm": 0.4083947241306305,
190
+ "learning_rate": 4.689393939393939e-05,
191
+ "loss": 0.0572,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.8089887640449438,
196
+ "grad_norm": 0.5864295363426208,
197
+ "learning_rate": 4.6742424242424245e-05,
198
+ "loss": 0.0769,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.8389513108614233,
203
+ "grad_norm": 0.7252892851829529,
204
+ "learning_rate": 4.659090909090909e-05,
205
+ "loss": 0.0619,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.8689138576779026,
210
+ "grad_norm": 0.42146825790405273,
211
+ "learning_rate": 4.6439393939393944e-05,
212
+ "loss": 0.0384,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.898876404494382,
217
+ "grad_norm": 0.593726634979248,
218
+ "learning_rate": 4.628787878787879e-05,
219
+ "loss": 0.052,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.9288389513108615,
224
+ "grad_norm": 0.5652066469192505,
225
+ "learning_rate": 4.6136363636363635e-05,
226
+ "loss": 0.0468,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.9588014981273408,
231
+ "grad_norm": 0.28684931993484497,
232
+ "learning_rate": 4.598484848484849e-05,
233
+ "loss": 0.0295,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.9887640449438202,
238
+ "grad_norm": 0.2981000244617462,
239
+ "learning_rate": 4.5833333333333334e-05,
240
+ "loss": 0.032,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 1.0149812734082397,
245
+ "grad_norm": 0.48514777421951294,
246
+ "learning_rate": 4.5681818181818186e-05,
247
+ "loss": 0.0506,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 1.0449438202247192,
252
+ "grad_norm": 0.32234543561935425,
253
+ "learning_rate": 4.553030303030303e-05,
254
+ "loss": 0.0318,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 1.0749063670411985,
259
+ "grad_norm": 0.38080576062202454,
260
+ "learning_rate": 4.5378787878787885e-05,
261
+ "loss": 0.0258,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 1.104868913857678,
266
+ "grad_norm": 0.3635996878147125,
267
+ "learning_rate": 4.522727272727273e-05,
268
+ "loss": 0.037,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 1.1348314606741572,
273
+ "grad_norm": 0.42449885606765747,
274
+ "learning_rate": 4.5075757575757577e-05,
275
+ "loss": 0.0393,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 1.1647940074906367,
280
+ "grad_norm": 0.5858486890792847,
281
+ "learning_rate": 4.492424242424242e-05,
282
+ "loss": 0.0207,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 1.1947565543071161,
287
+ "grad_norm": 0.24009667336940765,
288
+ "learning_rate": 4.4772727272727275e-05,
289
+ "loss": 0.0189,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 1.2247191011235956,
294
+ "grad_norm": 0.21841216087341309,
295
+ "learning_rate": 4.462121212121213e-05,
296
+ "loss": 0.0173,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 1.2546816479400749,
301
+ "grad_norm": 0.34650227427482605,
302
+ "learning_rate": 4.4469696969696973e-05,
303
+ "loss": 0.0311,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 1.2846441947565543,
308
+ "grad_norm": 0.3726528584957123,
309
+ "learning_rate": 4.431818181818182e-05,
310
+ "loss": 0.0272,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 1.3146067415730336,
315
+ "grad_norm": 0.2907704710960388,
316
+ "learning_rate": 4.4166666666666665e-05,
317
+ "loss": 0.0235,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 1.344569288389513,
322
+ "grad_norm": 0.21228495240211487,
323
+ "learning_rate": 4.401515151515152e-05,
324
+ "loss": 0.0206,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 1.3745318352059925,
329
+ "grad_norm": 0.2763824462890625,
330
+ "learning_rate": 4.386363636363637e-05,
331
+ "loss": 0.0222,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 1.404494382022472,
336
+ "grad_norm": 0.2596808969974518,
337
+ "learning_rate": 4.3712121212121216e-05,
338
+ "loss": 0.0171,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 1.4344569288389513,
343
+ "grad_norm": 0.36683645844459534,
344
+ "learning_rate": 4.356060606060606e-05,
345
+ "loss": 0.0213,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 1.4644194756554307,
350
+ "grad_norm": 0.25381800532341003,
351
+ "learning_rate": 4.340909090909091e-05,
352
+ "loss": 0.0149,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 1.49438202247191,
357
+ "grad_norm": 0.4874545633792877,
358
+ "learning_rate": 4.325757575757576e-05,
359
+ "loss": 0.0235,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 1.5243445692883895,
364
+ "grad_norm": 0.35136911273002625,
365
+ "learning_rate": 4.3106060606060606e-05,
366
+ "loss": 0.0186,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 1.554307116104869,
371
+ "grad_norm": 0.3259860873222351,
372
+ "learning_rate": 4.295454545454546e-05,
373
+ "loss": 0.0228,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 1.5842696629213484,
378
+ "grad_norm": 0.24276824295520782,
379
+ "learning_rate": 4.2803030303030305e-05,
380
+ "loss": 0.0147,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 1.6142322097378277,
385
+ "grad_norm": 0.4493170976638794,
386
+ "learning_rate": 4.265151515151515e-05,
387
+ "loss": 0.0152,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 1.6441947565543071,
392
+ "grad_norm": 0.4474326968193054,
393
+ "learning_rate": 4.25e-05,
394
+ "loss": 0.0199,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 1.6741573033707864,
399
+ "grad_norm": 0.229719340801239,
400
+ "learning_rate": 4.234848484848485e-05,
401
+ "loss": 0.0166,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 1.7041198501872659,
406
+ "grad_norm": 0.2303067445755005,
407
+ "learning_rate": 4.21969696969697e-05,
408
+ "loss": 0.017,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 1.7340823970037453,
413
+ "grad_norm": 0.24925805628299713,
414
+ "learning_rate": 4.204545454545455e-05,
415
+ "loss": 0.0147,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 1.7640449438202248,
420
+ "grad_norm": 0.18361054360866547,
421
+ "learning_rate": 4.189393939393939e-05,
422
+ "loss": 0.0191,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 1.7940074906367043,
427
+ "grad_norm": 0.2936908006668091,
428
+ "learning_rate": 4.1742424242424246e-05,
429
+ "loss": 0.0189,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 1.8239700374531835,
434
+ "grad_norm": 0.2073887437582016,
435
+ "learning_rate": 4.159090909090909e-05,
436
+ "loss": 0.0171,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 1.8539325842696628,
441
+ "grad_norm": 0.3212382197380066,
442
+ "learning_rate": 4.143939393939394e-05,
443
+ "loss": 0.0204,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 1.8838951310861423,
448
+ "grad_norm": 0.1888497769832611,
449
+ "learning_rate": 4.128787878787879e-05,
450
+ "loss": 0.0201,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 1.9138576779026217,
455
+ "grad_norm": 0.18828518688678741,
456
+ "learning_rate": 4.113636363636364e-05,
457
+ "loss": 0.0179,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 1.9438202247191012,
462
+ "grad_norm": 0.22073791921138763,
463
+ "learning_rate": 4.098484848484849e-05,
464
+ "loss": 0.02,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 1.9737827715355807,
469
+ "grad_norm": 0.23251274228096008,
470
+ "learning_rate": 4.0833333333333334e-05,
471
+ "loss": 0.0184,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 2.0,
476
+ "grad_norm": 0.2079184651374817,
477
+ "learning_rate": 4.068181818181818e-05,
478
+ "loss": 0.0192,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 2.0299625468164795,
483
+ "grad_norm": 0.21343930065631866,
484
+ "learning_rate": 4.053030303030303e-05,
485
+ "loss": 0.0166,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 2.059925093632959,
490
+ "grad_norm": 0.2166517972946167,
491
+ "learning_rate": 4.0378787878787885e-05,
492
+ "loss": 0.0159,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 2.0898876404494384,
497
+ "grad_norm": 0.17601799964904785,
498
+ "learning_rate": 4.022727272727273e-05,
499
+ "loss": 0.0157,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 2.1198501872659175,
504
+ "grad_norm": 0.292283296585083,
505
+ "learning_rate": 4.007575757575758e-05,
506
+ "loss": 0.0214,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 2.149812734082397,
511
+ "grad_norm": 0.2258112132549286,
512
+ "learning_rate": 3.992424242424242e-05,
513
+ "loss": 0.0184,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 2.1797752808988764,
518
+ "grad_norm": 0.15815454721450806,
519
+ "learning_rate": 3.9772727272727275e-05,
520
+ "loss": 0.017,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 2.209737827715356,
525
+ "grad_norm": 0.26803699135780334,
526
+ "learning_rate": 3.962121212121213e-05,
527
+ "loss": 0.0182,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 2.2397003745318353,
532
+ "grad_norm": 0.2198362499475479,
533
+ "learning_rate": 3.9469696969696974e-05,
534
+ "loss": 0.0167,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 2.2696629213483144,
539
+ "grad_norm": 0.201346293091774,
540
+ "learning_rate": 3.931818181818182e-05,
541
+ "loss": 0.0161,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 2.299625468164794,
546
+ "grad_norm": 0.22819150984287262,
547
+ "learning_rate": 3.9166666666666665e-05,
548
+ "loss": 0.015,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 2.3295880149812733,
553
+ "grad_norm": 0.2712112069129944,
554
+ "learning_rate": 3.901515151515152e-05,
555
+ "loss": 0.0163,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 2.359550561797753,
560
+ "grad_norm": 0.19178956747055054,
561
+ "learning_rate": 3.8863636363636364e-05,
562
+ "loss": 0.0163,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 2.3895131086142323,
567
+ "grad_norm": 0.1914001852273941,
568
+ "learning_rate": 3.8712121212121217e-05,
569
+ "loss": 0.0168,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 2.4194756554307117,
574
+ "grad_norm": 0.1301780492067337,
575
+ "learning_rate": 3.856060606060606e-05,
576
+ "loss": 0.0151,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 2.449438202247191,
581
+ "grad_norm": 0.22975341975688934,
582
+ "learning_rate": 3.840909090909091e-05,
583
+ "loss": 0.0171,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 2.4794007490636703,
588
+ "grad_norm": 0.2856428623199463,
589
+ "learning_rate": 3.825757575757576e-05,
590
+ "loss": 0.0182,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 2.5093632958801497,
595
+ "grad_norm": 0.22180147469043732,
596
+ "learning_rate": 3.810606060606061e-05,
597
+ "loss": 0.0164,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 2.539325842696629,
602
+ "grad_norm": 0.18585917353630066,
603
+ "learning_rate": 3.795454545454545e-05,
604
+ "loss": 0.0175,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 2.5692883895131087,
609
+ "grad_norm": 0.21161819994449615,
610
+ "learning_rate": 3.7803030303030305e-05,
611
+ "loss": 0.0149,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 2.599250936329588,
616
+ "grad_norm": 0.14073120057582855,
617
+ "learning_rate": 3.765151515151516e-05,
618
+ "loss": 0.0143,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 2.629213483146067,
623
+ "grad_norm": 0.1988099217414856,
624
+ "learning_rate": 3.7500000000000003e-05,
625
+ "loss": 0.0155,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 2.6591760299625467,
630
+ "grad_norm": 0.17829206585884094,
631
+ "learning_rate": 3.734848484848485e-05,
632
+ "loss": 0.0172,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 2.689138576779026,
637
+ "grad_norm": 0.25729623436927795,
638
+ "learning_rate": 3.7196969696969695e-05,
639
+ "loss": 0.0161,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 2.7191011235955056,
644
+ "grad_norm": 0.15630777180194855,
645
+ "learning_rate": 3.704545454545455e-05,
646
+ "loss": 0.0161,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 2.749063670411985,
651
+ "grad_norm": 0.10787078738212585,
652
+ "learning_rate": 3.68939393939394e-05,
653
+ "loss": 0.0139,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 2.7790262172284645,
658
+ "grad_norm": 0.11183971166610718,
659
+ "learning_rate": 3.6742424242424246e-05,
660
+ "loss": 0.0142,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 2.808988764044944,
665
+ "grad_norm": 0.3003017008304596,
666
+ "learning_rate": 3.659090909090909e-05,
667
+ "loss": 0.0201,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 2.8389513108614235,
672
+ "grad_norm": 0.15837068855762482,
673
+ "learning_rate": 3.643939393939394e-05,
674
+ "loss": 0.014,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 2.8689138576779025,
679
+ "grad_norm": 0.15499652922153473,
680
+ "learning_rate": 3.628787878787879e-05,
681
+ "loss": 0.0166,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 2.898876404494382,
686
+ "grad_norm": 0.166601300239563,
687
+ "learning_rate": 3.613636363636364e-05,
688
+ "loss": 0.0136,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 2.9288389513108615,
693
+ "grad_norm": 0.23306916654109955,
694
+ "learning_rate": 3.598484848484849e-05,
695
+ "loss": 0.0145,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 2.958801498127341,
700
+ "grad_norm": 0.23148281872272491,
701
+ "learning_rate": 3.5833333333333335e-05,
702
+ "loss": 0.0166,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 2.98876404494382,
707
+ "grad_norm": 0.2514810562133789,
708
+ "learning_rate": 3.568181818181818e-05,
709
+ "loss": 0.0197,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 3.0149812734082397,
714
+ "grad_norm": 0.15844318270683289,
715
+ "learning_rate": 3.553030303030303e-05,
716
+ "loss": 0.0127,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 3.044943820224719,
721
+ "grad_norm": 0.15709055960178375,
722
+ "learning_rate": 3.537878787878788e-05,
723
+ "loss": 0.0144,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 3.0749063670411987,
728
+ "grad_norm": 0.21092790365219116,
729
+ "learning_rate": 3.522727272727273e-05,
730
+ "loss": 0.0174,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 3.1048689138576777,
735
+ "grad_norm": 0.22406940162181854,
736
+ "learning_rate": 3.507575757575758e-05,
737
+ "loss": 0.0151,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 3.134831460674157,
742
+ "grad_norm": 0.17414535582065582,
743
+ "learning_rate": 3.492424242424242e-05,
744
+ "loss": 0.0159,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 3.1647940074906367,
749
+ "grad_norm": 0.1722804456949234,
750
+ "learning_rate": 3.4772727272727276e-05,
751
+ "loss": 0.0146,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 3.194756554307116,
756
+ "grad_norm": 0.26471957564353943,
757
+ "learning_rate": 3.462121212121212e-05,
758
+ "loss": 0.0157,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 3.2247191011235956,
763
+ "grad_norm": 0.13862167298793793,
764
+ "learning_rate": 3.4469696969696974e-05,
765
+ "loss": 0.0137,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 3.254681647940075,
770
+ "grad_norm": 0.24047966301441193,
771
+ "learning_rate": 3.431818181818182e-05,
772
+ "loss": 0.017,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 3.284644194756554,
777
+ "grad_norm": 0.1237376257777214,
778
+ "learning_rate": 3.4166666666666666e-05,
779
+ "loss": 0.0151,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 3.3146067415730336,
784
+ "grad_norm": 0.15304620563983917,
785
+ "learning_rate": 3.401515151515152e-05,
786
+ "loss": 0.0155,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 3.344569288389513,
791
+ "grad_norm": 0.15872317552566528,
792
+ "learning_rate": 3.3863636363636364e-05,
793
+ "loss": 0.0147,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 3.3745318352059925,
798
+ "grad_norm": 0.18952298164367676,
799
+ "learning_rate": 3.371212121212121e-05,
800
+ "loss": 0.0154,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 3.404494382022472,
805
+ "grad_norm": 0.21287596225738525,
806
+ "learning_rate": 3.356060606060606e-05,
807
+ "loss": 0.0166,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 3.4344569288389515,
812
+ "grad_norm": 0.19477762281894684,
813
+ "learning_rate": 3.3409090909090915e-05,
814
+ "loss": 0.0167,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 3.464419475655431,
819
+ "grad_norm": 0.1801714450120926,
820
+ "learning_rate": 3.325757575757576e-05,
821
+ "loss": 0.0145,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 3.49438202247191,
826
+ "grad_norm": 0.14180026948451996,
827
+ "learning_rate": 3.310606060606061e-05,
828
+ "loss": 0.0138,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 3.5243445692883895,
833
+ "grad_norm": 0.21012850105762482,
834
+ "learning_rate": 3.295454545454545e-05,
835
+ "loss": 0.0165,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 3.554307116104869,
840
+ "grad_norm": 0.1273059993982315,
841
+ "learning_rate": 3.2803030303030305e-05,
842
+ "loss": 0.0148,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 3.5842696629213484,
847
+ "grad_norm": 0.13745197653770447,
848
+ "learning_rate": 3.265151515151516e-05,
849
+ "loss": 0.0137,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 3.6142322097378274,
854
+ "grad_norm": 0.19960223138332367,
855
+ "learning_rate": 3.2500000000000004e-05,
856
+ "loss": 0.0178,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 3.644194756554307,
861
+ "grad_norm": 0.21453413367271423,
862
+ "learning_rate": 3.234848484848485e-05,
863
+ "loss": 0.0156,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 3.6741573033707864,
868
+ "grad_norm": 0.17091749608516693,
869
+ "learning_rate": 3.2196969696969696e-05,
870
+ "loss": 0.0157,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 3.704119850187266,
875
+ "grad_norm": 0.15684160590171814,
876
+ "learning_rate": 3.204545454545455e-05,
877
+ "loss": 0.0148,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 3.7340823970037453,
882
+ "grad_norm": 0.15323583781719208,
883
+ "learning_rate": 3.18939393939394e-05,
884
+ "loss": 0.015,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 3.764044943820225,
889
+ "grad_norm": 0.13383668661117554,
890
+ "learning_rate": 3.174242424242425e-05,
891
+ "loss": 0.0154,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 3.7940074906367043,
896
+ "grad_norm": 0.15054528415203094,
897
+ "learning_rate": 3.159090909090909e-05,
898
+ "loss": 0.0153,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 3.8239700374531838,
903
+ "grad_norm": 0.10618451982736588,
904
+ "learning_rate": 3.143939393939394e-05,
905
+ "loss": 0.0131,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 3.853932584269663,
910
+ "grad_norm": 0.20882849395275116,
911
+ "learning_rate": 3.128787878787879e-05,
912
+ "loss": 0.019,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 3.8838951310861423,
917
+ "grad_norm": 0.19676630198955536,
918
+ "learning_rate": 3.113636363636364e-05,
919
+ "loss": 0.0164,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 3.9138576779026217,
924
+ "grad_norm": 0.10724353790283203,
925
+ "learning_rate": 3.098484848484849e-05,
926
+ "loss": 0.0145,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 3.943820224719101,
931
+ "grad_norm": 0.11003574728965759,
932
+ "learning_rate": 3.0833333333333335e-05,
933
+ "loss": 0.0153,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 3.9737827715355807,
938
+ "grad_norm": 0.10973632335662842,
939
+ "learning_rate": 3.068181818181818e-05,
940
+ "loss": 0.0131,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 4.0,
945
+ "grad_norm": 0.21611331403255463,
946
+ "learning_rate": 3.0530303030303034e-05,
947
+ "loss": 0.0184,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 4.0299625468164795,
952
+ "grad_norm": 0.11275507509708405,
953
+ "learning_rate": 3.037878787878788e-05,
954
+ "loss": 0.0159,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 4.059925093632959,
959
+ "grad_norm": 0.182546004652977,
960
+ "learning_rate": 3.0227272727272725e-05,
961
+ "loss": 0.0143,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 4.089887640449438,
966
+ "grad_norm": 0.11307963728904724,
967
+ "learning_rate": 3.0075757575757578e-05,
968
+ "loss": 0.014,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 4.119850187265918,
973
+ "grad_norm": 0.13171932101249695,
974
+ "learning_rate": 2.9924242424242427e-05,
975
+ "loss": 0.0159,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 4.149812734082397,
980
+ "grad_norm": 0.2185821682214737,
981
+ "learning_rate": 2.9772727272727273e-05,
982
+ "loss": 0.0158,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 4.179775280898877,
987
+ "grad_norm": 0.1575690507888794,
988
+ "learning_rate": 2.9621212121212122e-05,
989
+ "loss": 0.0168,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 4.209737827715355,
994
+ "grad_norm": 0.1727718561887741,
995
+ "learning_rate": 2.9469696969696968e-05,
996
+ "loss": 0.0154,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 4.239700374531835,
1001
+ "grad_norm": 0.13435468077659607,
1002
+ "learning_rate": 2.9318181818181817e-05,
1003
+ "loss": 0.0165,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 4.269662921348314,
1008
+ "grad_norm": 0.15063047409057617,
1009
+ "learning_rate": 2.916666666666667e-05,
1010
+ "loss": 0.0173,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 4.299625468164794,
1015
+ "grad_norm": 0.12659698724746704,
1016
+ "learning_rate": 2.901515151515152e-05,
1017
+ "loss": 0.0152,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 4.329588014981273,
1022
+ "grad_norm": 0.19473259150981903,
1023
+ "learning_rate": 2.8863636363636365e-05,
1024
+ "loss": 0.016,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 4.359550561797753,
1029
+ "grad_norm": 0.1952139437198639,
1030
+ "learning_rate": 2.8712121212121214e-05,
1031
+ "loss": 0.0164,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 4.389513108614232,
1036
+ "grad_norm": 0.15907561779022217,
1037
+ "learning_rate": 2.856060606060606e-05,
1038
+ "loss": 0.0126,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 4.419475655430712,
1043
+ "grad_norm": 0.197600319981575,
1044
+ "learning_rate": 2.8409090909090912e-05,
1045
+ "loss": 0.0166,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 4.449438202247191,
1050
+ "grad_norm": 0.09373123943805695,
1051
+ "learning_rate": 2.825757575757576e-05,
1052
+ "loss": 0.016,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 4.479400749063671,
1057
+ "grad_norm": 0.14290565252304077,
1058
+ "learning_rate": 2.8106060606060607e-05,
1059
+ "loss": 0.0172,
1060
+ "step": 300
1061
+ },
1062
+ {
1063
+ "epoch": 4.50936329588015,
1064
+ "grad_norm": 0.1223093792796135,
1065
+ "learning_rate": 2.7954545454545457e-05,
1066
+ "loss": 0.0157,
1067
+ "step": 302
1068
+ },
1069
+ {
1070
+ "epoch": 4.539325842696629,
1071
+ "grad_norm": 0.11388926208019257,
1072
+ "learning_rate": 2.7803030303030303e-05,
1073
+ "loss": 0.015,
1074
+ "step": 304
1075
+ },
1076
+ {
1077
+ "epoch": 4.569288389513108,
1078
+ "grad_norm": 0.10850539058446884,
1079
+ "learning_rate": 2.7651515151515152e-05,
1080
+ "loss": 0.0166,
1081
+ "step": 306
1082
+ },
1083
+ {
1084
+ "epoch": 4.599250936329588,
1085
+ "grad_norm": 0.13963742554187775,
1086
+ "learning_rate": 2.7500000000000004e-05,
1087
+ "loss": 0.0158,
1088
+ "step": 308
1089
+ },
1090
+ {
1091
+ "epoch": 4.629213483146067,
1092
+ "grad_norm": 0.15747179090976715,
1093
+ "learning_rate": 2.734848484848485e-05,
1094
+ "loss": 0.0144,
1095
+ "step": 310
1096
+ },
1097
+ {
1098
+ "epoch": 4.659176029962547,
1099
+ "grad_norm": 0.1513000726699829,
1100
+ "learning_rate": 2.71969696969697e-05,
1101
+ "loss": 0.0164,
1102
+ "step": 312
1103
+ },
1104
+ {
1105
+ "epoch": 4.689138576779026,
1106
+ "grad_norm": 0.14622750878334045,
1107
+ "learning_rate": 2.7045454545454545e-05,
1108
+ "loss": 0.016,
1109
+ "step": 314
1110
+ },
1111
+ {
1112
+ "epoch": 4.719101123595506,
1113
+ "grad_norm": 0.1300605684518814,
1114
+ "learning_rate": 2.6893939393939394e-05,
1115
+ "loss": 0.0158,
1116
+ "step": 316
1117
+ },
1118
+ {
1119
+ "epoch": 4.749063670411985,
1120
+ "grad_norm": 0.1521446704864502,
1121
+ "learning_rate": 2.674242424242424e-05,
1122
+ "loss": 0.0139,
1123
+ "step": 318
1124
+ },
1125
+ {
1126
+ "epoch": 4.7790262172284645,
1127
+ "grad_norm": 0.13343091309070587,
1128
+ "learning_rate": 2.6590909090909093e-05,
1129
+ "loss": 0.0141,
1130
+ "step": 320
1131
+ },
1132
+ {
1133
+ "epoch": 4.808988764044944,
1134
+ "grad_norm": 0.1171831339597702,
1135
+ "learning_rate": 2.6439393939393942e-05,
1136
+ "loss": 0.0129,
1137
+ "step": 322
1138
+ },
1139
+ {
1140
+ "epoch": 4.8389513108614235,
1141
+ "grad_norm": 0.10482454299926758,
1142
+ "learning_rate": 2.6287878787878788e-05,
1143
+ "loss": 0.0115,
1144
+ "step": 324
1145
+ },
1146
+ {
1147
+ "epoch": 4.868913857677903,
1148
+ "grad_norm": 0.13335193693637848,
1149
+ "learning_rate": 2.6136363636363637e-05,
1150
+ "loss": 0.0155,
1151
+ "step": 326
1152
+ },
1153
+ {
1154
+ "epoch": 4.898876404494382,
1155
+ "grad_norm": 0.1327083259820938,
1156
+ "learning_rate": 2.5984848484848483e-05,
1157
+ "loss": 0.0154,
1158
+ "step": 328
1159
+ },
1160
+ {
1161
+ "epoch": 4.928838951310862,
1162
+ "grad_norm": 0.15616530179977417,
1163
+ "learning_rate": 2.5833333333333336e-05,
1164
+ "loss": 0.0186,
1165
+ "step": 330
1166
+ },
1167
+ {
1168
+ "epoch": 4.9588014981273405,
1169
+ "grad_norm": 0.1196502074599266,
1170
+ "learning_rate": 2.5681818181818185e-05,
1171
+ "loss": 0.0151,
1172
+ "step": 332
1173
+ },
1174
+ {
1175
+ "epoch": 4.98876404494382,
1176
+ "grad_norm": 0.11737090349197388,
1177
+ "learning_rate": 2.553030303030303e-05,
1178
+ "loss": 0.013,
1179
+ "step": 334
1180
+ },
1181
+ {
1182
+ "epoch": 5.01498127340824,
1183
+ "grad_norm": 0.14445465803146362,
1184
+ "learning_rate": 2.537878787878788e-05,
1185
+ "loss": 0.0134,
1186
+ "step": 336
1187
+ },
1188
+ {
1189
+ "epoch": 5.044943820224719,
1190
+ "grad_norm": 0.10734406858682632,
1191
+ "learning_rate": 2.5227272727272726e-05,
1192
+ "loss": 0.0138,
1193
+ "step": 338
1194
+ },
1195
+ {
1196
+ "epoch": 5.074906367041199,
1197
+ "grad_norm": 0.11528757214546204,
1198
+ "learning_rate": 2.5075757575757575e-05,
1199
+ "loss": 0.013,
1200
+ "step": 340
1201
+ },
1202
+ {
1203
+ "epoch": 5.104868913857678,
1204
+ "grad_norm": 0.17952029407024384,
1205
+ "learning_rate": 2.4924242424242424e-05,
1206
+ "loss": 0.0152,
1207
+ "step": 342
1208
+ },
1209
+ {
1210
+ "epoch": 5.134831460674158,
1211
+ "grad_norm": 0.12444639205932617,
1212
+ "learning_rate": 2.4772727272727277e-05,
1213
+ "loss": 0.0148,
1214
+ "step": 344
1215
+ },
1216
+ {
1217
+ "epoch": 5.164794007490637,
1218
+ "grad_norm": 0.12819650769233704,
1219
+ "learning_rate": 2.4621212121212123e-05,
1220
+ "loss": 0.0146,
1221
+ "step": 346
1222
+ },
1223
+ {
1224
+ "epoch": 5.194756554307116,
1225
+ "grad_norm": 0.13396833837032318,
1226
+ "learning_rate": 2.4469696969696972e-05,
1227
+ "loss": 0.0175,
1228
+ "step": 348
1229
+ },
1230
+ {
1231
+ "epoch": 5.224719101123595,
1232
+ "grad_norm": 0.1286836415529251,
1233
+ "learning_rate": 2.431818181818182e-05,
1234
+ "loss": 0.0144,
1235
+ "step": 350
1236
+ },
1237
+ {
1238
+ "epoch": 5.254681647940075,
1239
+ "grad_norm": 0.12591804563999176,
1240
+ "learning_rate": 2.4166666666666667e-05,
1241
+ "loss": 0.0167,
1242
+ "step": 352
1243
+ },
1244
+ {
1245
+ "epoch": 5.284644194756554,
1246
+ "grad_norm": 0.12226350605487823,
1247
+ "learning_rate": 2.4015151515151516e-05,
1248
+ "loss": 0.0133,
1249
+ "step": 354
1250
+ },
1251
+ {
1252
+ "epoch": 5.314606741573034,
1253
+ "grad_norm": 0.10504593700170517,
1254
+ "learning_rate": 2.3863636363636365e-05,
1255
+ "loss": 0.0135,
1256
+ "step": 356
1257
+ },
1258
+ {
1259
+ "epoch": 5.344569288389513,
1260
+ "grad_norm": 0.1078866645693779,
1261
+ "learning_rate": 2.3712121212121214e-05,
1262
+ "loss": 0.0147,
1263
+ "step": 358
1264
+ },
1265
+ {
1266
+ "epoch": 5.3745318352059925,
1267
+ "grad_norm": 0.28363969922065735,
1268
+ "learning_rate": 2.356060606060606e-05,
1269
+ "loss": 0.0156,
1270
+ "step": 360
1271
+ },
1272
+ {
1273
+ "epoch": 5.404494382022472,
1274
+ "grad_norm": 0.1177087053656578,
1275
+ "learning_rate": 2.340909090909091e-05,
1276
+ "loss": 0.0138,
1277
+ "step": 362
1278
+ },
1279
+ {
1280
+ "epoch": 5.4344569288389515,
1281
+ "grad_norm": 0.16584421694278717,
1282
+ "learning_rate": 2.325757575757576e-05,
1283
+ "loss": 0.0179,
1284
+ "step": 364
1285
+ },
1286
+ {
1287
+ "epoch": 5.464419475655431,
1288
+ "grad_norm": 0.10715971887111664,
1289
+ "learning_rate": 2.3106060606060605e-05,
1290
+ "loss": 0.0144,
1291
+ "step": 366
1292
+ },
1293
+ {
1294
+ "epoch": 5.49438202247191,
1295
+ "grad_norm": 0.11904123425483704,
1296
+ "learning_rate": 2.2954545454545457e-05,
1297
+ "loss": 0.0133,
1298
+ "step": 368
1299
+ },
1300
+ {
1301
+ "epoch": 5.52434456928839,
1302
+ "grad_norm": 0.19020037353038788,
1303
+ "learning_rate": 2.2803030303030303e-05,
1304
+ "loss": 0.0178,
1305
+ "step": 370
1306
+ },
1307
+ {
1308
+ "epoch": 5.554307116104869,
1309
+ "grad_norm": 0.1367521733045578,
1310
+ "learning_rate": 2.2651515151515152e-05,
1311
+ "loss": 0.0155,
1312
+ "step": 372
1313
+ },
1314
+ {
1315
+ "epoch": 5.584269662921348,
1316
+ "grad_norm": 0.12585178017616272,
1317
+ "learning_rate": 2.25e-05,
1318
+ "loss": 0.0143,
1319
+ "step": 374
1320
+ },
1321
+ {
1322
+ "epoch": 5.614232209737827,
1323
+ "grad_norm": 0.20084144175052643,
1324
+ "learning_rate": 2.234848484848485e-05,
1325
+ "loss": 0.0178,
1326
+ "step": 376
1327
+ },
1328
+ {
1329
+ "epoch": 5.644194756554307,
1330
+ "grad_norm": 0.12197957187891006,
1331
+ "learning_rate": 2.21969696969697e-05,
1332
+ "loss": 0.0142,
1333
+ "step": 378
1334
+ },
1335
+ {
1336
+ "epoch": 5.674157303370786,
1337
+ "grad_norm": 0.11580586433410645,
1338
+ "learning_rate": 2.2045454545454546e-05,
1339
+ "loss": 0.0158,
1340
+ "step": 380
1341
+ },
1342
+ {
1343
+ "epoch": 5.704119850187266,
1344
+ "grad_norm": 0.1596754640340805,
1345
+ "learning_rate": 2.1893939393939395e-05,
1346
+ "loss": 0.0153,
1347
+ "step": 382
1348
+ },
1349
+ {
1350
+ "epoch": 5.734082397003745,
1351
+ "grad_norm": 0.11820989102125168,
1352
+ "learning_rate": 2.1742424242424244e-05,
1353
+ "loss": 0.0133,
1354
+ "step": 384
1355
+ },
1356
+ {
1357
+ "epoch": 5.764044943820225,
1358
+ "grad_norm": 0.1528993546962738,
1359
+ "learning_rate": 2.1590909090909093e-05,
1360
+ "loss": 0.0131,
1361
+ "step": 386
1362
+ },
1363
+ {
1364
+ "epoch": 5.794007490636704,
1365
+ "grad_norm": 0.15335053205490112,
1366
+ "learning_rate": 2.143939393939394e-05,
1367
+ "loss": 0.0188,
1368
+ "step": 388
1369
+ },
1370
+ {
1371
+ "epoch": 5.823970037453184,
1372
+ "grad_norm": 0.13823996484279633,
1373
+ "learning_rate": 2.128787878787879e-05,
1374
+ "loss": 0.0156,
1375
+ "step": 390
1376
+ },
1377
+ {
1378
+ "epoch": 5.853932584269663,
1379
+ "grad_norm": 0.11527912318706512,
1380
+ "learning_rate": 2.1136363636363638e-05,
1381
+ "loss": 0.0156,
1382
+ "step": 392
1383
+ },
1384
+ {
1385
+ "epoch": 5.883895131086143,
1386
+ "grad_norm": 0.09302780777215958,
1387
+ "learning_rate": 2.0984848484848483e-05,
1388
+ "loss": 0.0144,
1389
+ "step": 394
1390
+ },
1391
+ {
1392
+ "epoch": 5.913857677902621,
1393
+ "grad_norm": 0.1214398592710495,
1394
+ "learning_rate": 2.0833333333333336e-05,
1395
+ "loss": 0.0137,
1396
+ "step": 396
1397
+ },
1398
+ {
1399
+ "epoch": 5.943820224719101,
1400
+ "grad_norm": 0.17180432379245758,
1401
+ "learning_rate": 2.0681818181818182e-05,
1402
+ "loss": 0.0158,
1403
+ "step": 398
1404
+ },
1405
+ {
1406
+ "epoch": 5.97378277153558,
1407
+ "grad_norm": 0.13470757007598877,
1408
+ "learning_rate": 2.053030303030303e-05,
1409
+ "loss": 0.016,
1410
+ "step": 400
1411
+ },
1412
+ {
1413
+ "epoch": 6.0,
1414
+ "grad_norm": 0.12095994502305984,
1415
+ "learning_rate": 2.037878787878788e-05,
1416
+ "loss": 0.0136,
1417
+ "step": 402
1418
+ },
1419
+ {
1420
+ "epoch": 6.0299625468164795,
1421
+ "grad_norm": 0.13292968273162842,
1422
+ "learning_rate": 2.022727272727273e-05,
1423
+ "loss": 0.0146,
1424
+ "step": 404
1425
+ },
1426
+ {
1427
+ "epoch": 6.059925093632959,
1428
+ "grad_norm": 0.143639475107193,
1429
+ "learning_rate": 2.0075757575757575e-05,
1430
+ "loss": 0.0159,
1431
+ "step": 406
1432
+ },
1433
+ {
1434
+ "epoch": 6.089887640449438,
1435
+ "grad_norm": 0.13313822448253632,
1436
+ "learning_rate": 1.9924242424242425e-05,
1437
+ "loss": 0.017,
1438
+ "step": 408
1439
+ },
1440
+ {
1441
+ "epoch": 6.119850187265918,
1442
+ "grad_norm": 0.17898374795913696,
1443
+ "learning_rate": 1.9772727272727274e-05,
1444
+ "loss": 0.0162,
1445
+ "step": 410
1446
+ },
1447
+ {
1448
+ "epoch": 6.149812734082397,
1449
+ "grad_norm": 0.12149132043123245,
1450
+ "learning_rate": 1.962121212121212e-05,
1451
+ "loss": 0.0143,
1452
+ "step": 412
1453
+ },
1454
+ {
1455
+ "epoch": 6.179775280898877,
1456
+ "grad_norm": 0.12255310267210007,
1457
+ "learning_rate": 1.9469696969696972e-05,
1458
+ "loss": 0.0148,
1459
+ "step": 414
1460
+ },
1461
+ {
1462
+ "epoch": 6.209737827715355,
1463
+ "grad_norm": 0.17352508008480072,
1464
+ "learning_rate": 1.9318181818181818e-05,
1465
+ "loss": 0.0153,
1466
+ "step": 416
1467
+ },
1468
+ {
1469
+ "epoch": 6.239700374531835,
1470
+ "grad_norm": 0.15836010873317719,
1471
+ "learning_rate": 1.9166666666666667e-05,
1472
+ "loss": 0.0152,
1473
+ "step": 418
1474
+ },
1475
+ {
1476
+ "epoch": 6.269662921348314,
1477
+ "grad_norm": 0.13117386400699615,
1478
+ "learning_rate": 1.9015151515151516e-05,
1479
+ "loss": 0.0131,
1480
+ "step": 420
1481
+ },
1482
+ {
1483
+ "epoch": 6.299625468164794,
1484
+ "grad_norm": 0.09744709730148315,
1485
+ "learning_rate": 1.8863636363636362e-05,
1486
+ "loss": 0.0133,
1487
+ "step": 422
1488
+ },
1489
+ {
1490
+ "epoch": 6.329588014981273,
1491
+ "grad_norm": 0.11249203234910965,
1492
+ "learning_rate": 1.8712121212121215e-05,
1493
+ "loss": 0.0137,
1494
+ "step": 424
1495
+ },
1496
+ {
1497
+ "epoch": 6.359550561797753,
1498
+ "grad_norm": 0.14073345065116882,
1499
+ "learning_rate": 1.856060606060606e-05,
1500
+ "loss": 0.0158,
1501
+ "step": 426
1502
+ },
1503
+ {
1504
+ "epoch": 6.389513108614232,
1505
+ "grad_norm": 0.19942159950733185,
1506
+ "learning_rate": 1.840909090909091e-05,
1507
+ "loss": 0.0179,
1508
+ "step": 428
1509
+ },
1510
+ {
1511
+ "epoch": 6.419475655430712,
1512
+ "grad_norm": 0.12104730308055878,
1513
+ "learning_rate": 1.825757575757576e-05,
1514
+ "loss": 0.0143,
1515
+ "step": 430
1516
+ },
1517
+ {
1518
+ "epoch": 6.449438202247191,
1519
+ "grad_norm": 0.12874731421470642,
1520
+ "learning_rate": 1.810606060606061e-05,
1521
+ "loss": 0.0147,
1522
+ "step": 432
1523
+ },
1524
+ {
1525
+ "epoch": 6.479400749063671,
1526
+ "grad_norm": 0.09665031731128693,
1527
+ "learning_rate": 1.7954545454545454e-05,
1528
+ "loss": 0.0126,
1529
+ "step": 434
1530
+ },
1531
+ {
1532
+ "epoch": 6.50936329588015,
1533
+ "grad_norm": 0.22135666012763977,
1534
+ "learning_rate": 1.7803030303030303e-05,
1535
+ "loss": 0.0162,
1536
+ "step": 436
1537
+ },
1538
+ {
1539
+ "epoch": 6.539325842696629,
1540
+ "grad_norm": 0.12249334901571274,
1541
+ "learning_rate": 1.7651515151515153e-05,
1542
+ "loss": 0.013,
1543
+ "step": 438
1544
+ },
1545
+ {
1546
+ "epoch": 6.569288389513108,
1547
+ "grad_norm": 0.15929952263832092,
1548
+ "learning_rate": 1.75e-05,
1549
+ "loss": 0.0144,
1550
+ "step": 440
1551
+ },
1552
+ {
1553
+ "epoch": 6.599250936329588,
1554
+ "grad_norm": 0.116636261343956,
1555
+ "learning_rate": 1.734848484848485e-05,
1556
+ "loss": 0.0136,
1557
+ "step": 442
1558
+ },
1559
+ {
1560
+ "epoch": 6.629213483146067,
1561
+ "grad_norm": 0.26052579283714294,
1562
+ "learning_rate": 1.7196969696969697e-05,
1563
+ "loss": 0.0167,
1564
+ "step": 444
1565
+ },
1566
+ {
1567
+ "epoch": 6.659176029962547,
1568
+ "grad_norm": 0.16209331154823303,
1569
+ "learning_rate": 1.7045454545454546e-05,
1570
+ "loss": 0.0152,
1571
+ "step": 446
1572
+ },
1573
+ {
1574
+ "epoch": 6.689138576779026,
1575
+ "grad_norm": 0.11612333357334137,
1576
+ "learning_rate": 1.6893939393939395e-05,
1577
+ "loss": 0.0153,
1578
+ "step": 448
1579
+ },
1580
+ {
1581
+ "epoch": 6.719101123595506,
1582
+ "grad_norm": 0.092486672103405,
1583
+ "learning_rate": 1.674242424242424e-05,
1584
+ "loss": 0.0133,
1585
+ "step": 450
1586
+ },
1587
+ {
1588
+ "epoch": 6.749063670411985,
1589
+ "grad_norm": 0.10298772156238556,
1590
+ "learning_rate": 1.6590909090909094e-05,
1591
+ "loss": 0.0136,
1592
+ "step": 452
1593
+ },
1594
+ {
1595
+ "epoch": 6.7790262172284645,
1596
+ "grad_norm": 0.13439835608005524,
1597
+ "learning_rate": 1.643939393939394e-05,
1598
+ "loss": 0.016,
1599
+ "step": 454
1600
+ },
1601
+ {
1602
+ "epoch": 6.808988764044944,
1603
+ "grad_norm": 0.14403583109378815,
1604
+ "learning_rate": 1.628787878787879e-05,
1605
+ "loss": 0.014,
1606
+ "step": 456
1607
+ },
1608
+ {
1609
+ "epoch": 6.8389513108614235,
1610
+ "grad_norm": 0.1841178834438324,
1611
+ "learning_rate": 1.6136363636363638e-05,
1612
+ "loss": 0.0149,
1613
+ "step": 458
1614
+ },
1615
+ {
1616
+ "epoch": 6.868913857677903,
1617
+ "grad_norm": 0.09390496462583542,
1618
+ "learning_rate": 1.5984848484848487e-05,
1619
+ "loss": 0.0141,
1620
+ "step": 460
1621
+ },
1622
+ {
1623
+ "epoch": 6.898876404494382,
1624
+ "grad_norm": 0.16365155577659607,
1625
+ "learning_rate": 1.5833333333333333e-05,
1626
+ "loss": 0.0157,
1627
+ "step": 462
1628
+ },
1629
+ {
1630
+ "epoch": 6.928838951310862,
1631
+ "grad_norm": 0.1577712446451187,
1632
+ "learning_rate": 1.5681818181818182e-05,
1633
+ "loss": 0.0141,
1634
+ "step": 464
1635
+ },
1636
+ {
1637
+ "epoch": 6.9588014981273405,
1638
+ "grad_norm": 0.173916295170784,
1639
+ "learning_rate": 1.553030303030303e-05,
1640
+ "loss": 0.0157,
1641
+ "step": 466
1642
+ },
1643
+ {
1644
+ "epoch": 6.98876404494382,
1645
+ "grad_norm": 0.16699424386024475,
1646
+ "learning_rate": 1.5378787878787877e-05,
1647
+ "loss": 0.0169,
1648
+ "step": 468
1649
+ },
1650
+ {
1651
+ "epoch": 7.01498127340824,
1652
+ "grad_norm": 0.12708672881126404,
1653
+ "learning_rate": 1.5227272727272728e-05,
1654
+ "loss": 0.0142,
1655
+ "step": 470
1656
+ },
1657
+ {
1658
+ "epoch": 7.044943820224719,
1659
+ "grad_norm": 0.15440689027309418,
1660
+ "learning_rate": 1.5075757575757576e-05,
1661
+ "loss": 0.0158,
1662
+ "step": 472
1663
+ },
1664
+ {
1665
+ "epoch": 7.074906367041199,
1666
+ "grad_norm": 0.1230991929769516,
1667
+ "learning_rate": 1.4924242424242423e-05,
1668
+ "loss": 0.0136,
1669
+ "step": 474
1670
+ },
1671
+ {
1672
+ "epoch": 7.104868913857678,
1673
+ "grad_norm": 0.21653351187705994,
1674
+ "learning_rate": 1.4772727272727274e-05,
1675
+ "loss": 0.0159,
1676
+ "step": 476
1677
+ },
1678
+ {
1679
+ "epoch": 7.134831460674158,
1680
+ "grad_norm": 0.1883053332567215,
1681
+ "learning_rate": 1.4621212121212122e-05,
1682
+ "loss": 0.0155,
1683
+ "step": 478
1684
+ },
1685
+ {
1686
+ "epoch": 7.164794007490637,
1687
+ "grad_norm": 0.22849740087985992,
1688
+ "learning_rate": 1.446969696969697e-05,
1689
+ "loss": 0.0171,
1690
+ "step": 480
1691
+ },
1692
+ {
1693
+ "epoch": 7.194756554307116,
1694
+ "grad_norm": 0.12744282186031342,
1695
+ "learning_rate": 1.431818181818182e-05,
1696
+ "loss": 0.0142,
1697
+ "step": 482
1698
+ },
1699
+ {
1700
+ "epoch": 7.224719101123595,
1701
+ "grad_norm": 0.09133846312761307,
1702
+ "learning_rate": 1.4166666666666668e-05,
1703
+ "loss": 0.0133,
1704
+ "step": 484
1705
+ },
1706
+ {
1707
+ "epoch": 7.254681647940075,
1708
+ "grad_norm": 0.13602511584758759,
1709
+ "learning_rate": 1.4015151515151515e-05,
1710
+ "loss": 0.014,
1711
+ "step": 486
1712
+ },
1713
+ {
1714
+ "epoch": 7.284644194756554,
1715
+ "grad_norm": 0.13092727959156036,
1716
+ "learning_rate": 1.3863636363636364e-05,
1717
+ "loss": 0.0149,
1718
+ "step": 488
1719
+ },
1720
+ {
1721
+ "epoch": 7.314606741573034,
1722
+ "grad_norm": 0.12762710452079773,
1723
+ "learning_rate": 1.3712121212121212e-05,
1724
+ "loss": 0.0143,
1725
+ "step": 490
1726
+ },
1727
+ {
1728
+ "epoch": 7.344569288389513,
1729
+ "grad_norm": 0.12416286021471024,
1730
+ "learning_rate": 1.3560606060606063e-05,
1731
+ "loss": 0.0145,
1732
+ "step": 492
1733
+ },
1734
+ {
1735
+ "epoch": 7.3745318352059925,
1736
+ "grad_norm": 0.145538792014122,
1737
+ "learning_rate": 1.340909090909091e-05,
1738
+ "loss": 0.0145,
1739
+ "step": 494
1740
+ },
1741
+ {
1742
+ "epoch": 7.404494382022472,
1743
+ "grad_norm": 0.11264869570732117,
1744
+ "learning_rate": 1.3257575757575758e-05,
1745
+ "loss": 0.0156,
1746
+ "step": 496
1747
+ },
1748
+ {
1749
+ "epoch": 7.4344569288389515,
1750
+ "grad_norm": 0.10543698072433472,
1751
+ "learning_rate": 1.3106060606060607e-05,
1752
+ "loss": 0.0141,
1753
+ "step": 498
1754
+ },
1755
+ {
1756
+ "epoch": 7.464419475655431,
1757
+ "grad_norm": 0.1221228539943695,
1758
+ "learning_rate": 1.2954545454545455e-05,
1759
+ "loss": 0.0146,
1760
+ "step": 500
1761
+ },
1762
+ {
1763
+ "epoch": 7.49438202247191,
1764
+ "grad_norm": 0.12155947834253311,
1765
+ "learning_rate": 1.2803030303030302e-05,
1766
+ "loss": 0.0141,
1767
+ "step": 502
1768
+ },
1769
+ {
1770
+ "epoch": 7.52434456928839,
1771
+ "grad_norm": 0.12504641711711884,
1772
+ "learning_rate": 1.2651515151515153e-05,
1773
+ "loss": 0.0128,
1774
+ "step": 504
1775
+ },
1776
+ {
1777
+ "epoch": 7.554307116104869,
1778
+ "grad_norm": 0.11169607192277908,
1779
+ "learning_rate": 1.25e-05,
1780
+ "loss": 0.0128,
1781
+ "step": 506
1782
+ },
1783
+ {
1784
+ "epoch": 7.584269662921348,
1785
+ "grad_norm": 0.1285315901041031,
1786
+ "learning_rate": 1.234848484848485e-05,
1787
+ "loss": 0.0161,
1788
+ "step": 508
1789
+ },
1790
+ {
1791
+ "epoch": 7.614232209737827,
1792
+ "grad_norm": 0.10635136067867279,
1793
+ "learning_rate": 1.2196969696969697e-05,
1794
+ "loss": 0.0149,
1795
+ "step": 510
1796
+ },
1797
+ {
1798
+ "epoch": 7.644194756554307,
1799
+ "grad_norm": 0.11686955392360687,
1800
+ "learning_rate": 1.2045454545454547e-05,
1801
+ "loss": 0.0138,
1802
+ "step": 512
1803
+ },
1804
+ {
1805
+ "epoch": 7.674157303370786,
1806
+ "grad_norm": 0.08601470291614532,
1807
+ "learning_rate": 1.1893939393939394e-05,
1808
+ "loss": 0.0131,
1809
+ "step": 514
1810
+ },
1811
+ {
1812
+ "epoch": 7.704119850187266,
1813
+ "grad_norm": 0.0880078673362732,
1814
+ "learning_rate": 1.1742424242424243e-05,
1815
+ "loss": 0.0131,
1816
+ "step": 516
1817
+ },
1818
+ {
1819
+ "epoch": 7.734082397003745,
1820
+ "grad_norm": 0.15093624591827393,
1821
+ "learning_rate": 1.159090909090909e-05,
1822
+ "loss": 0.0162,
1823
+ "step": 518
1824
+ },
1825
+ {
1826
+ "epoch": 7.764044943820225,
1827
+ "grad_norm": 0.11285064369440079,
1828
+ "learning_rate": 1.143939393939394e-05,
1829
+ "loss": 0.015,
1830
+ "step": 520
1831
+ },
1832
+ {
1833
+ "epoch": 7.794007490636704,
1834
+ "grad_norm": 0.10577835887670517,
1835
+ "learning_rate": 1.128787878787879e-05,
1836
+ "loss": 0.0132,
1837
+ "step": 522
1838
+ },
1839
+ {
1840
+ "epoch": 7.823970037453184,
1841
+ "grad_norm": 0.19718210399150848,
1842
+ "learning_rate": 1.1136363636363637e-05,
1843
+ "loss": 0.0143,
1844
+ "step": 524
1845
+ },
1846
+ {
1847
+ "epoch": 7.853932584269663,
1848
+ "grad_norm": 0.13446953892707825,
1849
+ "learning_rate": 1.0984848484848486e-05,
1850
+ "loss": 0.0157,
1851
+ "step": 526
1852
+ },
1853
+ {
1854
+ "epoch": 7.883895131086143,
1855
+ "grad_norm": 0.12463881075382233,
1856
+ "learning_rate": 1.0833333333333334e-05,
1857
+ "loss": 0.015,
1858
+ "step": 528
1859
+ },
1860
+ {
1861
+ "epoch": 7.913857677902621,
1862
+ "grad_norm": 0.13918359577655792,
1863
+ "learning_rate": 1.0681818181818181e-05,
1864
+ "loss": 0.0124,
1865
+ "step": 530
1866
+ },
1867
+ {
1868
+ "epoch": 7.943820224719101,
1869
+ "grad_norm": 0.1380302906036377,
1870
+ "learning_rate": 1.053030303030303e-05,
1871
+ "loss": 0.014,
1872
+ "step": 532
1873
+ },
1874
+ {
1875
+ "epoch": 7.97378277153558,
1876
+ "grad_norm": 0.14899957180023193,
1877
+ "learning_rate": 1.037878787878788e-05,
1878
+ "loss": 0.0175,
1879
+ "step": 534
1880
+ },
1881
+ {
1882
+ "epoch": 8.0,
1883
+ "grad_norm": 0.11646629869937897,
1884
+ "learning_rate": 1.0227272727272729e-05,
1885
+ "loss": 0.0145,
1886
+ "step": 536
1887
+ },
1888
+ {
1889
+ "epoch": 8.02996254681648,
1890
+ "grad_norm": 0.14022769033908844,
1891
+ "learning_rate": 1.0075757575757576e-05,
1892
+ "loss": 0.0121,
1893
+ "step": 538
1894
+ },
1895
+ {
1896
+ "epoch": 8.059925093632959,
1897
+ "grad_norm": 0.15053826570510864,
1898
+ "learning_rate": 9.924242424242425e-06,
1899
+ "loss": 0.0157,
1900
+ "step": 540
1901
+ },
1902
+ {
1903
+ "epoch": 8.089887640449438,
1904
+ "grad_norm": 0.11895288527011871,
1905
+ "learning_rate": 9.772727272727273e-06,
1906
+ "loss": 0.0141,
1907
+ "step": 542
1908
+ },
1909
+ {
1910
+ "epoch": 8.119850187265918,
1911
+ "grad_norm": 0.11707016080617905,
1912
+ "learning_rate": 9.62121212121212e-06,
1913
+ "loss": 0.0145,
1914
+ "step": 544
1915
+ },
1916
+ {
1917
+ "epoch": 8.149812734082397,
1918
+ "grad_norm": 0.10449573397636414,
1919
+ "learning_rate": 9.46969696969697e-06,
1920
+ "loss": 0.0146,
1921
+ "step": 546
1922
+ },
1923
+ {
1924
+ "epoch": 8.179775280898877,
1925
+ "grad_norm": 0.13925935328006744,
1926
+ "learning_rate": 9.318181818181819e-06,
1927
+ "loss": 0.014,
1928
+ "step": 548
1929
+ },
1930
+ {
1931
+ "epoch": 8.209737827715356,
1932
+ "grad_norm": 0.12868592143058777,
1933
+ "learning_rate": 9.166666666666666e-06,
1934
+ "loss": 0.0138,
1935
+ "step": 550
1936
+ },
1937
+ {
1938
+ "epoch": 8.239700374531836,
1939
+ "grad_norm": 0.11764951050281525,
1940
+ "learning_rate": 9.015151515151516e-06,
1941
+ "loss": 0.0147,
1942
+ "step": 552
1943
+ },
1944
+ {
1945
+ "epoch": 8.269662921348315,
1946
+ "grad_norm": 0.21383918821811676,
1947
+ "learning_rate": 8.863636363636365e-06,
1948
+ "loss": 0.0134,
1949
+ "step": 554
1950
+ },
1951
+ {
1952
+ "epoch": 8.299625468164795,
1953
+ "grad_norm": 0.14592906832695007,
1954
+ "learning_rate": 8.712121212121212e-06,
1955
+ "loss": 0.0151,
1956
+ "step": 556
1957
+ },
1958
+ {
1959
+ "epoch": 8.329588014981274,
1960
+ "grad_norm": 0.1377759724855423,
1961
+ "learning_rate": 8.56060606060606e-06,
1962
+ "loss": 0.0138,
1963
+ "step": 558
1964
+ },
1965
+ {
1966
+ "epoch": 8.359550561797754,
1967
+ "grad_norm": 0.15097083151340485,
1968
+ "learning_rate": 8.409090909090909e-06,
1969
+ "loss": 0.013,
1970
+ "step": 560
1971
+ },
1972
+ {
1973
+ "epoch": 8.389513108614231,
1974
+ "grad_norm": 0.1862707883119583,
1975
+ "learning_rate": 8.257575757575758e-06,
1976
+ "loss": 0.0119,
1977
+ "step": 562
1978
+ },
1979
+ {
1980
+ "epoch": 8.41947565543071,
1981
+ "grad_norm": 0.19083456695079803,
1982
+ "learning_rate": 8.106060606060606e-06,
1983
+ "loss": 0.0175,
1984
+ "step": 564
1985
+ },
1986
+ {
1987
+ "epoch": 8.44943820224719,
1988
+ "grad_norm": 0.18206746876239777,
1989
+ "learning_rate": 7.954545454545455e-06,
1990
+ "loss": 0.0153,
1991
+ "step": 566
1992
+ },
1993
+ {
1994
+ "epoch": 8.47940074906367,
1995
+ "grad_norm": 0.1560777872800827,
1996
+ "learning_rate": 7.803030303030304e-06,
1997
+ "loss": 0.0142,
1998
+ "step": 568
1999
+ },
2000
+ {
2001
+ "epoch": 8.50936329588015,
2002
+ "grad_norm": 0.11597474664449692,
2003
+ "learning_rate": 7.651515151515152e-06,
2004
+ "loss": 0.015,
2005
+ "step": 570
2006
+ },
2007
+ {
2008
+ "epoch": 8.539325842696629,
2009
+ "grad_norm": 0.14232860505580902,
2010
+ "learning_rate": 7.5e-06,
2011
+ "loss": 0.0154,
2012
+ "step": 572
2013
+ },
2014
+ {
2015
+ "epoch": 8.569288389513108,
2016
+ "grad_norm": 0.12590251863002777,
2017
+ "learning_rate": 7.3484848484848486e-06,
2018
+ "loss": 0.0141,
2019
+ "step": 574
2020
+ },
2021
+ {
2022
+ "epoch": 8.599250936329588,
2023
+ "grad_norm": 0.161521315574646,
2024
+ "learning_rate": 7.196969696969698e-06,
2025
+ "loss": 0.0152,
2026
+ "step": 576
2027
+ },
2028
+ {
2029
+ "epoch": 8.629213483146067,
2030
+ "grad_norm": 0.12818320095539093,
2031
+ "learning_rate": 7.045454545454545e-06,
2032
+ "loss": 0.0133,
2033
+ "step": 578
2034
+ },
2035
+ {
2036
+ "epoch": 8.659176029962547,
2037
+ "grad_norm": 0.10711938887834549,
2038
+ "learning_rate": 6.8939393939393945e-06,
2039
+ "loss": 0.0143,
2040
+ "step": 580
2041
+ },
2042
+ {
2043
+ "epoch": 8.689138576779026,
2044
+ "grad_norm": 0.11545701324939728,
2045
+ "learning_rate": 6.742424242424243e-06,
2046
+ "loss": 0.0153,
2047
+ "step": 582
2048
+ },
2049
+ {
2050
+ "epoch": 8.719101123595506,
2051
+ "grad_norm": 0.15045291185379028,
2052
+ "learning_rate": 6.59090909090909e-06,
2053
+ "loss": 0.0133,
2054
+ "step": 584
2055
+ },
2056
+ {
2057
+ "epoch": 8.749063670411985,
2058
+ "grad_norm": 0.1033000648021698,
2059
+ "learning_rate": 6.43939393939394e-06,
2060
+ "loss": 0.0145,
2061
+ "step": 586
2062
+ },
2063
+ {
2064
+ "epoch": 8.779026217228465,
2065
+ "grad_norm": 0.16855841875076294,
2066
+ "learning_rate": 6.287878787878789e-06,
2067
+ "loss": 0.0152,
2068
+ "step": 588
2069
+ },
2070
+ {
2071
+ "epoch": 8.808988764044944,
2072
+ "grad_norm": 0.11125820875167847,
2073
+ "learning_rate": 6.136363636363636e-06,
2074
+ "loss": 0.0143,
2075
+ "step": 590
2076
+ },
2077
+ {
2078
+ "epoch": 8.838951310861423,
2079
+ "grad_norm": 0.11163821816444397,
2080
+ "learning_rate": 5.984848484848485e-06,
2081
+ "loss": 0.0143,
2082
+ "step": 592
2083
+ },
2084
+ {
2085
+ "epoch": 8.868913857677903,
2086
+ "grad_norm": 0.11566553264856339,
2087
+ "learning_rate": 5.833333333333334e-06,
2088
+ "loss": 0.0142,
2089
+ "step": 594
2090
+ },
2091
+ {
2092
+ "epoch": 8.898876404494382,
2093
+ "grad_norm": 0.11087555438280106,
2094
+ "learning_rate": 5.681818181818182e-06,
2095
+ "loss": 0.0148,
2096
+ "step": 596
2097
+ },
2098
+ {
2099
+ "epoch": 8.928838951310862,
2100
+ "grad_norm": 0.1234087273478508,
2101
+ "learning_rate": 5.530303030303031e-06,
2102
+ "loss": 0.0156,
2103
+ "step": 598
2104
+ },
2105
+ {
2106
+ "epoch": 8.958801498127341,
2107
+ "grad_norm": 0.18318650126457214,
2108
+ "learning_rate": 5.378787878787879e-06,
2109
+ "loss": 0.0145,
2110
+ "step": 600
2111
+ },
2112
+ {
2113
+ "epoch": 8.98876404494382,
2114
+ "grad_norm": 0.09113040566444397,
2115
+ "learning_rate": 5.2272727272727274e-06,
2116
+ "loss": 0.0132,
2117
+ "step": 602
2118
+ },
2119
+ {
2120
+ "epoch": 9.014981273408239,
2121
+ "grad_norm": 0.10578633099794388,
2122
+ "learning_rate": 5.075757575757576e-06,
2123
+ "loss": 0.0143,
2124
+ "step": 604
2125
+ },
2126
+ {
2127
+ "epoch": 9.044943820224718,
2128
+ "grad_norm": 0.15693627297878265,
2129
+ "learning_rate": 4.924242424242424e-06,
2130
+ "loss": 0.015,
2131
+ "step": 606
2132
+ },
2133
+ {
2134
+ "epoch": 9.074906367041198,
2135
+ "grad_norm": 0.1018158420920372,
2136
+ "learning_rate": 4.772727272727273e-06,
2137
+ "loss": 0.0139,
2138
+ "step": 608
2139
+ },
2140
+ {
2141
+ "epoch": 9.104868913857677,
2142
+ "grad_norm": 0.17492976784706116,
2143
+ "learning_rate": 4.621212121212122e-06,
2144
+ "loss": 0.0156,
2145
+ "step": 610
2146
+ },
2147
+ {
2148
+ "epoch": 9.134831460674157,
2149
+ "grad_norm": 0.11221963167190552,
2150
+ "learning_rate": 4.46969696969697e-06,
2151
+ "loss": 0.0152,
2152
+ "step": 612
2153
+ },
2154
+ {
2155
+ "epoch": 9.164794007490636,
2156
+ "grad_norm": 0.12558336555957794,
2157
+ "learning_rate": 4.3181818181818185e-06,
2158
+ "loss": 0.0143,
2159
+ "step": 614
2160
+ },
2161
+ {
2162
+ "epoch": 9.194756554307116,
2163
+ "grad_norm": 0.11668603867292404,
2164
+ "learning_rate": 4.166666666666667e-06,
2165
+ "loss": 0.0127,
2166
+ "step": 616
2167
+ },
2168
+ {
2169
+ "epoch": 9.224719101123595,
2170
+ "grad_norm": 0.14164716005325317,
2171
+ "learning_rate": 4.015151515151515e-06,
2172
+ "loss": 0.0155,
2173
+ "step": 618
2174
+ },
2175
+ {
2176
+ "epoch": 9.254681647940075,
2177
+ "grad_norm": 0.12440814077854156,
2178
+ "learning_rate": 3.863636363636364e-06,
2179
+ "loss": 0.0134,
2180
+ "step": 620
2181
+ },
2182
+ {
2183
+ "epoch": 9.284644194756554,
2184
+ "grad_norm": 0.14497360587120056,
2185
+ "learning_rate": 3.7121212121212124e-06,
2186
+ "loss": 0.0152,
2187
+ "step": 622
2188
+ },
2189
+ {
2190
+ "epoch": 9.314606741573034,
2191
+ "grad_norm": 0.13429833948612213,
2192
+ "learning_rate": 3.5606060606060608e-06,
2193
+ "loss": 0.015,
2194
+ "step": 624
2195
+ },
2196
+ {
2197
+ "epoch": 9.344569288389513,
2198
+ "grad_norm": 0.11680711805820465,
2199
+ "learning_rate": 3.409090909090909e-06,
2200
+ "loss": 0.0141,
2201
+ "step": 626
2202
+ },
2203
+ {
2204
+ "epoch": 9.374531835205993,
2205
+ "grad_norm": 0.141137033700943,
2206
+ "learning_rate": 3.257575757575758e-06,
2207
+ "loss": 0.0137,
2208
+ "step": 628
2209
+ },
2210
+ {
2211
+ "epoch": 9.404494382022472,
2212
+ "grad_norm": 0.11425523459911346,
2213
+ "learning_rate": 3.106060606060606e-06,
2214
+ "loss": 0.0153,
2215
+ "step": 630
2216
+ },
2217
+ {
2218
+ "epoch": 9.434456928838951,
2219
+ "grad_norm": 0.175795778632164,
2220
+ "learning_rate": 2.9545454545454547e-06,
2221
+ "loss": 0.0137,
2222
+ "step": 632
2223
+ },
2224
+ {
2225
+ "epoch": 9.464419475655431,
2226
+ "grad_norm": 0.21211205422878265,
2227
+ "learning_rate": 2.803030303030303e-06,
2228
+ "loss": 0.0145,
2229
+ "step": 634
2230
+ },
2231
+ {
2232
+ "epoch": 9.49438202247191,
2233
+ "grad_norm": 0.12809644639492035,
2234
+ "learning_rate": 2.651515151515152e-06,
2235
+ "loss": 0.0137,
2236
+ "step": 636
2237
+ },
2238
+ {
2239
+ "epoch": 9.52434456928839,
2240
+ "grad_norm": 0.1471203863620758,
2241
+ "learning_rate": 2.5e-06,
2242
+ "loss": 0.0122,
2243
+ "step": 638
2244
+ },
2245
+ {
2246
+ "epoch": 9.55430711610487,
2247
+ "grad_norm": 0.11589685082435608,
2248
+ "learning_rate": 2.3484848484848486e-06,
2249
+ "loss": 0.0137,
2250
+ "step": 640
2251
+ },
2252
+ {
2253
+ "epoch": 9.584269662921349,
2254
+ "grad_norm": 0.11537714302539825,
2255
+ "learning_rate": 2.196969696969697e-06,
2256
+ "loss": 0.0147,
2257
+ "step": 642
2258
+ },
2259
+ {
2260
+ "epoch": 9.614232209737828,
2261
+ "grad_norm": 0.10002223402261734,
2262
+ "learning_rate": 2.0454545454545457e-06,
2263
+ "loss": 0.0139,
2264
+ "step": 644
2265
+ },
2266
+ {
2267
+ "epoch": 9.644194756554308,
2268
+ "grad_norm": 0.1463649868965149,
2269
+ "learning_rate": 1.8939393939393941e-06,
2270
+ "loss": 0.0138,
2271
+ "step": 646
2272
+ },
2273
+ {
2274
+ "epoch": 9.674157303370787,
2275
+ "grad_norm": 0.15200403332710266,
2276
+ "learning_rate": 1.7424242424242427e-06,
2277
+ "loss": 0.0127,
2278
+ "step": 648
2279
+ },
2280
+ {
2281
+ "epoch": 9.704119850187267,
2282
+ "grad_norm": 0.1294555813074112,
2283
+ "learning_rate": 1.5909090909090908e-06,
2284
+ "loss": 0.013,
2285
+ "step": 650
2286
+ },
2287
+ {
2288
+ "epoch": 9.734082397003746,
2289
+ "grad_norm": 0.12834538519382477,
2290
+ "learning_rate": 1.4393939393939396e-06,
2291
+ "loss": 0.014,
2292
+ "step": 652
2293
+ },
2294
+ {
2295
+ "epoch": 9.764044943820224,
2296
+ "grad_norm": 0.16599954664707184,
2297
+ "learning_rate": 1.287878787878788e-06,
2298
+ "loss": 0.0153,
2299
+ "step": 654
2300
+ },
2301
+ {
2302
+ "epoch": 9.794007490636703,
2303
+ "grad_norm": 0.14348356425762177,
2304
+ "learning_rate": 1.1363636363636364e-06,
2305
+ "loss": 0.0145,
2306
+ "step": 656
2307
+ },
2308
+ {
2309
+ "epoch": 9.823970037453183,
2310
+ "grad_norm": 0.1504441797733307,
2311
+ "learning_rate": 9.848484848484847e-07,
2312
+ "loss": 0.0148,
2313
+ "step": 658
2314
+ },
2315
+ {
2316
+ "epoch": 9.853932584269662,
2317
+ "grad_norm": 0.12484189122915268,
2318
+ "learning_rate": 8.333333333333333e-07,
2319
+ "loss": 0.0156,
2320
+ "step": 660
2321
+ },
2322
+ {
2323
+ "epoch": 9.883895131086142,
2324
+ "grad_norm": 0.17609864473342896,
2325
+ "learning_rate": 6.818181818181818e-07,
2326
+ "loss": 0.0154,
2327
+ "step": 662
2328
+ },
2329
+ {
2330
+ "epoch": 9.913857677902621,
2331
+ "grad_norm": 0.1843879073858261,
2332
+ "learning_rate": 5.303030303030304e-07,
2333
+ "loss": 0.0133,
2334
+ "step": 664
2335
+ },
2336
+ {
2337
+ "epoch": 9.9438202247191,
2338
+ "grad_norm": 0.145470529794693,
2339
+ "learning_rate": 3.787878787878788e-07,
2340
+ "loss": 0.0142,
2341
+ "step": 666
2342
+ },
2343
+ {
2344
+ "epoch": 9.97378277153558,
2345
+ "grad_norm": 0.13248123228549957,
2346
+ "learning_rate": 2.2727272727272726e-07,
2347
+ "loss": 0.0145,
2348
+ "step": 668
2349
+ },
2350
+ {
2351
+ "epoch": 10.0,
2352
+ "grad_norm": 0.18026700615882874,
2353
+ "learning_rate": 7.575757575757576e-08,
2354
+ "loss": 0.0139,
2355
+ "step": 670
2356
+ }
2357
+ ],
2358
+ "logging_steps": 2,
2359
+ "max_steps": 670,
2360
+ "num_input_tokens_seen": 0,
2361
+ "num_train_epochs": 10,
2362
+ "save_steps": 20,
2363
+ "stateful_callbacks": {
2364
+ "TrainerControl": {
2365
+ "args": {
2366
+ "should_epoch_stop": false,
2367
+ "should_evaluate": false,
2368
+ "should_log": false,
2369
+ "should_save": true,
2370
+ "should_training_stop": true
2371
+ },
2372
+ "attributes": {}
2373
+ }
2374
+ },
2375
+ "total_flos": 1.804222263410688e+16,
2376
+ "train_batch_size": 1,
2377
+ "trial_name": null,
2378
+ "trial_params": null
2379
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc984cd6b8e095021805ddd8e3c0a08d2950c17b15e17eebbeeaf65ff57c9fe
3
+ size 5777