matboz commited on
Commit
26d92a9
·
verified ·
1 Parent(s): af274bc

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +11 -0
  2. README.md +62 -0
  3. adapter_config.json +46 -0
  4. adapter_model.safetensors +3 -0
  5. chat_template.jinja +109 -0
  6. checkpoint-1099/README.md +209 -0
  7. checkpoint-1099/adapter_config.json +46 -0
  8. checkpoint-1099/adapter_model.safetensors +3 -0
  9. checkpoint-1099/chat_template.jinja +109 -0
  10. checkpoint-1099/optimizer.pt +3 -0
  11. checkpoint-1099/rng_state.pth +3 -0
  12. checkpoint-1099/scheduler.pt +3 -0
  13. checkpoint-1099/special_tokens_map.json +16 -0
  14. checkpoint-1099/tokenizer.json +3 -0
  15. checkpoint-1099/tokenizer_config.json +2062 -0
  16. checkpoint-1099/trainer_state.json +1124 -0
  17. checkpoint-1099/training_args.bin +3 -0
  18. checkpoint-1256/README.md +209 -0
  19. checkpoint-1256/adapter_config.json +46 -0
  20. checkpoint-1256/adapter_model.safetensors +3 -0
  21. checkpoint-1256/chat_template.jinja +109 -0
  22. checkpoint-1256/optimizer.pt +3 -0
  23. checkpoint-1256/rng_state.pth +3 -0
  24. checkpoint-1256/scheduler.pt +3 -0
  25. checkpoint-1256/special_tokens_map.json +16 -0
  26. checkpoint-1256/tokenizer.json +3 -0
  27. checkpoint-1256/tokenizer_config.json +2062 -0
  28. checkpoint-1256/trainer_state.json +1284 -0
  29. checkpoint-1256/training_args.bin +3 -0
  30. checkpoint-1413/README.md +209 -0
  31. checkpoint-1413/adapter_config.json +46 -0
  32. checkpoint-1413/adapter_model.safetensors +3 -0
  33. checkpoint-1413/chat_template.jinja +109 -0
  34. checkpoint-1413/optimizer.pt +3 -0
  35. checkpoint-1413/rng_state.pth +3 -0
  36. checkpoint-1413/scheduler.pt +3 -0
  37. checkpoint-1413/special_tokens_map.json +16 -0
  38. checkpoint-1413/tokenizer.json +3 -0
  39. checkpoint-1413/tokenizer_config.json +2062 -0
  40. checkpoint-1413/trainer_state.json +1444 -0
  41. checkpoint-1413/training_args.bin +3 -0
  42. checkpoint-157/README.md +209 -0
  43. checkpoint-157/adapter_config.json +46 -0
  44. checkpoint-157/adapter_model.safetensors +3 -0
  45. checkpoint-157/chat_template.jinja +109 -0
  46. checkpoint-157/optimizer.pt +3 -0
  47. checkpoint-157/rng_state.pth +3 -0
  48. checkpoint-157/scheduler.pt +3 -0
  49. checkpoint-157/special_tokens_map.json +16 -0
  50. checkpoint-157/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,14 @@ 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-1099/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-1256/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-1413/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-157/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-1570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-314/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-471/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-628/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-785/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-942/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ model_name: output_lion
5
+ tags:
6
+ - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ licence: license
12
+ pipeline_tag: text-generation
13
+ ---
14
+
15
+ # Model Card for output_lion
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
18
+ It has been trained using [TRL](https://github.com/huggingface/trl).
19
+
20
+ ## Quick start
21
+
22
+ ```python
23
+ from transformers import pipeline
24
+
25
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
26
+ generator = pipeline("text-generation", model="None", device="cuda")
27
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
28
+ print(output["generated_text"])
29
+ ```
30
+
31
+ ## Training procedure
32
+
33
+
34
+
35
+
36
+ This model was trained with SFT.
37
+
38
+ ### Framework versions
39
+
40
+ - PEFT 0.18.0
41
+ - TRL: 0.25.1
42
+ - Transformers: 4.57.1
43
+ - Pytorch: 2.9.0
44
+ - Datasets: 4.4.1
45
+ - Tokenizers: 0.22.1
46
+
47
+ ## Citations
48
+
49
+
50
+
51
+ Cite TRL as:
52
+
53
+ ```bibtex
54
+ @misc{vonwerra2022trl,
55
+ title = {{TRL: Transformer Reinforcement Learning}},
56
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
57
+ year = 2020,
58
+ journal = {GitHub repository},
59
+ publisher = {GitHub},
60
+ howpublished = {\url{https://github.com/huggingface/trl}}
61
+ }
62
+ ```
adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "down_proj",
34
+ "up_proj",
35
+ "q_proj",
36
+ "gate_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d26d134d82767eab116a7d16bdb5de674d8e5cdfe05b8cad09ed691489ec9fc
3
+ size 335604696
chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
checkpoint-1099/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.18.0
checkpoint-1099/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "down_proj",
34
+ "up_proj",
35
+ "q_proj",
36
+ "gate_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-1099/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ef2d607f40c9ee179585114b8ec05354aaea4b22b538ac1cfeb7f38e575231
3
+ size 335604696
checkpoint-1099/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
checkpoint-1099/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7bde9efa5648589a173eb97ca1c561fb9f3bd1c2a12ad2c64cf123acef1a11
3
+ size 671473443
checkpoint-1099/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a826db9e5c9d5394e491dc5fefc5688355ca381b950b87d75162260e4d6c0c
3
+ size 14645
checkpoint-1099/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77b512853040400efb1afd79f42d436c8c91effb509644b45ef4cf6d08399dc
3
+ size 1465
checkpoint-1099/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-1099/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-1099/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
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": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
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": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-1099/trainer_state.json ADDED
@@ -0,0 +1,1124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1099,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.3336982399225235,
14
+ "epoch": 0.064,
15
+ "grad_norm": 1.0639071464538574,
16
+ "learning_rate": 3.7500000000000005e-06,
17
+ "loss": 1.1401,
18
+ "mean_token_accuracy": 0.694624176621437,
19
+ "num_tokens": 170909.0,
20
+ "step": 10
21
+ },
22
+ {
23
+ "entropy": 1.3297590017318726,
24
+ "epoch": 0.128,
25
+ "grad_norm": 0.7065510749816895,
26
+ "learning_rate": 7.916666666666667e-06,
27
+ "loss": 1.0941,
28
+ "mean_token_accuracy": 0.6982980638742446,
29
+ "num_tokens": 339030.0,
30
+ "step": 20
31
+ },
32
+ {
33
+ "entropy": 1.345283743739128,
34
+ "epoch": 0.192,
35
+ "grad_norm": 0.4589855372905731,
36
+ "learning_rate": 1.2083333333333333e-05,
37
+ "loss": 0.9992,
38
+ "mean_token_accuracy": 0.7138096526265144,
39
+ "num_tokens": 507164.0,
40
+ "step": 30
41
+ },
42
+ {
43
+ "entropy": 1.364566907286644,
44
+ "epoch": 0.256,
45
+ "grad_norm": 0.3452564477920532,
46
+ "learning_rate": 1.6250000000000002e-05,
47
+ "loss": 0.9439,
48
+ "mean_token_accuracy": 0.7216050222516059,
49
+ "num_tokens": 675354.0,
50
+ "step": 40
51
+ },
52
+ {
53
+ "entropy": 1.3028314679861068,
54
+ "epoch": 0.32,
55
+ "grad_norm": 0.28635093569755554,
56
+ "learning_rate": 1.9999978697023387e-05,
57
+ "loss": 0.9158,
58
+ "mean_token_accuracy": 0.7276657372713089,
59
+ "num_tokens": 844110.0,
60
+ "step": 50
61
+ },
62
+ {
63
+ "entropy": 1.2932516396045686,
64
+ "epoch": 0.384,
65
+ "grad_norm": 0.27746596932411194,
66
+ "learning_rate": 1.999742244965125e-05,
67
+ "loss": 0.9036,
68
+ "mean_token_accuracy": 0.7287891209125519,
69
+ "num_tokens": 1011944.0,
70
+ "step": 60
71
+ },
72
+ {
73
+ "entropy": 1.2994182020425797,
74
+ "epoch": 0.448,
75
+ "grad_norm": 0.2701167166233063,
76
+ "learning_rate": 1.9990606854864625e-05,
77
+ "loss": 0.9067,
78
+ "mean_token_accuracy": 0.7304235219955444,
79
+ "num_tokens": 1173258.0,
80
+ "step": 70
81
+ },
82
+ {
83
+ "entropy": 1.2833235740661622,
84
+ "epoch": 0.512,
85
+ "grad_norm": 0.24232186377048492,
86
+ "learning_rate": 1.997953481641056e-05,
87
+ "loss": 0.8951,
88
+ "mean_token_accuracy": 0.7301426336169243,
89
+ "num_tokens": 1344619.0,
90
+ "step": 80
91
+ },
92
+ {
93
+ "entropy": 1.2982767909765243,
94
+ "epoch": 0.576,
95
+ "grad_norm": 0.27630752325057983,
96
+ "learning_rate": 1.9964211051470778e-05,
97
+ "loss": 0.898,
98
+ "mean_token_accuracy": 0.7295515269041062,
99
+ "num_tokens": 1512541.0,
100
+ "step": 90
101
+ },
102
+ {
103
+ "entropy": 1.2845446109771728,
104
+ "epoch": 0.64,
105
+ "grad_norm": 0.27921387553215027,
106
+ "learning_rate": 1.994464208865191e-05,
107
+ "loss": 0.8771,
108
+ "mean_token_accuracy": 0.7340485483407975,
109
+ "num_tokens": 1674752.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "entropy": 1.2960468918085097,
114
+ "epoch": 0.704,
115
+ "grad_norm": 0.28025951981544495,
116
+ "learning_rate": 1.9920836265204047e-05,
117
+ "loss": 0.922,
118
+ "mean_token_accuracy": 0.730307950079441,
119
+ "num_tokens": 1843831.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 1.277726098895073,
124
+ "epoch": 0.768,
125
+ "grad_norm": 0.2962108552455902,
126
+ "learning_rate": 1.989280372346868e-05,
127
+ "loss": 0.904,
128
+ "mean_token_accuracy": 0.7301651641726494,
129
+ "num_tokens": 2014821.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 1.2816721558570863,
134
+ "epoch": 0.832,
135
+ "grad_norm": 0.3098539113998413,
136
+ "learning_rate": 1.986055640655763e-05,
137
+ "loss": 0.8928,
138
+ "mean_token_accuracy": 0.7311756134033203,
139
+ "num_tokens": 2182032.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 1.2761377334594726,
144
+ "epoch": 0.896,
145
+ "grad_norm": 0.32843220233917236,
146
+ "learning_rate": 1.9824108053264726e-05,
147
+ "loss": 0.8856,
148
+ "mean_token_accuracy": 0.7321326151490212,
149
+ "num_tokens": 2349897.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 1.278924709558487,
154
+ "epoch": 0.96,
155
+ "grad_norm": 0.284488707780838,
156
+ "learning_rate": 1.9783474192212484e-05,
157
+ "loss": 0.889,
158
+ "mean_token_accuracy": 0.7330759033560753,
159
+ "num_tokens": 2518145.0,
160
+ "step": 150
161
+ },
162
+ {
163
+ "entropy": 1.2941713687535878,
164
+ "epoch": 1.0192,
165
+ "grad_norm": 0.28169313073158264,
166
+ "learning_rate": 1.9738672135236218e-05,
167
+ "loss": 0.8944,
168
+ "mean_token_accuracy": 0.7288601623999106,
169
+ "num_tokens": 2672610.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 1.2729155957698821,
174
+ "epoch": 1.0832,
175
+ "grad_norm": 0.37515658140182495,
176
+ "learning_rate": 1.968972097000843e-05,
177
+ "loss": 0.8668,
178
+ "mean_token_accuracy": 0.7360310450196266,
179
+ "num_tokens": 2837208.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 1.2722265392541885,
184
+ "epoch": 1.1472,
185
+ "grad_norm": 0.31570735573768616,
186
+ "learning_rate": 1.96366415519066e-05,
187
+ "loss": 0.8827,
188
+ "mean_token_accuracy": 0.7332133531570435,
189
+ "num_tokens": 3006803.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 1.2773896872997283,
194
+ "epoch": 1.2112,
195
+ "grad_norm": 0.3074122965335846,
196
+ "learning_rate": 1.957945649512788e-05,
197
+ "loss": 0.8815,
198
+ "mean_token_accuracy": 0.7360113054513931,
199
+ "num_tokens": 3175064.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 1.29012733399868,
204
+ "epoch": 1.2752,
205
+ "grad_norm": 0.31284573674201965,
206
+ "learning_rate": 1.951819016305442e-05,
207
+ "loss": 0.8938,
208
+ "mean_token_accuracy": 0.7312650114297867,
209
+ "num_tokens": 3344594.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "entropy": 1.2645655244588851,
214
+ "epoch": 1.3392,
215
+ "grad_norm": 0.34085312485694885,
216
+ "learning_rate": 1.9452868657873513e-05,
217
+ "loss": 0.8796,
218
+ "mean_token_accuracy": 0.7344238087534904,
219
+ "num_tokens": 3517915.0,
220
+ "step": 210
221
+ },
222
+ {
223
+ "entropy": 1.287526673078537,
224
+ "epoch": 1.4032,
225
+ "grad_norm": 0.34183570742607117,
226
+ "learning_rate": 1.9383519809456862e-05,
227
+ "loss": 0.8661,
228
+ "mean_token_accuracy": 0.7361385986208916,
229
+ "num_tokens": 3680950.0,
230
+ "step": 220
231
+ },
232
+ {
233
+ "entropy": 1.2799992829561233,
234
+ "epoch": 1.4672,
235
+ "grad_norm": 0.3413268029689789,
236
+ "learning_rate": 1.931017316350384e-05,
237
+ "loss": 0.8697,
238
+ "mean_token_accuracy": 0.7360603749752045,
239
+ "num_tokens": 3849839.0,
240
+ "step": 230
241
+ },
242
+ {
243
+ "entropy": 1.2659676790237426,
244
+ "epoch": 1.5312000000000001,
245
+ "grad_norm": 0.3698340356349945,
246
+ "learning_rate": 1.9232859968953702e-05,
247
+ "loss": 0.8485,
248
+ "mean_token_accuracy": 0.7409502565860748,
249
+ "num_tokens": 4013096.0,
250
+ "step": 240
251
+ },
252
+ {
253
+ "entropy": 1.2457158893346787,
254
+ "epoch": 1.5952,
255
+ "grad_norm": 0.3389880061149597,
256
+ "learning_rate": 1.9151613164672136e-05,
257
+ "loss": 0.8413,
258
+ "mean_token_accuracy": 0.7419567927718163,
259
+ "num_tokens": 4179020.0,
260
+ "step": 250
261
+ },
262
+ {
263
+ "entropy": 1.2573517620563508,
264
+ "epoch": 1.6592,
265
+ "grad_norm": 0.3342834413051605,
266
+ "learning_rate": 1.9066467365417844e-05,
267
+ "loss": 0.8608,
268
+ "mean_token_accuracy": 0.7395736679434777,
269
+ "num_tokens": 4346965.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 1.258076936006546,
274
+ "epoch": 1.7231999999999998,
275
+ "grad_norm": 0.3676120936870575,
276
+ "learning_rate": 1.8977458847095117e-05,
277
+ "loss": 0.8473,
278
+ "mean_token_accuracy": 0.7396213799715042,
279
+ "num_tokens": 4514752.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 1.2764853298664094,
284
+ "epoch": 1.7872,
285
+ "grad_norm": 0.3219451606273651,
286
+ "learning_rate": 1.888462553129867e-05,
287
+ "loss": 0.8648,
288
+ "mean_token_accuracy": 0.7372969388961792,
289
+ "num_tokens": 4683207.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 1.2711820542812347,
294
+ "epoch": 1.8512,
295
+ "grad_norm": 0.32780835032463074,
296
+ "learning_rate": 1.878800696915737e-05,
297
+ "loss": 0.8853,
298
+ "mean_token_accuracy": 0.731884841620922,
299
+ "num_tokens": 4854349.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 1.2870726704597473,
304
+ "epoch": 1.9152,
305
+ "grad_norm": 0.3790556788444519,
306
+ "learning_rate": 1.868764432448369e-05,
307
+ "loss": 0.9023,
308
+ "mean_token_accuracy": 0.7296474754810334,
309
+ "num_tokens": 5024479.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "entropy": 1.2802390396595,
314
+ "epoch": 1.9792,
315
+ "grad_norm": 0.3646782636642456,
316
+ "learning_rate": 1.8583580356236065e-05,
317
+ "loss": 0.8691,
318
+ "mean_token_accuracy": 0.7334814980626106,
319
+ "num_tokens": 5187186.0,
320
+ "step": 310
321
+ },
322
+ {
323
+ "entropy": 1.2680169150636003,
324
+ "epoch": 2.0384,
325
+ "grad_norm": 0.3757169842720032,
326
+ "learning_rate": 1.8475859400301708e-05,
327
+ "loss": 0.864,
328
+ "mean_token_accuracy": 0.7385773127143448,
329
+ "num_tokens": 5340338.0,
330
+ "step": 320
331
+ },
332
+ {
333
+ "entropy": 1.2285860389471055,
334
+ "epoch": 2.1024,
335
+ "grad_norm": 0.3415680229663849,
336
+ "learning_rate": 1.8364527350607527e-05,
337
+ "loss": 0.8503,
338
+ "mean_token_accuracy": 0.7417267143726349,
339
+ "num_tokens": 5511078.0,
340
+ "step": 330
341
+ },
342
+ {
343
+ "entropy": 1.2121232539415359,
344
+ "epoch": 2.1664,
345
+ "grad_norm": 0.3802167773246765,
346
+ "learning_rate": 1.824963163956726e-05,
347
+ "loss": 0.8147,
348
+ "mean_token_accuracy": 0.7479733288288116,
349
+ "num_tokens": 5678766.0,
350
+ "step": 340
351
+ },
352
+ {
353
+ "entropy": 1.2510919898748398,
354
+ "epoch": 2.2304,
355
+ "grad_norm": 0.37446126341819763,
356
+ "learning_rate": 1.8131221217873175e-05,
357
+ "loss": 0.851,
358
+ "mean_token_accuracy": 0.740390644967556,
359
+ "num_tokens": 5845310.0,
360
+ "step": 350
361
+ },
362
+ {
363
+ "entropy": 1.2513864248991013,
364
+ "epoch": 2.2944,
365
+ "grad_norm": 0.38065341114997864,
366
+ "learning_rate": 1.8009346533640877e-05,
367
+ "loss": 0.8321,
368
+ "mean_token_accuracy": 0.744195120036602,
369
+ "num_tokens": 6008026.0,
370
+ "step": 360
371
+ },
372
+ {
373
+ "entropy": 1.2588100284337997,
374
+ "epoch": 2.3584,
375
+ "grad_norm": 0.41983911395072937,
376
+ "learning_rate": 1.7884059510916167e-05,
377
+ "loss": 0.8676,
378
+ "mean_token_accuracy": 0.7367229193449021,
379
+ "num_tokens": 6174434.0,
380
+ "step": 370
381
+ },
382
+ {
383
+ "entropy": 1.255004408955574,
384
+ "epoch": 2.4224,
385
+ "grad_norm": 0.40530291199684143,
386
+ "learning_rate": 1.7755413527553087e-05,
387
+ "loss": 0.8535,
388
+ "mean_token_accuracy": 0.7384593844413757,
389
+ "num_tokens": 6344795.0,
390
+ "step": 380
391
+ },
392
+ {
393
+ "entropy": 1.2649497270584107,
394
+ "epoch": 2.4864,
395
+ "grad_norm": 0.3807426691055298,
396
+ "learning_rate": 1.7623463392472574e-05,
397
+ "loss": 0.8694,
398
+ "mean_token_accuracy": 0.7360624000430107,
399
+ "num_tokens": 6514897.0,
400
+ "step": 390
401
+ },
402
+ {
403
+ "entropy": 1.2368371874094009,
404
+ "epoch": 2.5504,
405
+ "grad_norm": 0.3913272023200989,
406
+ "learning_rate": 1.748826532231142e-05,
407
+ "loss": 0.8375,
408
+ "mean_token_accuracy": 0.7420043379068375,
409
+ "num_tokens": 6681240.0,
410
+ "step": 400
411
+ },
412
+ {
413
+ "entropy": 1.2518309116363526,
414
+ "epoch": 2.6144,
415
+ "grad_norm": 0.4146139323711395,
416
+ "learning_rate": 1.7349876917471474e-05,
417
+ "loss": 0.8486,
418
+ "mean_token_accuracy": 0.7402682423591613,
419
+ "num_tokens": 6847429.0,
420
+ "step": 410
421
+ },
422
+ {
423
+ "entropy": 1.2469070911407472,
424
+ "epoch": 2.6784,
425
+ "grad_norm": 0.3891793489456177,
426
+ "learning_rate": 1.7208357137579318e-05,
427
+ "loss": 0.8608,
428
+ "mean_token_accuracy": 0.7373070567846298,
429
+ "num_tokens": 7016692.0,
430
+ "step": 420
431
+ },
432
+ {
433
+ "entropy": 1.2509080231189729,
434
+ "epoch": 2.7424,
435
+ "grad_norm": 0.42574191093444824,
436
+ "learning_rate": 1.7063766276366814e-05,
437
+ "loss": 0.8647,
438
+ "mean_token_accuracy": 0.7349686965346336,
439
+ "num_tokens": 7184437.0,
440
+ "step": 430
441
+ },
442
+ {
443
+ "entropy": 1.2402510732412337,
444
+ "epoch": 2.8064,
445
+ "grad_norm": 0.3809674084186554,
446
+ "learning_rate": 1.6916165935983323e-05,
447
+ "loss": 0.8364,
448
+ "mean_token_accuracy": 0.7414919167757035,
449
+ "num_tokens": 7352089.0,
450
+ "step": 440
451
+ },
452
+ {
453
+ "entropy": 1.2501752972602844,
454
+ "epoch": 2.8704,
455
+ "grad_norm": 0.39809074997901917,
456
+ "learning_rate": 1.676561900075041e-05,
457
+ "loss": 0.846,
458
+ "mean_token_accuracy": 0.7401938289403915,
459
+ "num_tokens": 7519467.0,
460
+ "step": 450
461
+ },
462
+ {
463
+ "entropy": 1.2486298561096192,
464
+ "epoch": 2.9344,
465
+ "grad_norm": 0.4290047287940979,
466
+ "learning_rate": 1.6612189610370336e-05,
467
+ "loss": 0.8603,
468
+ "mean_token_accuracy": 0.7392841055989265,
469
+ "num_tokens": 7691471.0,
470
+ "step": 460
471
+ },
472
+ {
473
+ "entropy": 1.2415612161159515,
474
+ "epoch": 2.9984,
475
+ "grad_norm": 0.39543700218200684,
476
+ "learning_rate": 1.6455943132599698e-05,
477
+ "loss": 0.8428,
478
+ "mean_token_accuracy": 0.7418375059962272,
479
+ "num_tokens": 7858740.0,
480
+ "step": 470
481
+ },
482
+ {
483
+ "entropy": 1.2214874029159546,
484
+ "epoch": 3.0576,
485
+ "grad_norm": 0.42647498846054077,
486
+ "learning_rate": 1.6296946135399835e-05,
487
+ "loss": 0.8186,
488
+ "mean_token_accuracy": 0.7487845855790216,
489
+ "num_tokens": 8013016.0,
490
+ "step": 480
491
+ },
492
+ {
493
+ "entropy": 1.214153888821602,
494
+ "epoch": 3.1216,
495
+ "grad_norm": 0.47299304604530334,
496
+ "learning_rate": 1.613526635857591e-05,
497
+ "loss": 0.8272,
498
+ "mean_token_accuracy": 0.7459566310048104,
499
+ "num_tokens": 8186012.0,
500
+ "step": 490
501
+ },
502
+ {
503
+ "entropy": 1.2059749454259872,
504
+ "epoch": 3.1856,
505
+ "grad_norm": 0.5080869197845459,
506
+ "learning_rate": 1.5970972684916754e-05,
507
+ "loss": 0.814,
508
+ "mean_token_accuracy": 0.7468735337257385,
509
+ "num_tokens": 8356469.0,
510
+ "step": 500
511
+ },
512
+ {
513
+ "entropy": 1.229441523551941,
514
+ "epoch": 3.2496,
515
+ "grad_norm": 0.48198065161705017,
516
+ "learning_rate": 1.5804135110847708e-05,
517
+ "loss": 0.8346,
518
+ "mean_token_accuracy": 0.7422416999936103,
519
+ "num_tokens": 8522068.0,
520
+ "step": 510
521
+ },
522
+ {
523
+ "entropy": 1.2226635456085204,
524
+ "epoch": 3.3136,
525
+ "grad_norm": 0.49883201718330383,
526
+ "learning_rate": 1.5634824716609037e-05,
527
+ "loss": 0.8337,
528
+ "mean_token_accuracy": 0.7423326745629311,
529
+ "num_tokens": 8691189.0,
530
+ "step": 520
531
+ },
532
+ {
533
+ "entropy": 1.221450889110565,
534
+ "epoch": 3.3776,
535
+ "grad_norm": 0.5223852396011353,
536
+ "learning_rate": 1.5463113635972577e-05,
537
+ "loss": 0.8219,
538
+ "mean_token_accuracy": 0.7454505205154419,
539
+ "num_tokens": 8858829.0,
540
+ "step": 530
541
+ },
542
+ {
543
+ "entropy": 1.256075695157051,
544
+ "epoch": 3.4416,
545
+ "grad_norm": 0.5027040839195251,
546
+ "learning_rate": 1.528907502550954e-05,
547
+ "loss": 0.8696,
548
+ "mean_token_accuracy": 0.7371025711297989,
549
+ "num_tokens": 9023152.0,
550
+ "step": 540
551
+ },
552
+ {
553
+ "entropy": 1.2054291009902953,
554
+ "epoch": 3.5056000000000003,
555
+ "grad_norm": 0.5042998790740967,
556
+ "learning_rate": 1.5112783033422547e-05,
557
+ "loss": 0.8089,
558
+ "mean_token_accuracy": 0.7502285718917847,
559
+ "num_tokens": 9192345.0,
560
+ "step": 550
561
+ },
562
+ {
563
+ "entropy": 1.2278274714946746,
564
+ "epoch": 3.5696,
565
+ "grad_norm": 0.45448994636535645,
566
+ "learning_rate": 1.4934312767955193e-05,
567
+ "loss": 0.8243,
568
+ "mean_token_accuracy": 0.7445582717657089,
569
+ "num_tokens": 9359534.0,
570
+ "step": 560
571
+ },
572
+ {
573
+ "entropy": 1.2333297580480576,
574
+ "epoch": 3.6336,
575
+ "grad_norm": 0.5510305166244507,
576
+ "learning_rate": 1.4753740265392595e-05,
577
+ "loss": 0.829,
578
+ "mean_token_accuracy": 0.7417365327477455,
579
+ "num_tokens": 9524499.0,
580
+ "step": 570
581
+ },
582
+ {
583
+ "entropy": 1.218250796198845,
584
+ "epoch": 3.6976,
585
+ "grad_norm": 0.5383264422416687,
586
+ "learning_rate": 1.4571142457666536e-05,
587
+ "loss": 0.8224,
588
+ "mean_token_accuracy": 0.7461559876799584,
589
+ "num_tokens": 9691418.0,
590
+ "step": 580
591
+ },
592
+ {
593
+ "entropy": 1.197799614071846,
594
+ "epoch": 3.7616,
595
+ "grad_norm": 0.4910060465335846,
596
+ "learning_rate": 1.4386597139579041e-05,
597
+ "loss": 0.8106,
598
+ "mean_token_accuracy": 0.7503111377358437,
599
+ "num_tokens": 9860032.0,
600
+ "step": 590
601
+ },
602
+ {
603
+ "entropy": 1.2061665117740632,
604
+ "epoch": 3.8256,
605
+ "grad_norm": 0.4970499575138092,
606
+ "learning_rate": 1.4200182935658327e-05,
607
+ "loss": 0.8091,
608
+ "mean_token_accuracy": 0.7470731437206268,
609
+ "num_tokens": 10030071.0,
610
+ "step": 600
611
+ },
612
+ {
613
+ "entropy": 1.206977090239525,
614
+ "epoch": 3.8895999999999997,
615
+ "grad_norm": 0.4960206151008606,
616
+ "learning_rate": 1.4011979266661235e-05,
617
+ "loss": 0.8132,
618
+ "mean_token_accuracy": 0.7475115478038787,
619
+ "num_tokens": 10197218.0,
620
+ "step": 610
621
+ },
622
+ {
623
+ "entropy": 1.2226781100034714,
624
+ "epoch": 3.9536,
625
+ "grad_norm": 0.5883672833442688,
626
+ "learning_rate": 1.3822066315736477e-05,
627
+ "loss": 0.8151,
628
+ "mean_token_accuracy": 0.747152166068554,
629
+ "num_tokens": 10363213.0,
630
+ "step": 620
631
+ },
632
+ {
633
+ "entropy": 1.222595163293787,
634
+ "epoch": 4.0128,
635
+ "grad_norm": 0.5304821133613586,
636
+ "learning_rate": 1.363052499426302e-05,
637
+ "loss": 0.8143,
638
+ "mean_token_accuracy": 0.744894308012885,
639
+ "num_tokens": 10516376.0,
640
+ "step": 630
641
+ },
642
+ {
643
+ "entropy": 1.1796708509325982,
644
+ "epoch": 4.0768,
645
+ "grad_norm": 0.5488530993461609,
646
+ "learning_rate": 1.3437436907378225e-05,
647
+ "loss": 0.7843,
648
+ "mean_token_accuracy": 0.7553770825266838,
649
+ "num_tokens": 10681877.0,
650
+ "step": 640
651
+ },
652
+ {
653
+ "entropy": 1.2144078850746154,
654
+ "epoch": 4.1408,
655
+ "grad_norm": 0.5689272880554199,
656
+ "learning_rate": 1.3242884319210463e-05,
657
+ "loss": 0.8319,
658
+ "mean_token_accuracy": 0.7462387323379517,
659
+ "num_tokens": 10853452.0,
660
+ "step": 650
661
+ },
662
+ {
663
+ "entropy": 1.1723882287740708,
664
+ "epoch": 4.2048,
665
+ "grad_norm": 0.5823758244514465,
666
+ "learning_rate": 1.3046950117830888e-05,
667
+ "loss": 0.7754,
668
+ "mean_token_accuracy": 0.757102370262146,
669
+ "num_tokens": 11021186.0,
670
+ "step": 660
671
+ },
672
+ {
673
+ "entropy": 1.1938336580991744,
674
+ "epoch": 4.2688,
675
+ "grad_norm": 0.6302596926689148,
676
+ "learning_rate": 1.2849717779939439e-05,
677
+ "loss": 0.8064,
678
+ "mean_token_accuracy": 0.7491099700331688,
679
+ "num_tokens": 11188079.0,
680
+ "step": 670
681
+ },
682
+ {
683
+ "entropy": 1.1738565742969513,
684
+ "epoch": 4.3328,
685
+ "grad_norm": 0.6567224264144897,
686
+ "learning_rate": 1.2651271335300063e-05,
687
+ "loss": 0.7881,
688
+ "mean_token_accuracy": 0.7507374078035355,
689
+ "num_tokens": 11357861.0,
690
+ "step": 680
691
+ },
692
+ {
693
+ "entropy": 1.198876941204071,
694
+ "epoch": 4.3968,
695
+ "grad_norm": 0.62027907371521,
696
+ "learning_rate": 1.2451695330940268e-05,
697
+ "loss": 0.8046,
698
+ "mean_token_accuracy": 0.7497236520051956,
699
+ "num_tokens": 11524052.0,
700
+ "step": 690
701
+ },
702
+ {
703
+ "entropy": 1.1681430846452714,
704
+ "epoch": 4.4608,
705
+ "grad_norm": 0.6131038069725037,
706
+ "learning_rate": 1.2251074795130339e-05,
707
+ "loss": 0.7887,
708
+ "mean_token_accuracy": 0.7542851880192757,
709
+ "num_tokens": 11693539.0,
710
+ "step": 700
711
+ },
712
+ {
713
+ "entropy": 1.2012270838022232,
714
+ "epoch": 4.5248,
715
+ "grad_norm": 0.6755374073982239,
716
+ "learning_rate": 1.2049495201157489e-05,
717
+ "loss": 0.8051,
718
+ "mean_token_accuracy": 0.7475825384259224,
719
+ "num_tokens": 11859545.0,
720
+ "step": 710
721
+ },
722
+ {
723
+ "entropy": 1.190478339791298,
724
+ "epoch": 4.5888,
725
+ "grad_norm": 0.6316648125648499,
726
+ "learning_rate": 1.1847042430910451e-05,
727
+ "loss": 0.7912,
728
+ "mean_token_accuracy": 0.7512465313076973,
729
+ "num_tokens": 12025362.0,
730
+ "step": 720
731
+ },
732
+ {
733
+ "entropy": 1.1802339136600495,
734
+ "epoch": 4.6528,
735
+ "grad_norm": 0.6220593452453613,
736
+ "learning_rate": 1.1643802738289955e-05,
737
+ "loss": 0.7913,
738
+ "mean_token_accuracy": 0.7516302943229676,
739
+ "num_tokens": 12193592.0,
740
+ "step": 730
741
+ },
742
+ {
743
+ "entropy": 1.1827380925416946,
744
+ "epoch": 4.7168,
745
+ "grad_norm": 0.5833670496940613,
746
+ "learning_rate": 1.1439862712460721e-05,
747
+ "loss": 0.8028,
748
+ "mean_token_accuracy": 0.7484710603952408,
749
+ "num_tokens": 12361308.0,
750
+ "step": 740
751
+ },
752
+ {
753
+ "entropy": 1.1752862721681594,
754
+ "epoch": 4.7808,
755
+ "grad_norm": 0.6545965671539307,
756
+ "learning_rate": 1.1235309240960621e-05,
757
+ "loss": 0.7858,
758
+ "mean_token_accuracy": 0.7553699359297752,
759
+ "num_tokens": 12530382.0,
760
+ "step": 750
761
+ },
762
+ {
763
+ "entropy": 1.177734187245369,
764
+ "epoch": 4.8448,
765
+ "grad_norm": 0.6953952312469482,
766
+ "learning_rate": 1.1030229472682719e-05,
767
+ "loss": 0.7852,
768
+ "mean_token_accuracy": 0.7533090978860855,
769
+ "num_tokens": 12695004.0,
770
+ "step": 760
771
+ },
772
+ {
773
+ "entropy": 1.1654743909835816,
774
+ "epoch": 4.9088,
775
+ "grad_norm": 0.6737579107284546,
776
+ "learning_rate": 1.0824710780745954e-05,
777
+ "loss": 0.7878,
778
+ "mean_token_accuracy": 0.7544879004359245,
779
+ "num_tokens": 12864450.0,
780
+ "step": 770
781
+ },
782
+ {
783
+ "entropy": 1.1805586963891983,
784
+ "epoch": 4.9728,
785
+ "grad_norm": 0.6320992708206177,
786
+ "learning_rate": 1.06188407252703e-05,
787
+ "loss": 0.7994,
788
+ "mean_token_accuracy": 0.7510025933384895,
789
+ "num_tokens": 13033199.0,
790
+ "step": 780
791
+ },
792
+ {
793
+ "entropy": 1.165472733007895,
794
+ "epoch": 5.032,
795
+ "grad_norm": 0.652460515499115,
796
+ "learning_rate": 1.0412707016072254e-05,
797
+ "loss": 0.7596,
798
+ "mean_token_accuracy": 0.7593615957208582,
799
+ "num_tokens": 13189187.0,
800
+ "step": 790
801
+ },
802
+ {
803
+ "entropy": 1.1522447764873505,
804
+ "epoch": 5.096,
805
+ "grad_norm": 0.8098700046539307,
806
+ "learning_rate": 1.0206397475296548e-05,
807
+ "loss": 0.768,
808
+ "mean_token_accuracy": 0.7569398522377014,
809
+ "num_tokens": 13358010.0,
810
+ "step": 800
811
+ },
812
+ {
813
+ "entropy": 1.155535000562668,
814
+ "epoch": 5.16,
815
+ "grad_norm": 0.7569311261177063,
816
+ "learning_rate": 1e-05,
817
+ "loss": 0.766,
818
+ "mean_token_accuracy": 0.7563902020454407,
819
+ "num_tokens": 13524722.0,
820
+ "step": 810
821
+ },
822
+ {
823
+ "entropy": 1.157894878089428,
824
+ "epoch": 5.224,
825
+ "grad_norm": 0.8364959359169006,
826
+ "learning_rate": 9.793602524703456e-06,
827
+ "loss": 0.7693,
828
+ "mean_token_accuracy": 0.7581299751996994,
829
+ "num_tokens": 13690529.0,
830
+ "step": 820
831
+ },
832
+ {
833
+ "entropy": 1.145342645049095,
834
+ "epoch": 5.288,
835
+ "grad_norm": 0.7824255228042603,
836
+ "learning_rate": 9.58729298392775e-06,
837
+ "loss": 0.7611,
838
+ "mean_token_accuracy": 0.761179718375206,
839
+ "num_tokens": 13859442.0,
840
+ "step": 830
841
+ },
842
+ {
843
+ "entropy": 1.1661550253629684,
844
+ "epoch": 5.352,
845
+ "grad_norm": 0.7638425230979919,
846
+ "learning_rate": 9.381159274729704e-06,
847
+ "loss": 0.7825,
848
+ "mean_token_accuracy": 0.7569466888904571,
849
+ "num_tokens": 14028485.0,
850
+ "step": 840
851
+ },
852
+ {
853
+ "entropy": 1.1383796483278275,
854
+ "epoch": 5.416,
855
+ "grad_norm": 0.7410515546798706,
856
+ "learning_rate": 9.175289219254051e-06,
857
+ "loss": 0.7497,
858
+ "mean_token_accuracy": 0.7625020772218705,
859
+ "num_tokens": 14198221.0,
860
+ "step": 850
861
+ },
862
+ {
863
+ "entropy": 1.1481939822435379,
864
+ "epoch": 5.48,
865
+ "grad_norm": 0.7490608096122742,
866
+ "learning_rate": 8.969770527317283e-06,
867
+ "loss": 0.7477,
868
+ "mean_token_accuracy": 0.7623027458786964,
869
+ "num_tokens": 14367293.0,
870
+ "step": 860
871
+ },
872
+ {
873
+ "entropy": 1.1579900979995728,
874
+ "epoch": 5.5440000000000005,
875
+ "grad_norm": 0.7536274790763855,
876
+ "learning_rate": 8.764690759039382e-06,
877
+ "loss": 0.7692,
878
+ "mean_token_accuracy": 0.7568637877702713,
879
+ "num_tokens": 14535472.0,
880
+ "step": 870
881
+ },
882
+ {
883
+ "entropy": 1.1517672553658485,
884
+ "epoch": 5.608,
885
+ "grad_norm": 0.824515163898468,
886
+ "learning_rate": 8.56013728753928e-06,
887
+ "loss": 0.7621,
888
+ "mean_token_accuracy": 0.7600950643420219,
889
+ "num_tokens": 14700265.0,
890
+ "step": 880
891
+ },
892
+ {
893
+ "entropy": 1.1413051068782807,
894
+ "epoch": 5.672,
895
+ "grad_norm": 0.7741249203681946,
896
+ "learning_rate": 8.356197261710048e-06,
897
+ "loss": 0.7518,
898
+ "mean_token_accuracy": 0.7614945828914642,
899
+ "num_tokens": 14866673.0,
900
+ "step": 890
901
+ },
902
+ {
903
+ "entropy": 1.171517863869667,
904
+ "epoch": 5.736,
905
+ "grad_norm": 0.7269055247306824,
906
+ "learning_rate": 8.152957569089552e-06,
907
+ "loss": 0.7836,
908
+ "mean_token_accuracy": 0.7550232648849488,
909
+ "num_tokens": 15031602.0,
910
+ "step": 900
911
+ },
912
+ {
913
+ "entropy": 1.1627105355262757,
914
+ "epoch": 5.8,
915
+ "grad_norm": 0.8189387321472168,
916
+ "learning_rate": 7.950504798842513e-06,
917
+ "loss": 0.7818,
918
+ "mean_token_accuracy": 0.7560641661286354,
919
+ "num_tokens": 15200656.0,
920
+ "step": 910
921
+ },
922
+ {
923
+ "entropy": 1.1600016862154008,
924
+ "epoch": 5.864,
925
+ "grad_norm": 0.8086869716644287,
926
+ "learning_rate": 7.748925204869667e-06,
927
+ "loss": 0.7637,
928
+ "mean_token_accuracy": 0.7589102029800415,
929
+ "num_tokens": 15368071.0,
930
+ "step": 920
931
+ },
932
+ {
933
+ "entropy": 1.1717667609453202,
934
+ "epoch": 5.928,
935
+ "grad_norm": 0.8845758438110352,
936
+ "learning_rate": 7.548304669059735e-06,
937
+ "loss": 0.7792,
938
+ "mean_token_accuracy": 0.7552744656801224,
939
+ "num_tokens": 15533538.0,
940
+ "step": 930
941
+ },
942
+ {
943
+ "entropy": 1.1296544909477233,
944
+ "epoch": 5.992,
945
+ "grad_norm": 0.8191102147102356,
946
+ "learning_rate": 7.348728664699939e-06,
947
+ "loss": 0.7392,
948
+ "mean_token_accuracy": 0.7642928868532181,
949
+ "num_tokens": 15702224.0,
950
+ "step": 940
951
+ },
952
+ {
953
+ "entropy": 1.1310625011856492,
954
+ "epoch": 6.0512,
955
+ "grad_norm": 1.03687584400177,
956
+ "learning_rate": 7.150282220060564e-06,
957
+ "loss": 0.7322,
958
+ "mean_token_accuracy": 0.7652509937415252,
959
+ "num_tokens": 15855871.0,
960
+ "step": 950
961
+ },
962
+ {
963
+ "entropy": 1.12939695417881,
964
+ "epoch": 6.1152,
965
+ "grad_norm": 0.9026349186897278,
966
+ "learning_rate": 6.9530498821691165e-06,
967
+ "loss": 0.7312,
968
+ "mean_token_accuracy": 0.7661619514226914,
969
+ "num_tokens": 16022959.0,
970
+ "step": 960
971
+ },
972
+ {
973
+ "entropy": 1.1230400115251542,
974
+ "epoch": 6.1792,
975
+ "grad_norm": 0.9334505200386047,
976
+ "learning_rate": 6.757115680789539e-06,
977
+ "loss": 0.7166,
978
+ "mean_token_accuracy": 0.7693509578704834,
979
+ "num_tokens": 16184586.0,
980
+ "step": 970
981
+ },
982
+ {
983
+ "entropy": 1.1167623370885849,
984
+ "epoch": 6.2432,
985
+ "grad_norm": 0.8687794804573059,
986
+ "learning_rate": 6.562563092621776e-06,
987
+ "loss": 0.7309,
988
+ "mean_token_accuracy": 0.7661765992641449,
989
+ "num_tokens": 16356436.0,
990
+ "step": 980
991
+ },
992
+ {
993
+ "entropy": 1.1170607119798661,
994
+ "epoch": 6.3072,
995
+ "grad_norm": 0.9250707626342773,
996
+ "learning_rate": 6.369475005736984e-06,
997
+ "loss": 0.728,
998
+ "mean_token_accuracy": 0.7687151193618774,
999
+ "num_tokens": 16522765.0,
1000
+ "step": 990
1001
+ },
1002
+ {
1003
+ "entropy": 1.1269994646310806,
1004
+ "epoch": 6.3712,
1005
+ "grad_norm": 0.9762291312217712,
1006
+ "learning_rate": 6.177933684263524e-06,
1007
+ "loss": 0.7427,
1008
+ "mean_token_accuracy": 0.7661235600709915,
1009
+ "num_tokens": 16689964.0,
1010
+ "step": 1000
1011
+ },
1012
+ {
1013
+ "entropy": 1.1308791995048524,
1014
+ "epoch": 6.4352,
1015
+ "grad_norm": 0.9405747652053833,
1016
+ "learning_rate": 5.988020733338767e-06,
1017
+ "loss": 0.7282,
1018
+ "mean_token_accuracy": 0.7662904724478722,
1019
+ "num_tokens": 16855846.0,
1020
+ "step": 1010
1021
+ },
1022
+ {
1023
+ "entropy": 1.1322367668151856,
1024
+ "epoch": 6.4992,
1025
+ "grad_norm": 0.8870813250541687,
1026
+ "learning_rate": 5.7998170643416795e-06,
1027
+ "loss": 0.7448,
1028
+ "mean_token_accuracy": 0.7629623278975487,
1029
+ "num_tokens": 17024434.0,
1030
+ "step": 1020
1031
+ },
1032
+ {
1033
+ "entropy": 1.1535383015871048,
1034
+ "epoch": 6.5632,
1035
+ "grad_norm": 0.9254381060600281,
1036
+ "learning_rate": 5.613402860420962e-06,
1037
+ "loss": 0.7691,
1038
+ "mean_token_accuracy": 0.7590128257870674,
1039
+ "num_tokens": 17195067.0,
1040
+ "step": 1030
1041
+ },
1042
+ {
1043
+ "entropy": 1.1291758388280868,
1044
+ "epoch": 6.6272,
1045
+ "grad_norm": 0.8941587209701538,
1046
+ "learning_rate": 5.428857542333465e-06,
1047
+ "loss": 0.7423,
1048
+ "mean_token_accuracy": 0.7641170158982277,
1049
+ "num_tokens": 17367933.0,
1050
+ "step": 1040
1051
+ },
1052
+ {
1053
+ "entropy": 1.1354484647512435,
1054
+ "epoch": 6.6912,
1055
+ "grad_norm": 0.9986079335212708,
1056
+ "learning_rate": 5.246259734607411e-06,
1057
+ "loss": 0.7558,
1058
+ "mean_token_accuracy": 0.7625504702329635,
1059
+ "num_tokens": 17534589.0,
1060
+ "step": 1050
1061
+ },
1062
+ {
1063
+ "entropy": 1.1145919933915138,
1064
+ "epoch": 6.7552,
1065
+ "grad_norm": 0.9608755707740784,
1066
+ "learning_rate": 5.065687232044811e-06,
1067
+ "loss": 0.7207,
1068
+ "mean_token_accuracy": 0.767878831923008,
1069
+ "num_tokens": 17702136.0,
1070
+ "step": 1060
1071
+ },
1072
+ {
1073
+ "entropy": 1.1152497231960297,
1074
+ "epoch": 6.8192,
1075
+ "grad_norm": 0.930647611618042,
1076
+ "learning_rate": 4.887216966577458e-06,
1077
+ "loss": 0.7136,
1078
+ "mean_token_accuracy": 0.7703010246157647,
1079
+ "num_tokens": 17868339.0,
1080
+ "step": 1070
1081
+ },
1082
+ {
1083
+ "entropy": 1.1384254783391952,
1084
+ "epoch": 6.8832,
1085
+ "grad_norm": 0.981146514415741,
1086
+ "learning_rate": 4.710924974490463e-06,
1087
+ "loss": 0.7725,
1088
+ "mean_token_accuracy": 0.7612431243062019,
1089
+ "num_tokens": 18041328.0,
1090
+ "step": 1080
1091
+ },
1092
+ {
1093
+ "entropy": 1.1156837493181229,
1094
+ "epoch": 6.9472000000000005,
1095
+ "grad_norm": 1.031293511390686,
1096
+ "learning_rate": 4.536886364027428e-06,
1097
+ "loss": 0.7187,
1098
+ "mean_token_accuracy": 0.7708014816045761,
1099
+ "num_tokens": 18207019.0,
1100
+ "step": 1090
1101
+ }
1102
+ ],
1103
+ "logging_steps": 10,
1104
+ "max_steps": 1570,
1105
+ "num_input_tokens_seen": 0,
1106
+ "num_train_epochs": 10,
1107
+ "save_steps": 500,
1108
+ "stateful_callbacks": {
1109
+ "TrainerControl": {
1110
+ "args": {
1111
+ "should_epoch_stop": false,
1112
+ "should_evaluate": false,
1113
+ "should_log": false,
1114
+ "should_save": true,
1115
+ "should_training_stop": false
1116
+ },
1117
+ "attributes": {}
1118
+ }
1119
+ },
1120
+ "total_flos": 1.5203030056607416e+18,
1121
+ "train_batch_size": 16,
1122
+ "trial_name": null,
1123
+ "trial_params": null
1124
+ }
checkpoint-1099/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715b5f801a71e6f8ee2177ab148805ed1d1c0732f395811ea0f0c2c52c99d11c
3
+ size 6225
checkpoint-1256/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.18.0
checkpoint-1256/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "down_proj",
34
+ "up_proj",
35
+ "q_proj",
36
+ "gate_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-1256/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94f5fffb029b6c176d1697ebfe24dca12b7f0eb22187fde1a5da9092190c1c6
3
+ size 335604696
checkpoint-1256/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
checkpoint-1256/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197a02d7699b5590567ee05361a97935a2ff86ccc75a210258264be60f7b2810
3
+ size 671473443
checkpoint-1256/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3407e10f6cc7aefb2e188af40188935a5312368f9cde74ccfff5e2b736230f
3
+ size 14645
checkpoint-1256/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7982033c288e64397c4c99f80c20c49f163f0a8e548abd9ca71f6e3a665ad4
3
+ size 1465
checkpoint-1256/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-1256/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-1256/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
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": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
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": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-1256/trainer_state.json ADDED
@@ -0,0 +1,1284 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1256,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.3336982399225235,
14
+ "epoch": 0.064,
15
+ "grad_norm": 1.0639071464538574,
16
+ "learning_rate": 3.7500000000000005e-06,
17
+ "loss": 1.1401,
18
+ "mean_token_accuracy": 0.694624176621437,
19
+ "num_tokens": 170909.0,
20
+ "step": 10
21
+ },
22
+ {
23
+ "entropy": 1.3297590017318726,
24
+ "epoch": 0.128,
25
+ "grad_norm": 0.7065510749816895,
26
+ "learning_rate": 7.916666666666667e-06,
27
+ "loss": 1.0941,
28
+ "mean_token_accuracy": 0.6982980638742446,
29
+ "num_tokens": 339030.0,
30
+ "step": 20
31
+ },
32
+ {
33
+ "entropy": 1.345283743739128,
34
+ "epoch": 0.192,
35
+ "grad_norm": 0.4589855372905731,
36
+ "learning_rate": 1.2083333333333333e-05,
37
+ "loss": 0.9992,
38
+ "mean_token_accuracy": 0.7138096526265144,
39
+ "num_tokens": 507164.0,
40
+ "step": 30
41
+ },
42
+ {
43
+ "entropy": 1.364566907286644,
44
+ "epoch": 0.256,
45
+ "grad_norm": 0.3452564477920532,
46
+ "learning_rate": 1.6250000000000002e-05,
47
+ "loss": 0.9439,
48
+ "mean_token_accuracy": 0.7216050222516059,
49
+ "num_tokens": 675354.0,
50
+ "step": 40
51
+ },
52
+ {
53
+ "entropy": 1.3028314679861068,
54
+ "epoch": 0.32,
55
+ "grad_norm": 0.28635093569755554,
56
+ "learning_rate": 1.9999978697023387e-05,
57
+ "loss": 0.9158,
58
+ "mean_token_accuracy": 0.7276657372713089,
59
+ "num_tokens": 844110.0,
60
+ "step": 50
61
+ },
62
+ {
63
+ "entropy": 1.2932516396045686,
64
+ "epoch": 0.384,
65
+ "grad_norm": 0.27746596932411194,
66
+ "learning_rate": 1.999742244965125e-05,
67
+ "loss": 0.9036,
68
+ "mean_token_accuracy": 0.7287891209125519,
69
+ "num_tokens": 1011944.0,
70
+ "step": 60
71
+ },
72
+ {
73
+ "entropy": 1.2994182020425797,
74
+ "epoch": 0.448,
75
+ "grad_norm": 0.2701167166233063,
76
+ "learning_rate": 1.9990606854864625e-05,
77
+ "loss": 0.9067,
78
+ "mean_token_accuracy": 0.7304235219955444,
79
+ "num_tokens": 1173258.0,
80
+ "step": 70
81
+ },
82
+ {
83
+ "entropy": 1.2833235740661622,
84
+ "epoch": 0.512,
85
+ "grad_norm": 0.24232186377048492,
86
+ "learning_rate": 1.997953481641056e-05,
87
+ "loss": 0.8951,
88
+ "mean_token_accuracy": 0.7301426336169243,
89
+ "num_tokens": 1344619.0,
90
+ "step": 80
91
+ },
92
+ {
93
+ "entropy": 1.2982767909765243,
94
+ "epoch": 0.576,
95
+ "grad_norm": 0.27630752325057983,
96
+ "learning_rate": 1.9964211051470778e-05,
97
+ "loss": 0.898,
98
+ "mean_token_accuracy": 0.7295515269041062,
99
+ "num_tokens": 1512541.0,
100
+ "step": 90
101
+ },
102
+ {
103
+ "entropy": 1.2845446109771728,
104
+ "epoch": 0.64,
105
+ "grad_norm": 0.27921387553215027,
106
+ "learning_rate": 1.994464208865191e-05,
107
+ "loss": 0.8771,
108
+ "mean_token_accuracy": 0.7340485483407975,
109
+ "num_tokens": 1674752.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "entropy": 1.2960468918085097,
114
+ "epoch": 0.704,
115
+ "grad_norm": 0.28025951981544495,
116
+ "learning_rate": 1.9920836265204047e-05,
117
+ "loss": 0.922,
118
+ "mean_token_accuracy": 0.730307950079441,
119
+ "num_tokens": 1843831.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 1.277726098895073,
124
+ "epoch": 0.768,
125
+ "grad_norm": 0.2962108552455902,
126
+ "learning_rate": 1.989280372346868e-05,
127
+ "loss": 0.904,
128
+ "mean_token_accuracy": 0.7301651641726494,
129
+ "num_tokens": 2014821.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 1.2816721558570863,
134
+ "epoch": 0.832,
135
+ "grad_norm": 0.3098539113998413,
136
+ "learning_rate": 1.986055640655763e-05,
137
+ "loss": 0.8928,
138
+ "mean_token_accuracy": 0.7311756134033203,
139
+ "num_tokens": 2182032.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 1.2761377334594726,
144
+ "epoch": 0.896,
145
+ "grad_norm": 0.32843220233917236,
146
+ "learning_rate": 1.9824108053264726e-05,
147
+ "loss": 0.8856,
148
+ "mean_token_accuracy": 0.7321326151490212,
149
+ "num_tokens": 2349897.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 1.278924709558487,
154
+ "epoch": 0.96,
155
+ "grad_norm": 0.284488707780838,
156
+ "learning_rate": 1.9783474192212484e-05,
157
+ "loss": 0.889,
158
+ "mean_token_accuracy": 0.7330759033560753,
159
+ "num_tokens": 2518145.0,
160
+ "step": 150
161
+ },
162
+ {
163
+ "entropy": 1.2941713687535878,
164
+ "epoch": 1.0192,
165
+ "grad_norm": 0.28169313073158264,
166
+ "learning_rate": 1.9738672135236218e-05,
167
+ "loss": 0.8944,
168
+ "mean_token_accuracy": 0.7288601623999106,
169
+ "num_tokens": 2672610.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 1.2729155957698821,
174
+ "epoch": 1.0832,
175
+ "grad_norm": 0.37515658140182495,
176
+ "learning_rate": 1.968972097000843e-05,
177
+ "loss": 0.8668,
178
+ "mean_token_accuracy": 0.7360310450196266,
179
+ "num_tokens": 2837208.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 1.2722265392541885,
184
+ "epoch": 1.1472,
185
+ "grad_norm": 0.31570735573768616,
186
+ "learning_rate": 1.96366415519066e-05,
187
+ "loss": 0.8827,
188
+ "mean_token_accuracy": 0.7332133531570435,
189
+ "num_tokens": 3006803.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 1.2773896872997283,
194
+ "epoch": 1.2112,
195
+ "grad_norm": 0.3074122965335846,
196
+ "learning_rate": 1.957945649512788e-05,
197
+ "loss": 0.8815,
198
+ "mean_token_accuracy": 0.7360113054513931,
199
+ "num_tokens": 3175064.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 1.29012733399868,
204
+ "epoch": 1.2752,
205
+ "grad_norm": 0.31284573674201965,
206
+ "learning_rate": 1.951819016305442e-05,
207
+ "loss": 0.8938,
208
+ "mean_token_accuracy": 0.7312650114297867,
209
+ "num_tokens": 3344594.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "entropy": 1.2645655244588851,
214
+ "epoch": 1.3392,
215
+ "grad_norm": 0.34085312485694885,
216
+ "learning_rate": 1.9452868657873513e-05,
217
+ "loss": 0.8796,
218
+ "mean_token_accuracy": 0.7344238087534904,
219
+ "num_tokens": 3517915.0,
220
+ "step": 210
221
+ },
222
+ {
223
+ "entropy": 1.287526673078537,
224
+ "epoch": 1.4032,
225
+ "grad_norm": 0.34183570742607117,
226
+ "learning_rate": 1.9383519809456862e-05,
227
+ "loss": 0.8661,
228
+ "mean_token_accuracy": 0.7361385986208916,
229
+ "num_tokens": 3680950.0,
230
+ "step": 220
231
+ },
232
+ {
233
+ "entropy": 1.2799992829561233,
234
+ "epoch": 1.4672,
235
+ "grad_norm": 0.3413268029689789,
236
+ "learning_rate": 1.931017316350384e-05,
237
+ "loss": 0.8697,
238
+ "mean_token_accuracy": 0.7360603749752045,
239
+ "num_tokens": 3849839.0,
240
+ "step": 230
241
+ },
242
+ {
243
+ "entropy": 1.2659676790237426,
244
+ "epoch": 1.5312000000000001,
245
+ "grad_norm": 0.3698340356349945,
246
+ "learning_rate": 1.9232859968953702e-05,
247
+ "loss": 0.8485,
248
+ "mean_token_accuracy": 0.7409502565860748,
249
+ "num_tokens": 4013096.0,
250
+ "step": 240
251
+ },
252
+ {
253
+ "entropy": 1.2457158893346787,
254
+ "epoch": 1.5952,
255
+ "grad_norm": 0.3389880061149597,
256
+ "learning_rate": 1.9151613164672136e-05,
257
+ "loss": 0.8413,
258
+ "mean_token_accuracy": 0.7419567927718163,
259
+ "num_tokens": 4179020.0,
260
+ "step": 250
261
+ },
262
+ {
263
+ "entropy": 1.2573517620563508,
264
+ "epoch": 1.6592,
265
+ "grad_norm": 0.3342834413051605,
266
+ "learning_rate": 1.9066467365417844e-05,
267
+ "loss": 0.8608,
268
+ "mean_token_accuracy": 0.7395736679434777,
269
+ "num_tokens": 4346965.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 1.258076936006546,
274
+ "epoch": 1.7231999999999998,
275
+ "grad_norm": 0.3676120936870575,
276
+ "learning_rate": 1.8977458847095117e-05,
277
+ "loss": 0.8473,
278
+ "mean_token_accuracy": 0.7396213799715042,
279
+ "num_tokens": 4514752.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 1.2764853298664094,
284
+ "epoch": 1.7872,
285
+ "grad_norm": 0.3219451606273651,
286
+ "learning_rate": 1.888462553129867e-05,
287
+ "loss": 0.8648,
288
+ "mean_token_accuracy": 0.7372969388961792,
289
+ "num_tokens": 4683207.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 1.2711820542812347,
294
+ "epoch": 1.8512,
295
+ "grad_norm": 0.32780835032463074,
296
+ "learning_rate": 1.878800696915737e-05,
297
+ "loss": 0.8853,
298
+ "mean_token_accuracy": 0.731884841620922,
299
+ "num_tokens": 4854349.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 1.2870726704597473,
304
+ "epoch": 1.9152,
305
+ "grad_norm": 0.3790556788444519,
306
+ "learning_rate": 1.868764432448369e-05,
307
+ "loss": 0.9023,
308
+ "mean_token_accuracy": 0.7296474754810334,
309
+ "num_tokens": 5024479.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "entropy": 1.2802390396595,
314
+ "epoch": 1.9792,
315
+ "grad_norm": 0.3646782636642456,
316
+ "learning_rate": 1.8583580356236065e-05,
317
+ "loss": 0.8691,
318
+ "mean_token_accuracy": 0.7334814980626106,
319
+ "num_tokens": 5187186.0,
320
+ "step": 310
321
+ },
322
+ {
323
+ "entropy": 1.2680169150636003,
324
+ "epoch": 2.0384,
325
+ "grad_norm": 0.3757169842720032,
326
+ "learning_rate": 1.8475859400301708e-05,
327
+ "loss": 0.864,
328
+ "mean_token_accuracy": 0.7385773127143448,
329
+ "num_tokens": 5340338.0,
330
+ "step": 320
331
+ },
332
+ {
333
+ "entropy": 1.2285860389471055,
334
+ "epoch": 2.1024,
335
+ "grad_norm": 0.3415680229663849,
336
+ "learning_rate": 1.8364527350607527e-05,
337
+ "loss": 0.8503,
338
+ "mean_token_accuracy": 0.7417267143726349,
339
+ "num_tokens": 5511078.0,
340
+ "step": 330
341
+ },
342
+ {
343
+ "entropy": 1.2121232539415359,
344
+ "epoch": 2.1664,
345
+ "grad_norm": 0.3802167773246765,
346
+ "learning_rate": 1.824963163956726e-05,
347
+ "loss": 0.8147,
348
+ "mean_token_accuracy": 0.7479733288288116,
349
+ "num_tokens": 5678766.0,
350
+ "step": 340
351
+ },
352
+ {
353
+ "entropy": 1.2510919898748398,
354
+ "epoch": 2.2304,
355
+ "grad_norm": 0.37446126341819763,
356
+ "learning_rate": 1.8131221217873175e-05,
357
+ "loss": 0.851,
358
+ "mean_token_accuracy": 0.740390644967556,
359
+ "num_tokens": 5845310.0,
360
+ "step": 350
361
+ },
362
+ {
363
+ "entropy": 1.2513864248991013,
364
+ "epoch": 2.2944,
365
+ "grad_norm": 0.38065341114997864,
366
+ "learning_rate": 1.8009346533640877e-05,
367
+ "loss": 0.8321,
368
+ "mean_token_accuracy": 0.744195120036602,
369
+ "num_tokens": 6008026.0,
370
+ "step": 360
371
+ },
372
+ {
373
+ "entropy": 1.2588100284337997,
374
+ "epoch": 2.3584,
375
+ "grad_norm": 0.41983911395072937,
376
+ "learning_rate": 1.7884059510916167e-05,
377
+ "loss": 0.8676,
378
+ "mean_token_accuracy": 0.7367229193449021,
379
+ "num_tokens": 6174434.0,
380
+ "step": 370
381
+ },
382
+ {
383
+ "entropy": 1.255004408955574,
384
+ "epoch": 2.4224,
385
+ "grad_norm": 0.40530291199684143,
386
+ "learning_rate": 1.7755413527553087e-05,
387
+ "loss": 0.8535,
388
+ "mean_token_accuracy": 0.7384593844413757,
389
+ "num_tokens": 6344795.0,
390
+ "step": 380
391
+ },
392
+ {
393
+ "entropy": 1.2649497270584107,
394
+ "epoch": 2.4864,
395
+ "grad_norm": 0.3807426691055298,
396
+ "learning_rate": 1.7623463392472574e-05,
397
+ "loss": 0.8694,
398
+ "mean_token_accuracy": 0.7360624000430107,
399
+ "num_tokens": 6514897.0,
400
+ "step": 390
401
+ },
402
+ {
403
+ "entropy": 1.2368371874094009,
404
+ "epoch": 2.5504,
405
+ "grad_norm": 0.3913272023200989,
406
+ "learning_rate": 1.748826532231142e-05,
407
+ "loss": 0.8375,
408
+ "mean_token_accuracy": 0.7420043379068375,
409
+ "num_tokens": 6681240.0,
410
+ "step": 400
411
+ },
412
+ {
413
+ "entropy": 1.2518309116363526,
414
+ "epoch": 2.6144,
415
+ "grad_norm": 0.4146139323711395,
416
+ "learning_rate": 1.7349876917471474e-05,
417
+ "loss": 0.8486,
418
+ "mean_token_accuracy": 0.7402682423591613,
419
+ "num_tokens": 6847429.0,
420
+ "step": 410
421
+ },
422
+ {
423
+ "entropy": 1.2469070911407472,
424
+ "epoch": 2.6784,
425
+ "grad_norm": 0.3891793489456177,
426
+ "learning_rate": 1.7208357137579318e-05,
427
+ "loss": 0.8608,
428
+ "mean_token_accuracy": 0.7373070567846298,
429
+ "num_tokens": 7016692.0,
430
+ "step": 420
431
+ },
432
+ {
433
+ "entropy": 1.2509080231189729,
434
+ "epoch": 2.7424,
435
+ "grad_norm": 0.42574191093444824,
436
+ "learning_rate": 1.7063766276366814e-05,
437
+ "loss": 0.8647,
438
+ "mean_token_accuracy": 0.7349686965346336,
439
+ "num_tokens": 7184437.0,
440
+ "step": 430
441
+ },
442
+ {
443
+ "entropy": 1.2402510732412337,
444
+ "epoch": 2.8064,
445
+ "grad_norm": 0.3809674084186554,
446
+ "learning_rate": 1.6916165935983323e-05,
447
+ "loss": 0.8364,
448
+ "mean_token_accuracy": 0.7414919167757035,
449
+ "num_tokens": 7352089.0,
450
+ "step": 440
451
+ },
452
+ {
453
+ "entropy": 1.2501752972602844,
454
+ "epoch": 2.8704,
455
+ "grad_norm": 0.39809074997901917,
456
+ "learning_rate": 1.676561900075041e-05,
457
+ "loss": 0.846,
458
+ "mean_token_accuracy": 0.7401938289403915,
459
+ "num_tokens": 7519467.0,
460
+ "step": 450
461
+ },
462
+ {
463
+ "entropy": 1.2486298561096192,
464
+ "epoch": 2.9344,
465
+ "grad_norm": 0.4290047287940979,
466
+ "learning_rate": 1.6612189610370336e-05,
467
+ "loss": 0.8603,
468
+ "mean_token_accuracy": 0.7392841055989265,
469
+ "num_tokens": 7691471.0,
470
+ "step": 460
471
+ },
472
+ {
473
+ "entropy": 1.2415612161159515,
474
+ "epoch": 2.9984,
475
+ "grad_norm": 0.39543700218200684,
476
+ "learning_rate": 1.6455943132599698e-05,
477
+ "loss": 0.8428,
478
+ "mean_token_accuracy": 0.7418375059962272,
479
+ "num_tokens": 7858740.0,
480
+ "step": 470
481
+ },
482
+ {
483
+ "entropy": 1.2214874029159546,
484
+ "epoch": 3.0576,
485
+ "grad_norm": 0.42647498846054077,
486
+ "learning_rate": 1.6296946135399835e-05,
487
+ "loss": 0.8186,
488
+ "mean_token_accuracy": 0.7487845855790216,
489
+ "num_tokens": 8013016.0,
490
+ "step": 480
491
+ },
492
+ {
493
+ "entropy": 1.214153888821602,
494
+ "epoch": 3.1216,
495
+ "grad_norm": 0.47299304604530334,
496
+ "learning_rate": 1.613526635857591e-05,
497
+ "loss": 0.8272,
498
+ "mean_token_accuracy": 0.7459566310048104,
499
+ "num_tokens": 8186012.0,
500
+ "step": 490
501
+ },
502
+ {
503
+ "entropy": 1.2059749454259872,
504
+ "epoch": 3.1856,
505
+ "grad_norm": 0.5080869197845459,
506
+ "learning_rate": 1.5970972684916754e-05,
507
+ "loss": 0.814,
508
+ "mean_token_accuracy": 0.7468735337257385,
509
+ "num_tokens": 8356469.0,
510
+ "step": 500
511
+ },
512
+ {
513
+ "entropy": 1.229441523551941,
514
+ "epoch": 3.2496,
515
+ "grad_norm": 0.48198065161705017,
516
+ "learning_rate": 1.5804135110847708e-05,
517
+ "loss": 0.8346,
518
+ "mean_token_accuracy": 0.7422416999936103,
519
+ "num_tokens": 8522068.0,
520
+ "step": 510
521
+ },
522
+ {
523
+ "entropy": 1.2226635456085204,
524
+ "epoch": 3.3136,
525
+ "grad_norm": 0.49883201718330383,
526
+ "learning_rate": 1.5634824716609037e-05,
527
+ "loss": 0.8337,
528
+ "mean_token_accuracy": 0.7423326745629311,
529
+ "num_tokens": 8691189.0,
530
+ "step": 520
531
+ },
532
+ {
533
+ "entropy": 1.221450889110565,
534
+ "epoch": 3.3776,
535
+ "grad_norm": 0.5223852396011353,
536
+ "learning_rate": 1.5463113635972577e-05,
537
+ "loss": 0.8219,
538
+ "mean_token_accuracy": 0.7454505205154419,
539
+ "num_tokens": 8858829.0,
540
+ "step": 530
541
+ },
542
+ {
543
+ "entropy": 1.256075695157051,
544
+ "epoch": 3.4416,
545
+ "grad_norm": 0.5027040839195251,
546
+ "learning_rate": 1.528907502550954e-05,
547
+ "loss": 0.8696,
548
+ "mean_token_accuracy": 0.7371025711297989,
549
+ "num_tokens": 9023152.0,
550
+ "step": 540
551
+ },
552
+ {
553
+ "entropy": 1.2054291009902953,
554
+ "epoch": 3.5056000000000003,
555
+ "grad_norm": 0.5042998790740967,
556
+ "learning_rate": 1.5112783033422547e-05,
557
+ "loss": 0.8089,
558
+ "mean_token_accuracy": 0.7502285718917847,
559
+ "num_tokens": 9192345.0,
560
+ "step": 550
561
+ },
562
+ {
563
+ "entropy": 1.2278274714946746,
564
+ "epoch": 3.5696,
565
+ "grad_norm": 0.45448994636535645,
566
+ "learning_rate": 1.4934312767955193e-05,
567
+ "loss": 0.8243,
568
+ "mean_token_accuracy": 0.7445582717657089,
569
+ "num_tokens": 9359534.0,
570
+ "step": 560
571
+ },
572
+ {
573
+ "entropy": 1.2333297580480576,
574
+ "epoch": 3.6336,
575
+ "grad_norm": 0.5510305166244507,
576
+ "learning_rate": 1.4753740265392595e-05,
577
+ "loss": 0.829,
578
+ "mean_token_accuracy": 0.7417365327477455,
579
+ "num_tokens": 9524499.0,
580
+ "step": 570
581
+ },
582
+ {
583
+ "entropy": 1.218250796198845,
584
+ "epoch": 3.6976,
585
+ "grad_norm": 0.5383264422416687,
586
+ "learning_rate": 1.4571142457666536e-05,
587
+ "loss": 0.8224,
588
+ "mean_token_accuracy": 0.7461559876799584,
589
+ "num_tokens": 9691418.0,
590
+ "step": 580
591
+ },
592
+ {
593
+ "entropy": 1.197799614071846,
594
+ "epoch": 3.7616,
595
+ "grad_norm": 0.4910060465335846,
596
+ "learning_rate": 1.4386597139579041e-05,
597
+ "loss": 0.8106,
598
+ "mean_token_accuracy": 0.7503111377358437,
599
+ "num_tokens": 9860032.0,
600
+ "step": 590
601
+ },
602
+ {
603
+ "entropy": 1.2061665117740632,
604
+ "epoch": 3.8256,
605
+ "grad_norm": 0.4970499575138092,
606
+ "learning_rate": 1.4200182935658327e-05,
607
+ "loss": 0.8091,
608
+ "mean_token_accuracy": 0.7470731437206268,
609
+ "num_tokens": 10030071.0,
610
+ "step": 600
611
+ },
612
+ {
613
+ "entropy": 1.206977090239525,
614
+ "epoch": 3.8895999999999997,
615
+ "grad_norm": 0.4960206151008606,
616
+ "learning_rate": 1.4011979266661235e-05,
617
+ "loss": 0.8132,
618
+ "mean_token_accuracy": 0.7475115478038787,
619
+ "num_tokens": 10197218.0,
620
+ "step": 610
621
+ },
622
+ {
623
+ "entropy": 1.2226781100034714,
624
+ "epoch": 3.9536,
625
+ "grad_norm": 0.5883672833442688,
626
+ "learning_rate": 1.3822066315736477e-05,
627
+ "loss": 0.8151,
628
+ "mean_token_accuracy": 0.747152166068554,
629
+ "num_tokens": 10363213.0,
630
+ "step": 620
631
+ },
632
+ {
633
+ "entropy": 1.222595163293787,
634
+ "epoch": 4.0128,
635
+ "grad_norm": 0.5304821133613586,
636
+ "learning_rate": 1.363052499426302e-05,
637
+ "loss": 0.8143,
638
+ "mean_token_accuracy": 0.744894308012885,
639
+ "num_tokens": 10516376.0,
640
+ "step": 630
641
+ },
642
+ {
643
+ "entropy": 1.1796708509325982,
644
+ "epoch": 4.0768,
645
+ "grad_norm": 0.5488530993461609,
646
+ "learning_rate": 1.3437436907378225e-05,
647
+ "loss": 0.7843,
648
+ "mean_token_accuracy": 0.7553770825266838,
649
+ "num_tokens": 10681877.0,
650
+ "step": 640
651
+ },
652
+ {
653
+ "entropy": 1.2144078850746154,
654
+ "epoch": 4.1408,
655
+ "grad_norm": 0.5689272880554199,
656
+ "learning_rate": 1.3242884319210463e-05,
657
+ "loss": 0.8319,
658
+ "mean_token_accuracy": 0.7462387323379517,
659
+ "num_tokens": 10853452.0,
660
+ "step": 650
661
+ },
662
+ {
663
+ "entropy": 1.1723882287740708,
664
+ "epoch": 4.2048,
665
+ "grad_norm": 0.5823758244514465,
666
+ "learning_rate": 1.3046950117830888e-05,
667
+ "loss": 0.7754,
668
+ "mean_token_accuracy": 0.757102370262146,
669
+ "num_tokens": 11021186.0,
670
+ "step": 660
671
+ },
672
+ {
673
+ "entropy": 1.1938336580991744,
674
+ "epoch": 4.2688,
675
+ "grad_norm": 0.6302596926689148,
676
+ "learning_rate": 1.2849717779939439e-05,
677
+ "loss": 0.8064,
678
+ "mean_token_accuracy": 0.7491099700331688,
679
+ "num_tokens": 11188079.0,
680
+ "step": 670
681
+ },
682
+ {
683
+ "entropy": 1.1738565742969513,
684
+ "epoch": 4.3328,
685
+ "grad_norm": 0.6567224264144897,
686
+ "learning_rate": 1.2651271335300063e-05,
687
+ "loss": 0.7881,
688
+ "mean_token_accuracy": 0.7507374078035355,
689
+ "num_tokens": 11357861.0,
690
+ "step": 680
691
+ },
692
+ {
693
+ "entropy": 1.198876941204071,
694
+ "epoch": 4.3968,
695
+ "grad_norm": 0.62027907371521,
696
+ "learning_rate": 1.2451695330940268e-05,
697
+ "loss": 0.8046,
698
+ "mean_token_accuracy": 0.7497236520051956,
699
+ "num_tokens": 11524052.0,
700
+ "step": 690
701
+ },
702
+ {
703
+ "entropy": 1.1681430846452714,
704
+ "epoch": 4.4608,
705
+ "grad_norm": 0.6131038069725037,
706
+ "learning_rate": 1.2251074795130339e-05,
707
+ "loss": 0.7887,
708
+ "mean_token_accuracy": 0.7542851880192757,
709
+ "num_tokens": 11693539.0,
710
+ "step": 700
711
+ },
712
+ {
713
+ "entropy": 1.2012270838022232,
714
+ "epoch": 4.5248,
715
+ "grad_norm": 0.6755374073982239,
716
+ "learning_rate": 1.2049495201157489e-05,
717
+ "loss": 0.8051,
718
+ "mean_token_accuracy": 0.7475825384259224,
719
+ "num_tokens": 11859545.0,
720
+ "step": 710
721
+ },
722
+ {
723
+ "entropy": 1.190478339791298,
724
+ "epoch": 4.5888,
725
+ "grad_norm": 0.6316648125648499,
726
+ "learning_rate": 1.1847042430910451e-05,
727
+ "loss": 0.7912,
728
+ "mean_token_accuracy": 0.7512465313076973,
729
+ "num_tokens": 12025362.0,
730
+ "step": 720
731
+ },
732
+ {
733
+ "entropy": 1.1802339136600495,
734
+ "epoch": 4.6528,
735
+ "grad_norm": 0.6220593452453613,
736
+ "learning_rate": 1.1643802738289955e-05,
737
+ "loss": 0.7913,
738
+ "mean_token_accuracy": 0.7516302943229676,
739
+ "num_tokens": 12193592.0,
740
+ "step": 730
741
+ },
742
+ {
743
+ "entropy": 1.1827380925416946,
744
+ "epoch": 4.7168,
745
+ "grad_norm": 0.5833670496940613,
746
+ "learning_rate": 1.1439862712460721e-05,
747
+ "loss": 0.8028,
748
+ "mean_token_accuracy": 0.7484710603952408,
749
+ "num_tokens": 12361308.0,
750
+ "step": 740
751
+ },
752
+ {
753
+ "entropy": 1.1752862721681594,
754
+ "epoch": 4.7808,
755
+ "grad_norm": 0.6545965671539307,
756
+ "learning_rate": 1.1235309240960621e-05,
757
+ "loss": 0.7858,
758
+ "mean_token_accuracy": 0.7553699359297752,
759
+ "num_tokens": 12530382.0,
760
+ "step": 750
761
+ },
762
+ {
763
+ "entropy": 1.177734187245369,
764
+ "epoch": 4.8448,
765
+ "grad_norm": 0.6953952312469482,
766
+ "learning_rate": 1.1030229472682719e-05,
767
+ "loss": 0.7852,
768
+ "mean_token_accuracy": 0.7533090978860855,
769
+ "num_tokens": 12695004.0,
770
+ "step": 760
771
+ },
772
+ {
773
+ "entropy": 1.1654743909835816,
774
+ "epoch": 4.9088,
775
+ "grad_norm": 0.6737579107284546,
776
+ "learning_rate": 1.0824710780745954e-05,
777
+ "loss": 0.7878,
778
+ "mean_token_accuracy": 0.7544879004359245,
779
+ "num_tokens": 12864450.0,
780
+ "step": 770
781
+ },
782
+ {
783
+ "entropy": 1.1805586963891983,
784
+ "epoch": 4.9728,
785
+ "grad_norm": 0.6320992708206177,
786
+ "learning_rate": 1.06188407252703e-05,
787
+ "loss": 0.7994,
788
+ "mean_token_accuracy": 0.7510025933384895,
789
+ "num_tokens": 13033199.0,
790
+ "step": 780
791
+ },
792
+ {
793
+ "entropy": 1.165472733007895,
794
+ "epoch": 5.032,
795
+ "grad_norm": 0.652460515499115,
796
+ "learning_rate": 1.0412707016072254e-05,
797
+ "loss": 0.7596,
798
+ "mean_token_accuracy": 0.7593615957208582,
799
+ "num_tokens": 13189187.0,
800
+ "step": 790
801
+ },
802
+ {
803
+ "entropy": 1.1522447764873505,
804
+ "epoch": 5.096,
805
+ "grad_norm": 0.8098700046539307,
806
+ "learning_rate": 1.0206397475296548e-05,
807
+ "loss": 0.768,
808
+ "mean_token_accuracy": 0.7569398522377014,
809
+ "num_tokens": 13358010.0,
810
+ "step": 800
811
+ },
812
+ {
813
+ "entropy": 1.155535000562668,
814
+ "epoch": 5.16,
815
+ "grad_norm": 0.7569311261177063,
816
+ "learning_rate": 1e-05,
817
+ "loss": 0.766,
818
+ "mean_token_accuracy": 0.7563902020454407,
819
+ "num_tokens": 13524722.0,
820
+ "step": 810
821
+ },
822
+ {
823
+ "entropy": 1.157894878089428,
824
+ "epoch": 5.224,
825
+ "grad_norm": 0.8364959359169006,
826
+ "learning_rate": 9.793602524703456e-06,
827
+ "loss": 0.7693,
828
+ "mean_token_accuracy": 0.7581299751996994,
829
+ "num_tokens": 13690529.0,
830
+ "step": 820
831
+ },
832
+ {
833
+ "entropy": 1.145342645049095,
834
+ "epoch": 5.288,
835
+ "grad_norm": 0.7824255228042603,
836
+ "learning_rate": 9.58729298392775e-06,
837
+ "loss": 0.7611,
838
+ "mean_token_accuracy": 0.761179718375206,
839
+ "num_tokens": 13859442.0,
840
+ "step": 830
841
+ },
842
+ {
843
+ "entropy": 1.1661550253629684,
844
+ "epoch": 5.352,
845
+ "grad_norm": 0.7638425230979919,
846
+ "learning_rate": 9.381159274729704e-06,
847
+ "loss": 0.7825,
848
+ "mean_token_accuracy": 0.7569466888904571,
849
+ "num_tokens": 14028485.0,
850
+ "step": 840
851
+ },
852
+ {
853
+ "entropy": 1.1383796483278275,
854
+ "epoch": 5.416,
855
+ "grad_norm": 0.7410515546798706,
856
+ "learning_rate": 9.175289219254051e-06,
857
+ "loss": 0.7497,
858
+ "mean_token_accuracy": 0.7625020772218705,
859
+ "num_tokens": 14198221.0,
860
+ "step": 850
861
+ },
862
+ {
863
+ "entropy": 1.1481939822435379,
864
+ "epoch": 5.48,
865
+ "grad_norm": 0.7490608096122742,
866
+ "learning_rate": 8.969770527317283e-06,
867
+ "loss": 0.7477,
868
+ "mean_token_accuracy": 0.7623027458786964,
869
+ "num_tokens": 14367293.0,
870
+ "step": 860
871
+ },
872
+ {
873
+ "entropy": 1.1579900979995728,
874
+ "epoch": 5.5440000000000005,
875
+ "grad_norm": 0.7536274790763855,
876
+ "learning_rate": 8.764690759039382e-06,
877
+ "loss": 0.7692,
878
+ "mean_token_accuracy": 0.7568637877702713,
879
+ "num_tokens": 14535472.0,
880
+ "step": 870
881
+ },
882
+ {
883
+ "entropy": 1.1517672553658485,
884
+ "epoch": 5.608,
885
+ "grad_norm": 0.824515163898468,
886
+ "learning_rate": 8.56013728753928e-06,
887
+ "loss": 0.7621,
888
+ "mean_token_accuracy": 0.7600950643420219,
889
+ "num_tokens": 14700265.0,
890
+ "step": 880
891
+ },
892
+ {
893
+ "entropy": 1.1413051068782807,
894
+ "epoch": 5.672,
895
+ "grad_norm": 0.7741249203681946,
896
+ "learning_rate": 8.356197261710048e-06,
897
+ "loss": 0.7518,
898
+ "mean_token_accuracy": 0.7614945828914642,
899
+ "num_tokens": 14866673.0,
900
+ "step": 890
901
+ },
902
+ {
903
+ "entropy": 1.171517863869667,
904
+ "epoch": 5.736,
905
+ "grad_norm": 0.7269055247306824,
906
+ "learning_rate": 8.152957569089552e-06,
907
+ "loss": 0.7836,
908
+ "mean_token_accuracy": 0.7550232648849488,
909
+ "num_tokens": 15031602.0,
910
+ "step": 900
911
+ },
912
+ {
913
+ "entropy": 1.1627105355262757,
914
+ "epoch": 5.8,
915
+ "grad_norm": 0.8189387321472168,
916
+ "learning_rate": 7.950504798842513e-06,
917
+ "loss": 0.7818,
918
+ "mean_token_accuracy": 0.7560641661286354,
919
+ "num_tokens": 15200656.0,
920
+ "step": 910
921
+ },
922
+ {
923
+ "entropy": 1.1600016862154008,
924
+ "epoch": 5.864,
925
+ "grad_norm": 0.8086869716644287,
926
+ "learning_rate": 7.748925204869667e-06,
927
+ "loss": 0.7637,
928
+ "mean_token_accuracy": 0.7589102029800415,
929
+ "num_tokens": 15368071.0,
930
+ "step": 920
931
+ },
932
+ {
933
+ "entropy": 1.1717667609453202,
934
+ "epoch": 5.928,
935
+ "grad_norm": 0.8845758438110352,
936
+ "learning_rate": 7.548304669059735e-06,
937
+ "loss": 0.7792,
938
+ "mean_token_accuracy": 0.7552744656801224,
939
+ "num_tokens": 15533538.0,
940
+ "step": 930
941
+ },
942
+ {
943
+ "entropy": 1.1296544909477233,
944
+ "epoch": 5.992,
945
+ "grad_norm": 0.8191102147102356,
946
+ "learning_rate": 7.348728664699939e-06,
947
+ "loss": 0.7392,
948
+ "mean_token_accuracy": 0.7642928868532181,
949
+ "num_tokens": 15702224.0,
950
+ "step": 940
951
+ },
952
+ {
953
+ "entropy": 1.1310625011856492,
954
+ "epoch": 6.0512,
955
+ "grad_norm": 1.03687584400177,
956
+ "learning_rate": 7.150282220060564e-06,
957
+ "loss": 0.7322,
958
+ "mean_token_accuracy": 0.7652509937415252,
959
+ "num_tokens": 15855871.0,
960
+ "step": 950
961
+ },
962
+ {
963
+ "entropy": 1.12939695417881,
964
+ "epoch": 6.1152,
965
+ "grad_norm": 0.9026349186897278,
966
+ "learning_rate": 6.9530498821691165e-06,
967
+ "loss": 0.7312,
968
+ "mean_token_accuracy": 0.7661619514226914,
969
+ "num_tokens": 16022959.0,
970
+ "step": 960
971
+ },
972
+ {
973
+ "entropy": 1.1230400115251542,
974
+ "epoch": 6.1792,
975
+ "grad_norm": 0.9334505200386047,
976
+ "learning_rate": 6.757115680789539e-06,
977
+ "loss": 0.7166,
978
+ "mean_token_accuracy": 0.7693509578704834,
979
+ "num_tokens": 16184586.0,
980
+ "step": 970
981
+ },
982
+ {
983
+ "entropy": 1.1167623370885849,
984
+ "epoch": 6.2432,
985
+ "grad_norm": 0.8687794804573059,
986
+ "learning_rate": 6.562563092621776e-06,
987
+ "loss": 0.7309,
988
+ "mean_token_accuracy": 0.7661765992641449,
989
+ "num_tokens": 16356436.0,
990
+ "step": 980
991
+ },
992
+ {
993
+ "entropy": 1.1170607119798661,
994
+ "epoch": 6.3072,
995
+ "grad_norm": 0.9250707626342773,
996
+ "learning_rate": 6.369475005736984e-06,
997
+ "loss": 0.728,
998
+ "mean_token_accuracy": 0.7687151193618774,
999
+ "num_tokens": 16522765.0,
1000
+ "step": 990
1001
+ },
1002
+ {
1003
+ "entropy": 1.1269994646310806,
1004
+ "epoch": 6.3712,
1005
+ "grad_norm": 0.9762291312217712,
1006
+ "learning_rate": 6.177933684263524e-06,
1007
+ "loss": 0.7427,
1008
+ "mean_token_accuracy": 0.7661235600709915,
1009
+ "num_tokens": 16689964.0,
1010
+ "step": 1000
1011
+ },
1012
+ {
1013
+ "entropy": 1.1308791995048524,
1014
+ "epoch": 6.4352,
1015
+ "grad_norm": 0.9405747652053833,
1016
+ "learning_rate": 5.988020733338767e-06,
1017
+ "loss": 0.7282,
1018
+ "mean_token_accuracy": 0.7662904724478722,
1019
+ "num_tokens": 16855846.0,
1020
+ "step": 1010
1021
+ },
1022
+ {
1023
+ "entropy": 1.1322367668151856,
1024
+ "epoch": 6.4992,
1025
+ "grad_norm": 0.8870813250541687,
1026
+ "learning_rate": 5.7998170643416795e-06,
1027
+ "loss": 0.7448,
1028
+ "mean_token_accuracy": 0.7629623278975487,
1029
+ "num_tokens": 17024434.0,
1030
+ "step": 1020
1031
+ },
1032
+ {
1033
+ "entropy": 1.1535383015871048,
1034
+ "epoch": 6.5632,
1035
+ "grad_norm": 0.9254381060600281,
1036
+ "learning_rate": 5.613402860420962e-06,
1037
+ "loss": 0.7691,
1038
+ "mean_token_accuracy": 0.7590128257870674,
1039
+ "num_tokens": 17195067.0,
1040
+ "step": 1030
1041
+ },
1042
+ {
1043
+ "entropy": 1.1291758388280868,
1044
+ "epoch": 6.6272,
1045
+ "grad_norm": 0.8941587209701538,
1046
+ "learning_rate": 5.428857542333465e-06,
1047
+ "loss": 0.7423,
1048
+ "mean_token_accuracy": 0.7641170158982277,
1049
+ "num_tokens": 17367933.0,
1050
+ "step": 1040
1051
+ },
1052
+ {
1053
+ "entropy": 1.1354484647512435,
1054
+ "epoch": 6.6912,
1055
+ "grad_norm": 0.9986079335212708,
1056
+ "learning_rate": 5.246259734607411e-06,
1057
+ "loss": 0.7558,
1058
+ "mean_token_accuracy": 0.7625504702329635,
1059
+ "num_tokens": 17534589.0,
1060
+ "step": 1050
1061
+ },
1062
+ {
1063
+ "entropy": 1.1145919933915138,
1064
+ "epoch": 6.7552,
1065
+ "grad_norm": 0.9608755707740784,
1066
+ "learning_rate": 5.065687232044811e-06,
1067
+ "loss": 0.7207,
1068
+ "mean_token_accuracy": 0.767878831923008,
1069
+ "num_tokens": 17702136.0,
1070
+ "step": 1060
1071
+ },
1072
+ {
1073
+ "entropy": 1.1152497231960297,
1074
+ "epoch": 6.8192,
1075
+ "grad_norm": 0.930647611618042,
1076
+ "learning_rate": 4.887216966577458e-06,
1077
+ "loss": 0.7136,
1078
+ "mean_token_accuracy": 0.7703010246157647,
1079
+ "num_tokens": 17868339.0,
1080
+ "step": 1070
1081
+ },
1082
+ {
1083
+ "entropy": 1.1384254783391952,
1084
+ "epoch": 6.8832,
1085
+ "grad_norm": 0.981146514415741,
1086
+ "learning_rate": 4.710924974490463e-06,
1087
+ "loss": 0.7725,
1088
+ "mean_token_accuracy": 0.7612431243062019,
1089
+ "num_tokens": 18041328.0,
1090
+ "step": 1080
1091
+ },
1092
+ {
1093
+ "entropy": 1.1156837493181229,
1094
+ "epoch": 6.9472000000000005,
1095
+ "grad_norm": 1.031293511390686,
1096
+ "learning_rate": 4.536886364027428e-06,
1097
+ "loss": 0.7187,
1098
+ "mean_token_accuracy": 0.7708014816045761,
1099
+ "num_tokens": 18207019.0,
1100
+ "step": 1090
1101
+ },
1102
+ {
1103
+ "entropy": 1.1324091795328501,
1104
+ "epoch": 7.0064,
1105
+ "grad_norm": 0.9793551564216614,
1106
+ "learning_rate": 4.365175283390968e-06,
1107
+ "loss": 0.7325,
1108
+ "mean_token_accuracy": 0.7669887091662433,
1109
+ "num_tokens": 18362086.0,
1110
+ "step": 1100
1111
+ },
1112
+ {
1113
+ "entropy": 1.1103261813521386,
1114
+ "epoch": 7.0704,
1115
+ "grad_norm": 1.0026472806930542,
1116
+ "learning_rate": 4.195864889152295e-06,
1117
+ "loss": 0.7056,
1118
+ "mean_token_accuracy": 0.7747725829482078,
1119
+ "num_tokens": 18529192.0,
1120
+ "step": 1110
1121
+ },
1122
+ {
1123
+ "entropy": 1.1086191982030869,
1124
+ "epoch": 7.1344,
1125
+ "grad_norm": 1.0708081722259521,
1126
+ "learning_rate": 4.029027315083251e-06,
1127
+ "loss": 0.7261,
1128
+ "mean_token_accuracy": 0.7677501872181892,
1129
+ "num_tokens": 18697843.0,
1130
+ "step": 1120
1131
+ },
1132
+ {
1133
+ "entropy": 1.0975075036287307,
1134
+ "epoch": 7.1984,
1135
+ "grad_norm": 0.9521598219871521,
1136
+ "learning_rate": 3.864733641424093e-06,
1137
+ "loss": 0.7059,
1138
+ "mean_token_accuracy": 0.7746093690395355,
1139
+ "num_tokens": 18866212.0,
1140
+ "step": 1130
1141
+ },
1142
+ {
1143
+ "entropy": 1.1038097634911537,
1144
+ "epoch": 7.2624,
1145
+ "grad_norm": 1.0327914953231812,
1146
+ "learning_rate": 3.703053864600169e-06,
1147
+ "loss": 0.7114,
1148
+ "mean_token_accuracy": 0.7727755904197693,
1149
+ "num_tokens": 19033743.0,
1150
+ "step": 1140
1151
+ },
1152
+ {
1153
+ "entropy": 1.1110169142484665,
1154
+ "epoch": 7.3264,
1155
+ "grad_norm": 1.0147864818572998,
1156
+ "learning_rate": 3.544056867400306e-06,
1157
+ "loss": 0.7138,
1158
+ "mean_token_accuracy": 0.769483657181263,
1159
+ "num_tokens": 19200496.0,
1160
+ "step": 1150
1161
+ },
1162
+ {
1163
+ "entropy": 1.0948543518781662,
1164
+ "epoch": 7.3904,
1165
+ "grad_norm": 1.0380463600158691,
1166
+ "learning_rate": 3.3878103896296677e-06,
1167
+ "loss": 0.705,
1168
+ "mean_token_accuracy": 0.7747946813702583,
1169
+ "num_tokens": 19367582.0,
1170
+ "step": 1160
1171
+ },
1172
+ {
1173
+ "entropy": 1.1144859746098519,
1174
+ "epoch": 7.4544,
1175
+ "grad_norm": 1.100961446762085,
1176
+ "learning_rate": 3.2343809992495945e-06,
1177
+ "loss": 0.7052,
1178
+ "mean_token_accuracy": 0.7745175659656525,
1179
+ "num_tokens": 19533688.0,
1180
+ "step": 1170
1181
+ },
1182
+ {
1183
+ "entropy": 1.107055227458477,
1184
+ "epoch": 7.5184,
1185
+ "grad_norm": 1.0504915714263916,
1186
+ "learning_rate": 3.083834064016682e-06,
1187
+ "loss": 0.7194,
1188
+ "mean_token_accuracy": 0.7694016128778458,
1189
+ "num_tokens": 19703466.0,
1190
+ "step": 1180
1191
+ },
1192
+ {
1193
+ "entropy": 1.1040660321712494,
1194
+ "epoch": 7.5824,
1195
+ "grad_norm": 1.0282219648361206,
1196
+ "learning_rate": 2.9362337236331884e-06,
1197
+ "loss": 0.7114,
1198
+ "mean_token_accuracy": 0.7717982798814773,
1199
+ "num_tokens": 19868961.0,
1200
+ "step": 1190
1201
+ },
1202
+ {
1203
+ "entropy": 1.0966812744736671,
1204
+ "epoch": 7.6464,
1205
+ "grad_norm": 1.0571895837783813,
1206
+ "learning_rate": 2.791642862420686e-06,
1207
+ "loss": 0.7038,
1208
+ "mean_token_accuracy": 0.7714879170060158,
1209
+ "num_tokens": 20038228.0,
1210
+ "step": 1200
1211
+ },
1212
+ {
1213
+ "entropy": 1.0895270451903343,
1214
+ "epoch": 7.7104,
1215
+ "grad_norm": 1.016501545906067,
1216
+ "learning_rate": 2.6501230825285294e-06,
1217
+ "loss": 0.709,
1218
+ "mean_token_accuracy": 0.7727946832776069,
1219
+ "num_tokens": 20206537.0,
1220
+ "step": 1210
1221
+ },
1222
+ {
1223
+ "entropy": 1.1009603932499885,
1224
+ "epoch": 7.7744,
1225
+ "grad_norm": 1.0647404193878174,
1226
+ "learning_rate": 2.5117346776885843e-06,
1227
+ "loss": 0.7222,
1228
+ "mean_token_accuracy": 0.7703997671604157,
1229
+ "num_tokens": 20378633.0,
1230
+ "step": 1220
1231
+ },
1232
+ {
1233
+ "entropy": 1.1264784708619118,
1234
+ "epoch": 7.8384,
1235
+ "grad_norm": 1.0770481824874878,
1236
+ "learning_rate": 2.3765366075274287e-06,
1237
+ "loss": 0.7404,
1238
+ "mean_token_accuracy": 0.7675652742385864,
1239
+ "num_tokens": 20546008.0,
1240
+ "step": 1230
1241
+ },
1242
+ {
1243
+ "entropy": 1.1074893057346344,
1244
+ "epoch": 7.9024,
1245
+ "grad_norm": 1.008133888244629,
1246
+ "learning_rate": 2.2445864724469146e-06,
1247
+ "loss": 0.7169,
1248
+ "mean_token_accuracy": 0.7722549349069595,
1249
+ "num_tokens": 20713626.0,
1250
+ "step": 1240
1251
+ },
1252
+ {
1253
+ "entropy": 1.102501641213894,
1254
+ "epoch": 7.9664,
1255
+ "grad_norm": 1.1541906595230103,
1256
+ "learning_rate": 2.1159404890838365e-06,
1257
+ "loss": 0.7081,
1258
+ "mean_token_accuracy": 0.7719982087612152,
1259
+ "num_tokens": 20879013.0,
1260
+ "step": 1250
1261
+ }
1262
+ ],
1263
+ "logging_steps": 10,
1264
+ "max_steps": 1570,
1265
+ "num_input_tokens_seen": 0,
1266
+ "num_train_epochs": 10,
1267
+ "save_steps": 500,
1268
+ "stateful_callbacks": {
1269
+ "TrainerControl": {
1270
+ "args": {
1271
+ "should_epoch_stop": false,
1272
+ "should_evaluate": false,
1273
+ "should_log": false,
1274
+ "should_save": true,
1275
+ "should_training_stop": false
1276
+ },
1277
+ "attributes": {}
1278
+ }
1279
+ },
1280
+ "total_flos": 1.7374525148847145e+18,
1281
+ "train_batch_size": 16,
1282
+ "trial_name": null,
1283
+ "trial_params": null
1284
+ }
checkpoint-1256/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715b5f801a71e6f8ee2177ab148805ed1d1c0732f395811ea0f0c2c52c99d11c
3
+ size 6225
checkpoint-1413/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.18.0
checkpoint-1413/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "down_proj",
34
+ "up_proj",
35
+ "q_proj",
36
+ "gate_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-1413/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547707a6793ca0a66f9906e6021f336f6891e4b22ad1754445973cce9fa55e0d
3
+ size 335604696
checkpoint-1413/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
checkpoint-1413/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76af1108dfc2aaf81ec066caad3b2b09a9e62fd0439982659a6092072a4f6118
3
+ size 671473443
checkpoint-1413/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c553d289e4b9fd780569da673f45000b5a9908c6c7cd3a852d1f832d48766148
3
+ size 14645
checkpoint-1413/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8308b326ca34e482aacdc316d4eaa218ce5669c2b2fb82fa6608fefa112cdb
3
+ size 1465
checkpoint-1413/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-1413/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-1413/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
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": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
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": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-1413/trainer_state.json ADDED
@@ -0,0 +1,1444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 9.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1413,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.3336982399225235,
14
+ "epoch": 0.064,
15
+ "grad_norm": 1.0639071464538574,
16
+ "learning_rate": 3.7500000000000005e-06,
17
+ "loss": 1.1401,
18
+ "mean_token_accuracy": 0.694624176621437,
19
+ "num_tokens": 170909.0,
20
+ "step": 10
21
+ },
22
+ {
23
+ "entropy": 1.3297590017318726,
24
+ "epoch": 0.128,
25
+ "grad_norm": 0.7065510749816895,
26
+ "learning_rate": 7.916666666666667e-06,
27
+ "loss": 1.0941,
28
+ "mean_token_accuracy": 0.6982980638742446,
29
+ "num_tokens": 339030.0,
30
+ "step": 20
31
+ },
32
+ {
33
+ "entropy": 1.345283743739128,
34
+ "epoch": 0.192,
35
+ "grad_norm": 0.4589855372905731,
36
+ "learning_rate": 1.2083333333333333e-05,
37
+ "loss": 0.9992,
38
+ "mean_token_accuracy": 0.7138096526265144,
39
+ "num_tokens": 507164.0,
40
+ "step": 30
41
+ },
42
+ {
43
+ "entropy": 1.364566907286644,
44
+ "epoch": 0.256,
45
+ "grad_norm": 0.3452564477920532,
46
+ "learning_rate": 1.6250000000000002e-05,
47
+ "loss": 0.9439,
48
+ "mean_token_accuracy": 0.7216050222516059,
49
+ "num_tokens": 675354.0,
50
+ "step": 40
51
+ },
52
+ {
53
+ "entropy": 1.3028314679861068,
54
+ "epoch": 0.32,
55
+ "grad_norm": 0.28635093569755554,
56
+ "learning_rate": 1.9999978697023387e-05,
57
+ "loss": 0.9158,
58
+ "mean_token_accuracy": 0.7276657372713089,
59
+ "num_tokens": 844110.0,
60
+ "step": 50
61
+ },
62
+ {
63
+ "entropy": 1.2932516396045686,
64
+ "epoch": 0.384,
65
+ "grad_norm": 0.27746596932411194,
66
+ "learning_rate": 1.999742244965125e-05,
67
+ "loss": 0.9036,
68
+ "mean_token_accuracy": 0.7287891209125519,
69
+ "num_tokens": 1011944.0,
70
+ "step": 60
71
+ },
72
+ {
73
+ "entropy": 1.2994182020425797,
74
+ "epoch": 0.448,
75
+ "grad_norm": 0.2701167166233063,
76
+ "learning_rate": 1.9990606854864625e-05,
77
+ "loss": 0.9067,
78
+ "mean_token_accuracy": 0.7304235219955444,
79
+ "num_tokens": 1173258.0,
80
+ "step": 70
81
+ },
82
+ {
83
+ "entropy": 1.2833235740661622,
84
+ "epoch": 0.512,
85
+ "grad_norm": 0.24232186377048492,
86
+ "learning_rate": 1.997953481641056e-05,
87
+ "loss": 0.8951,
88
+ "mean_token_accuracy": 0.7301426336169243,
89
+ "num_tokens": 1344619.0,
90
+ "step": 80
91
+ },
92
+ {
93
+ "entropy": 1.2982767909765243,
94
+ "epoch": 0.576,
95
+ "grad_norm": 0.27630752325057983,
96
+ "learning_rate": 1.9964211051470778e-05,
97
+ "loss": 0.898,
98
+ "mean_token_accuracy": 0.7295515269041062,
99
+ "num_tokens": 1512541.0,
100
+ "step": 90
101
+ },
102
+ {
103
+ "entropy": 1.2845446109771728,
104
+ "epoch": 0.64,
105
+ "grad_norm": 0.27921387553215027,
106
+ "learning_rate": 1.994464208865191e-05,
107
+ "loss": 0.8771,
108
+ "mean_token_accuracy": 0.7340485483407975,
109
+ "num_tokens": 1674752.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "entropy": 1.2960468918085097,
114
+ "epoch": 0.704,
115
+ "grad_norm": 0.28025951981544495,
116
+ "learning_rate": 1.9920836265204047e-05,
117
+ "loss": 0.922,
118
+ "mean_token_accuracy": 0.730307950079441,
119
+ "num_tokens": 1843831.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 1.277726098895073,
124
+ "epoch": 0.768,
125
+ "grad_norm": 0.2962108552455902,
126
+ "learning_rate": 1.989280372346868e-05,
127
+ "loss": 0.904,
128
+ "mean_token_accuracy": 0.7301651641726494,
129
+ "num_tokens": 2014821.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 1.2816721558570863,
134
+ "epoch": 0.832,
135
+ "grad_norm": 0.3098539113998413,
136
+ "learning_rate": 1.986055640655763e-05,
137
+ "loss": 0.8928,
138
+ "mean_token_accuracy": 0.7311756134033203,
139
+ "num_tokens": 2182032.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 1.2761377334594726,
144
+ "epoch": 0.896,
145
+ "grad_norm": 0.32843220233917236,
146
+ "learning_rate": 1.9824108053264726e-05,
147
+ "loss": 0.8856,
148
+ "mean_token_accuracy": 0.7321326151490212,
149
+ "num_tokens": 2349897.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 1.278924709558487,
154
+ "epoch": 0.96,
155
+ "grad_norm": 0.284488707780838,
156
+ "learning_rate": 1.9783474192212484e-05,
157
+ "loss": 0.889,
158
+ "mean_token_accuracy": 0.7330759033560753,
159
+ "num_tokens": 2518145.0,
160
+ "step": 150
161
+ },
162
+ {
163
+ "entropy": 1.2941713687535878,
164
+ "epoch": 1.0192,
165
+ "grad_norm": 0.28169313073158264,
166
+ "learning_rate": 1.9738672135236218e-05,
167
+ "loss": 0.8944,
168
+ "mean_token_accuracy": 0.7288601623999106,
169
+ "num_tokens": 2672610.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 1.2729155957698821,
174
+ "epoch": 1.0832,
175
+ "grad_norm": 0.37515658140182495,
176
+ "learning_rate": 1.968972097000843e-05,
177
+ "loss": 0.8668,
178
+ "mean_token_accuracy": 0.7360310450196266,
179
+ "num_tokens": 2837208.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 1.2722265392541885,
184
+ "epoch": 1.1472,
185
+ "grad_norm": 0.31570735573768616,
186
+ "learning_rate": 1.96366415519066e-05,
187
+ "loss": 0.8827,
188
+ "mean_token_accuracy": 0.7332133531570435,
189
+ "num_tokens": 3006803.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 1.2773896872997283,
194
+ "epoch": 1.2112,
195
+ "grad_norm": 0.3074122965335846,
196
+ "learning_rate": 1.957945649512788e-05,
197
+ "loss": 0.8815,
198
+ "mean_token_accuracy": 0.7360113054513931,
199
+ "num_tokens": 3175064.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 1.29012733399868,
204
+ "epoch": 1.2752,
205
+ "grad_norm": 0.31284573674201965,
206
+ "learning_rate": 1.951819016305442e-05,
207
+ "loss": 0.8938,
208
+ "mean_token_accuracy": 0.7312650114297867,
209
+ "num_tokens": 3344594.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "entropy": 1.2645655244588851,
214
+ "epoch": 1.3392,
215
+ "grad_norm": 0.34085312485694885,
216
+ "learning_rate": 1.9452868657873513e-05,
217
+ "loss": 0.8796,
218
+ "mean_token_accuracy": 0.7344238087534904,
219
+ "num_tokens": 3517915.0,
220
+ "step": 210
221
+ },
222
+ {
223
+ "entropy": 1.287526673078537,
224
+ "epoch": 1.4032,
225
+ "grad_norm": 0.34183570742607117,
226
+ "learning_rate": 1.9383519809456862e-05,
227
+ "loss": 0.8661,
228
+ "mean_token_accuracy": 0.7361385986208916,
229
+ "num_tokens": 3680950.0,
230
+ "step": 220
231
+ },
232
+ {
233
+ "entropy": 1.2799992829561233,
234
+ "epoch": 1.4672,
235
+ "grad_norm": 0.3413268029689789,
236
+ "learning_rate": 1.931017316350384e-05,
237
+ "loss": 0.8697,
238
+ "mean_token_accuracy": 0.7360603749752045,
239
+ "num_tokens": 3849839.0,
240
+ "step": 230
241
+ },
242
+ {
243
+ "entropy": 1.2659676790237426,
244
+ "epoch": 1.5312000000000001,
245
+ "grad_norm": 0.3698340356349945,
246
+ "learning_rate": 1.9232859968953702e-05,
247
+ "loss": 0.8485,
248
+ "mean_token_accuracy": 0.7409502565860748,
249
+ "num_tokens": 4013096.0,
250
+ "step": 240
251
+ },
252
+ {
253
+ "entropy": 1.2457158893346787,
254
+ "epoch": 1.5952,
255
+ "grad_norm": 0.3389880061149597,
256
+ "learning_rate": 1.9151613164672136e-05,
257
+ "loss": 0.8413,
258
+ "mean_token_accuracy": 0.7419567927718163,
259
+ "num_tokens": 4179020.0,
260
+ "step": 250
261
+ },
262
+ {
263
+ "entropy": 1.2573517620563508,
264
+ "epoch": 1.6592,
265
+ "grad_norm": 0.3342834413051605,
266
+ "learning_rate": 1.9066467365417844e-05,
267
+ "loss": 0.8608,
268
+ "mean_token_accuracy": 0.7395736679434777,
269
+ "num_tokens": 4346965.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 1.258076936006546,
274
+ "epoch": 1.7231999999999998,
275
+ "grad_norm": 0.3676120936870575,
276
+ "learning_rate": 1.8977458847095117e-05,
277
+ "loss": 0.8473,
278
+ "mean_token_accuracy": 0.7396213799715042,
279
+ "num_tokens": 4514752.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 1.2764853298664094,
284
+ "epoch": 1.7872,
285
+ "grad_norm": 0.3219451606273651,
286
+ "learning_rate": 1.888462553129867e-05,
287
+ "loss": 0.8648,
288
+ "mean_token_accuracy": 0.7372969388961792,
289
+ "num_tokens": 4683207.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 1.2711820542812347,
294
+ "epoch": 1.8512,
295
+ "grad_norm": 0.32780835032463074,
296
+ "learning_rate": 1.878800696915737e-05,
297
+ "loss": 0.8853,
298
+ "mean_token_accuracy": 0.731884841620922,
299
+ "num_tokens": 4854349.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 1.2870726704597473,
304
+ "epoch": 1.9152,
305
+ "grad_norm": 0.3790556788444519,
306
+ "learning_rate": 1.868764432448369e-05,
307
+ "loss": 0.9023,
308
+ "mean_token_accuracy": 0.7296474754810334,
309
+ "num_tokens": 5024479.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "entropy": 1.2802390396595,
314
+ "epoch": 1.9792,
315
+ "grad_norm": 0.3646782636642456,
316
+ "learning_rate": 1.8583580356236065e-05,
317
+ "loss": 0.8691,
318
+ "mean_token_accuracy": 0.7334814980626106,
319
+ "num_tokens": 5187186.0,
320
+ "step": 310
321
+ },
322
+ {
323
+ "entropy": 1.2680169150636003,
324
+ "epoch": 2.0384,
325
+ "grad_norm": 0.3757169842720032,
326
+ "learning_rate": 1.8475859400301708e-05,
327
+ "loss": 0.864,
328
+ "mean_token_accuracy": 0.7385773127143448,
329
+ "num_tokens": 5340338.0,
330
+ "step": 320
331
+ },
332
+ {
333
+ "entropy": 1.2285860389471055,
334
+ "epoch": 2.1024,
335
+ "grad_norm": 0.3415680229663849,
336
+ "learning_rate": 1.8364527350607527e-05,
337
+ "loss": 0.8503,
338
+ "mean_token_accuracy": 0.7417267143726349,
339
+ "num_tokens": 5511078.0,
340
+ "step": 330
341
+ },
342
+ {
343
+ "entropy": 1.2121232539415359,
344
+ "epoch": 2.1664,
345
+ "grad_norm": 0.3802167773246765,
346
+ "learning_rate": 1.824963163956726e-05,
347
+ "loss": 0.8147,
348
+ "mean_token_accuracy": 0.7479733288288116,
349
+ "num_tokens": 5678766.0,
350
+ "step": 340
351
+ },
352
+ {
353
+ "entropy": 1.2510919898748398,
354
+ "epoch": 2.2304,
355
+ "grad_norm": 0.37446126341819763,
356
+ "learning_rate": 1.8131221217873175e-05,
357
+ "loss": 0.851,
358
+ "mean_token_accuracy": 0.740390644967556,
359
+ "num_tokens": 5845310.0,
360
+ "step": 350
361
+ },
362
+ {
363
+ "entropy": 1.2513864248991013,
364
+ "epoch": 2.2944,
365
+ "grad_norm": 0.38065341114997864,
366
+ "learning_rate": 1.8009346533640877e-05,
367
+ "loss": 0.8321,
368
+ "mean_token_accuracy": 0.744195120036602,
369
+ "num_tokens": 6008026.0,
370
+ "step": 360
371
+ },
372
+ {
373
+ "entropy": 1.2588100284337997,
374
+ "epoch": 2.3584,
375
+ "grad_norm": 0.41983911395072937,
376
+ "learning_rate": 1.7884059510916167e-05,
377
+ "loss": 0.8676,
378
+ "mean_token_accuracy": 0.7367229193449021,
379
+ "num_tokens": 6174434.0,
380
+ "step": 370
381
+ },
382
+ {
383
+ "entropy": 1.255004408955574,
384
+ "epoch": 2.4224,
385
+ "grad_norm": 0.40530291199684143,
386
+ "learning_rate": 1.7755413527553087e-05,
387
+ "loss": 0.8535,
388
+ "mean_token_accuracy": 0.7384593844413757,
389
+ "num_tokens": 6344795.0,
390
+ "step": 380
391
+ },
392
+ {
393
+ "entropy": 1.2649497270584107,
394
+ "epoch": 2.4864,
395
+ "grad_norm": 0.3807426691055298,
396
+ "learning_rate": 1.7623463392472574e-05,
397
+ "loss": 0.8694,
398
+ "mean_token_accuracy": 0.7360624000430107,
399
+ "num_tokens": 6514897.0,
400
+ "step": 390
401
+ },
402
+ {
403
+ "entropy": 1.2368371874094009,
404
+ "epoch": 2.5504,
405
+ "grad_norm": 0.3913272023200989,
406
+ "learning_rate": 1.748826532231142e-05,
407
+ "loss": 0.8375,
408
+ "mean_token_accuracy": 0.7420043379068375,
409
+ "num_tokens": 6681240.0,
410
+ "step": 400
411
+ },
412
+ {
413
+ "entropy": 1.2518309116363526,
414
+ "epoch": 2.6144,
415
+ "grad_norm": 0.4146139323711395,
416
+ "learning_rate": 1.7349876917471474e-05,
417
+ "loss": 0.8486,
418
+ "mean_token_accuracy": 0.7402682423591613,
419
+ "num_tokens": 6847429.0,
420
+ "step": 410
421
+ },
422
+ {
423
+ "entropy": 1.2469070911407472,
424
+ "epoch": 2.6784,
425
+ "grad_norm": 0.3891793489456177,
426
+ "learning_rate": 1.7208357137579318e-05,
427
+ "loss": 0.8608,
428
+ "mean_token_accuracy": 0.7373070567846298,
429
+ "num_tokens": 7016692.0,
430
+ "step": 420
431
+ },
432
+ {
433
+ "entropy": 1.2509080231189729,
434
+ "epoch": 2.7424,
435
+ "grad_norm": 0.42574191093444824,
436
+ "learning_rate": 1.7063766276366814e-05,
437
+ "loss": 0.8647,
438
+ "mean_token_accuracy": 0.7349686965346336,
439
+ "num_tokens": 7184437.0,
440
+ "step": 430
441
+ },
442
+ {
443
+ "entropy": 1.2402510732412337,
444
+ "epoch": 2.8064,
445
+ "grad_norm": 0.3809674084186554,
446
+ "learning_rate": 1.6916165935983323e-05,
447
+ "loss": 0.8364,
448
+ "mean_token_accuracy": 0.7414919167757035,
449
+ "num_tokens": 7352089.0,
450
+ "step": 440
451
+ },
452
+ {
453
+ "entropy": 1.2501752972602844,
454
+ "epoch": 2.8704,
455
+ "grad_norm": 0.39809074997901917,
456
+ "learning_rate": 1.676561900075041e-05,
457
+ "loss": 0.846,
458
+ "mean_token_accuracy": 0.7401938289403915,
459
+ "num_tokens": 7519467.0,
460
+ "step": 450
461
+ },
462
+ {
463
+ "entropy": 1.2486298561096192,
464
+ "epoch": 2.9344,
465
+ "grad_norm": 0.4290047287940979,
466
+ "learning_rate": 1.6612189610370336e-05,
467
+ "loss": 0.8603,
468
+ "mean_token_accuracy": 0.7392841055989265,
469
+ "num_tokens": 7691471.0,
470
+ "step": 460
471
+ },
472
+ {
473
+ "entropy": 1.2415612161159515,
474
+ "epoch": 2.9984,
475
+ "grad_norm": 0.39543700218200684,
476
+ "learning_rate": 1.6455943132599698e-05,
477
+ "loss": 0.8428,
478
+ "mean_token_accuracy": 0.7418375059962272,
479
+ "num_tokens": 7858740.0,
480
+ "step": 470
481
+ },
482
+ {
483
+ "entropy": 1.2214874029159546,
484
+ "epoch": 3.0576,
485
+ "grad_norm": 0.42647498846054077,
486
+ "learning_rate": 1.6296946135399835e-05,
487
+ "loss": 0.8186,
488
+ "mean_token_accuracy": 0.7487845855790216,
489
+ "num_tokens": 8013016.0,
490
+ "step": 480
491
+ },
492
+ {
493
+ "entropy": 1.214153888821602,
494
+ "epoch": 3.1216,
495
+ "grad_norm": 0.47299304604530334,
496
+ "learning_rate": 1.613526635857591e-05,
497
+ "loss": 0.8272,
498
+ "mean_token_accuracy": 0.7459566310048104,
499
+ "num_tokens": 8186012.0,
500
+ "step": 490
501
+ },
502
+ {
503
+ "entropy": 1.2059749454259872,
504
+ "epoch": 3.1856,
505
+ "grad_norm": 0.5080869197845459,
506
+ "learning_rate": 1.5970972684916754e-05,
507
+ "loss": 0.814,
508
+ "mean_token_accuracy": 0.7468735337257385,
509
+ "num_tokens": 8356469.0,
510
+ "step": 500
511
+ },
512
+ {
513
+ "entropy": 1.229441523551941,
514
+ "epoch": 3.2496,
515
+ "grad_norm": 0.48198065161705017,
516
+ "learning_rate": 1.5804135110847708e-05,
517
+ "loss": 0.8346,
518
+ "mean_token_accuracy": 0.7422416999936103,
519
+ "num_tokens": 8522068.0,
520
+ "step": 510
521
+ },
522
+ {
523
+ "entropy": 1.2226635456085204,
524
+ "epoch": 3.3136,
525
+ "grad_norm": 0.49883201718330383,
526
+ "learning_rate": 1.5634824716609037e-05,
527
+ "loss": 0.8337,
528
+ "mean_token_accuracy": 0.7423326745629311,
529
+ "num_tokens": 8691189.0,
530
+ "step": 520
531
+ },
532
+ {
533
+ "entropy": 1.221450889110565,
534
+ "epoch": 3.3776,
535
+ "grad_norm": 0.5223852396011353,
536
+ "learning_rate": 1.5463113635972577e-05,
537
+ "loss": 0.8219,
538
+ "mean_token_accuracy": 0.7454505205154419,
539
+ "num_tokens": 8858829.0,
540
+ "step": 530
541
+ },
542
+ {
543
+ "entropy": 1.256075695157051,
544
+ "epoch": 3.4416,
545
+ "grad_norm": 0.5027040839195251,
546
+ "learning_rate": 1.528907502550954e-05,
547
+ "loss": 0.8696,
548
+ "mean_token_accuracy": 0.7371025711297989,
549
+ "num_tokens": 9023152.0,
550
+ "step": 540
551
+ },
552
+ {
553
+ "entropy": 1.2054291009902953,
554
+ "epoch": 3.5056000000000003,
555
+ "grad_norm": 0.5042998790740967,
556
+ "learning_rate": 1.5112783033422547e-05,
557
+ "loss": 0.8089,
558
+ "mean_token_accuracy": 0.7502285718917847,
559
+ "num_tokens": 9192345.0,
560
+ "step": 550
561
+ },
562
+ {
563
+ "entropy": 1.2278274714946746,
564
+ "epoch": 3.5696,
565
+ "grad_norm": 0.45448994636535645,
566
+ "learning_rate": 1.4934312767955193e-05,
567
+ "loss": 0.8243,
568
+ "mean_token_accuracy": 0.7445582717657089,
569
+ "num_tokens": 9359534.0,
570
+ "step": 560
571
+ },
572
+ {
573
+ "entropy": 1.2333297580480576,
574
+ "epoch": 3.6336,
575
+ "grad_norm": 0.5510305166244507,
576
+ "learning_rate": 1.4753740265392595e-05,
577
+ "loss": 0.829,
578
+ "mean_token_accuracy": 0.7417365327477455,
579
+ "num_tokens": 9524499.0,
580
+ "step": 570
581
+ },
582
+ {
583
+ "entropy": 1.218250796198845,
584
+ "epoch": 3.6976,
585
+ "grad_norm": 0.5383264422416687,
586
+ "learning_rate": 1.4571142457666536e-05,
587
+ "loss": 0.8224,
588
+ "mean_token_accuracy": 0.7461559876799584,
589
+ "num_tokens": 9691418.0,
590
+ "step": 580
591
+ },
592
+ {
593
+ "entropy": 1.197799614071846,
594
+ "epoch": 3.7616,
595
+ "grad_norm": 0.4910060465335846,
596
+ "learning_rate": 1.4386597139579041e-05,
597
+ "loss": 0.8106,
598
+ "mean_token_accuracy": 0.7503111377358437,
599
+ "num_tokens": 9860032.0,
600
+ "step": 590
601
+ },
602
+ {
603
+ "entropy": 1.2061665117740632,
604
+ "epoch": 3.8256,
605
+ "grad_norm": 0.4970499575138092,
606
+ "learning_rate": 1.4200182935658327e-05,
607
+ "loss": 0.8091,
608
+ "mean_token_accuracy": 0.7470731437206268,
609
+ "num_tokens": 10030071.0,
610
+ "step": 600
611
+ },
612
+ {
613
+ "entropy": 1.206977090239525,
614
+ "epoch": 3.8895999999999997,
615
+ "grad_norm": 0.4960206151008606,
616
+ "learning_rate": 1.4011979266661235e-05,
617
+ "loss": 0.8132,
618
+ "mean_token_accuracy": 0.7475115478038787,
619
+ "num_tokens": 10197218.0,
620
+ "step": 610
621
+ },
622
+ {
623
+ "entropy": 1.2226781100034714,
624
+ "epoch": 3.9536,
625
+ "grad_norm": 0.5883672833442688,
626
+ "learning_rate": 1.3822066315736477e-05,
627
+ "loss": 0.8151,
628
+ "mean_token_accuracy": 0.747152166068554,
629
+ "num_tokens": 10363213.0,
630
+ "step": 620
631
+ },
632
+ {
633
+ "entropy": 1.222595163293787,
634
+ "epoch": 4.0128,
635
+ "grad_norm": 0.5304821133613586,
636
+ "learning_rate": 1.363052499426302e-05,
637
+ "loss": 0.8143,
638
+ "mean_token_accuracy": 0.744894308012885,
639
+ "num_tokens": 10516376.0,
640
+ "step": 630
641
+ },
642
+ {
643
+ "entropy": 1.1796708509325982,
644
+ "epoch": 4.0768,
645
+ "grad_norm": 0.5488530993461609,
646
+ "learning_rate": 1.3437436907378225e-05,
647
+ "loss": 0.7843,
648
+ "mean_token_accuracy": 0.7553770825266838,
649
+ "num_tokens": 10681877.0,
650
+ "step": 640
651
+ },
652
+ {
653
+ "entropy": 1.2144078850746154,
654
+ "epoch": 4.1408,
655
+ "grad_norm": 0.5689272880554199,
656
+ "learning_rate": 1.3242884319210463e-05,
657
+ "loss": 0.8319,
658
+ "mean_token_accuracy": 0.7462387323379517,
659
+ "num_tokens": 10853452.0,
660
+ "step": 650
661
+ },
662
+ {
663
+ "entropy": 1.1723882287740708,
664
+ "epoch": 4.2048,
665
+ "grad_norm": 0.5823758244514465,
666
+ "learning_rate": 1.3046950117830888e-05,
667
+ "loss": 0.7754,
668
+ "mean_token_accuracy": 0.757102370262146,
669
+ "num_tokens": 11021186.0,
670
+ "step": 660
671
+ },
672
+ {
673
+ "entropy": 1.1938336580991744,
674
+ "epoch": 4.2688,
675
+ "grad_norm": 0.6302596926689148,
676
+ "learning_rate": 1.2849717779939439e-05,
677
+ "loss": 0.8064,
678
+ "mean_token_accuracy": 0.7491099700331688,
679
+ "num_tokens": 11188079.0,
680
+ "step": 670
681
+ },
682
+ {
683
+ "entropy": 1.1738565742969513,
684
+ "epoch": 4.3328,
685
+ "grad_norm": 0.6567224264144897,
686
+ "learning_rate": 1.2651271335300063e-05,
687
+ "loss": 0.7881,
688
+ "mean_token_accuracy": 0.7507374078035355,
689
+ "num_tokens": 11357861.0,
690
+ "step": 680
691
+ },
692
+ {
693
+ "entropy": 1.198876941204071,
694
+ "epoch": 4.3968,
695
+ "grad_norm": 0.62027907371521,
696
+ "learning_rate": 1.2451695330940268e-05,
697
+ "loss": 0.8046,
698
+ "mean_token_accuracy": 0.7497236520051956,
699
+ "num_tokens": 11524052.0,
700
+ "step": 690
701
+ },
702
+ {
703
+ "entropy": 1.1681430846452714,
704
+ "epoch": 4.4608,
705
+ "grad_norm": 0.6131038069725037,
706
+ "learning_rate": 1.2251074795130339e-05,
707
+ "loss": 0.7887,
708
+ "mean_token_accuracy": 0.7542851880192757,
709
+ "num_tokens": 11693539.0,
710
+ "step": 700
711
+ },
712
+ {
713
+ "entropy": 1.2012270838022232,
714
+ "epoch": 4.5248,
715
+ "grad_norm": 0.6755374073982239,
716
+ "learning_rate": 1.2049495201157489e-05,
717
+ "loss": 0.8051,
718
+ "mean_token_accuracy": 0.7475825384259224,
719
+ "num_tokens": 11859545.0,
720
+ "step": 710
721
+ },
722
+ {
723
+ "entropy": 1.190478339791298,
724
+ "epoch": 4.5888,
725
+ "grad_norm": 0.6316648125648499,
726
+ "learning_rate": 1.1847042430910451e-05,
727
+ "loss": 0.7912,
728
+ "mean_token_accuracy": 0.7512465313076973,
729
+ "num_tokens": 12025362.0,
730
+ "step": 720
731
+ },
732
+ {
733
+ "entropy": 1.1802339136600495,
734
+ "epoch": 4.6528,
735
+ "grad_norm": 0.6220593452453613,
736
+ "learning_rate": 1.1643802738289955e-05,
737
+ "loss": 0.7913,
738
+ "mean_token_accuracy": 0.7516302943229676,
739
+ "num_tokens": 12193592.0,
740
+ "step": 730
741
+ },
742
+ {
743
+ "entropy": 1.1827380925416946,
744
+ "epoch": 4.7168,
745
+ "grad_norm": 0.5833670496940613,
746
+ "learning_rate": 1.1439862712460721e-05,
747
+ "loss": 0.8028,
748
+ "mean_token_accuracy": 0.7484710603952408,
749
+ "num_tokens": 12361308.0,
750
+ "step": 740
751
+ },
752
+ {
753
+ "entropy": 1.1752862721681594,
754
+ "epoch": 4.7808,
755
+ "grad_norm": 0.6545965671539307,
756
+ "learning_rate": 1.1235309240960621e-05,
757
+ "loss": 0.7858,
758
+ "mean_token_accuracy": 0.7553699359297752,
759
+ "num_tokens": 12530382.0,
760
+ "step": 750
761
+ },
762
+ {
763
+ "entropy": 1.177734187245369,
764
+ "epoch": 4.8448,
765
+ "grad_norm": 0.6953952312469482,
766
+ "learning_rate": 1.1030229472682719e-05,
767
+ "loss": 0.7852,
768
+ "mean_token_accuracy": 0.7533090978860855,
769
+ "num_tokens": 12695004.0,
770
+ "step": 760
771
+ },
772
+ {
773
+ "entropy": 1.1654743909835816,
774
+ "epoch": 4.9088,
775
+ "grad_norm": 0.6737579107284546,
776
+ "learning_rate": 1.0824710780745954e-05,
777
+ "loss": 0.7878,
778
+ "mean_token_accuracy": 0.7544879004359245,
779
+ "num_tokens": 12864450.0,
780
+ "step": 770
781
+ },
782
+ {
783
+ "entropy": 1.1805586963891983,
784
+ "epoch": 4.9728,
785
+ "grad_norm": 0.6320992708206177,
786
+ "learning_rate": 1.06188407252703e-05,
787
+ "loss": 0.7994,
788
+ "mean_token_accuracy": 0.7510025933384895,
789
+ "num_tokens": 13033199.0,
790
+ "step": 780
791
+ },
792
+ {
793
+ "entropy": 1.165472733007895,
794
+ "epoch": 5.032,
795
+ "grad_norm": 0.652460515499115,
796
+ "learning_rate": 1.0412707016072254e-05,
797
+ "loss": 0.7596,
798
+ "mean_token_accuracy": 0.7593615957208582,
799
+ "num_tokens": 13189187.0,
800
+ "step": 790
801
+ },
802
+ {
803
+ "entropy": 1.1522447764873505,
804
+ "epoch": 5.096,
805
+ "grad_norm": 0.8098700046539307,
806
+ "learning_rate": 1.0206397475296548e-05,
807
+ "loss": 0.768,
808
+ "mean_token_accuracy": 0.7569398522377014,
809
+ "num_tokens": 13358010.0,
810
+ "step": 800
811
+ },
812
+ {
813
+ "entropy": 1.155535000562668,
814
+ "epoch": 5.16,
815
+ "grad_norm": 0.7569311261177063,
816
+ "learning_rate": 1e-05,
817
+ "loss": 0.766,
818
+ "mean_token_accuracy": 0.7563902020454407,
819
+ "num_tokens": 13524722.0,
820
+ "step": 810
821
+ },
822
+ {
823
+ "entropy": 1.157894878089428,
824
+ "epoch": 5.224,
825
+ "grad_norm": 0.8364959359169006,
826
+ "learning_rate": 9.793602524703456e-06,
827
+ "loss": 0.7693,
828
+ "mean_token_accuracy": 0.7581299751996994,
829
+ "num_tokens": 13690529.0,
830
+ "step": 820
831
+ },
832
+ {
833
+ "entropy": 1.145342645049095,
834
+ "epoch": 5.288,
835
+ "grad_norm": 0.7824255228042603,
836
+ "learning_rate": 9.58729298392775e-06,
837
+ "loss": 0.7611,
838
+ "mean_token_accuracy": 0.761179718375206,
839
+ "num_tokens": 13859442.0,
840
+ "step": 830
841
+ },
842
+ {
843
+ "entropy": 1.1661550253629684,
844
+ "epoch": 5.352,
845
+ "grad_norm": 0.7638425230979919,
846
+ "learning_rate": 9.381159274729704e-06,
847
+ "loss": 0.7825,
848
+ "mean_token_accuracy": 0.7569466888904571,
849
+ "num_tokens": 14028485.0,
850
+ "step": 840
851
+ },
852
+ {
853
+ "entropy": 1.1383796483278275,
854
+ "epoch": 5.416,
855
+ "grad_norm": 0.7410515546798706,
856
+ "learning_rate": 9.175289219254051e-06,
857
+ "loss": 0.7497,
858
+ "mean_token_accuracy": 0.7625020772218705,
859
+ "num_tokens": 14198221.0,
860
+ "step": 850
861
+ },
862
+ {
863
+ "entropy": 1.1481939822435379,
864
+ "epoch": 5.48,
865
+ "grad_norm": 0.7490608096122742,
866
+ "learning_rate": 8.969770527317283e-06,
867
+ "loss": 0.7477,
868
+ "mean_token_accuracy": 0.7623027458786964,
869
+ "num_tokens": 14367293.0,
870
+ "step": 860
871
+ },
872
+ {
873
+ "entropy": 1.1579900979995728,
874
+ "epoch": 5.5440000000000005,
875
+ "grad_norm": 0.7536274790763855,
876
+ "learning_rate": 8.764690759039382e-06,
877
+ "loss": 0.7692,
878
+ "mean_token_accuracy": 0.7568637877702713,
879
+ "num_tokens": 14535472.0,
880
+ "step": 870
881
+ },
882
+ {
883
+ "entropy": 1.1517672553658485,
884
+ "epoch": 5.608,
885
+ "grad_norm": 0.824515163898468,
886
+ "learning_rate": 8.56013728753928e-06,
887
+ "loss": 0.7621,
888
+ "mean_token_accuracy": 0.7600950643420219,
889
+ "num_tokens": 14700265.0,
890
+ "step": 880
891
+ },
892
+ {
893
+ "entropy": 1.1413051068782807,
894
+ "epoch": 5.672,
895
+ "grad_norm": 0.7741249203681946,
896
+ "learning_rate": 8.356197261710048e-06,
897
+ "loss": 0.7518,
898
+ "mean_token_accuracy": 0.7614945828914642,
899
+ "num_tokens": 14866673.0,
900
+ "step": 890
901
+ },
902
+ {
903
+ "entropy": 1.171517863869667,
904
+ "epoch": 5.736,
905
+ "grad_norm": 0.7269055247306824,
906
+ "learning_rate": 8.152957569089552e-06,
907
+ "loss": 0.7836,
908
+ "mean_token_accuracy": 0.7550232648849488,
909
+ "num_tokens": 15031602.0,
910
+ "step": 900
911
+ },
912
+ {
913
+ "entropy": 1.1627105355262757,
914
+ "epoch": 5.8,
915
+ "grad_norm": 0.8189387321472168,
916
+ "learning_rate": 7.950504798842513e-06,
917
+ "loss": 0.7818,
918
+ "mean_token_accuracy": 0.7560641661286354,
919
+ "num_tokens": 15200656.0,
920
+ "step": 910
921
+ },
922
+ {
923
+ "entropy": 1.1600016862154008,
924
+ "epoch": 5.864,
925
+ "grad_norm": 0.8086869716644287,
926
+ "learning_rate": 7.748925204869667e-06,
927
+ "loss": 0.7637,
928
+ "mean_token_accuracy": 0.7589102029800415,
929
+ "num_tokens": 15368071.0,
930
+ "step": 920
931
+ },
932
+ {
933
+ "entropy": 1.1717667609453202,
934
+ "epoch": 5.928,
935
+ "grad_norm": 0.8845758438110352,
936
+ "learning_rate": 7.548304669059735e-06,
937
+ "loss": 0.7792,
938
+ "mean_token_accuracy": 0.7552744656801224,
939
+ "num_tokens": 15533538.0,
940
+ "step": 930
941
+ },
942
+ {
943
+ "entropy": 1.1296544909477233,
944
+ "epoch": 5.992,
945
+ "grad_norm": 0.8191102147102356,
946
+ "learning_rate": 7.348728664699939e-06,
947
+ "loss": 0.7392,
948
+ "mean_token_accuracy": 0.7642928868532181,
949
+ "num_tokens": 15702224.0,
950
+ "step": 940
951
+ },
952
+ {
953
+ "entropy": 1.1310625011856492,
954
+ "epoch": 6.0512,
955
+ "grad_norm": 1.03687584400177,
956
+ "learning_rate": 7.150282220060564e-06,
957
+ "loss": 0.7322,
958
+ "mean_token_accuracy": 0.7652509937415252,
959
+ "num_tokens": 15855871.0,
960
+ "step": 950
961
+ },
962
+ {
963
+ "entropy": 1.12939695417881,
964
+ "epoch": 6.1152,
965
+ "grad_norm": 0.9026349186897278,
966
+ "learning_rate": 6.9530498821691165e-06,
967
+ "loss": 0.7312,
968
+ "mean_token_accuracy": 0.7661619514226914,
969
+ "num_tokens": 16022959.0,
970
+ "step": 960
971
+ },
972
+ {
973
+ "entropy": 1.1230400115251542,
974
+ "epoch": 6.1792,
975
+ "grad_norm": 0.9334505200386047,
976
+ "learning_rate": 6.757115680789539e-06,
977
+ "loss": 0.7166,
978
+ "mean_token_accuracy": 0.7693509578704834,
979
+ "num_tokens": 16184586.0,
980
+ "step": 970
981
+ },
982
+ {
983
+ "entropy": 1.1167623370885849,
984
+ "epoch": 6.2432,
985
+ "grad_norm": 0.8687794804573059,
986
+ "learning_rate": 6.562563092621776e-06,
987
+ "loss": 0.7309,
988
+ "mean_token_accuracy": 0.7661765992641449,
989
+ "num_tokens": 16356436.0,
990
+ "step": 980
991
+ },
992
+ {
993
+ "entropy": 1.1170607119798661,
994
+ "epoch": 6.3072,
995
+ "grad_norm": 0.9250707626342773,
996
+ "learning_rate": 6.369475005736984e-06,
997
+ "loss": 0.728,
998
+ "mean_token_accuracy": 0.7687151193618774,
999
+ "num_tokens": 16522765.0,
1000
+ "step": 990
1001
+ },
1002
+ {
1003
+ "entropy": 1.1269994646310806,
1004
+ "epoch": 6.3712,
1005
+ "grad_norm": 0.9762291312217712,
1006
+ "learning_rate": 6.177933684263524e-06,
1007
+ "loss": 0.7427,
1008
+ "mean_token_accuracy": 0.7661235600709915,
1009
+ "num_tokens": 16689964.0,
1010
+ "step": 1000
1011
+ },
1012
+ {
1013
+ "entropy": 1.1308791995048524,
1014
+ "epoch": 6.4352,
1015
+ "grad_norm": 0.9405747652053833,
1016
+ "learning_rate": 5.988020733338767e-06,
1017
+ "loss": 0.7282,
1018
+ "mean_token_accuracy": 0.7662904724478722,
1019
+ "num_tokens": 16855846.0,
1020
+ "step": 1010
1021
+ },
1022
+ {
1023
+ "entropy": 1.1322367668151856,
1024
+ "epoch": 6.4992,
1025
+ "grad_norm": 0.8870813250541687,
1026
+ "learning_rate": 5.7998170643416795e-06,
1027
+ "loss": 0.7448,
1028
+ "mean_token_accuracy": 0.7629623278975487,
1029
+ "num_tokens": 17024434.0,
1030
+ "step": 1020
1031
+ },
1032
+ {
1033
+ "entropy": 1.1535383015871048,
1034
+ "epoch": 6.5632,
1035
+ "grad_norm": 0.9254381060600281,
1036
+ "learning_rate": 5.613402860420962e-06,
1037
+ "loss": 0.7691,
1038
+ "mean_token_accuracy": 0.7590128257870674,
1039
+ "num_tokens": 17195067.0,
1040
+ "step": 1030
1041
+ },
1042
+ {
1043
+ "entropy": 1.1291758388280868,
1044
+ "epoch": 6.6272,
1045
+ "grad_norm": 0.8941587209701538,
1046
+ "learning_rate": 5.428857542333465e-06,
1047
+ "loss": 0.7423,
1048
+ "mean_token_accuracy": 0.7641170158982277,
1049
+ "num_tokens": 17367933.0,
1050
+ "step": 1040
1051
+ },
1052
+ {
1053
+ "entropy": 1.1354484647512435,
1054
+ "epoch": 6.6912,
1055
+ "grad_norm": 0.9986079335212708,
1056
+ "learning_rate": 5.246259734607411e-06,
1057
+ "loss": 0.7558,
1058
+ "mean_token_accuracy": 0.7625504702329635,
1059
+ "num_tokens": 17534589.0,
1060
+ "step": 1050
1061
+ },
1062
+ {
1063
+ "entropy": 1.1145919933915138,
1064
+ "epoch": 6.7552,
1065
+ "grad_norm": 0.9608755707740784,
1066
+ "learning_rate": 5.065687232044811e-06,
1067
+ "loss": 0.7207,
1068
+ "mean_token_accuracy": 0.767878831923008,
1069
+ "num_tokens": 17702136.0,
1070
+ "step": 1060
1071
+ },
1072
+ {
1073
+ "entropy": 1.1152497231960297,
1074
+ "epoch": 6.8192,
1075
+ "grad_norm": 0.930647611618042,
1076
+ "learning_rate": 4.887216966577458e-06,
1077
+ "loss": 0.7136,
1078
+ "mean_token_accuracy": 0.7703010246157647,
1079
+ "num_tokens": 17868339.0,
1080
+ "step": 1070
1081
+ },
1082
+ {
1083
+ "entropy": 1.1384254783391952,
1084
+ "epoch": 6.8832,
1085
+ "grad_norm": 0.981146514415741,
1086
+ "learning_rate": 4.710924974490463e-06,
1087
+ "loss": 0.7725,
1088
+ "mean_token_accuracy": 0.7612431243062019,
1089
+ "num_tokens": 18041328.0,
1090
+ "step": 1080
1091
+ },
1092
+ {
1093
+ "entropy": 1.1156837493181229,
1094
+ "epoch": 6.9472000000000005,
1095
+ "grad_norm": 1.031293511390686,
1096
+ "learning_rate": 4.536886364027428e-06,
1097
+ "loss": 0.7187,
1098
+ "mean_token_accuracy": 0.7708014816045761,
1099
+ "num_tokens": 18207019.0,
1100
+ "step": 1090
1101
+ },
1102
+ {
1103
+ "entropy": 1.1324091795328501,
1104
+ "epoch": 7.0064,
1105
+ "grad_norm": 0.9793551564216614,
1106
+ "learning_rate": 4.365175283390968e-06,
1107
+ "loss": 0.7325,
1108
+ "mean_token_accuracy": 0.7669887091662433,
1109
+ "num_tokens": 18362086.0,
1110
+ "step": 1100
1111
+ },
1112
+ {
1113
+ "entropy": 1.1103261813521386,
1114
+ "epoch": 7.0704,
1115
+ "grad_norm": 1.0026472806930542,
1116
+ "learning_rate": 4.195864889152295e-06,
1117
+ "loss": 0.7056,
1118
+ "mean_token_accuracy": 0.7747725829482078,
1119
+ "num_tokens": 18529192.0,
1120
+ "step": 1110
1121
+ },
1122
+ {
1123
+ "entropy": 1.1086191982030869,
1124
+ "epoch": 7.1344,
1125
+ "grad_norm": 1.0708081722259521,
1126
+ "learning_rate": 4.029027315083251e-06,
1127
+ "loss": 0.7261,
1128
+ "mean_token_accuracy": 0.7677501872181892,
1129
+ "num_tokens": 18697843.0,
1130
+ "step": 1120
1131
+ },
1132
+ {
1133
+ "entropy": 1.0975075036287307,
1134
+ "epoch": 7.1984,
1135
+ "grad_norm": 0.9521598219871521,
1136
+ "learning_rate": 3.864733641424093e-06,
1137
+ "loss": 0.7059,
1138
+ "mean_token_accuracy": 0.7746093690395355,
1139
+ "num_tokens": 18866212.0,
1140
+ "step": 1130
1141
+ },
1142
+ {
1143
+ "entropy": 1.1038097634911537,
1144
+ "epoch": 7.2624,
1145
+ "grad_norm": 1.0327914953231812,
1146
+ "learning_rate": 3.703053864600169e-06,
1147
+ "loss": 0.7114,
1148
+ "mean_token_accuracy": 0.7727755904197693,
1149
+ "num_tokens": 19033743.0,
1150
+ "step": 1140
1151
+ },
1152
+ {
1153
+ "entropy": 1.1110169142484665,
1154
+ "epoch": 7.3264,
1155
+ "grad_norm": 1.0147864818572998,
1156
+ "learning_rate": 3.544056867400306e-06,
1157
+ "loss": 0.7138,
1158
+ "mean_token_accuracy": 0.769483657181263,
1159
+ "num_tokens": 19200496.0,
1160
+ "step": 1150
1161
+ },
1162
+ {
1163
+ "entropy": 1.0948543518781662,
1164
+ "epoch": 7.3904,
1165
+ "grad_norm": 1.0380463600158691,
1166
+ "learning_rate": 3.3878103896296677e-06,
1167
+ "loss": 0.705,
1168
+ "mean_token_accuracy": 0.7747946813702583,
1169
+ "num_tokens": 19367582.0,
1170
+ "step": 1160
1171
+ },
1172
+ {
1173
+ "entropy": 1.1144859746098519,
1174
+ "epoch": 7.4544,
1175
+ "grad_norm": 1.100961446762085,
1176
+ "learning_rate": 3.2343809992495945e-06,
1177
+ "loss": 0.7052,
1178
+ "mean_token_accuracy": 0.7745175659656525,
1179
+ "num_tokens": 19533688.0,
1180
+ "step": 1170
1181
+ },
1182
+ {
1183
+ "entropy": 1.107055227458477,
1184
+ "epoch": 7.5184,
1185
+ "grad_norm": 1.0504915714263916,
1186
+ "learning_rate": 3.083834064016682e-06,
1187
+ "loss": 0.7194,
1188
+ "mean_token_accuracy": 0.7694016128778458,
1189
+ "num_tokens": 19703466.0,
1190
+ "step": 1180
1191
+ },
1192
+ {
1193
+ "entropy": 1.1040660321712494,
1194
+ "epoch": 7.5824,
1195
+ "grad_norm": 1.0282219648361206,
1196
+ "learning_rate": 2.9362337236331884e-06,
1197
+ "loss": 0.7114,
1198
+ "mean_token_accuracy": 0.7717982798814773,
1199
+ "num_tokens": 19868961.0,
1200
+ "step": 1190
1201
+ },
1202
+ {
1203
+ "entropy": 1.0966812744736671,
1204
+ "epoch": 7.6464,
1205
+ "grad_norm": 1.0571895837783813,
1206
+ "learning_rate": 2.791642862420686e-06,
1207
+ "loss": 0.7038,
1208
+ "mean_token_accuracy": 0.7714879170060158,
1209
+ "num_tokens": 20038228.0,
1210
+ "step": 1200
1211
+ },
1212
+ {
1213
+ "entropy": 1.0895270451903343,
1214
+ "epoch": 7.7104,
1215
+ "grad_norm": 1.016501545906067,
1216
+ "learning_rate": 2.6501230825285294e-06,
1217
+ "loss": 0.709,
1218
+ "mean_token_accuracy": 0.7727946832776069,
1219
+ "num_tokens": 20206537.0,
1220
+ "step": 1210
1221
+ },
1222
+ {
1223
+ "entropy": 1.1009603932499885,
1224
+ "epoch": 7.7744,
1225
+ "grad_norm": 1.0647404193878174,
1226
+ "learning_rate": 2.5117346776885843e-06,
1227
+ "loss": 0.7222,
1228
+ "mean_token_accuracy": 0.7703997671604157,
1229
+ "num_tokens": 20378633.0,
1230
+ "step": 1220
1231
+ },
1232
+ {
1233
+ "entropy": 1.1264784708619118,
1234
+ "epoch": 7.8384,
1235
+ "grad_norm": 1.0770481824874878,
1236
+ "learning_rate": 2.3765366075274287e-06,
1237
+ "loss": 0.7404,
1238
+ "mean_token_accuracy": 0.7675652742385864,
1239
+ "num_tokens": 20546008.0,
1240
+ "step": 1230
1241
+ },
1242
+ {
1243
+ "entropy": 1.1074893057346344,
1244
+ "epoch": 7.9024,
1245
+ "grad_norm": 1.008133888244629,
1246
+ "learning_rate": 2.2445864724469146e-06,
1247
+ "loss": 0.7169,
1248
+ "mean_token_accuracy": 0.7722549349069595,
1249
+ "num_tokens": 20713626.0,
1250
+ "step": 1240
1251
+ },
1252
+ {
1253
+ "entropy": 1.102501641213894,
1254
+ "epoch": 7.9664,
1255
+ "grad_norm": 1.1541906595230103,
1256
+ "learning_rate": 2.1159404890838365e-06,
1257
+ "loss": 0.7081,
1258
+ "mean_token_accuracy": 0.7719982087612152,
1259
+ "num_tokens": 20879013.0,
1260
+ "step": 1250
1261
+ },
1262
+ {
1263
+ "entropy": 1.11241014905878,
1264
+ "epoch": 8.0256,
1265
+ "grad_norm": 1.1066633462905884,
1266
+ "learning_rate": 1.990653466359125e-06,
1267
+ "loss": 0.7222,
1268
+ "mean_token_accuracy": 0.7699585975827398,
1269
+ "num_tokens": 21032374.0,
1270
+ "step": 1260
1271
+ },
1272
+ {
1273
+ "entropy": 1.0768096685409545,
1274
+ "epoch": 8.0896,
1275
+ "grad_norm": 1.1172068119049072,
1276
+ "learning_rate": 1.8687787821268255e-06,
1277
+ "loss": 0.6777,
1278
+ "mean_token_accuracy": 0.7810665085911751,
1279
+ "num_tokens": 21201542.0,
1280
+ "step": 1270
1281
+ },
1282
+ {
1283
+ "entropy": 1.06906708329916,
1284
+ "epoch": 8.1536,
1285
+ "grad_norm": 1.0443674325942993,
1286
+ "learning_rate": 1.7503683604327426e-06,
1287
+ "loss": 0.6805,
1288
+ "mean_token_accuracy": 0.7791709944605827,
1289
+ "num_tokens": 21367941.0,
1290
+ "step": 1280
1291
+ },
1292
+ {
1293
+ "entropy": 1.0811031743884087,
1294
+ "epoch": 8.2176,
1295
+ "grad_norm": 1.0284481048583984,
1296
+ "learning_rate": 1.6354726493924745e-06,
1297
+ "loss": 0.7007,
1298
+ "mean_token_accuracy": 0.7756990104913711,
1299
+ "num_tokens": 21539293.0,
1300
+ "step": 1290
1301
+ },
1302
+ {
1303
+ "entropy": 1.1065931975841523,
1304
+ "epoch": 8.2816,
1305
+ "grad_norm": 1.178467869758606,
1306
+ "learning_rate": 1.5241405996982928e-06,
1307
+ "loss": 0.718,
1308
+ "mean_token_accuracy": 0.7737029820680619,
1309
+ "num_tokens": 21706358.0,
1310
+ "step": 1300
1311
+ },
1312
+ {
1313
+ "entropy": 1.093373966217041,
1314
+ "epoch": 8.3456,
1315
+ "grad_norm": 1.117495059967041,
1316
+ "learning_rate": 1.4164196437639355e-06,
1317
+ "loss": 0.6916,
1318
+ "mean_token_accuracy": 0.7787188529968262,
1319
+ "num_tokens": 21871375.0,
1320
+ "step": 1310
1321
+ },
1322
+ {
1323
+ "entropy": 1.1055374339222908,
1324
+ "epoch": 8.4096,
1325
+ "grad_norm": 1.0783363580703735,
1326
+ "learning_rate": 1.3123556755163114e-06,
1327
+ "loss": 0.7112,
1328
+ "mean_token_accuracy": 0.7722780853509903,
1329
+ "num_tokens": 22037173.0,
1330
+ "step": 1320
1331
+ },
1332
+ {
1333
+ "entropy": 1.0927375853061676,
1334
+ "epoch": 8.4736,
1335
+ "grad_norm": 1.1262452602386475,
1336
+ "learning_rate": 1.2119930308426264e-06,
1337
+ "loss": 0.7001,
1338
+ "mean_token_accuracy": 0.7766996636986733,
1339
+ "num_tokens": 22205102.0,
1340
+ "step": 1330
1341
+ },
1342
+ {
1343
+ "entropy": 1.0972368210554122,
1344
+ "epoch": 8.5376,
1345
+ "grad_norm": 1.1962639093399048,
1346
+ "learning_rate": 1.1153744687013313e-06,
1347
+ "loss": 0.7097,
1348
+ "mean_token_accuracy": 0.7727304697036743,
1349
+ "num_tokens": 22373200.0,
1350
+ "step": 1340
1351
+ },
1352
+ {
1353
+ "entropy": 1.1027744889259339,
1354
+ "epoch": 8.6016,
1355
+ "grad_norm": 1.0765749216079712,
1356
+ "learning_rate": 1.0225411529048857e-06,
1357
+ "loss": 0.7072,
1358
+ "mean_token_accuracy": 0.7723638415336609,
1359
+ "num_tokens": 22541291.0,
1360
+ "step": 1350
1361
+ },
1362
+ {
1363
+ "entropy": 1.0950715363025665,
1364
+ "epoch": 8.6656,
1365
+ "grad_norm": 1.1464935541152954,
1366
+ "learning_rate": 9.33532634582156e-07,
1367
+ "loss": 0.6949,
1368
+ "mean_token_accuracy": 0.7763179376721382,
1369
+ "num_tokens": 22708932.0,
1370
+ "step": 1360
1371
+ },
1372
+ {
1373
+ "entropy": 1.0963666126132012,
1374
+ "epoch": 8.7296,
1375
+ "grad_norm": 1.108978033065796,
1376
+ "learning_rate": 8.483868353278657e-07,
1377
+ "loss": 0.7122,
1378
+ "mean_token_accuracy": 0.7702845230698585,
1379
+ "num_tokens": 22878179.0,
1380
+ "step": 1370
1381
+ },
1382
+ {
1383
+ "entropy": 1.1044292539358138,
1384
+ "epoch": 8.7936,
1385
+ "grad_norm": 1.1283209323883057,
1386
+ "learning_rate": 7.671400310462984e-07,
1387
+ "loss": 0.7034,
1388
+ "mean_token_accuracy": 0.7736527293920517,
1389
+ "num_tokens": 23045004.0,
1390
+ "step": 1380
1391
+ },
1392
+ {
1393
+ "entropy": 1.0912333846092224,
1394
+ "epoch": 8.8576,
1395
+ "grad_norm": 1.0597506761550903,
1396
+ "learning_rate": 6.898268364961591e-07,
1397
+ "loss": 0.6962,
1398
+ "mean_token_accuracy": 0.7772096663713455,
1399
+ "num_tokens": 23212735.0,
1400
+ "step": 1390
1401
+ },
1402
+ {
1403
+ "entropy": 1.1004265248775482,
1404
+ "epoch": 8.9216,
1405
+ "grad_norm": 1.112018346786499,
1406
+ "learning_rate": 6.164801905431394e-07,
1407
+ "loss": 0.6991,
1408
+ "mean_token_accuracy": 0.7758379429578781,
1409
+ "num_tokens": 23378986.0,
1410
+ "step": 1400
1411
+ },
1412
+ {
1413
+ "entropy": 1.0893720075488091,
1414
+ "epoch": 8.9856,
1415
+ "grad_norm": 1.1084034442901611,
1416
+ "learning_rate": 5.471313421264879e-07,
1417
+ "loss": 0.702,
1418
+ "mean_token_accuracy": 0.7754257380962372,
1419
+ "num_tokens": 23548830.0,
1420
+ "step": 1410
1421
+ }
1422
+ ],
1423
+ "logging_steps": 10,
1424
+ "max_steps": 1570,
1425
+ "num_input_tokens_seen": 0,
1426
+ "num_train_epochs": 10,
1427
+ "save_steps": 500,
1428
+ "stateful_callbacks": {
1429
+ "TrainerControl": {
1430
+ "args": {
1431
+ "should_epoch_stop": false,
1432
+ "should_evaluate": false,
1433
+ "should_log": false,
1434
+ "should_save": true,
1435
+ "should_training_stop": false
1436
+ },
1437
+ "attributes": {}
1438
+ }
1439
+ },
1440
+ "total_flos": 1.9543747240490435e+18,
1441
+ "train_batch_size": 16,
1442
+ "trial_name": null,
1443
+ "trial_params": null
1444
+ }
checkpoint-1413/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715b5f801a71e6f8ee2177ab148805ed1d1c0732f395811ea0f0c2c52c99d11c
3
+ size 6225
checkpoint-157/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.18.0
checkpoint-157/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "v_proj",
33
+ "down_proj",
34
+ "up_proj",
35
+ "q_proj",
36
+ "gate_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoint-157/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199ca8d5c865987381c92ef383a21dd0c975c80d79fcbfa9336596424afeb16b
3
+ size 335604696
checkpoint-157/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
checkpoint-157/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c70e478bbeec75441c024045a275160fe90cd180aa3e9f371a1d0679c7f66df
3
+ size 671473443
checkpoint-157/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6401955714c137a2213216b4ead251aebf1a37703b9362b9706ddfe3fedac984
3
+ size 14645
checkpoint-157/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24a6a04700d51b0eaccb461e7f9c4848367f9209d248c5ef2160107e4529ada
3
+ size 1465
checkpoint-157/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-157/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920