PuxAI commited on
Commit
4a3ee03
·
verified ·
1 Parent(s): 095a95d

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 +5 -0
  2. experiments/de-en-pt-zh/README.md +59 -0
  3. experiments/de-en-pt-zh/adapter/README.md +210 -0
  4. experiments/de-en-pt-zh/adapter/adapter_config.json +50 -0
  5. experiments/de-en-pt-zh/adapter/adapter_model.safetensors +3 -0
  6. experiments/de-en-pt-zh/adapter/chat_template.jinja +109 -0
  7. experiments/de-en-pt-zh/adapter/special_tokens_map.json +23 -0
  8. experiments/de-en-pt-zh/adapter/tokenizer.json +3 -0
  9. experiments/de-en-pt-zh/adapter/tokenizer_config.json +2066 -0
  10. experiments/de-en-pt-zh/checkpoint-1000/README.md +210 -0
  11. experiments/de-en-pt-zh/checkpoint-1000/adapter_config.json +50 -0
  12. experiments/de-en-pt-zh/checkpoint-1000/adapter_model.safetensors +3 -0
  13. experiments/de-en-pt-zh/checkpoint-1000/chat_template.jinja +109 -0
  14. experiments/de-en-pt-zh/checkpoint-1000/optimizer.pt +3 -0
  15. experiments/de-en-pt-zh/checkpoint-1000/rng_state.pth +3 -0
  16. experiments/de-en-pt-zh/checkpoint-1000/scheduler.pt +3 -0
  17. experiments/de-en-pt-zh/checkpoint-1000/special_tokens_map.json +23 -0
  18. experiments/de-en-pt-zh/checkpoint-1000/tokenizer.json +3 -0
  19. experiments/de-en-pt-zh/checkpoint-1000/tokenizer_config.json +2066 -0
  20. experiments/de-en-pt-zh/checkpoint-1000/trainer_state.json +1434 -0
  21. experiments/de-en-pt-zh/checkpoint-1000/training_args.bin +3 -0
  22. experiments/de-en-pt-zh/checkpoint-1500/README.md +210 -0
  23. experiments/de-en-pt-zh/checkpoint-1500/adapter_config.json +50 -0
  24. experiments/de-en-pt-zh/checkpoint-1500/adapter_model.safetensors +3 -0
  25. experiments/de-en-pt-zh/checkpoint-1500/chat_template.jinja +109 -0
  26. experiments/de-en-pt-zh/checkpoint-1500/optimizer.pt +3 -0
  27. experiments/de-en-pt-zh/checkpoint-1500/rng_state.pth +3 -0
  28. experiments/de-en-pt-zh/checkpoint-1500/scheduler.pt +3 -0
  29. experiments/de-en-pt-zh/checkpoint-1500/special_tokens_map.json +23 -0
  30. experiments/de-en-pt-zh/checkpoint-1500/tokenizer.json +3 -0
  31. experiments/de-en-pt-zh/checkpoint-1500/tokenizer_config.json +2066 -0
  32. experiments/de-en-pt-zh/checkpoint-1500/trainer_state.json +2134 -0
  33. experiments/de-en-pt-zh/checkpoint-1500/training_args.bin +3 -0
  34. experiments/de-en-pt-zh/checkpoint-1580/README.md +210 -0
  35. experiments/de-en-pt-zh/checkpoint-1580/adapter_config.json +50 -0
  36. experiments/de-en-pt-zh/checkpoint-1580/adapter_model.safetensors +3 -0
  37. experiments/de-en-pt-zh/checkpoint-1580/chat_template.jinja +109 -0
  38. experiments/de-en-pt-zh/checkpoint-1580/optimizer.pt +3 -0
  39. experiments/de-en-pt-zh/checkpoint-1580/rng_state.pth +3 -0
  40. experiments/de-en-pt-zh/checkpoint-1580/scheduler.pt +3 -0
  41. experiments/de-en-pt-zh/checkpoint-1580/special_tokens_map.json +23 -0
  42. experiments/de-en-pt-zh/checkpoint-1580/tokenizer.json +3 -0
  43. experiments/de-en-pt-zh/checkpoint-1580/tokenizer_config.json +2066 -0
  44. experiments/de-en-pt-zh/checkpoint-1580/trainer_state.json +2246 -0
  45. experiments/de-en-pt-zh/checkpoint-1580/training_args.bin +3 -0
  46. experiments/de-en-pt-zh/checkpoint-500/README.md +210 -0
  47. experiments/de-en-pt-zh/checkpoint-500/adapter_config.json +50 -0
  48. experiments/de-en-pt-zh/checkpoint-500/adapter_model.safetensors +3 -0
  49. experiments/de-en-pt-zh/checkpoint-500/chat_template.jinja +109 -0
  50. experiments/de-en-pt-zh/checkpoint-500/optimizer.pt +3 -0
.gitattributes CHANGED
@@ -70,3 +70,8 @@ experiments/de-pt-zh/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  experiments/de-pt-zh/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
  experiments/de-pt-zh/checkpoint-1185/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
  experiments/de-pt-zh/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
70
  experiments/de-pt-zh/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
  experiments/de-pt-zh/checkpoint-1185/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
  experiments/de-pt-zh/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ experiments/de-en-pt-zh/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ experiments/de-en-pt-zh/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ experiments/de-en-pt-zh/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ experiments/de-en-pt-zh/checkpoint-1580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ experiments/de-en-pt-zh/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
experiments/de-en-pt-zh/README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
3
+ library_name: transformers
4
+ model_name: de-en-pt-zh
5
+ tags:
6
+ - generated_from_trainer
7
+ - unsloth
8
+ - sft
9
+ - trl
10
+ licence: license
11
+ ---
12
+
13
+ # Model Card for de-en-pt-zh
14
+
15
+ This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-instruct-bnb-4bit](https://huggingface.co/unsloth/meta-llama-3.1-8b-instruct-bnb-4bit).
16
+ It has been trained using [TRL](https://github.com/huggingface/trl).
17
+
18
+ ## Quick start
19
+
20
+ ```python
21
+ from transformers import pipeline
22
+
23
+ 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?"
24
+ generator = pipeline("text-generation", model="None", device="cuda")
25
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
+ print(output["generated_text"])
27
+ ```
28
+
29
+ ## Training procedure
30
+
31
+
32
+
33
+
34
+ This model was trained with SFT.
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 0.22.2
39
+ - Transformers: 4.56.0
40
+ - Pytorch: 2.8.0+cu129
41
+ - Datasets: 4.3.0
42
+ - Tokenizers: 0.22.0
43
+
44
+ ## Citations
45
+
46
+
47
+
48
+ Cite TRL as:
49
+
50
+ ```bibtex
51
+ @misc{vonwerra2022trl,
52
+ title = {{TRL: Transformer Reinforcement Learning}},
53
+ 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},
54
+ year = 2020,
55
+ journal = {GitHub repository},
56
+ publisher = {GitHub},
57
+ howpublished = {\url{https://github.com/huggingface/trl}}
58
+ }
59
+ ```
experiments/de-en-pt-zh/adapter/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.1
experiments/de-en-pt-zh/adapter/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.1,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 8,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "gate_proj",
37
+ "v_proj",
38
+ "o_proj",
39
+ "k_proj",
40
+ "up_proj",
41
+ "down_proj",
42
+ "q_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true
50
+ }
experiments/de-en-pt-zh/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051126fb9ec33a14e0ca6905264f0cdf6fa6a95969cce1b5cbcee93a06dd58c9
3
+ size 83945296
experiments/de-en-pt-zh/adapter/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 %}
experiments/de-en-pt-zh/adapter/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
experiments/de-en-pt-zh/adapter/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
experiments/de-en-pt-zh/adapter/tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "left",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast",
2065
+ "unk_token": null
2066
+ }
experiments/de-en-pt-zh/checkpoint-1000/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.1
experiments/de-en-pt-zh/checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.1,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 8,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "gate_proj",
37
+ "v_proj",
38
+ "o_proj",
39
+ "k_proj",
40
+ "up_proj",
41
+ "down_proj",
42
+ "q_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true
50
+ }
experiments/de-en-pt-zh/checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834fddf3f3b4f812d71ea789ec5f3bbd9bcfa2780a0b2b89304b836e24b58e0c
3
+ size 83945296
experiments/de-en-pt-zh/checkpoint-1000/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 %}
experiments/de-en-pt-zh/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22cd44cbd6079206a3bdf28cd9def7b2fcd700d31537fcffc8b2cc7c716eff4
3
+ size 43123429
experiments/de-en-pt-zh/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead85b09410a86a07e70ed121bc4123b9656db163ec170d8c68860f53d32663b
3
+ size 14645
experiments/de-en-pt-zh/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b83d2b61763737893f22a960e5241e4b9d5d7cf00b6381e3c81c0dd6945f88
3
+ size 1465
experiments/de-en-pt-zh/checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
experiments/de-en-pt-zh/checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
experiments/de-en-pt-zh/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast",
2065
+ "unk_token": null
2066
+ }
experiments/de-en-pt-zh/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.1645569620253164,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015822784810126583,
14
+ "grad_norm": 6.080485820770264,
15
+ "learning_rate": 0.0002,
16
+ "loss": 2.7599,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03164556962025317,
21
+ "grad_norm": 1.6470410823822021,
22
+ "learning_rate": 0.00019936548223350255,
23
+ "loss": 0.8662,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04746835443037975,
28
+ "grad_norm": 1.656543254852295,
29
+ "learning_rate": 0.00019873096446700508,
30
+ "loss": 0.5796,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06329113924050633,
35
+ "grad_norm": 0.9287125468254089,
36
+ "learning_rate": 0.00019809644670050762,
37
+ "loss": 0.5521,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07911392405063292,
42
+ "grad_norm": 0.9500881433486938,
43
+ "learning_rate": 0.00019746192893401016,
44
+ "loss": 0.4879,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.0949367088607595,
49
+ "grad_norm": 0.6434516310691833,
50
+ "learning_rate": 0.00019682741116751272,
51
+ "loss": 0.467,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.11075949367088607,
56
+ "grad_norm": 0.8102421760559082,
57
+ "learning_rate": 0.00019619289340101523,
58
+ "loss": 0.4872,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12658227848101267,
63
+ "grad_norm": 0.8061529397964478,
64
+ "learning_rate": 0.00019555837563451777,
65
+ "loss": 0.4883,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.14240506329113925,
70
+ "grad_norm": 0.8552656769752502,
71
+ "learning_rate": 0.00019492385786802033,
72
+ "loss": 0.4634,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15822784810126583,
77
+ "grad_norm": 0.6702130436897278,
78
+ "learning_rate": 0.00019428934010152284,
79
+ "loss": 0.4606,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17405063291139242,
84
+ "grad_norm": 0.7621438503265381,
85
+ "learning_rate": 0.00019365482233502538,
86
+ "loss": 0.5159,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.189873417721519,
91
+ "grad_norm": 0.6256672143936157,
92
+ "learning_rate": 0.00019302030456852794,
93
+ "loss": 0.4818,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20569620253164558,
98
+ "grad_norm": 0.6232669353485107,
99
+ "learning_rate": 0.00019238578680203048,
100
+ "loss": 0.4926,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.22151898734177214,
105
+ "grad_norm": 0.6387396454811096,
106
+ "learning_rate": 0.000191751269035533,
107
+ "loss": 0.4841,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.23734177215189872,
112
+ "grad_norm": 0.6436880230903625,
113
+ "learning_rate": 0.00019111675126903555,
114
+ "loss": 0.4871,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.25316455696202533,
119
+ "grad_norm": 0.7336615920066833,
120
+ "learning_rate": 0.0001904822335025381,
121
+ "loss": 0.4568,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2689873417721519,
126
+ "grad_norm": 0.7388893961906433,
127
+ "learning_rate": 0.0001898477157360406,
128
+ "loss": 0.4553,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2848101265822785,
133
+ "grad_norm": 0.6054999828338623,
134
+ "learning_rate": 0.00018921319796954316,
135
+ "loss": 0.4405,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.30063291139240506,
140
+ "grad_norm": 0.7911633253097534,
141
+ "learning_rate": 0.0001885786802030457,
142
+ "loss": 0.5219,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31645569620253167,
147
+ "grad_norm": 0.5389903783798218,
148
+ "learning_rate": 0.00018794416243654824,
149
+ "loss": 0.4525,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.3322784810126582,
154
+ "grad_norm": 0.7426465749740601,
155
+ "learning_rate": 0.00018730964467005077,
156
+ "loss": 0.4856,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34810126582278483,
161
+ "grad_norm": 0.7140562534332275,
162
+ "learning_rate": 0.0001866751269035533,
163
+ "loss": 0.4918,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.3639240506329114,
168
+ "grad_norm": 0.624547004699707,
169
+ "learning_rate": 0.00018604060913705585,
170
+ "loss": 0.4806,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.379746835443038,
175
+ "grad_norm": 0.8368127942085266,
176
+ "learning_rate": 0.00018540609137055838,
177
+ "loss": 0.4915,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.39556962025316456,
182
+ "grad_norm": 0.6069784164428711,
183
+ "learning_rate": 0.00018477157360406092,
184
+ "loss": 0.485,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.41139240506329117,
189
+ "grad_norm": 0.6394964456558228,
190
+ "learning_rate": 0.00018413705583756346,
191
+ "loss": 0.4815,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4272151898734177,
196
+ "grad_norm": 0.6225919127464294,
197
+ "learning_rate": 0.000183502538071066,
198
+ "loss": 0.4744,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.4430379746835443,
203
+ "grad_norm": 0.7593483328819275,
204
+ "learning_rate": 0.00018286802030456853,
205
+ "loss": 0.4505,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4588607594936709,
210
+ "grad_norm": 0.5810648202896118,
211
+ "learning_rate": 0.00018223350253807107,
212
+ "loss": 0.435,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.47468354430379744,
217
+ "grad_norm": 0.7975546717643738,
218
+ "learning_rate": 0.00018159898477157363,
219
+ "loss": 0.4685,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.49050632911392406,
224
+ "grad_norm": 0.6529037356376648,
225
+ "learning_rate": 0.00018096446700507614,
226
+ "loss": 0.4089,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5063291139240507,
231
+ "grad_norm": 0.7088711857795715,
232
+ "learning_rate": 0.00018032994923857868,
233
+ "loss": 0.4388,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5221518987341772,
238
+ "grad_norm": 0.5964807271957397,
239
+ "learning_rate": 0.00017969543147208124,
240
+ "loss": 0.4104,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5379746835443038,
245
+ "grad_norm": 0.6564443707466125,
246
+ "learning_rate": 0.00017906091370558375,
247
+ "loss": 0.4717,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5537974683544303,
252
+ "grad_norm": 0.6912603974342346,
253
+ "learning_rate": 0.0001784263959390863,
254
+ "loss": 0.4528,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.569620253164557,
259
+ "grad_norm": 0.6068799495697021,
260
+ "learning_rate": 0.00017779187817258885,
261
+ "loss": 0.4714,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5854430379746836,
266
+ "grad_norm": 0.6037777066230774,
267
+ "learning_rate": 0.0001771573604060914,
268
+ "loss": 0.5058,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.6012658227848101,
273
+ "grad_norm": 0.586581826210022,
274
+ "learning_rate": 0.0001765228426395939,
275
+ "loss": 0.439,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6170886075949367,
280
+ "grad_norm": 0.6780263185501099,
281
+ "learning_rate": 0.00017588832487309646,
282
+ "loss": 0.4269,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6329113924050633,
287
+ "grad_norm": 0.7488175630569458,
288
+ "learning_rate": 0.000175253807106599,
289
+ "loss": 0.4481,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6487341772151899,
294
+ "grad_norm": 0.6138256788253784,
295
+ "learning_rate": 0.0001746192893401015,
296
+ "loss": 0.4654,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6645569620253164,
301
+ "grad_norm": 0.7444900274276733,
302
+ "learning_rate": 0.00017398477157360407,
303
+ "loss": 0.4165,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.680379746835443,
308
+ "grad_norm": 0.6231881380081177,
309
+ "learning_rate": 0.0001733502538071066,
310
+ "loss": 0.4469,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6962025316455697,
315
+ "grad_norm": 0.6703267097473145,
316
+ "learning_rate": 0.00017271573604060915,
317
+ "loss": 0.4279,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7120253164556962,
322
+ "grad_norm": 0.4783850312232971,
323
+ "learning_rate": 0.00017208121827411168,
324
+ "loss": 0.4654,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7278481012658228,
329
+ "grad_norm": 0.7536376118659973,
330
+ "learning_rate": 0.00017144670050761422,
331
+ "loss": 0.4537,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7436708860759493,
336
+ "grad_norm": 0.7595057487487793,
337
+ "learning_rate": 0.00017081218274111676,
338
+ "loss": 0.486,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.759493670886076,
343
+ "grad_norm": 0.8007245659828186,
344
+ "learning_rate": 0.0001701776649746193,
345
+ "loss": 0.3919,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7753164556962026,
350
+ "grad_norm": 0.6637867093086243,
351
+ "learning_rate": 0.00016954314720812183,
352
+ "loss": 0.418,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7911392405063291,
357
+ "grad_norm": 0.653685986995697,
358
+ "learning_rate": 0.00016890862944162437,
359
+ "loss": 0.4326,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.8069620253164557,
364
+ "grad_norm": 0.6465121507644653,
365
+ "learning_rate": 0.00016827411167512693,
366
+ "loss": 0.445,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8227848101265823,
371
+ "grad_norm": 0.6836300492286682,
372
+ "learning_rate": 0.00016763959390862944,
373
+ "loss": 0.4348,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8386075949367089,
378
+ "grad_norm": 0.7092205882072449,
379
+ "learning_rate": 0.00016700507614213198,
380
+ "loss": 0.4081,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8544303797468354,
385
+ "grad_norm": 0.7940587997436523,
386
+ "learning_rate": 0.00016637055837563454,
387
+ "loss": 0.4316,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.870253164556962,
392
+ "grad_norm": 0.6765463352203369,
393
+ "learning_rate": 0.00016573604060913705,
394
+ "loss": 0.45,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8860759493670886,
399
+ "grad_norm": 0.8914448022842407,
400
+ "learning_rate": 0.0001651015228426396,
401
+ "loss": 0.4202,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.9018987341772152,
406
+ "grad_norm": 0.6309791207313538,
407
+ "learning_rate": 0.00016446700507614215,
408
+ "loss": 0.4308,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9177215189873418,
413
+ "grad_norm": 0.7343917489051819,
414
+ "learning_rate": 0.0001638324873096447,
415
+ "loss": 0.4387,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9335443037974683,
420
+ "grad_norm": 0.5776176452636719,
421
+ "learning_rate": 0.0001631979695431472,
422
+ "loss": 0.4239,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9493670886075949,
427
+ "grad_norm": 0.6677407026290894,
428
+ "learning_rate": 0.00016256345177664976,
429
+ "loss": 0.4481,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9651898734177216,
434
+ "grad_norm": 0.6818298101425171,
435
+ "learning_rate": 0.0001619289340101523,
436
+ "loss": 0.4089,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9810126582278481,
441
+ "grad_norm": 0.9606236219406128,
442
+ "learning_rate": 0.0001612944162436548,
443
+ "loss": 0.4491,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9968354430379747,
448
+ "grad_norm": 0.6414772272109985,
449
+ "learning_rate": 0.00016065989847715737,
450
+ "loss": 0.4639,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.0126582278481013,
455
+ "grad_norm": 0.5724285244941711,
456
+ "learning_rate": 0.0001600253807106599,
457
+ "loss": 0.3448,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0284810126582278,
462
+ "grad_norm": 0.8723211884498596,
463
+ "learning_rate": 0.00015939086294416242,
464
+ "loss": 0.3483,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0443037974683544,
469
+ "grad_norm": 0.6645333170890808,
470
+ "learning_rate": 0.00015875634517766498,
471
+ "loss": 0.3136,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0601265822784811,
476
+ "grad_norm": 0.7657269239425659,
477
+ "learning_rate": 0.00015812182741116752,
478
+ "loss": 0.3426,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0759493670886076,
483
+ "grad_norm": 0.6551052927970886,
484
+ "learning_rate": 0.00015748730964467006,
485
+ "loss": 0.3482,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0917721518987342,
490
+ "grad_norm": 0.7337777018547058,
491
+ "learning_rate": 0.0001568527918781726,
492
+ "loss": 0.3128,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.1075949367088607,
497
+ "grad_norm": 0.8943917751312256,
498
+ "learning_rate": 0.00015621827411167513,
499
+ "loss": 0.3134,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1234177215189873,
504
+ "grad_norm": 0.71893310546875,
505
+ "learning_rate": 0.00015558375634517767,
506
+ "loss": 0.2815,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.139240506329114,
511
+ "grad_norm": 0.7433806657791138,
512
+ "learning_rate": 0.0001549492385786802,
513
+ "loss": 0.3216,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.1550632911392404,
518
+ "grad_norm": 0.7051471471786499,
519
+ "learning_rate": 0.00015431472081218274,
520
+ "loss": 0.3719,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1708860759493671,
525
+ "grad_norm": 0.6804415583610535,
526
+ "learning_rate": 0.00015368020304568528,
527
+ "loss": 0.3449,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1867088607594938,
532
+ "grad_norm": 0.9129506945610046,
533
+ "learning_rate": 0.00015304568527918784,
534
+ "loss": 0.3574,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.2025316455696202,
539
+ "grad_norm": 0.8387975692749023,
540
+ "learning_rate": 0.00015241116751269035,
541
+ "loss": 0.3321,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.2183544303797469,
546
+ "grad_norm": 0.689298152923584,
547
+ "learning_rate": 0.0001517766497461929,
548
+ "loss": 0.3156,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.2341772151898733,
553
+ "grad_norm": 0.681196928024292,
554
+ "learning_rate": 0.00015114213197969545,
555
+ "loss": 0.3371,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.25,
560
+ "grad_norm": 0.8151982426643372,
561
+ "learning_rate": 0.00015050761421319796,
562
+ "loss": 0.3356,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2658227848101267,
567
+ "grad_norm": 0.789669394493103,
568
+ "learning_rate": 0.0001498730964467005,
569
+ "loss": 0.3063,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2816455696202531,
574
+ "grad_norm": 0.7262426614761353,
575
+ "learning_rate": 0.00014923857868020306,
576
+ "loss": 0.3179,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2974683544303798,
581
+ "grad_norm": 0.717400074005127,
582
+ "learning_rate": 0.0001486040609137056,
583
+ "loss": 0.3266,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.3132911392405062,
588
+ "grad_norm": 0.8459286093711853,
589
+ "learning_rate": 0.0001479695431472081,
590
+ "loss": 0.3323,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3291139240506329,
595
+ "grad_norm": 0.831169843673706,
596
+ "learning_rate": 0.00014733502538071067,
597
+ "loss": 0.3101,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3449367088607596,
602
+ "grad_norm": 0.6811087727546692,
603
+ "learning_rate": 0.0001467005076142132,
604
+ "loss": 0.3166,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.360759493670886,
609
+ "grad_norm": 0.813766360282898,
610
+ "learning_rate": 0.00014606598984771572,
611
+ "loss": 0.3274,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3765822784810127,
616
+ "grad_norm": 0.7633799314498901,
617
+ "learning_rate": 0.00014543147208121828,
618
+ "loss": 0.3351,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3924050632911391,
623
+ "grad_norm": 0.7631050944328308,
624
+ "learning_rate": 0.00014479695431472082,
625
+ "loss": 0.3045,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.4082278481012658,
630
+ "grad_norm": 0.8526734709739685,
631
+ "learning_rate": 0.00014416243654822336,
632
+ "loss": 0.3479,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4240506329113924,
637
+ "grad_norm": 0.7672425508499146,
638
+ "learning_rate": 0.0001435279187817259,
639
+ "loss": 0.3302,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.439873417721519,
644
+ "grad_norm": 0.8053662776947021,
645
+ "learning_rate": 0.00014289340101522843,
646
+ "loss": 0.2994,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4556962025316456,
651
+ "grad_norm": 0.9087522625923157,
652
+ "learning_rate": 0.00014225888324873097,
653
+ "loss": 0.3233,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4715189873417722,
658
+ "grad_norm": 0.7690944075584412,
659
+ "learning_rate": 0.0001416243654822335,
660
+ "loss": 0.2887,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4873417721518987,
665
+ "grad_norm": 0.8058143854141235,
666
+ "learning_rate": 0.00014098984771573604,
667
+ "loss": 0.2982,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.5031645569620253,
672
+ "grad_norm": 0.7568528056144714,
673
+ "learning_rate": 0.00014035532994923858,
674
+ "loss": 0.3103,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.518987341772152,
679
+ "grad_norm": 0.755690336227417,
680
+ "learning_rate": 0.00013972081218274114,
681
+ "loss": 0.3009,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5348101265822784,
686
+ "grad_norm": 0.8576112985610962,
687
+ "learning_rate": 0.00013908629441624365,
688
+ "loss": 0.3317,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.5506329113924051,
693
+ "grad_norm": 0.8156176805496216,
694
+ "learning_rate": 0.0001384517766497462,
695
+ "loss": 0.3187,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5664556962025316,
700
+ "grad_norm": 0.8467602729797363,
701
+ "learning_rate": 0.00013781725888324875,
702
+ "loss": 0.3155,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5822784810126582,
707
+ "grad_norm": 0.8999772071838379,
708
+ "learning_rate": 0.00013718274111675126,
709
+ "loss": 0.3402,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5981012658227849,
714
+ "grad_norm": 0.808548092842102,
715
+ "learning_rate": 0.0001365482233502538,
716
+ "loss": 0.296,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.6139240506329116,
721
+ "grad_norm": 0.7033184170722961,
722
+ "learning_rate": 0.00013591370558375636,
723
+ "loss": 0.3052,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.629746835443038,
728
+ "grad_norm": 0.8576298356056213,
729
+ "learning_rate": 0.00013527918781725887,
730
+ "loss": 0.3253,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6455696202531644,
735
+ "grad_norm": 0.6722769141197205,
736
+ "learning_rate": 0.0001346446700507614,
737
+ "loss": 0.2941,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6613924050632911,
742
+ "grad_norm": 0.6628623008728027,
743
+ "learning_rate": 0.00013401015228426397,
744
+ "loss": 0.3016,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6772151898734178,
749
+ "grad_norm": 0.9596195220947266,
750
+ "learning_rate": 0.0001333756345177665,
751
+ "loss": 0.3234,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6930379746835444,
756
+ "grad_norm": 0.8452304005622864,
757
+ "learning_rate": 0.00013274111675126905,
758
+ "loss": 0.3458,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.7088607594936709,
763
+ "grad_norm": 0.7414538860321045,
764
+ "learning_rate": 0.00013210659898477158,
765
+ "loss": 0.3133,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.7246835443037973,
770
+ "grad_norm": 0.6833527088165283,
771
+ "learning_rate": 0.00013147208121827412,
772
+ "loss": 0.3008,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.740506329113924,
777
+ "grad_norm": 0.8556643724441528,
778
+ "learning_rate": 0.00013083756345177666,
779
+ "loss": 0.3035,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7563291139240507,
784
+ "grad_norm": 0.9071274399757385,
785
+ "learning_rate": 0.0001302030456852792,
786
+ "loss": 0.304,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7721518987341773,
791
+ "grad_norm": 1.0122044086456299,
792
+ "learning_rate": 0.00012956852791878173,
793
+ "loss": 0.2956,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7879746835443038,
798
+ "grad_norm": 0.9109578132629395,
799
+ "learning_rate": 0.00012893401015228427,
800
+ "loss": 0.3101,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.8037974683544302,
805
+ "grad_norm": 0.9648177623748779,
806
+ "learning_rate": 0.0001282994923857868,
807
+ "loss": 0.2987,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.8196202531645569,
812
+ "grad_norm": 0.8060092926025391,
813
+ "learning_rate": 0.00012766497461928934,
814
+ "loss": 0.3011,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.8354430379746836,
819
+ "grad_norm": 0.7650238871574402,
820
+ "learning_rate": 0.00012703045685279188,
821
+ "loss": 0.3207,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8512658227848102,
826
+ "grad_norm": 1.0391228199005127,
827
+ "learning_rate": 0.00012639593908629442,
828
+ "loss": 0.3,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.8670886075949367,
833
+ "grad_norm": 0.7758641242980957,
834
+ "learning_rate": 0.00012576142131979695,
835
+ "loss": 0.3109,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8829113924050633,
840
+ "grad_norm": 0.819521427154541,
841
+ "learning_rate": 0.0001251269035532995,
842
+ "loss": 0.2921,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8987341772151898,
847
+ "grad_norm": 0.7439246773719788,
848
+ "learning_rate": 0.00012449238578680205,
849
+ "loss": 0.3091,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.9145569620253164,
854
+ "grad_norm": 0.8022212386131287,
855
+ "learning_rate": 0.00012385786802030456,
856
+ "loss": 0.3252,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.9303797468354431,
861
+ "grad_norm": 1.0216495990753174,
862
+ "learning_rate": 0.0001232233502538071,
863
+ "loss": 0.3434,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9462025316455698,
868
+ "grad_norm": 0.821251630783081,
869
+ "learning_rate": 0.00012258883248730966,
870
+ "loss": 0.325,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9620253164556962,
875
+ "grad_norm": 0.744149386882782,
876
+ "learning_rate": 0.00012195431472081217,
877
+ "loss": 0.3286,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.9778481012658227,
882
+ "grad_norm": 0.8488931655883789,
883
+ "learning_rate": 0.00012131979695431472,
884
+ "loss": 0.3048,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.9936708860759493,
889
+ "grad_norm": 0.8845570087432861,
890
+ "learning_rate": 0.00012068527918781727,
891
+ "loss": 0.3027,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.009493670886076,
896
+ "grad_norm": 0.6925209164619446,
897
+ "learning_rate": 0.00012005076142131981,
898
+ "loss": 0.2111,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.0253164556962027,
903
+ "grad_norm": 1.101040244102478,
904
+ "learning_rate": 0.00011941624365482233,
905
+ "loss": 0.1921,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.041139240506329,
910
+ "grad_norm": 1.030375361442566,
911
+ "learning_rate": 0.00011878172588832489,
912
+ "loss": 0.1878,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.0569620253164556,
917
+ "grad_norm": 0.8349786996841431,
918
+ "learning_rate": 0.00011814720812182742,
919
+ "loss": 0.1839,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.0727848101265822,
924
+ "grad_norm": 0.7567915320396423,
925
+ "learning_rate": 0.00011751269035532995,
926
+ "loss": 0.1978,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.088607594936709,
931
+ "grad_norm": 0.9065817594528198,
932
+ "learning_rate": 0.0001168781725888325,
933
+ "loss": 0.1904,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.1044303797468356,
938
+ "grad_norm": 0.8686302900314331,
939
+ "learning_rate": 0.00011624365482233503,
940
+ "loss": 0.1898,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.1202531645569622,
945
+ "grad_norm": 0.81605064868927,
946
+ "learning_rate": 0.00011560913705583758,
947
+ "loss": 0.186,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.1360759493670884,
952
+ "grad_norm": 0.8041939735412598,
953
+ "learning_rate": 0.0001149746192893401,
954
+ "loss": 0.1988,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.151898734177215,
959
+ "grad_norm": 0.9789828658103943,
960
+ "learning_rate": 0.00011434010152284264,
961
+ "loss": 0.1886,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1677215189873418,
966
+ "grad_norm": 0.822130560874939,
967
+ "learning_rate": 0.0001137055837563452,
968
+ "loss": 0.1903,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1835443037974684,
973
+ "grad_norm": 0.8661246299743652,
974
+ "learning_rate": 0.00011307106598984772,
975
+ "loss": 0.1911,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.199367088607595,
980
+ "grad_norm": 0.814487636089325,
981
+ "learning_rate": 0.00011243654822335025,
982
+ "loss": 0.1801,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.2151898734177213,
987
+ "grad_norm": 0.9888129830360413,
988
+ "learning_rate": 0.0001118020304568528,
989
+ "loss": 0.1859,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.231012658227848,
994
+ "grad_norm": 0.790763258934021,
995
+ "learning_rate": 0.00011116751269035533,
996
+ "loss": 0.1834,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2468354430379747,
1001
+ "grad_norm": 0.7045260667800903,
1002
+ "learning_rate": 0.00011053299492385786,
1003
+ "loss": 0.1769,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.2626582278481013,
1008
+ "grad_norm": 0.8450356125831604,
1009
+ "learning_rate": 0.00010989847715736041,
1010
+ "loss": 0.1912,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.278481012658228,
1015
+ "grad_norm": 0.9821575284004211,
1016
+ "learning_rate": 0.00010926395939086295,
1017
+ "loss": 0.194,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2943037974683547,
1022
+ "grad_norm": 0.827716588973999,
1023
+ "learning_rate": 0.00010862944162436547,
1024
+ "loss": 0.1952,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.310126582278481,
1029
+ "grad_norm": 1.0735716819763184,
1030
+ "learning_rate": 0.00010799492385786802,
1031
+ "loss": 0.1962,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.3259493670886076,
1036
+ "grad_norm": 0.759575605392456,
1037
+ "learning_rate": 0.00010736040609137057,
1038
+ "loss": 0.1899,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.3417721518987342,
1043
+ "grad_norm": 1.0905171632766724,
1044
+ "learning_rate": 0.00010672588832487308,
1045
+ "loss": 0.1836,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.357594936708861,
1050
+ "grad_norm": 0.9864721894264221,
1051
+ "learning_rate": 0.00010609137055837564,
1052
+ "loss": 0.1988,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.3734177215189876,
1057
+ "grad_norm": 0.8583397269248962,
1058
+ "learning_rate": 0.00010545685279187819,
1059
+ "loss": 0.2032,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3892405063291138,
1064
+ "grad_norm": 0.8750898241996765,
1065
+ "learning_rate": 0.00010482233502538072,
1066
+ "loss": 0.1913,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.4050632911392404,
1071
+ "grad_norm": 0.8484179377555847,
1072
+ "learning_rate": 0.00010418781725888325,
1073
+ "loss": 0.1932,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.420886075949367,
1078
+ "grad_norm": 0.8363800048828125,
1079
+ "learning_rate": 0.0001035532994923858,
1080
+ "loss": 0.1961,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.4367088607594938,
1085
+ "grad_norm": 1.0165894031524658,
1086
+ "learning_rate": 0.00010291878172588833,
1087
+ "loss": 0.1997,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4525316455696204,
1092
+ "grad_norm": 0.9139420986175537,
1093
+ "learning_rate": 0.00010228426395939086,
1094
+ "loss": 0.185,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.4683544303797467,
1099
+ "grad_norm": 0.8798001408576965,
1100
+ "learning_rate": 0.0001016497461928934,
1101
+ "loss": 0.1842,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.4841772151898733,
1106
+ "grad_norm": 0.8399237394332886,
1107
+ "learning_rate": 0.00010101522842639594,
1108
+ "loss": 0.1759,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.5,
1113
+ "grad_norm": 0.883194625377655,
1114
+ "learning_rate": 0.0001003807106598985,
1115
+ "loss": 0.2027,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.5158227848101267,
1120
+ "grad_norm": 1.1090173721313477,
1121
+ "learning_rate": 9.974619289340103e-05,
1122
+ "loss": 0.192,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.5316455696202533,
1127
+ "grad_norm": 0.8255505561828613,
1128
+ "learning_rate": 9.911167512690355e-05,
1129
+ "loss": 0.1962,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.5474683544303796,
1134
+ "grad_norm": 1.0160300731658936,
1135
+ "learning_rate": 9.847715736040609e-05,
1136
+ "loss": 0.1932,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.5632911392405062,
1141
+ "grad_norm": 0.7054086327552795,
1142
+ "learning_rate": 9.784263959390864e-05,
1143
+ "loss": 0.186,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.579113924050633,
1148
+ "grad_norm": 0.7671273946762085,
1149
+ "learning_rate": 9.720812182741116e-05,
1150
+ "loss": 0.1851,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5949367088607596,
1155
+ "grad_norm": 0.9428186416625977,
1156
+ "learning_rate": 9.657360406091371e-05,
1157
+ "loss": 0.1903,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.6107594936708862,
1162
+ "grad_norm": 0.8303772807121277,
1163
+ "learning_rate": 9.593908629441625e-05,
1164
+ "loss": 0.1877,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.6265822784810124,
1169
+ "grad_norm": 0.9931467175483704,
1170
+ "learning_rate": 9.530456852791879e-05,
1171
+ "loss": 0.2038,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.642405063291139,
1176
+ "grad_norm": 0.8338640928268433,
1177
+ "learning_rate": 9.467005076142132e-05,
1178
+ "loss": 0.1782,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.6582278481012658,
1183
+ "grad_norm": 1.0357074737548828,
1184
+ "learning_rate": 9.403553299492386e-05,
1185
+ "loss": 0.204,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6740506329113924,
1190
+ "grad_norm": 0.7227370142936707,
1191
+ "learning_rate": 9.34010152284264e-05,
1192
+ "loss": 0.1871,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.689873417721519,
1197
+ "grad_norm": 0.8483996987342834,
1198
+ "learning_rate": 9.276649746192894e-05,
1199
+ "loss": 0.1884,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.7056962025316453,
1204
+ "grad_norm": 0.7692596912384033,
1205
+ "learning_rate": 9.213197969543149e-05,
1206
+ "loss": 0.1987,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.721518987341772,
1211
+ "grad_norm": 0.9548447728157043,
1212
+ "learning_rate": 9.149746192893401e-05,
1213
+ "loss": 0.1836,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.7373417721518987,
1218
+ "grad_norm": 0.9363961219787598,
1219
+ "learning_rate": 9.086294416243655e-05,
1220
+ "loss": 0.1815,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.7531645569620253,
1225
+ "grad_norm": 1.0330653190612793,
1226
+ "learning_rate": 9.02284263959391e-05,
1227
+ "loss": 0.1957,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.768987341772152,
1232
+ "grad_norm": 0.8239451050758362,
1233
+ "learning_rate": 8.959390862944162e-05,
1234
+ "loss": 0.1945,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7848101265822782,
1239
+ "grad_norm": 0.7226342558860779,
1240
+ "learning_rate": 8.895939086294417e-05,
1241
+ "loss": 0.1819,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.8006329113924053,
1246
+ "grad_norm": 1.2467807531356812,
1247
+ "learning_rate": 8.83248730964467e-05,
1248
+ "loss": 0.1723,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.8164556962025316,
1253
+ "grad_norm": 0.8140600919723511,
1254
+ "learning_rate": 8.769035532994924e-05,
1255
+ "loss": 0.1898,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.8322784810126582,
1260
+ "grad_norm": 0.8722625970840454,
1261
+ "learning_rate": 8.705583756345178e-05,
1262
+ "loss": 0.1895,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.848101265822785,
1267
+ "grad_norm": 1.1079012155532837,
1268
+ "learning_rate": 8.642131979695432e-05,
1269
+ "loss": 0.1999,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8639240506329116,
1274
+ "grad_norm": 0.8730645775794983,
1275
+ "learning_rate": 8.578680203045685e-05,
1276
+ "loss": 0.1891,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.879746835443038,
1281
+ "grad_norm": 0.9077411890029907,
1282
+ "learning_rate": 8.515228426395939e-05,
1283
+ "loss": 0.1756,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.8955696202531644,
1288
+ "grad_norm": 0.9811768531799316,
1289
+ "learning_rate": 8.451776649746194e-05,
1290
+ "loss": 0.1937,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.911392405063291,
1295
+ "grad_norm": 0.8190383911132812,
1296
+ "learning_rate": 8.388324873096446e-05,
1297
+ "loss": 0.1947,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.9272151898734178,
1302
+ "grad_norm": 1.0100188255310059,
1303
+ "learning_rate": 8.324873096446701e-05,
1304
+ "loss": 0.2103,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.9430379746835444,
1309
+ "grad_norm": 0.7750146389007568,
1310
+ "learning_rate": 8.261421319796955e-05,
1311
+ "loss": 0.1828,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.958860759493671,
1316
+ "grad_norm": 0.7670167684555054,
1317
+ "learning_rate": 8.197969543147207e-05,
1318
+ "loss": 0.1848,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.9746835443037973,
1323
+ "grad_norm": 0.7348405718803406,
1324
+ "learning_rate": 8.134517766497463e-05,
1325
+ "loss": 0.1852,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.990506329113924,
1330
+ "grad_norm": 0.8744247555732727,
1331
+ "learning_rate": 8.071065989847716e-05,
1332
+ "loss": 0.1878,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 3.0063291139240507,
1337
+ "grad_norm": 0.5043367743492126,
1338
+ "learning_rate": 8.00761421319797e-05,
1339
+ "loss": 0.153,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 3.0221518987341773,
1344
+ "grad_norm": 0.5560520887374878,
1345
+ "learning_rate": 7.944162436548224e-05,
1346
+ "loss": 0.1149,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 3.037974683544304,
1351
+ "grad_norm": 0.8911687135696411,
1352
+ "learning_rate": 7.880710659898477e-05,
1353
+ "loss": 0.1172,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 3.0537974683544302,
1358
+ "grad_norm": 0.7934268116950989,
1359
+ "learning_rate": 7.817258883248731e-05,
1360
+ "loss": 0.1155,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.069620253164557,
1365
+ "grad_norm": 0.6288787722587585,
1366
+ "learning_rate": 7.753807106598985e-05,
1367
+ "loss": 0.1079,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 3.0854430379746836,
1372
+ "grad_norm": 0.6213780641555786,
1373
+ "learning_rate": 7.69035532994924e-05,
1374
+ "loss": 0.1196,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 3.1012658227848102,
1379
+ "grad_norm": 0.8186531066894531,
1380
+ "learning_rate": 7.626903553299492e-05,
1381
+ "loss": 0.1215,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 3.117088607594937,
1386
+ "grad_norm": 0.6212114691734314,
1387
+ "learning_rate": 7.563451776649747e-05,
1388
+ "loss": 0.1222,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 3.132911392405063,
1393
+ "grad_norm": 0.6861391067504883,
1394
+ "learning_rate": 7.500000000000001e-05,
1395
+ "loss": 0.1142,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 3.1487341772151898,
1400
+ "grad_norm": 0.5754695534706116,
1401
+ "learning_rate": 7.436548223350253e-05,
1402
+ "loss": 0.1144,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 3.1645569620253164,
1407
+ "grad_norm": 0.9572857022285461,
1408
+ "learning_rate": 7.373096446700508e-05,
1409
+ "loss": 0.1157,
1410
+ "step": 1000
1411
+ }
1412
+ ],
1413
+ "logging_steps": 5,
1414
+ "max_steps": 1580,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 5,
1417
+ "save_steps": 500,
1418
+ "stateful_callbacks": {
1419
+ "TrainerControl": {
1420
+ "args": {
1421
+ "should_epoch_stop": false,
1422
+ "should_evaluate": false,
1423
+ "should_log": false,
1424
+ "should_save": true,
1425
+ "should_training_stop": false
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 8.683279684499866e+16,
1431
+ "train_batch_size": 16,
1432
+ "trial_name": null,
1433
+ "trial_params": null
1434
+ }
experiments/de-en-pt-zh/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1f965478a30d642e1d3280129a9cb365127c4096496511633d6b72e8ccf15e
3
+ size 6289
experiments/de-en-pt-zh/checkpoint-1500/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.1
experiments/de-en-pt-zh/checkpoint-1500/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.1,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 8,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "gate_proj",
37
+ "v_proj",
38
+ "o_proj",
39
+ "k_proj",
40
+ "up_proj",
41
+ "down_proj",
42
+ "q_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true
50
+ }
experiments/de-en-pt-zh/checkpoint-1500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50eb536131a48802399250e219fd00b6ea71a00bcf3351d537e6dd4fe59afdbb
3
+ size 83945296
experiments/de-en-pt-zh/checkpoint-1500/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 %}
experiments/de-en-pt-zh/checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b514a5abaf55dd7ec34b72a3ebd43a6ff564cc076e1e85206f192beb7fc93c5f
3
+ size 43123429
experiments/de-en-pt-zh/checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c790abd0eaf70f617b2b2cfddcb2e808817e6bea31b87435b9f860fc0067e13a
3
+ size 14645
experiments/de-en-pt-zh/checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220f36a0a4023e86d7b17400d7984cec7692207b558d19ef4561ba0236be8bf8
3
+ size 1465
experiments/de-en-pt-zh/checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
experiments/de-en-pt-zh/checkpoint-1500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
experiments/de-en-pt-zh/checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast",
2065
+ "unk_token": null
2066
+ }
experiments/de-en-pt-zh/checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,2134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.746835443037975,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015822784810126583,
14
+ "grad_norm": 6.080485820770264,
15
+ "learning_rate": 0.0002,
16
+ "loss": 2.7599,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03164556962025317,
21
+ "grad_norm": 1.6470410823822021,
22
+ "learning_rate": 0.00019936548223350255,
23
+ "loss": 0.8662,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04746835443037975,
28
+ "grad_norm": 1.656543254852295,
29
+ "learning_rate": 0.00019873096446700508,
30
+ "loss": 0.5796,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06329113924050633,
35
+ "grad_norm": 0.9287125468254089,
36
+ "learning_rate": 0.00019809644670050762,
37
+ "loss": 0.5521,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07911392405063292,
42
+ "grad_norm": 0.9500881433486938,
43
+ "learning_rate": 0.00019746192893401016,
44
+ "loss": 0.4879,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.0949367088607595,
49
+ "grad_norm": 0.6434516310691833,
50
+ "learning_rate": 0.00019682741116751272,
51
+ "loss": 0.467,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.11075949367088607,
56
+ "grad_norm": 0.8102421760559082,
57
+ "learning_rate": 0.00019619289340101523,
58
+ "loss": 0.4872,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12658227848101267,
63
+ "grad_norm": 0.8061529397964478,
64
+ "learning_rate": 0.00019555837563451777,
65
+ "loss": 0.4883,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.14240506329113925,
70
+ "grad_norm": 0.8552656769752502,
71
+ "learning_rate": 0.00019492385786802033,
72
+ "loss": 0.4634,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15822784810126583,
77
+ "grad_norm": 0.6702130436897278,
78
+ "learning_rate": 0.00019428934010152284,
79
+ "loss": 0.4606,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17405063291139242,
84
+ "grad_norm": 0.7621438503265381,
85
+ "learning_rate": 0.00019365482233502538,
86
+ "loss": 0.5159,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.189873417721519,
91
+ "grad_norm": 0.6256672143936157,
92
+ "learning_rate": 0.00019302030456852794,
93
+ "loss": 0.4818,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20569620253164558,
98
+ "grad_norm": 0.6232669353485107,
99
+ "learning_rate": 0.00019238578680203048,
100
+ "loss": 0.4926,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.22151898734177214,
105
+ "grad_norm": 0.6387396454811096,
106
+ "learning_rate": 0.000191751269035533,
107
+ "loss": 0.4841,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.23734177215189872,
112
+ "grad_norm": 0.6436880230903625,
113
+ "learning_rate": 0.00019111675126903555,
114
+ "loss": 0.4871,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.25316455696202533,
119
+ "grad_norm": 0.7336615920066833,
120
+ "learning_rate": 0.0001904822335025381,
121
+ "loss": 0.4568,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2689873417721519,
126
+ "grad_norm": 0.7388893961906433,
127
+ "learning_rate": 0.0001898477157360406,
128
+ "loss": 0.4553,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2848101265822785,
133
+ "grad_norm": 0.6054999828338623,
134
+ "learning_rate": 0.00018921319796954316,
135
+ "loss": 0.4405,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.30063291139240506,
140
+ "grad_norm": 0.7911633253097534,
141
+ "learning_rate": 0.0001885786802030457,
142
+ "loss": 0.5219,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31645569620253167,
147
+ "grad_norm": 0.5389903783798218,
148
+ "learning_rate": 0.00018794416243654824,
149
+ "loss": 0.4525,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.3322784810126582,
154
+ "grad_norm": 0.7426465749740601,
155
+ "learning_rate": 0.00018730964467005077,
156
+ "loss": 0.4856,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34810126582278483,
161
+ "grad_norm": 0.7140562534332275,
162
+ "learning_rate": 0.0001866751269035533,
163
+ "loss": 0.4918,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.3639240506329114,
168
+ "grad_norm": 0.624547004699707,
169
+ "learning_rate": 0.00018604060913705585,
170
+ "loss": 0.4806,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.379746835443038,
175
+ "grad_norm": 0.8368127942085266,
176
+ "learning_rate": 0.00018540609137055838,
177
+ "loss": 0.4915,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.39556962025316456,
182
+ "grad_norm": 0.6069784164428711,
183
+ "learning_rate": 0.00018477157360406092,
184
+ "loss": 0.485,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.41139240506329117,
189
+ "grad_norm": 0.6394964456558228,
190
+ "learning_rate": 0.00018413705583756346,
191
+ "loss": 0.4815,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4272151898734177,
196
+ "grad_norm": 0.6225919127464294,
197
+ "learning_rate": 0.000183502538071066,
198
+ "loss": 0.4744,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.4430379746835443,
203
+ "grad_norm": 0.7593483328819275,
204
+ "learning_rate": 0.00018286802030456853,
205
+ "loss": 0.4505,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4588607594936709,
210
+ "grad_norm": 0.5810648202896118,
211
+ "learning_rate": 0.00018223350253807107,
212
+ "loss": 0.435,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.47468354430379744,
217
+ "grad_norm": 0.7975546717643738,
218
+ "learning_rate": 0.00018159898477157363,
219
+ "loss": 0.4685,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.49050632911392406,
224
+ "grad_norm": 0.6529037356376648,
225
+ "learning_rate": 0.00018096446700507614,
226
+ "loss": 0.4089,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5063291139240507,
231
+ "grad_norm": 0.7088711857795715,
232
+ "learning_rate": 0.00018032994923857868,
233
+ "loss": 0.4388,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5221518987341772,
238
+ "grad_norm": 0.5964807271957397,
239
+ "learning_rate": 0.00017969543147208124,
240
+ "loss": 0.4104,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5379746835443038,
245
+ "grad_norm": 0.6564443707466125,
246
+ "learning_rate": 0.00017906091370558375,
247
+ "loss": 0.4717,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5537974683544303,
252
+ "grad_norm": 0.6912603974342346,
253
+ "learning_rate": 0.0001784263959390863,
254
+ "loss": 0.4528,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.569620253164557,
259
+ "grad_norm": 0.6068799495697021,
260
+ "learning_rate": 0.00017779187817258885,
261
+ "loss": 0.4714,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5854430379746836,
266
+ "grad_norm": 0.6037777066230774,
267
+ "learning_rate": 0.0001771573604060914,
268
+ "loss": 0.5058,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.6012658227848101,
273
+ "grad_norm": 0.586581826210022,
274
+ "learning_rate": 0.0001765228426395939,
275
+ "loss": 0.439,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6170886075949367,
280
+ "grad_norm": 0.6780263185501099,
281
+ "learning_rate": 0.00017588832487309646,
282
+ "loss": 0.4269,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6329113924050633,
287
+ "grad_norm": 0.7488175630569458,
288
+ "learning_rate": 0.000175253807106599,
289
+ "loss": 0.4481,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6487341772151899,
294
+ "grad_norm": 0.6138256788253784,
295
+ "learning_rate": 0.0001746192893401015,
296
+ "loss": 0.4654,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6645569620253164,
301
+ "grad_norm": 0.7444900274276733,
302
+ "learning_rate": 0.00017398477157360407,
303
+ "loss": 0.4165,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.680379746835443,
308
+ "grad_norm": 0.6231881380081177,
309
+ "learning_rate": 0.0001733502538071066,
310
+ "loss": 0.4469,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6962025316455697,
315
+ "grad_norm": 0.6703267097473145,
316
+ "learning_rate": 0.00017271573604060915,
317
+ "loss": 0.4279,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7120253164556962,
322
+ "grad_norm": 0.4783850312232971,
323
+ "learning_rate": 0.00017208121827411168,
324
+ "loss": 0.4654,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7278481012658228,
329
+ "grad_norm": 0.7536376118659973,
330
+ "learning_rate": 0.00017144670050761422,
331
+ "loss": 0.4537,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7436708860759493,
336
+ "grad_norm": 0.7595057487487793,
337
+ "learning_rate": 0.00017081218274111676,
338
+ "loss": 0.486,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.759493670886076,
343
+ "grad_norm": 0.8007245659828186,
344
+ "learning_rate": 0.0001701776649746193,
345
+ "loss": 0.3919,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7753164556962026,
350
+ "grad_norm": 0.6637867093086243,
351
+ "learning_rate": 0.00016954314720812183,
352
+ "loss": 0.418,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7911392405063291,
357
+ "grad_norm": 0.653685986995697,
358
+ "learning_rate": 0.00016890862944162437,
359
+ "loss": 0.4326,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.8069620253164557,
364
+ "grad_norm": 0.6465121507644653,
365
+ "learning_rate": 0.00016827411167512693,
366
+ "loss": 0.445,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8227848101265823,
371
+ "grad_norm": 0.6836300492286682,
372
+ "learning_rate": 0.00016763959390862944,
373
+ "loss": 0.4348,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8386075949367089,
378
+ "grad_norm": 0.7092205882072449,
379
+ "learning_rate": 0.00016700507614213198,
380
+ "loss": 0.4081,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8544303797468354,
385
+ "grad_norm": 0.7940587997436523,
386
+ "learning_rate": 0.00016637055837563454,
387
+ "loss": 0.4316,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.870253164556962,
392
+ "grad_norm": 0.6765463352203369,
393
+ "learning_rate": 0.00016573604060913705,
394
+ "loss": 0.45,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8860759493670886,
399
+ "grad_norm": 0.8914448022842407,
400
+ "learning_rate": 0.0001651015228426396,
401
+ "loss": 0.4202,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.9018987341772152,
406
+ "grad_norm": 0.6309791207313538,
407
+ "learning_rate": 0.00016446700507614215,
408
+ "loss": 0.4308,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9177215189873418,
413
+ "grad_norm": 0.7343917489051819,
414
+ "learning_rate": 0.0001638324873096447,
415
+ "loss": 0.4387,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9335443037974683,
420
+ "grad_norm": 0.5776176452636719,
421
+ "learning_rate": 0.0001631979695431472,
422
+ "loss": 0.4239,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9493670886075949,
427
+ "grad_norm": 0.6677407026290894,
428
+ "learning_rate": 0.00016256345177664976,
429
+ "loss": 0.4481,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9651898734177216,
434
+ "grad_norm": 0.6818298101425171,
435
+ "learning_rate": 0.0001619289340101523,
436
+ "loss": 0.4089,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9810126582278481,
441
+ "grad_norm": 0.9606236219406128,
442
+ "learning_rate": 0.0001612944162436548,
443
+ "loss": 0.4491,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9968354430379747,
448
+ "grad_norm": 0.6414772272109985,
449
+ "learning_rate": 0.00016065989847715737,
450
+ "loss": 0.4639,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.0126582278481013,
455
+ "grad_norm": 0.5724285244941711,
456
+ "learning_rate": 0.0001600253807106599,
457
+ "loss": 0.3448,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0284810126582278,
462
+ "grad_norm": 0.8723211884498596,
463
+ "learning_rate": 0.00015939086294416242,
464
+ "loss": 0.3483,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0443037974683544,
469
+ "grad_norm": 0.6645333170890808,
470
+ "learning_rate": 0.00015875634517766498,
471
+ "loss": 0.3136,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0601265822784811,
476
+ "grad_norm": 0.7657269239425659,
477
+ "learning_rate": 0.00015812182741116752,
478
+ "loss": 0.3426,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0759493670886076,
483
+ "grad_norm": 0.6551052927970886,
484
+ "learning_rate": 0.00015748730964467006,
485
+ "loss": 0.3482,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0917721518987342,
490
+ "grad_norm": 0.7337777018547058,
491
+ "learning_rate": 0.0001568527918781726,
492
+ "loss": 0.3128,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.1075949367088607,
497
+ "grad_norm": 0.8943917751312256,
498
+ "learning_rate": 0.00015621827411167513,
499
+ "loss": 0.3134,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1234177215189873,
504
+ "grad_norm": 0.71893310546875,
505
+ "learning_rate": 0.00015558375634517767,
506
+ "loss": 0.2815,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.139240506329114,
511
+ "grad_norm": 0.7433806657791138,
512
+ "learning_rate": 0.0001549492385786802,
513
+ "loss": 0.3216,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.1550632911392404,
518
+ "grad_norm": 0.7051471471786499,
519
+ "learning_rate": 0.00015431472081218274,
520
+ "loss": 0.3719,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1708860759493671,
525
+ "grad_norm": 0.6804415583610535,
526
+ "learning_rate": 0.00015368020304568528,
527
+ "loss": 0.3449,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1867088607594938,
532
+ "grad_norm": 0.9129506945610046,
533
+ "learning_rate": 0.00015304568527918784,
534
+ "loss": 0.3574,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.2025316455696202,
539
+ "grad_norm": 0.8387975692749023,
540
+ "learning_rate": 0.00015241116751269035,
541
+ "loss": 0.3321,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.2183544303797469,
546
+ "grad_norm": 0.689298152923584,
547
+ "learning_rate": 0.0001517766497461929,
548
+ "loss": 0.3156,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.2341772151898733,
553
+ "grad_norm": 0.681196928024292,
554
+ "learning_rate": 0.00015114213197969545,
555
+ "loss": 0.3371,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.25,
560
+ "grad_norm": 0.8151982426643372,
561
+ "learning_rate": 0.00015050761421319796,
562
+ "loss": 0.3356,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2658227848101267,
567
+ "grad_norm": 0.789669394493103,
568
+ "learning_rate": 0.0001498730964467005,
569
+ "loss": 0.3063,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2816455696202531,
574
+ "grad_norm": 0.7262426614761353,
575
+ "learning_rate": 0.00014923857868020306,
576
+ "loss": 0.3179,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2974683544303798,
581
+ "grad_norm": 0.717400074005127,
582
+ "learning_rate": 0.0001486040609137056,
583
+ "loss": 0.3266,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.3132911392405062,
588
+ "grad_norm": 0.8459286093711853,
589
+ "learning_rate": 0.0001479695431472081,
590
+ "loss": 0.3323,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3291139240506329,
595
+ "grad_norm": 0.831169843673706,
596
+ "learning_rate": 0.00014733502538071067,
597
+ "loss": 0.3101,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3449367088607596,
602
+ "grad_norm": 0.6811087727546692,
603
+ "learning_rate": 0.0001467005076142132,
604
+ "loss": 0.3166,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.360759493670886,
609
+ "grad_norm": 0.813766360282898,
610
+ "learning_rate": 0.00014606598984771572,
611
+ "loss": 0.3274,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3765822784810127,
616
+ "grad_norm": 0.7633799314498901,
617
+ "learning_rate": 0.00014543147208121828,
618
+ "loss": 0.3351,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3924050632911391,
623
+ "grad_norm": 0.7631050944328308,
624
+ "learning_rate": 0.00014479695431472082,
625
+ "loss": 0.3045,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.4082278481012658,
630
+ "grad_norm": 0.8526734709739685,
631
+ "learning_rate": 0.00014416243654822336,
632
+ "loss": 0.3479,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4240506329113924,
637
+ "grad_norm": 0.7672425508499146,
638
+ "learning_rate": 0.0001435279187817259,
639
+ "loss": 0.3302,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.439873417721519,
644
+ "grad_norm": 0.8053662776947021,
645
+ "learning_rate": 0.00014289340101522843,
646
+ "loss": 0.2994,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4556962025316456,
651
+ "grad_norm": 0.9087522625923157,
652
+ "learning_rate": 0.00014225888324873097,
653
+ "loss": 0.3233,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4715189873417722,
658
+ "grad_norm": 0.7690944075584412,
659
+ "learning_rate": 0.0001416243654822335,
660
+ "loss": 0.2887,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4873417721518987,
665
+ "grad_norm": 0.8058143854141235,
666
+ "learning_rate": 0.00014098984771573604,
667
+ "loss": 0.2982,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.5031645569620253,
672
+ "grad_norm": 0.7568528056144714,
673
+ "learning_rate": 0.00014035532994923858,
674
+ "loss": 0.3103,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.518987341772152,
679
+ "grad_norm": 0.755690336227417,
680
+ "learning_rate": 0.00013972081218274114,
681
+ "loss": 0.3009,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5348101265822784,
686
+ "grad_norm": 0.8576112985610962,
687
+ "learning_rate": 0.00013908629441624365,
688
+ "loss": 0.3317,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.5506329113924051,
693
+ "grad_norm": 0.8156176805496216,
694
+ "learning_rate": 0.0001384517766497462,
695
+ "loss": 0.3187,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5664556962025316,
700
+ "grad_norm": 0.8467602729797363,
701
+ "learning_rate": 0.00013781725888324875,
702
+ "loss": 0.3155,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5822784810126582,
707
+ "grad_norm": 0.8999772071838379,
708
+ "learning_rate": 0.00013718274111675126,
709
+ "loss": 0.3402,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5981012658227849,
714
+ "grad_norm": 0.808548092842102,
715
+ "learning_rate": 0.0001365482233502538,
716
+ "loss": 0.296,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.6139240506329116,
721
+ "grad_norm": 0.7033184170722961,
722
+ "learning_rate": 0.00013591370558375636,
723
+ "loss": 0.3052,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.629746835443038,
728
+ "grad_norm": 0.8576298356056213,
729
+ "learning_rate": 0.00013527918781725887,
730
+ "loss": 0.3253,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6455696202531644,
735
+ "grad_norm": 0.6722769141197205,
736
+ "learning_rate": 0.0001346446700507614,
737
+ "loss": 0.2941,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6613924050632911,
742
+ "grad_norm": 0.6628623008728027,
743
+ "learning_rate": 0.00013401015228426397,
744
+ "loss": 0.3016,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6772151898734178,
749
+ "grad_norm": 0.9596195220947266,
750
+ "learning_rate": 0.0001333756345177665,
751
+ "loss": 0.3234,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6930379746835444,
756
+ "grad_norm": 0.8452304005622864,
757
+ "learning_rate": 0.00013274111675126905,
758
+ "loss": 0.3458,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.7088607594936709,
763
+ "grad_norm": 0.7414538860321045,
764
+ "learning_rate": 0.00013210659898477158,
765
+ "loss": 0.3133,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.7246835443037973,
770
+ "grad_norm": 0.6833527088165283,
771
+ "learning_rate": 0.00013147208121827412,
772
+ "loss": 0.3008,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.740506329113924,
777
+ "grad_norm": 0.8556643724441528,
778
+ "learning_rate": 0.00013083756345177666,
779
+ "loss": 0.3035,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7563291139240507,
784
+ "grad_norm": 0.9071274399757385,
785
+ "learning_rate": 0.0001302030456852792,
786
+ "loss": 0.304,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7721518987341773,
791
+ "grad_norm": 1.0122044086456299,
792
+ "learning_rate": 0.00012956852791878173,
793
+ "loss": 0.2956,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7879746835443038,
798
+ "grad_norm": 0.9109578132629395,
799
+ "learning_rate": 0.00012893401015228427,
800
+ "loss": 0.3101,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.8037974683544302,
805
+ "grad_norm": 0.9648177623748779,
806
+ "learning_rate": 0.0001282994923857868,
807
+ "loss": 0.2987,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.8196202531645569,
812
+ "grad_norm": 0.8060092926025391,
813
+ "learning_rate": 0.00012766497461928934,
814
+ "loss": 0.3011,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.8354430379746836,
819
+ "grad_norm": 0.7650238871574402,
820
+ "learning_rate": 0.00012703045685279188,
821
+ "loss": 0.3207,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8512658227848102,
826
+ "grad_norm": 1.0391228199005127,
827
+ "learning_rate": 0.00012639593908629442,
828
+ "loss": 0.3,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.8670886075949367,
833
+ "grad_norm": 0.7758641242980957,
834
+ "learning_rate": 0.00012576142131979695,
835
+ "loss": 0.3109,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8829113924050633,
840
+ "grad_norm": 0.819521427154541,
841
+ "learning_rate": 0.0001251269035532995,
842
+ "loss": 0.2921,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8987341772151898,
847
+ "grad_norm": 0.7439246773719788,
848
+ "learning_rate": 0.00012449238578680205,
849
+ "loss": 0.3091,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.9145569620253164,
854
+ "grad_norm": 0.8022212386131287,
855
+ "learning_rate": 0.00012385786802030456,
856
+ "loss": 0.3252,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.9303797468354431,
861
+ "grad_norm": 1.0216495990753174,
862
+ "learning_rate": 0.0001232233502538071,
863
+ "loss": 0.3434,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9462025316455698,
868
+ "grad_norm": 0.821251630783081,
869
+ "learning_rate": 0.00012258883248730966,
870
+ "loss": 0.325,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9620253164556962,
875
+ "grad_norm": 0.744149386882782,
876
+ "learning_rate": 0.00012195431472081217,
877
+ "loss": 0.3286,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.9778481012658227,
882
+ "grad_norm": 0.8488931655883789,
883
+ "learning_rate": 0.00012131979695431472,
884
+ "loss": 0.3048,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.9936708860759493,
889
+ "grad_norm": 0.8845570087432861,
890
+ "learning_rate": 0.00012068527918781727,
891
+ "loss": 0.3027,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.009493670886076,
896
+ "grad_norm": 0.6925209164619446,
897
+ "learning_rate": 0.00012005076142131981,
898
+ "loss": 0.2111,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.0253164556962027,
903
+ "grad_norm": 1.101040244102478,
904
+ "learning_rate": 0.00011941624365482233,
905
+ "loss": 0.1921,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.041139240506329,
910
+ "grad_norm": 1.030375361442566,
911
+ "learning_rate": 0.00011878172588832489,
912
+ "loss": 0.1878,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.0569620253164556,
917
+ "grad_norm": 0.8349786996841431,
918
+ "learning_rate": 0.00011814720812182742,
919
+ "loss": 0.1839,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.0727848101265822,
924
+ "grad_norm": 0.7567915320396423,
925
+ "learning_rate": 0.00011751269035532995,
926
+ "loss": 0.1978,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.088607594936709,
931
+ "grad_norm": 0.9065817594528198,
932
+ "learning_rate": 0.0001168781725888325,
933
+ "loss": 0.1904,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.1044303797468356,
938
+ "grad_norm": 0.8686302900314331,
939
+ "learning_rate": 0.00011624365482233503,
940
+ "loss": 0.1898,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.1202531645569622,
945
+ "grad_norm": 0.81605064868927,
946
+ "learning_rate": 0.00011560913705583758,
947
+ "loss": 0.186,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.1360759493670884,
952
+ "grad_norm": 0.8041939735412598,
953
+ "learning_rate": 0.0001149746192893401,
954
+ "loss": 0.1988,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.151898734177215,
959
+ "grad_norm": 0.9789828658103943,
960
+ "learning_rate": 0.00011434010152284264,
961
+ "loss": 0.1886,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1677215189873418,
966
+ "grad_norm": 0.822130560874939,
967
+ "learning_rate": 0.0001137055837563452,
968
+ "loss": 0.1903,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1835443037974684,
973
+ "grad_norm": 0.8661246299743652,
974
+ "learning_rate": 0.00011307106598984772,
975
+ "loss": 0.1911,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.199367088607595,
980
+ "grad_norm": 0.814487636089325,
981
+ "learning_rate": 0.00011243654822335025,
982
+ "loss": 0.1801,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.2151898734177213,
987
+ "grad_norm": 0.9888129830360413,
988
+ "learning_rate": 0.0001118020304568528,
989
+ "loss": 0.1859,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.231012658227848,
994
+ "grad_norm": 0.790763258934021,
995
+ "learning_rate": 0.00011116751269035533,
996
+ "loss": 0.1834,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2468354430379747,
1001
+ "grad_norm": 0.7045260667800903,
1002
+ "learning_rate": 0.00011053299492385786,
1003
+ "loss": 0.1769,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.2626582278481013,
1008
+ "grad_norm": 0.8450356125831604,
1009
+ "learning_rate": 0.00010989847715736041,
1010
+ "loss": 0.1912,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.278481012658228,
1015
+ "grad_norm": 0.9821575284004211,
1016
+ "learning_rate": 0.00010926395939086295,
1017
+ "loss": 0.194,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2943037974683547,
1022
+ "grad_norm": 0.827716588973999,
1023
+ "learning_rate": 0.00010862944162436547,
1024
+ "loss": 0.1952,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.310126582278481,
1029
+ "grad_norm": 1.0735716819763184,
1030
+ "learning_rate": 0.00010799492385786802,
1031
+ "loss": 0.1962,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.3259493670886076,
1036
+ "grad_norm": 0.759575605392456,
1037
+ "learning_rate": 0.00010736040609137057,
1038
+ "loss": 0.1899,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.3417721518987342,
1043
+ "grad_norm": 1.0905171632766724,
1044
+ "learning_rate": 0.00010672588832487308,
1045
+ "loss": 0.1836,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.357594936708861,
1050
+ "grad_norm": 0.9864721894264221,
1051
+ "learning_rate": 0.00010609137055837564,
1052
+ "loss": 0.1988,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.3734177215189876,
1057
+ "grad_norm": 0.8583397269248962,
1058
+ "learning_rate": 0.00010545685279187819,
1059
+ "loss": 0.2032,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3892405063291138,
1064
+ "grad_norm": 0.8750898241996765,
1065
+ "learning_rate": 0.00010482233502538072,
1066
+ "loss": 0.1913,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.4050632911392404,
1071
+ "grad_norm": 0.8484179377555847,
1072
+ "learning_rate": 0.00010418781725888325,
1073
+ "loss": 0.1932,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.420886075949367,
1078
+ "grad_norm": 0.8363800048828125,
1079
+ "learning_rate": 0.0001035532994923858,
1080
+ "loss": 0.1961,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.4367088607594938,
1085
+ "grad_norm": 1.0165894031524658,
1086
+ "learning_rate": 0.00010291878172588833,
1087
+ "loss": 0.1997,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4525316455696204,
1092
+ "grad_norm": 0.9139420986175537,
1093
+ "learning_rate": 0.00010228426395939086,
1094
+ "loss": 0.185,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.4683544303797467,
1099
+ "grad_norm": 0.8798001408576965,
1100
+ "learning_rate": 0.0001016497461928934,
1101
+ "loss": 0.1842,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.4841772151898733,
1106
+ "grad_norm": 0.8399237394332886,
1107
+ "learning_rate": 0.00010101522842639594,
1108
+ "loss": 0.1759,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.5,
1113
+ "grad_norm": 0.883194625377655,
1114
+ "learning_rate": 0.0001003807106598985,
1115
+ "loss": 0.2027,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.5158227848101267,
1120
+ "grad_norm": 1.1090173721313477,
1121
+ "learning_rate": 9.974619289340103e-05,
1122
+ "loss": 0.192,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.5316455696202533,
1127
+ "grad_norm": 0.8255505561828613,
1128
+ "learning_rate": 9.911167512690355e-05,
1129
+ "loss": 0.1962,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.5474683544303796,
1134
+ "grad_norm": 1.0160300731658936,
1135
+ "learning_rate": 9.847715736040609e-05,
1136
+ "loss": 0.1932,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.5632911392405062,
1141
+ "grad_norm": 0.7054086327552795,
1142
+ "learning_rate": 9.784263959390864e-05,
1143
+ "loss": 0.186,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.579113924050633,
1148
+ "grad_norm": 0.7671273946762085,
1149
+ "learning_rate": 9.720812182741116e-05,
1150
+ "loss": 0.1851,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5949367088607596,
1155
+ "grad_norm": 0.9428186416625977,
1156
+ "learning_rate": 9.657360406091371e-05,
1157
+ "loss": 0.1903,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.6107594936708862,
1162
+ "grad_norm": 0.8303772807121277,
1163
+ "learning_rate": 9.593908629441625e-05,
1164
+ "loss": 0.1877,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.6265822784810124,
1169
+ "grad_norm": 0.9931467175483704,
1170
+ "learning_rate": 9.530456852791879e-05,
1171
+ "loss": 0.2038,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.642405063291139,
1176
+ "grad_norm": 0.8338640928268433,
1177
+ "learning_rate": 9.467005076142132e-05,
1178
+ "loss": 0.1782,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.6582278481012658,
1183
+ "grad_norm": 1.0357074737548828,
1184
+ "learning_rate": 9.403553299492386e-05,
1185
+ "loss": 0.204,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6740506329113924,
1190
+ "grad_norm": 0.7227370142936707,
1191
+ "learning_rate": 9.34010152284264e-05,
1192
+ "loss": 0.1871,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.689873417721519,
1197
+ "grad_norm": 0.8483996987342834,
1198
+ "learning_rate": 9.276649746192894e-05,
1199
+ "loss": 0.1884,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.7056962025316453,
1204
+ "grad_norm": 0.7692596912384033,
1205
+ "learning_rate": 9.213197969543149e-05,
1206
+ "loss": 0.1987,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.721518987341772,
1211
+ "grad_norm": 0.9548447728157043,
1212
+ "learning_rate": 9.149746192893401e-05,
1213
+ "loss": 0.1836,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.7373417721518987,
1218
+ "grad_norm": 0.9363961219787598,
1219
+ "learning_rate": 9.086294416243655e-05,
1220
+ "loss": 0.1815,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.7531645569620253,
1225
+ "grad_norm": 1.0330653190612793,
1226
+ "learning_rate": 9.02284263959391e-05,
1227
+ "loss": 0.1957,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.768987341772152,
1232
+ "grad_norm": 0.8239451050758362,
1233
+ "learning_rate": 8.959390862944162e-05,
1234
+ "loss": 0.1945,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7848101265822782,
1239
+ "grad_norm": 0.7226342558860779,
1240
+ "learning_rate": 8.895939086294417e-05,
1241
+ "loss": 0.1819,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.8006329113924053,
1246
+ "grad_norm": 1.2467807531356812,
1247
+ "learning_rate": 8.83248730964467e-05,
1248
+ "loss": 0.1723,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.8164556962025316,
1253
+ "grad_norm": 0.8140600919723511,
1254
+ "learning_rate": 8.769035532994924e-05,
1255
+ "loss": 0.1898,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.8322784810126582,
1260
+ "grad_norm": 0.8722625970840454,
1261
+ "learning_rate": 8.705583756345178e-05,
1262
+ "loss": 0.1895,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.848101265822785,
1267
+ "grad_norm": 1.1079012155532837,
1268
+ "learning_rate": 8.642131979695432e-05,
1269
+ "loss": 0.1999,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8639240506329116,
1274
+ "grad_norm": 0.8730645775794983,
1275
+ "learning_rate": 8.578680203045685e-05,
1276
+ "loss": 0.1891,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.879746835443038,
1281
+ "grad_norm": 0.9077411890029907,
1282
+ "learning_rate": 8.515228426395939e-05,
1283
+ "loss": 0.1756,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.8955696202531644,
1288
+ "grad_norm": 0.9811768531799316,
1289
+ "learning_rate": 8.451776649746194e-05,
1290
+ "loss": 0.1937,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.911392405063291,
1295
+ "grad_norm": 0.8190383911132812,
1296
+ "learning_rate": 8.388324873096446e-05,
1297
+ "loss": 0.1947,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.9272151898734178,
1302
+ "grad_norm": 1.0100188255310059,
1303
+ "learning_rate": 8.324873096446701e-05,
1304
+ "loss": 0.2103,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.9430379746835444,
1309
+ "grad_norm": 0.7750146389007568,
1310
+ "learning_rate": 8.261421319796955e-05,
1311
+ "loss": 0.1828,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.958860759493671,
1316
+ "grad_norm": 0.7670167684555054,
1317
+ "learning_rate": 8.197969543147207e-05,
1318
+ "loss": 0.1848,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.9746835443037973,
1323
+ "grad_norm": 0.7348405718803406,
1324
+ "learning_rate": 8.134517766497463e-05,
1325
+ "loss": 0.1852,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.990506329113924,
1330
+ "grad_norm": 0.8744247555732727,
1331
+ "learning_rate": 8.071065989847716e-05,
1332
+ "loss": 0.1878,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 3.0063291139240507,
1337
+ "grad_norm": 0.5043367743492126,
1338
+ "learning_rate": 8.00761421319797e-05,
1339
+ "loss": 0.153,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 3.0221518987341773,
1344
+ "grad_norm": 0.5560520887374878,
1345
+ "learning_rate": 7.944162436548224e-05,
1346
+ "loss": 0.1149,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 3.037974683544304,
1351
+ "grad_norm": 0.8911687135696411,
1352
+ "learning_rate": 7.880710659898477e-05,
1353
+ "loss": 0.1172,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 3.0537974683544302,
1358
+ "grad_norm": 0.7934268116950989,
1359
+ "learning_rate": 7.817258883248731e-05,
1360
+ "loss": 0.1155,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.069620253164557,
1365
+ "grad_norm": 0.6288787722587585,
1366
+ "learning_rate": 7.753807106598985e-05,
1367
+ "loss": 0.1079,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 3.0854430379746836,
1372
+ "grad_norm": 0.6213780641555786,
1373
+ "learning_rate": 7.69035532994924e-05,
1374
+ "loss": 0.1196,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 3.1012658227848102,
1379
+ "grad_norm": 0.8186531066894531,
1380
+ "learning_rate": 7.626903553299492e-05,
1381
+ "loss": 0.1215,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 3.117088607594937,
1386
+ "grad_norm": 0.6212114691734314,
1387
+ "learning_rate": 7.563451776649747e-05,
1388
+ "loss": 0.1222,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 3.132911392405063,
1393
+ "grad_norm": 0.6861391067504883,
1394
+ "learning_rate": 7.500000000000001e-05,
1395
+ "loss": 0.1142,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 3.1487341772151898,
1400
+ "grad_norm": 0.5754695534706116,
1401
+ "learning_rate": 7.436548223350253e-05,
1402
+ "loss": 0.1144,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 3.1645569620253164,
1407
+ "grad_norm": 0.9572857022285461,
1408
+ "learning_rate": 7.373096446700508e-05,
1409
+ "loss": 0.1157,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 3.180379746835443,
1414
+ "grad_norm": 0.6589420437812805,
1415
+ "learning_rate": 7.309644670050762e-05,
1416
+ "loss": 0.1195,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 3.1962025316455698,
1421
+ "grad_norm": 0.7942759990692139,
1422
+ "learning_rate": 7.246192893401015e-05,
1423
+ "loss": 0.1199,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 3.212025316455696,
1428
+ "grad_norm": 0.7023386359214783,
1429
+ "learning_rate": 7.182741116751269e-05,
1430
+ "loss": 0.1198,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 3.2278481012658227,
1435
+ "grad_norm": 0.5077189207077026,
1436
+ "learning_rate": 7.119289340101524e-05,
1437
+ "loss": 0.1193,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 3.2436708860759493,
1442
+ "grad_norm": 1.0440549850463867,
1443
+ "learning_rate": 7.055837563451776e-05,
1444
+ "loss": 0.1141,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 3.259493670886076,
1449
+ "grad_norm": 0.6728818416595459,
1450
+ "learning_rate": 6.99238578680203e-05,
1451
+ "loss": 0.1184,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 3.2753164556962027,
1456
+ "grad_norm": 0.6550622582435608,
1457
+ "learning_rate": 6.928934010152285e-05,
1458
+ "loss": 0.1207,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 3.291139240506329,
1463
+ "grad_norm": 0.9485641121864319,
1464
+ "learning_rate": 6.865482233502538e-05,
1465
+ "loss": 0.1185,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 3.3069620253164556,
1470
+ "grad_norm": 0.7015439867973328,
1471
+ "learning_rate": 6.802030456852793e-05,
1472
+ "loss": 0.1166,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 3.3227848101265822,
1477
+ "grad_norm": 0.7128148674964905,
1478
+ "learning_rate": 6.738578680203046e-05,
1479
+ "loss": 0.1211,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 3.338607594936709,
1484
+ "grad_norm": 0.8616880178451538,
1485
+ "learning_rate": 6.6751269035533e-05,
1486
+ "loss": 0.1224,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 3.3544303797468356,
1491
+ "grad_norm": 1.673384189605713,
1492
+ "learning_rate": 6.611675126903554e-05,
1493
+ "loss": 0.1125,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 3.370253164556962,
1498
+ "grad_norm": 0.7952456474304199,
1499
+ "learning_rate": 6.548223350253807e-05,
1500
+ "loss": 0.1196,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 3.3860759493670884,
1505
+ "grad_norm": 0.7431464791297913,
1506
+ "learning_rate": 6.484771573604061e-05,
1507
+ "loss": 0.1172,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 3.401898734177215,
1512
+ "grad_norm": 0.9536241292953491,
1513
+ "learning_rate": 6.421319796954315e-05,
1514
+ "loss": 0.1227,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 3.4177215189873418,
1519
+ "grad_norm": 0.6027010679244995,
1520
+ "learning_rate": 6.35786802030457e-05,
1521
+ "loss": 0.1183,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 3.4335443037974684,
1526
+ "grad_norm": 0.6765082478523254,
1527
+ "learning_rate": 6.294416243654822e-05,
1528
+ "loss": 0.1222,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 3.449367088607595,
1533
+ "grad_norm": 0.8334203958511353,
1534
+ "learning_rate": 6.230964467005076e-05,
1535
+ "loss": 0.1188,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 3.4651898734177213,
1540
+ "grad_norm": 0.7078428864479065,
1541
+ "learning_rate": 6.167512690355331e-05,
1542
+ "loss": 0.1237,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 3.481012658227848,
1547
+ "grad_norm": 0.5793551206588745,
1548
+ "learning_rate": 6.104060913705584e-05,
1549
+ "loss": 0.1171,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 3.4968354430379747,
1554
+ "grad_norm": 0.816104531288147,
1555
+ "learning_rate": 6.040609137055838e-05,
1556
+ "loss": 0.1216,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 3.5126582278481013,
1561
+ "grad_norm": 0.5165361166000366,
1562
+ "learning_rate": 5.977157360406092e-05,
1563
+ "loss": 0.123,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 3.528481012658228,
1568
+ "grad_norm": 0.7187574505805969,
1569
+ "learning_rate": 5.913705583756346e-05,
1570
+ "loss": 0.1196,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 3.5443037974683547,
1575
+ "grad_norm": 0.8947055339813232,
1576
+ "learning_rate": 5.850253807106599e-05,
1577
+ "loss": 0.121,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 3.560126582278481,
1582
+ "grad_norm": 0.6461635828018188,
1583
+ "learning_rate": 5.786802030456853e-05,
1584
+ "loss": 0.1171,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 3.5759493670886076,
1589
+ "grad_norm": 0.5806897282600403,
1590
+ "learning_rate": 5.723350253807107e-05,
1591
+ "loss": 0.1095,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 3.5917721518987342,
1596
+ "grad_norm": 0.48626071214675903,
1597
+ "learning_rate": 5.65989847715736e-05,
1598
+ "loss": 0.117,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 3.607594936708861,
1603
+ "grad_norm": 0.7649936079978943,
1604
+ "learning_rate": 5.5964467005076145e-05,
1605
+ "loss": 0.1214,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 3.6234177215189876,
1610
+ "grad_norm": 0.8777173757553101,
1611
+ "learning_rate": 5.532994923857868e-05,
1612
+ "loss": 0.126,
1613
+ "step": 1145
1614
+ },
1615
+ {
1616
+ "epoch": 3.6392405063291138,
1617
+ "grad_norm": 0.7628064155578613,
1618
+ "learning_rate": 5.469543147208121e-05,
1619
+ "loss": 0.1194,
1620
+ "step": 1150
1621
+ },
1622
+ {
1623
+ "epoch": 3.6550632911392404,
1624
+ "grad_norm": 0.6170560717582703,
1625
+ "learning_rate": 5.406091370558376e-05,
1626
+ "loss": 0.119,
1627
+ "step": 1155
1628
+ },
1629
+ {
1630
+ "epoch": 3.670886075949367,
1631
+ "grad_norm": 0.6344670057296753,
1632
+ "learning_rate": 5.342639593908629e-05,
1633
+ "loss": 0.1153,
1634
+ "step": 1160
1635
+ },
1636
+ {
1637
+ "epoch": 3.6867088607594938,
1638
+ "grad_norm": 0.6660630702972412,
1639
+ "learning_rate": 5.2791878172588836e-05,
1640
+ "loss": 0.1224,
1641
+ "step": 1165
1642
+ },
1643
+ {
1644
+ "epoch": 3.7025316455696204,
1645
+ "grad_norm": 0.7865625619888306,
1646
+ "learning_rate": 5.215736040609137e-05,
1647
+ "loss": 0.1257,
1648
+ "step": 1170
1649
+ },
1650
+ {
1651
+ "epoch": 3.7183544303797467,
1652
+ "grad_norm": 0.611803412437439,
1653
+ "learning_rate": 5.152284263959392e-05,
1654
+ "loss": 0.1195,
1655
+ "step": 1175
1656
+ },
1657
+ {
1658
+ "epoch": 3.7341772151898733,
1659
+ "grad_norm": 0.9372175931930542,
1660
+ "learning_rate": 5.088832487309645e-05,
1661
+ "loss": 0.1239,
1662
+ "step": 1180
1663
+ },
1664
+ {
1665
+ "epoch": 3.75,
1666
+ "grad_norm": 0.6816895008087158,
1667
+ "learning_rate": 5.0253807106598984e-05,
1668
+ "loss": 0.1228,
1669
+ "step": 1185
1670
+ },
1671
+ {
1672
+ "epoch": 3.7658227848101267,
1673
+ "grad_norm": 0.5107612013816833,
1674
+ "learning_rate": 4.961928934010153e-05,
1675
+ "loss": 0.1171,
1676
+ "step": 1190
1677
+ },
1678
+ {
1679
+ "epoch": 3.7816455696202533,
1680
+ "grad_norm": 0.5778011679649353,
1681
+ "learning_rate": 4.8984771573604064e-05,
1682
+ "loss": 0.1253,
1683
+ "step": 1195
1684
+ },
1685
+ {
1686
+ "epoch": 3.7974683544303796,
1687
+ "grad_norm": 0.7186105251312256,
1688
+ "learning_rate": 4.83502538071066e-05,
1689
+ "loss": 0.1155,
1690
+ "step": 1200
1691
+ },
1692
+ {
1693
+ "epoch": 3.8132911392405062,
1694
+ "grad_norm": 0.7445695996284485,
1695
+ "learning_rate": 4.771573604060914e-05,
1696
+ "loss": 0.1176,
1697
+ "step": 1205
1698
+ },
1699
+ {
1700
+ "epoch": 3.829113924050633,
1701
+ "grad_norm": 0.593574047088623,
1702
+ "learning_rate": 4.7081218274111674e-05,
1703
+ "loss": 0.1158,
1704
+ "step": 1210
1705
+ },
1706
+ {
1707
+ "epoch": 3.8449367088607596,
1708
+ "grad_norm": 0.5334892272949219,
1709
+ "learning_rate": 4.644670050761422e-05,
1710
+ "loss": 0.1172,
1711
+ "step": 1215
1712
+ },
1713
+ {
1714
+ "epoch": 3.8607594936708862,
1715
+ "grad_norm": 0.5709195137023926,
1716
+ "learning_rate": 4.5812182741116755e-05,
1717
+ "loss": 0.1158,
1718
+ "step": 1220
1719
+ },
1720
+ {
1721
+ "epoch": 3.8765822784810124,
1722
+ "grad_norm": 0.6969111561775208,
1723
+ "learning_rate": 4.517766497461929e-05,
1724
+ "loss": 0.1198,
1725
+ "step": 1225
1726
+ },
1727
+ {
1728
+ "epoch": 3.892405063291139,
1729
+ "grad_norm": 0.5967200398445129,
1730
+ "learning_rate": 4.454314720812183e-05,
1731
+ "loss": 0.115,
1732
+ "step": 1230
1733
+ },
1734
+ {
1735
+ "epoch": 3.9082278481012658,
1736
+ "grad_norm": 0.6755451560020447,
1737
+ "learning_rate": 4.3908629441624365e-05,
1738
+ "loss": 0.1171,
1739
+ "step": 1235
1740
+ },
1741
+ {
1742
+ "epoch": 3.9240506329113924,
1743
+ "grad_norm": 0.7690590620040894,
1744
+ "learning_rate": 4.32741116751269e-05,
1745
+ "loss": 0.117,
1746
+ "step": 1240
1747
+ },
1748
+ {
1749
+ "epoch": 3.939873417721519,
1750
+ "grad_norm": 0.7448693513870239,
1751
+ "learning_rate": 4.2639593908629446e-05,
1752
+ "loss": 0.1183,
1753
+ "step": 1245
1754
+ },
1755
+ {
1756
+ "epoch": 3.9556962025316453,
1757
+ "grad_norm": 0.6257800459861755,
1758
+ "learning_rate": 4.200507614213198e-05,
1759
+ "loss": 0.1122,
1760
+ "step": 1250
1761
+ },
1762
+ {
1763
+ "epoch": 3.971518987341772,
1764
+ "grad_norm": 0.7136058807373047,
1765
+ "learning_rate": 4.137055837563452e-05,
1766
+ "loss": 0.1172,
1767
+ "step": 1255
1768
+ },
1769
+ {
1770
+ "epoch": 3.9873417721518987,
1771
+ "grad_norm": 0.8732256293296814,
1772
+ "learning_rate": 4.073604060913706e-05,
1773
+ "loss": 0.1198,
1774
+ "step": 1260
1775
+ },
1776
+ {
1777
+ "epoch": 4.003164556962025,
1778
+ "grad_norm": 0.3908518850803375,
1779
+ "learning_rate": 4.010152284263959e-05,
1780
+ "loss": 0.1182,
1781
+ "step": 1265
1782
+ },
1783
+ {
1784
+ "epoch": 4.018987341772152,
1785
+ "grad_norm": 0.3654375672340393,
1786
+ "learning_rate": 3.946700507614213e-05,
1787
+ "loss": 0.0943,
1788
+ "step": 1270
1789
+ },
1790
+ {
1791
+ "epoch": 4.034810126582278,
1792
+ "grad_norm": 0.44177666306495667,
1793
+ "learning_rate": 3.8832487309644673e-05,
1794
+ "loss": 0.093,
1795
+ "step": 1275
1796
+ },
1797
+ {
1798
+ "epoch": 4.050632911392405,
1799
+ "grad_norm": 0.548538863658905,
1800
+ "learning_rate": 3.819796954314721e-05,
1801
+ "loss": 0.0905,
1802
+ "step": 1280
1803
+ },
1804
+ {
1805
+ "epoch": 4.0664556962025316,
1806
+ "grad_norm": 0.34858939051628113,
1807
+ "learning_rate": 3.756345177664975e-05,
1808
+ "loss": 0.0882,
1809
+ "step": 1285
1810
+ },
1811
+ {
1812
+ "epoch": 4.082278481012658,
1813
+ "grad_norm": 0.44596415758132935,
1814
+ "learning_rate": 3.692893401015229e-05,
1815
+ "loss": 0.091,
1816
+ "step": 1290
1817
+ },
1818
+ {
1819
+ "epoch": 4.098101265822785,
1820
+ "grad_norm": 0.4271854758262634,
1821
+ "learning_rate": 3.629441624365482e-05,
1822
+ "loss": 0.0907,
1823
+ "step": 1295
1824
+ },
1825
+ {
1826
+ "epoch": 4.113924050632911,
1827
+ "grad_norm": 0.7120389938354492,
1828
+ "learning_rate": 3.565989847715736e-05,
1829
+ "loss": 0.0931,
1830
+ "step": 1300
1831
+ },
1832
+ {
1833
+ "epoch": 4.129746835443038,
1834
+ "grad_norm": 0.44612565636634827,
1835
+ "learning_rate": 3.50253807106599e-05,
1836
+ "loss": 0.0887,
1837
+ "step": 1305
1838
+ },
1839
+ {
1840
+ "epoch": 4.1455696202531644,
1841
+ "grad_norm": 0.34034597873687744,
1842
+ "learning_rate": 3.439086294416244e-05,
1843
+ "loss": 0.0903,
1844
+ "step": 1310
1845
+ },
1846
+ {
1847
+ "epoch": 4.1613924050632916,
1848
+ "grad_norm": 0.4155871570110321,
1849
+ "learning_rate": 3.3756345177664975e-05,
1850
+ "loss": 0.092,
1851
+ "step": 1315
1852
+ },
1853
+ {
1854
+ "epoch": 4.177215189873418,
1855
+ "grad_norm": 0.5939737558364868,
1856
+ "learning_rate": 3.312182741116752e-05,
1857
+ "loss": 0.0928,
1858
+ "step": 1320
1859
+ },
1860
+ {
1861
+ "epoch": 4.193037974683544,
1862
+ "grad_norm": 0.611441969871521,
1863
+ "learning_rate": 3.248730964467005e-05,
1864
+ "loss": 0.0897,
1865
+ "step": 1325
1866
+ },
1867
+ {
1868
+ "epoch": 4.208860759493671,
1869
+ "grad_norm": 0.6120615601539612,
1870
+ "learning_rate": 3.185279187817259e-05,
1871
+ "loss": 0.0936,
1872
+ "step": 1330
1873
+ },
1874
+ {
1875
+ "epoch": 4.224683544303797,
1876
+ "grad_norm": 0.4837358593940735,
1877
+ "learning_rate": 3.121827411167513e-05,
1878
+ "loss": 0.0896,
1879
+ "step": 1335
1880
+ },
1881
+ {
1882
+ "epoch": 4.2405063291139244,
1883
+ "grad_norm": 0.40970176458358765,
1884
+ "learning_rate": 3.0583756345177666e-05,
1885
+ "loss": 0.0928,
1886
+ "step": 1340
1887
+ },
1888
+ {
1889
+ "epoch": 4.256329113924051,
1890
+ "grad_norm": 0.4805232286453247,
1891
+ "learning_rate": 2.9949238578680206e-05,
1892
+ "loss": 0.0903,
1893
+ "step": 1345
1894
+ },
1895
+ {
1896
+ "epoch": 4.272151898734177,
1897
+ "grad_norm": 0.4605880379676819,
1898
+ "learning_rate": 2.9314720812182743e-05,
1899
+ "loss": 0.0903,
1900
+ "step": 1350
1901
+ },
1902
+ {
1903
+ "epoch": 4.287974683544304,
1904
+ "grad_norm": 0.4408807158470154,
1905
+ "learning_rate": 2.8680203045685283e-05,
1906
+ "loss": 0.0916,
1907
+ "step": 1355
1908
+ },
1909
+ {
1910
+ "epoch": 4.30379746835443,
1911
+ "grad_norm": 0.4075123071670532,
1912
+ "learning_rate": 2.8045685279187816e-05,
1913
+ "loss": 0.0878,
1914
+ "step": 1360
1915
+ },
1916
+ {
1917
+ "epoch": 4.319620253164557,
1918
+ "grad_norm": 0.5319828987121582,
1919
+ "learning_rate": 2.7411167512690357e-05,
1920
+ "loss": 0.0907,
1921
+ "step": 1365
1922
+ },
1923
+ {
1924
+ "epoch": 4.3354430379746836,
1925
+ "grad_norm": 0.5517973899841309,
1926
+ "learning_rate": 2.6776649746192893e-05,
1927
+ "loss": 0.0895,
1928
+ "step": 1370
1929
+ },
1930
+ {
1931
+ "epoch": 4.35126582278481,
1932
+ "grad_norm": 0.48083606362342834,
1933
+ "learning_rate": 2.6142131979695434e-05,
1934
+ "loss": 0.0921,
1935
+ "step": 1375
1936
+ },
1937
+ {
1938
+ "epoch": 4.367088607594937,
1939
+ "grad_norm": 0.5320701599121094,
1940
+ "learning_rate": 2.5507614213197974e-05,
1941
+ "loss": 0.0917,
1942
+ "step": 1380
1943
+ },
1944
+ {
1945
+ "epoch": 4.382911392405063,
1946
+ "grad_norm": 0.416904479265213,
1947
+ "learning_rate": 2.4873096446700507e-05,
1948
+ "loss": 0.0928,
1949
+ "step": 1385
1950
+ },
1951
+ {
1952
+ "epoch": 4.39873417721519,
1953
+ "grad_norm": 0.49495264887809753,
1954
+ "learning_rate": 2.4238578680203047e-05,
1955
+ "loss": 0.0911,
1956
+ "step": 1390
1957
+ },
1958
+ {
1959
+ "epoch": 4.4145569620253164,
1960
+ "grad_norm": 0.5663470029830933,
1961
+ "learning_rate": 2.3604060913705588e-05,
1962
+ "loss": 0.095,
1963
+ "step": 1395
1964
+ },
1965
+ {
1966
+ "epoch": 4.430379746835443,
1967
+ "grad_norm": 0.49303102493286133,
1968
+ "learning_rate": 2.296954314720812e-05,
1969
+ "loss": 0.0937,
1970
+ "step": 1400
1971
+ },
1972
+ {
1973
+ "epoch": 4.44620253164557,
1974
+ "grad_norm": 0.3795440196990967,
1975
+ "learning_rate": 2.233502538071066e-05,
1976
+ "loss": 0.0899,
1977
+ "step": 1405
1978
+ },
1979
+ {
1980
+ "epoch": 4.462025316455696,
1981
+ "grad_norm": 0.4684379994869232,
1982
+ "learning_rate": 2.17005076142132e-05,
1983
+ "loss": 0.0924,
1984
+ "step": 1410
1985
+ },
1986
+ {
1987
+ "epoch": 4.477848101265823,
1988
+ "grad_norm": 0.3904794156551361,
1989
+ "learning_rate": 2.1065989847715735e-05,
1990
+ "loss": 0.0922,
1991
+ "step": 1415
1992
+ },
1993
+ {
1994
+ "epoch": 4.493670886075949,
1995
+ "grad_norm": 0.6037257313728333,
1996
+ "learning_rate": 2.0431472081218275e-05,
1997
+ "loss": 0.096,
1998
+ "step": 1420
1999
+ },
2000
+ {
2001
+ "epoch": 4.509493670886076,
2002
+ "grad_norm": 0.30922073125839233,
2003
+ "learning_rate": 1.9796954314720815e-05,
2004
+ "loss": 0.091,
2005
+ "step": 1425
2006
+ },
2007
+ {
2008
+ "epoch": 4.525316455696203,
2009
+ "grad_norm": 0.5561403036117554,
2010
+ "learning_rate": 1.916243654822335e-05,
2011
+ "loss": 0.0905,
2012
+ "step": 1430
2013
+ },
2014
+ {
2015
+ "epoch": 4.541139240506329,
2016
+ "grad_norm": 0.389127641916275,
2017
+ "learning_rate": 1.852791878172589e-05,
2018
+ "loss": 0.0906,
2019
+ "step": 1435
2020
+ },
2021
+ {
2022
+ "epoch": 4.556962025316456,
2023
+ "grad_norm": 0.38574787974357605,
2024
+ "learning_rate": 1.789340101522843e-05,
2025
+ "loss": 0.0891,
2026
+ "step": 1440
2027
+ },
2028
+ {
2029
+ "epoch": 4.572784810126582,
2030
+ "grad_norm": 0.42243725061416626,
2031
+ "learning_rate": 1.7258883248730966e-05,
2032
+ "loss": 0.0961,
2033
+ "step": 1445
2034
+ },
2035
+ {
2036
+ "epoch": 4.588607594936709,
2037
+ "grad_norm": 0.522402286529541,
2038
+ "learning_rate": 1.6624365482233503e-05,
2039
+ "loss": 0.0889,
2040
+ "step": 1450
2041
+ },
2042
+ {
2043
+ "epoch": 4.6044303797468356,
2044
+ "grad_norm": 0.3562035858631134,
2045
+ "learning_rate": 1.5989847715736043e-05,
2046
+ "loss": 0.0879,
2047
+ "step": 1455
2048
+ },
2049
+ {
2050
+ "epoch": 4.620253164556962,
2051
+ "grad_norm": 0.7289389967918396,
2052
+ "learning_rate": 1.535532994923858e-05,
2053
+ "loss": 0.0955,
2054
+ "step": 1460
2055
+ },
2056
+ {
2057
+ "epoch": 4.636075949367089,
2058
+ "grad_norm": 0.4322461783885956,
2059
+ "learning_rate": 1.4720812182741117e-05,
2060
+ "loss": 0.0933,
2061
+ "step": 1465
2062
+ },
2063
+ {
2064
+ "epoch": 4.651898734177215,
2065
+ "grad_norm": 0.5375872850418091,
2066
+ "learning_rate": 1.4086294416243657e-05,
2067
+ "loss": 0.0911,
2068
+ "step": 1470
2069
+ },
2070
+ {
2071
+ "epoch": 4.667721518987342,
2072
+ "grad_norm": 0.4194104075431824,
2073
+ "learning_rate": 1.3451776649746192e-05,
2074
+ "loss": 0.0878,
2075
+ "step": 1475
2076
+ },
2077
+ {
2078
+ "epoch": 4.6835443037974684,
2079
+ "grad_norm": 0.4603971242904663,
2080
+ "learning_rate": 1.281725888324873e-05,
2081
+ "loss": 0.0916,
2082
+ "step": 1480
2083
+ },
2084
+ {
2085
+ "epoch": 4.699367088607595,
2086
+ "grad_norm": 0.34578830003738403,
2087
+ "learning_rate": 1.218274111675127e-05,
2088
+ "loss": 0.0905,
2089
+ "step": 1485
2090
+ },
2091
+ {
2092
+ "epoch": 4.715189873417722,
2093
+ "grad_norm": 0.7133288383483887,
2094
+ "learning_rate": 1.1548223350253808e-05,
2095
+ "loss": 0.0889,
2096
+ "step": 1490
2097
+ },
2098
+ {
2099
+ "epoch": 4.731012658227848,
2100
+ "grad_norm": 0.6632990837097168,
2101
+ "learning_rate": 1.0913705583756344e-05,
2102
+ "loss": 0.0912,
2103
+ "step": 1495
2104
+ },
2105
+ {
2106
+ "epoch": 4.746835443037975,
2107
+ "grad_norm": 0.339555561542511,
2108
+ "learning_rate": 1.0279187817258885e-05,
2109
+ "loss": 0.091,
2110
+ "step": 1500
2111
+ }
2112
+ ],
2113
+ "logging_steps": 5,
2114
+ "max_steps": 1580,
2115
+ "num_input_tokens_seen": 0,
2116
+ "num_train_epochs": 5,
2117
+ "save_steps": 500,
2118
+ "stateful_callbacks": {
2119
+ "TrainerControl": {
2120
+ "args": {
2121
+ "should_epoch_stop": false,
2122
+ "should_evaluate": false,
2123
+ "should_log": false,
2124
+ "should_save": true,
2125
+ "should_training_stop": false
2126
+ },
2127
+ "attributes": {}
2128
+ }
2129
+ },
2130
+ "total_flos": 1.3027597240614912e+17,
2131
+ "train_batch_size": 16,
2132
+ "trial_name": null,
2133
+ "trial_params": null
2134
+ }
experiments/de-en-pt-zh/checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1f965478a30d642e1d3280129a9cb365127c4096496511633d6b72e8ccf15e
3
+ size 6289
experiments/de-en-pt-zh/checkpoint-1580/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.1
experiments/de-en-pt-zh/checkpoint-1580/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.1,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 8,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "gate_proj",
37
+ "v_proj",
38
+ "o_proj",
39
+ "k_proj",
40
+ "up_proj",
41
+ "down_proj",
42
+ "q_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true
50
+ }
experiments/de-en-pt-zh/checkpoint-1580/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051126fb9ec33a14e0ca6905264f0cdf6fa6a95969cce1b5cbcee93a06dd58c9
3
+ size 83945296
experiments/de-en-pt-zh/checkpoint-1580/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 %}
experiments/de-en-pt-zh/checkpoint-1580/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cedc14f9390b752f44508d1a359a92966b3903d06f27c12b7d672c9e38623a
3
+ size 43123429
experiments/de-en-pt-zh/checkpoint-1580/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da18f8889d1a2c7f22914265e4646c514d34fc958c2d5959ecdbd416ac8c634e
3
+ size 14645
experiments/de-en-pt-zh/checkpoint-1580/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a97f21c0a7d8518fbc52270f43024d3897b647f2dc864b2af25dddfb74924be
3
+ size 1465
experiments/de-en-pt-zh/checkpoint-1580/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
experiments/de-en-pt-zh/checkpoint-1580/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
experiments/de-en-pt-zh/checkpoint-1580/tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast",
2065
+ "unk_token": null
2066
+ }
experiments/de-en-pt-zh/checkpoint-1580/trainer_state.json ADDED
@@ -0,0 +1,2246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1580,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015822784810126583,
14
+ "grad_norm": 6.080485820770264,
15
+ "learning_rate": 0.0002,
16
+ "loss": 2.7599,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03164556962025317,
21
+ "grad_norm": 1.6470410823822021,
22
+ "learning_rate": 0.00019936548223350255,
23
+ "loss": 0.8662,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.04746835443037975,
28
+ "grad_norm": 1.656543254852295,
29
+ "learning_rate": 0.00019873096446700508,
30
+ "loss": 0.5796,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.06329113924050633,
35
+ "grad_norm": 0.9287125468254089,
36
+ "learning_rate": 0.00019809644670050762,
37
+ "loss": 0.5521,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.07911392405063292,
42
+ "grad_norm": 0.9500881433486938,
43
+ "learning_rate": 0.00019746192893401016,
44
+ "loss": 0.4879,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.0949367088607595,
49
+ "grad_norm": 0.6434516310691833,
50
+ "learning_rate": 0.00019682741116751272,
51
+ "loss": 0.467,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.11075949367088607,
56
+ "grad_norm": 0.8102421760559082,
57
+ "learning_rate": 0.00019619289340101523,
58
+ "loss": 0.4872,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.12658227848101267,
63
+ "grad_norm": 0.8061529397964478,
64
+ "learning_rate": 0.00019555837563451777,
65
+ "loss": 0.4883,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.14240506329113925,
70
+ "grad_norm": 0.8552656769752502,
71
+ "learning_rate": 0.00019492385786802033,
72
+ "loss": 0.4634,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.15822784810126583,
77
+ "grad_norm": 0.6702130436897278,
78
+ "learning_rate": 0.00019428934010152284,
79
+ "loss": 0.4606,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.17405063291139242,
84
+ "grad_norm": 0.7621438503265381,
85
+ "learning_rate": 0.00019365482233502538,
86
+ "loss": 0.5159,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.189873417721519,
91
+ "grad_norm": 0.6256672143936157,
92
+ "learning_rate": 0.00019302030456852794,
93
+ "loss": 0.4818,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.20569620253164558,
98
+ "grad_norm": 0.6232669353485107,
99
+ "learning_rate": 0.00019238578680203048,
100
+ "loss": 0.4926,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.22151898734177214,
105
+ "grad_norm": 0.6387396454811096,
106
+ "learning_rate": 0.000191751269035533,
107
+ "loss": 0.4841,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.23734177215189872,
112
+ "grad_norm": 0.6436880230903625,
113
+ "learning_rate": 0.00019111675126903555,
114
+ "loss": 0.4871,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.25316455696202533,
119
+ "grad_norm": 0.7336615920066833,
120
+ "learning_rate": 0.0001904822335025381,
121
+ "loss": 0.4568,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2689873417721519,
126
+ "grad_norm": 0.7388893961906433,
127
+ "learning_rate": 0.0001898477157360406,
128
+ "loss": 0.4553,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2848101265822785,
133
+ "grad_norm": 0.6054999828338623,
134
+ "learning_rate": 0.00018921319796954316,
135
+ "loss": 0.4405,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.30063291139240506,
140
+ "grad_norm": 0.7911633253097534,
141
+ "learning_rate": 0.0001885786802030457,
142
+ "loss": 0.5219,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.31645569620253167,
147
+ "grad_norm": 0.5389903783798218,
148
+ "learning_rate": 0.00018794416243654824,
149
+ "loss": 0.4525,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.3322784810126582,
154
+ "grad_norm": 0.7426465749740601,
155
+ "learning_rate": 0.00018730964467005077,
156
+ "loss": 0.4856,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.34810126582278483,
161
+ "grad_norm": 0.7140562534332275,
162
+ "learning_rate": 0.0001866751269035533,
163
+ "loss": 0.4918,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.3639240506329114,
168
+ "grad_norm": 0.624547004699707,
169
+ "learning_rate": 0.00018604060913705585,
170
+ "loss": 0.4806,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.379746835443038,
175
+ "grad_norm": 0.8368127942085266,
176
+ "learning_rate": 0.00018540609137055838,
177
+ "loss": 0.4915,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.39556962025316456,
182
+ "grad_norm": 0.6069784164428711,
183
+ "learning_rate": 0.00018477157360406092,
184
+ "loss": 0.485,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.41139240506329117,
189
+ "grad_norm": 0.6394964456558228,
190
+ "learning_rate": 0.00018413705583756346,
191
+ "loss": 0.4815,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.4272151898734177,
196
+ "grad_norm": 0.6225919127464294,
197
+ "learning_rate": 0.000183502538071066,
198
+ "loss": 0.4744,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.4430379746835443,
203
+ "grad_norm": 0.7593483328819275,
204
+ "learning_rate": 0.00018286802030456853,
205
+ "loss": 0.4505,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.4588607594936709,
210
+ "grad_norm": 0.5810648202896118,
211
+ "learning_rate": 0.00018223350253807107,
212
+ "loss": 0.435,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.47468354430379744,
217
+ "grad_norm": 0.7975546717643738,
218
+ "learning_rate": 0.00018159898477157363,
219
+ "loss": 0.4685,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.49050632911392406,
224
+ "grad_norm": 0.6529037356376648,
225
+ "learning_rate": 0.00018096446700507614,
226
+ "loss": 0.4089,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.5063291139240507,
231
+ "grad_norm": 0.7088711857795715,
232
+ "learning_rate": 0.00018032994923857868,
233
+ "loss": 0.4388,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.5221518987341772,
238
+ "grad_norm": 0.5964807271957397,
239
+ "learning_rate": 0.00017969543147208124,
240
+ "loss": 0.4104,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.5379746835443038,
245
+ "grad_norm": 0.6564443707466125,
246
+ "learning_rate": 0.00017906091370558375,
247
+ "loss": 0.4717,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.5537974683544303,
252
+ "grad_norm": 0.6912603974342346,
253
+ "learning_rate": 0.0001784263959390863,
254
+ "loss": 0.4528,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.569620253164557,
259
+ "grad_norm": 0.6068799495697021,
260
+ "learning_rate": 0.00017779187817258885,
261
+ "loss": 0.4714,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.5854430379746836,
266
+ "grad_norm": 0.6037777066230774,
267
+ "learning_rate": 0.0001771573604060914,
268
+ "loss": 0.5058,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.6012658227848101,
273
+ "grad_norm": 0.586581826210022,
274
+ "learning_rate": 0.0001765228426395939,
275
+ "loss": 0.439,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.6170886075949367,
280
+ "grad_norm": 0.6780263185501099,
281
+ "learning_rate": 0.00017588832487309646,
282
+ "loss": 0.4269,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.6329113924050633,
287
+ "grad_norm": 0.7488175630569458,
288
+ "learning_rate": 0.000175253807106599,
289
+ "loss": 0.4481,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.6487341772151899,
294
+ "grad_norm": 0.6138256788253784,
295
+ "learning_rate": 0.0001746192893401015,
296
+ "loss": 0.4654,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.6645569620253164,
301
+ "grad_norm": 0.7444900274276733,
302
+ "learning_rate": 0.00017398477157360407,
303
+ "loss": 0.4165,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.680379746835443,
308
+ "grad_norm": 0.6231881380081177,
309
+ "learning_rate": 0.0001733502538071066,
310
+ "loss": 0.4469,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.6962025316455697,
315
+ "grad_norm": 0.6703267097473145,
316
+ "learning_rate": 0.00017271573604060915,
317
+ "loss": 0.4279,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.7120253164556962,
322
+ "grad_norm": 0.4783850312232971,
323
+ "learning_rate": 0.00017208121827411168,
324
+ "loss": 0.4654,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.7278481012658228,
329
+ "grad_norm": 0.7536376118659973,
330
+ "learning_rate": 0.00017144670050761422,
331
+ "loss": 0.4537,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.7436708860759493,
336
+ "grad_norm": 0.7595057487487793,
337
+ "learning_rate": 0.00017081218274111676,
338
+ "loss": 0.486,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.759493670886076,
343
+ "grad_norm": 0.8007245659828186,
344
+ "learning_rate": 0.0001701776649746193,
345
+ "loss": 0.3919,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.7753164556962026,
350
+ "grad_norm": 0.6637867093086243,
351
+ "learning_rate": 0.00016954314720812183,
352
+ "loss": 0.418,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.7911392405063291,
357
+ "grad_norm": 0.653685986995697,
358
+ "learning_rate": 0.00016890862944162437,
359
+ "loss": 0.4326,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.8069620253164557,
364
+ "grad_norm": 0.6465121507644653,
365
+ "learning_rate": 0.00016827411167512693,
366
+ "loss": 0.445,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.8227848101265823,
371
+ "grad_norm": 0.6836300492286682,
372
+ "learning_rate": 0.00016763959390862944,
373
+ "loss": 0.4348,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.8386075949367089,
378
+ "grad_norm": 0.7092205882072449,
379
+ "learning_rate": 0.00016700507614213198,
380
+ "loss": 0.4081,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.8544303797468354,
385
+ "grad_norm": 0.7940587997436523,
386
+ "learning_rate": 0.00016637055837563454,
387
+ "loss": 0.4316,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.870253164556962,
392
+ "grad_norm": 0.6765463352203369,
393
+ "learning_rate": 0.00016573604060913705,
394
+ "loss": 0.45,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.8860759493670886,
399
+ "grad_norm": 0.8914448022842407,
400
+ "learning_rate": 0.0001651015228426396,
401
+ "loss": 0.4202,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.9018987341772152,
406
+ "grad_norm": 0.6309791207313538,
407
+ "learning_rate": 0.00016446700507614215,
408
+ "loss": 0.4308,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.9177215189873418,
413
+ "grad_norm": 0.7343917489051819,
414
+ "learning_rate": 0.0001638324873096447,
415
+ "loss": 0.4387,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.9335443037974683,
420
+ "grad_norm": 0.5776176452636719,
421
+ "learning_rate": 0.0001631979695431472,
422
+ "loss": 0.4239,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.9493670886075949,
427
+ "grad_norm": 0.6677407026290894,
428
+ "learning_rate": 0.00016256345177664976,
429
+ "loss": 0.4481,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.9651898734177216,
434
+ "grad_norm": 0.6818298101425171,
435
+ "learning_rate": 0.0001619289340101523,
436
+ "loss": 0.4089,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.9810126582278481,
441
+ "grad_norm": 0.9606236219406128,
442
+ "learning_rate": 0.0001612944162436548,
443
+ "loss": 0.4491,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.9968354430379747,
448
+ "grad_norm": 0.6414772272109985,
449
+ "learning_rate": 0.00016065989847715737,
450
+ "loss": 0.4639,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.0126582278481013,
455
+ "grad_norm": 0.5724285244941711,
456
+ "learning_rate": 0.0001600253807106599,
457
+ "loss": 0.3448,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.0284810126582278,
462
+ "grad_norm": 0.8723211884498596,
463
+ "learning_rate": 0.00015939086294416242,
464
+ "loss": 0.3483,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 1.0443037974683544,
469
+ "grad_norm": 0.6645333170890808,
470
+ "learning_rate": 0.00015875634517766498,
471
+ "loss": 0.3136,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 1.0601265822784811,
476
+ "grad_norm": 0.7657269239425659,
477
+ "learning_rate": 0.00015812182741116752,
478
+ "loss": 0.3426,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 1.0759493670886076,
483
+ "grad_norm": 0.6551052927970886,
484
+ "learning_rate": 0.00015748730964467006,
485
+ "loss": 0.3482,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 1.0917721518987342,
490
+ "grad_norm": 0.7337777018547058,
491
+ "learning_rate": 0.0001568527918781726,
492
+ "loss": 0.3128,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 1.1075949367088607,
497
+ "grad_norm": 0.8943917751312256,
498
+ "learning_rate": 0.00015621827411167513,
499
+ "loss": 0.3134,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 1.1234177215189873,
504
+ "grad_norm": 0.71893310546875,
505
+ "learning_rate": 0.00015558375634517767,
506
+ "loss": 0.2815,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 1.139240506329114,
511
+ "grad_norm": 0.7433806657791138,
512
+ "learning_rate": 0.0001549492385786802,
513
+ "loss": 0.3216,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 1.1550632911392404,
518
+ "grad_norm": 0.7051471471786499,
519
+ "learning_rate": 0.00015431472081218274,
520
+ "loss": 0.3719,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 1.1708860759493671,
525
+ "grad_norm": 0.6804415583610535,
526
+ "learning_rate": 0.00015368020304568528,
527
+ "loss": 0.3449,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 1.1867088607594938,
532
+ "grad_norm": 0.9129506945610046,
533
+ "learning_rate": 0.00015304568527918784,
534
+ "loss": 0.3574,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 1.2025316455696202,
539
+ "grad_norm": 0.8387975692749023,
540
+ "learning_rate": 0.00015241116751269035,
541
+ "loss": 0.3321,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.2183544303797469,
546
+ "grad_norm": 0.689298152923584,
547
+ "learning_rate": 0.0001517766497461929,
548
+ "loss": 0.3156,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.2341772151898733,
553
+ "grad_norm": 0.681196928024292,
554
+ "learning_rate": 0.00015114213197969545,
555
+ "loss": 0.3371,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.25,
560
+ "grad_norm": 0.8151982426643372,
561
+ "learning_rate": 0.00015050761421319796,
562
+ "loss": 0.3356,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.2658227848101267,
567
+ "grad_norm": 0.789669394493103,
568
+ "learning_rate": 0.0001498730964467005,
569
+ "loss": 0.3063,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.2816455696202531,
574
+ "grad_norm": 0.7262426614761353,
575
+ "learning_rate": 0.00014923857868020306,
576
+ "loss": 0.3179,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.2974683544303798,
581
+ "grad_norm": 0.717400074005127,
582
+ "learning_rate": 0.0001486040609137056,
583
+ "loss": 0.3266,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.3132911392405062,
588
+ "grad_norm": 0.8459286093711853,
589
+ "learning_rate": 0.0001479695431472081,
590
+ "loss": 0.3323,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.3291139240506329,
595
+ "grad_norm": 0.831169843673706,
596
+ "learning_rate": 0.00014733502538071067,
597
+ "loss": 0.3101,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.3449367088607596,
602
+ "grad_norm": 0.6811087727546692,
603
+ "learning_rate": 0.0001467005076142132,
604
+ "loss": 0.3166,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.360759493670886,
609
+ "grad_norm": 0.813766360282898,
610
+ "learning_rate": 0.00014606598984771572,
611
+ "loss": 0.3274,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.3765822784810127,
616
+ "grad_norm": 0.7633799314498901,
617
+ "learning_rate": 0.00014543147208121828,
618
+ "loss": 0.3351,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.3924050632911391,
623
+ "grad_norm": 0.7631050944328308,
624
+ "learning_rate": 0.00014479695431472082,
625
+ "loss": 0.3045,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.4082278481012658,
630
+ "grad_norm": 0.8526734709739685,
631
+ "learning_rate": 0.00014416243654822336,
632
+ "loss": 0.3479,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.4240506329113924,
637
+ "grad_norm": 0.7672425508499146,
638
+ "learning_rate": 0.0001435279187817259,
639
+ "loss": 0.3302,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.439873417721519,
644
+ "grad_norm": 0.8053662776947021,
645
+ "learning_rate": 0.00014289340101522843,
646
+ "loss": 0.2994,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.4556962025316456,
651
+ "grad_norm": 0.9087522625923157,
652
+ "learning_rate": 0.00014225888324873097,
653
+ "loss": 0.3233,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.4715189873417722,
658
+ "grad_norm": 0.7690944075584412,
659
+ "learning_rate": 0.0001416243654822335,
660
+ "loss": 0.2887,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.4873417721518987,
665
+ "grad_norm": 0.8058143854141235,
666
+ "learning_rate": 0.00014098984771573604,
667
+ "loss": 0.2982,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.5031645569620253,
672
+ "grad_norm": 0.7568528056144714,
673
+ "learning_rate": 0.00014035532994923858,
674
+ "loss": 0.3103,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.518987341772152,
679
+ "grad_norm": 0.755690336227417,
680
+ "learning_rate": 0.00013972081218274114,
681
+ "loss": 0.3009,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.5348101265822784,
686
+ "grad_norm": 0.8576112985610962,
687
+ "learning_rate": 0.00013908629441624365,
688
+ "loss": 0.3317,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.5506329113924051,
693
+ "grad_norm": 0.8156176805496216,
694
+ "learning_rate": 0.0001384517766497462,
695
+ "loss": 0.3187,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.5664556962025316,
700
+ "grad_norm": 0.8467602729797363,
701
+ "learning_rate": 0.00013781725888324875,
702
+ "loss": 0.3155,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.5822784810126582,
707
+ "grad_norm": 0.8999772071838379,
708
+ "learning_rate": 0.00013718274111675126,
709
+ "loss": 0.3402,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.5981012658227849,
714
+ "grad_norm": 0.808548092842102,
715
+ "learning_rate": 0.0001365482233502538,
716
+ "loss": 0.296,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.6139240506329116,
721
+ "grad_norm": 0.7033184170722961,
722
+ "learning_rate": 0.00013591370558375636,
723
+ "loss": 0.3052,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.629746835443038,
728
+ "grad_norm": 0.8576298356056213,
729
+ "learning_rate": 0.00013527918781725887,
730
+ "loss": 0.3253,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.6455696202531644,
735
+ "grad_norm": 0.6722769141197205,
736
+ "learning_rate": 0.0001346446700507614,
737
+ "loss": 0.2941,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.6613924050632911,
742
+ "grad_norm": 0.6628623008728027,
743
+ "learning_rate": 0.00013401015228426397,
744
+ "loss": 0.3016,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.6772151898734178,
749
+ "grad_norm": 0.9596195220947266,
750
+ "learning_rate": 0.0001333756345177665,
751
+ "loss": 0.3234,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.6930379746835444,
756
+ "grad_norm": 0.8452304005622864,
757
+ "learning_rate": 0.00013274111675126905,
758
+ "loss": 0.3458,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.7088607594936709,
763
+ "grad_norm": 0.7414538860321045,
764
+ "learning_rate": 0.00013210659898477158,
765
+ "loss": 0.3133,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.7246835443037973,
770
+ "grad_norm": 0.6833527088165283,
771
+ "learning_rate": 0.00013147208121827412,
772
+ "loss": 0.3008,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.740506329113924,
777
+ "grad_norm": 0.8556643724441528,
778
+ "learning_rate": 0.00013083756345177666,
779
+ "loss": 0.3035,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.7563291139240507,
784
+ "grad_norm": 0.9071274399757385,
785
+ "learning_rate": 0.0001302030456852792,
786
+ "loss": 0.304,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.7721518987341773,
791
+ "grad_norm": 1.0122044086456299,
792
+ "learning_rate": 0.00012956852791878173,
793
+ "loss": 0.2956,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.7879746835443038,
798
+ "grad_norm": 0.9109578132629395,
799
+ "learning_rate": 0.00012893401015228427,
800
+ "loss": 0.3101,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.8037974683544302,
805
+ "grad_norm": 0.9648177623748779,
806
+ "learning_rate": 0.0001282994923857868,
807
+ "loss": 0.2987,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.8196202531645569,
812
+ "grad_norm": 0.8060092926025391,
813
+ "learning_rate": 0.00012766497461928934,
814
+ "loss": 0.3011,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.8354430379746836,
819
+ "grad_norm": 0.7650238871574402,
820
+ "learning_rate": 0.00012703045685279188,
821
+ "loss": 0.3207,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.8512658227848102,
826
+ "grad_norm": 1.0391228199005127,
827
+ "learning_rate": 0.00012639593908629442,
828
+ "loss": 0.3,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.8670886075949367,
833
+ "grad_norm": 0.7758641242980957,
834
+ "learning_rate": 0.00012576142131979695,
835
+ "loss": 0.3109,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.8829113924050633,
840
+ "grad_norm": 0.819521427154541,
841
+ "learning_rate": 0.0001251269035532995,
842
+ "loss": 0.2921,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.8987341772151898,
847
+ "grad_norm": 0.7439246773719788,
848
+ "learning_rate": 0.00012449238578680205,
849
+ "loss": 0.3091,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.9145569620253164,
854
+ "grad_norm": 0.8022212386131287,
855
+ "learning_rate": 0.00012385786802030456,
856
+ "loss": 0.3252,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.9303797468354431,
861
+ "grad_norm": 1.0216495990753174,
862
+ "learning_rate": 0.0001232233502538071,
863
+ "loss": 0.3434,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.9462025316455698,
868
+ "grad_norm": 0.821251630783081,
869
+ "learning_rate": 0.00012258883248730966,
870
+ "loss": 0.325,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.9620253164556962,
875
+ "grad_norm": 0.744149386882782,
876
+ "learning_rate": 0.00012195431472081217,
877
+ "loss": 0.3286,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.9778481012658227,
882
+ "grad_norm": 0.8488931655883789,
883
+ "learning_rate": 0.00012131979695431472,
884
+ "loss": 0.3048,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.9936708860759493,
889
+ "grad_norm": 0.8845570087432861,
890
+ "learning_rate": 0.00012068527918781727,
891
+ "loss": 0.3027,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 2.009493670886076,
896
+ "grad_norm": 0.6925209164619446,
897
+ "learning_rate": 0.00012005076142131981,
898
+ "loss": 0.2111,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 2.0253164556962027,
903
+ "grad_norm": 1.101040244102478,
904
+ "learning_rate": 0.00011941624365482233,
905
+ "loss": 0.1921,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 2.041139240506329,
910
+ "grad_norm": 1.030375361442566,
911
+ "learning_rate": 0.00011878172588832489,
912
+ "loss": 0.1878,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 2.0569620253164556,
917
+ "grad_norm": 0.8349786996841431,
918
+ "learning_rate": 0.00011814720812182742,
919
+ "loss": 0.1839,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 2.0727848101265822,
924
+ "grad_norm": 0.7567915320396423,
925
+ "learning_rate": 0.00011751269035532995,
926
+ "loss": 0.1978,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 2.088607594936709,
931
+ "grad_norm": 0.9065817594528198,
932
+ "learning_rate": 0.0001168781725888325,
933
+ "loss": 0.1904,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 2.1044303797468356,
938
+ "grad_norm": 0.8686302900314331,
939
+ "learning_rate": 0.00011624365482233503,
940
+ "loss": 0.1898,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 2.1202531645569622,
945
+ "grad_norm": 0.81605064868927,
946
+ "learning_rate": 0.00011560913705583758,
947
+ "loss": 0.186,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 2.1360759493670884,
952
+ "grad_norm": 0.8041939735412598,
953
+ "learning_rate": 0.0001149746192893401,
954
+ "loss": 0.1988,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 2.151898734177215,
959
+ "grad_norm": 0.9789828658103943,
960
+ "learning_rate": 0.00011434010152284264,
961
+ "loss": 0.1886,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 2.1677215189873418,
966
+ "grad_norm": 0.822130560874939,
967
+ "learning_rate": 0.0001137055837563452,
968
+ "loss": 0.1903,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 2.1835443037974684,
973
+ "grad_norm": 0.8661246299743652,
974
+ "learning_rate": 0.00011307106598984772,
975
+ "loss": 0.1911,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 2.199367088607595,
980
+ "grad_norm": 0.814487636089325,
981
+ "learning_rate": 0.00011243654822335025,
982
+ "loss": 0.1801,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 2.2151898734177213,
987
+ "grad_norm": 0.9888129830360413,
988
+ "learning_rate": 0.0001118020304568528,
989
+ "loss": 0.1859,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 2.231012658227848,
994
+ "grad_norm": 0.790763258934021,
995
+ "learning_rate": 0.00011116751269035533,
996
+ "loss": 0.1834,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 2.2468354430379747,
1001
+ "grad_norm": 0.7045260667800903,
1002
+ "learning_rate": 0.00011053299492385786,
1003
+ "loss": 0.1769,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 2.2626582278481013,
1008
+ "grad_norm": 0.8450356125831604,
1009
+ "learning_rate": 0.00010989847715736041,
1010
+ "loss": 0.1912,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 2.278481012658228,
1015
+ "grad_norm": 0.9821575284004211,
1016
+ "learning_rate": 0.00010926395939086295,
1017
+ "loss": 0.194,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 2.2943037974683547,
1022
+ "grad_norm": 0.827716588973999,
1023
+ "learning_rate": 0.00010862944162436547,
1024
+ "loss": 0.1952,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 2.310126582278481,
1029
+ "grad_norm": 1.0735716819763184,
1030
+ "learning_rate": 0.00010799492385786802,
1031
+ "loss": 0.1962,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 2.3259493670886076,
1036
+ "grad_norm": 0.759575605392456,
1037
+ "learning_rate": 0.00010736040609137057,
1038
+ "loss": 0.1899,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 2.3417721518987342,
1043
+ "grad_norm": 1.0905171632766724,
1044
+ "learning_rate": 0.00010672588832487308,
1045
+ "loss": 0.1836,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 2.357594936708861,
1050
+ "grad_norm": 0.9864721894264221,
1051
+ "learning_rate": 0.00010609137055837564,
1052
+ "loss": 0.1988,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 2.3734177215189876,
1057
+ "grad_norm": 0.8583397269248962,
1058
+ "learning_rate": 0.00010545685279187819,
1059
+ "loss": 0.2032,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 2.3892405063291138,
1064
+ "grad_norm": 0.8750898241996765,
1065
+ "learning_rate": 0.00010482233502538072,
1066
+ "loss": 0.1913,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 2.4050632911392404,
1071
+ "grad_norm": 0.8484179377555847,
1072
+ "learning_rate": 0.00010418781725888325,
1073
+ "loss": 0.1932,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.420886075949367,
1078
+ "grad_norm": 0.8363800048828125,
1079
+ "learning_rate": 0.0001035532994923858,
1080
+ "loss": 0.1961,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.4367088607594938,
1085
+ "grad_norm": 1.0165894031524658,
1086
+ "learning_rate": 0.00010291878172588833,
1087
+ "loss": 0.1997,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.4525316455696204,
1092
+ "grad_norm": 0.9139420986175537,
1093
+ "learning_rate": 0.00010228426395939086,
1094
+ "loss": 0.185,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.4683544303797467,
1099
+ "grad_norm": 0.8798001408576965,
1100
+ "learning_rate": 0.0001016497461928934,
1101
+ "loss": 0.1842,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.4841772151898733,
1106
+ "grad_norm": 0.8399237394332886,
1107
+ "learning_rate": 0.00010101522842639594,
1108
+ "loss": 0.1759,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.5,
1113
+ "grad_norm": 0.883194625377655,
1114
+ "learning_rate": 0.0001003807106598985,
1115
+ "loss": 0.2027,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.5158227848101267,
1120
+ "grad_norm": 1.1090173721313477,
1121
+ "learning_rate": 9.974619289340103e-05,
1122
+ "loss": 0.192,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.5316455696202533,
1127
+ "grad_norm": 0.8255505561828613,
1128
+ "learning_rate": 9.911167512690355e-05,
1129
+ "loss": 0.1962,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.5474683544303796,
1134
+ "grad_norm": 1.0160300731658936,
1135
+ "learning_rate": 9.847715736040609e-05,
1136
+ "loss": 0.1932,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.5632911392405062,
1141
+ "grad_norm": 0.7054086327552795,
1142
+ "learning_rate": 9.784263959390864e-05,
1143
+ "loss": 0.186,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.579113924050633,
1148
+ "grad_norm": 0.7671273946762085,
1149
+ "learning_rate": 9.720812182741116e-05,
1150
+ "loss": 0.1851,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.5949367088607596,
1155
+ "grad_norm": 0.9428186416625977,
1156
+ "learning_rate": 9.657360406091371e-05,
1157
+ "loss": 0.1903,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.6107594936708862,
1162
+ "grad_norm": 0.8303772807121277,
1163
+ "learning_rate": 9.593908629441625e-05,
1164
+ "loss": 0.1877,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.6265822784810124,
1169
+ "grad_norm": 0.9931467175483704,
1170
+ "learning_rate": 9.530456852791879e-05,
1171
+ "loss": 0.2038,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.642405063291139,
1176
+ "grad_norm": 0.8338640928268433,
1177
+ "learning_rate": 9.467005076142132e-05,
1178
+ "loss": 0.1782,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.6582278481012658,
1183
+ "grad_norm": 1.0357074737548828,
1184
+ "learning_rate": 9.403553299492386e-05,
1185
+ "loss": 0.204,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.6740506329113924,
1190
+ "grad_norm": 0.7227370142936707,
1191
+ "learning_rate": 9.34010152284264e-05,
1192
+ "loss": 0.1871,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.689873417721519,
1197
+ "grad_norm": 0.8483996987342834,
1198
+ "learning_rate": 9.276649746192894e-05,
1199
+ "loss": 0.1884,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.7056962025316453,
1204
+ "grad_norm": 0.7692596912384033,
1205
+ "learning_rate": 9.213197969543149e-05,
1206
+ "loss": 0.1987,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.721518987341772,
1211
+ "grad_norm": 0.9548447728157043,
1212
+ "learning_rate": 9.149746192893401e-05,
1213
+ "loss": 0.1836,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.7373417721518987,
1218
+ "grad_norm": 0.9363961219787598,
1219
+ "learning_rate": 9.086294416243655e-05,
1220
+ "loss": 0.1815,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.7531645569620253,
1225
+ "grad_norm": 1.0330653190612793,
1226
+ "learning_rate": 9.02284263959391e-05,
1227
+ "loss": 0.1957,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.768987341772152,
1232
+ "grad_norm": 0.8239451050758362,
1233
+ "learning_rate": 8.959390862944162e-05,
1234
+ "loss": 0.1945,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.7848101265822782,
1239
+ "grad_norm": 0.7226342558860779,
1240
+ "learning_rate": 8.895939086294417e-05,
1241
+ "loss": 0.1819,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.8006329113924053,
1246
+ "grad_norm": 1.2467807531356812,
1247
+ "learning_rate": 8.83248730964467e-05,
1248
+ "loss": 0.1723,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.8164556962025316,
1253
+ "grad_norm": 0.8140600919723511,
1254
+ "learning_rate": 8.769035532994924e-05,
1255
+ "loss": 0.1898,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.8322784810126582,
1260
+ "grad_norm": 0.8722625970840454,
1261
+ "learning_rate": 8.705583756345178e-05,
1262
+ "loss": 0.1895,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.848101265822785,
1267
+ "grad_norm": 1.1079012155532837,
1268
+ "learning_rate": 8.642131979695432e-05,
1269
+ "loss": 0.1999,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.8639240506329116,
1274
+ "grad_norm": 0.8730645775794983,
1275
+ "learning_rate": 8.578680203045685e-05,
1276
+ "loss": 0.1891,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.879746835443038,
1281
+ "grad_norm": 0.9077411890029907,
1282
+ "learning_rate": 8.515228426395939e-05,
1283
+ "loss": 0.1756,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.8955696202531644,
1288
+ "grad_norm": 0.9811768531799316,
1289
+ "learning_rate": 8.451776649746194e-05,
1290
+ "loss": 0.1937,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.911392405063291,
1295
+ "grad_norm": 0.8190383911132812,
1296
+ "learning_rate": 8.388324873096446e-05,
1297
+ "loss": 0.1947,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.9272151898734178,
1302
+ "grad_norm": 1.0100188255310059,
1303
+ "learning_rate": 8.324873096446701e-05,
1304
+ "loss": 0.2103,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.9430379746835444,
1309
+ "grad_norm": 0.7750146389007568,
1310
+ "learning_rate": 8.261421319796955e-05,
1311
+ "loss": 0.1828,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.958860759493671,
1316
+ "grad_norm": 0.7670167684555054,
1317
+ "learning_rate": 8.197969543147207e-05,
1318
+ "loss": 0.1848,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.9746835443037973,
1323
+ "grad_norm": 0.7348405718803406,
1324
+ "learning_rate": 8.134517766497463e-05,
1325
+ "loss": 0.1852,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.990506329113924,
1330
+ "grad_norm": 0.8744247555732727,
1331
+ "learning_rate": 8.071065989847716e-05,
1332
+ "loss": 0.1878,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 3.0063291139240507,
1337
+ "grad_norm": 0.5043367743492126,
1338
+ "learning_rate": 8.00761421319797e-05,
1339
+ "loss": 0.153,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 3.0221518987341773,
1344
+ "grad_norm": 0.5560520887374878,
1345
+ "learning_rate": 7.944162436548224e-05,
1346
+ "loss": 0.1149,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 3.037974683544304,
1351
+ "grad_norm": 0.8911687135696411,
1352
+ "learning_rate": 7.880710659898477e-05,
1353
+ "loss": 0.1172,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 3.0537974683544302,
1358
+ "grad_norm": 0.7934268116950989,
1359
+ "learning_rate": 7.817258883248731e-05,
1360
+ "loss": 0.1155,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 3.069620253164557,
1365
+ "grad_norm": 0.6288787722587585,
1366
+ "learning_rate": 7.753807106598985e-05,
1367
+ "loss": 0.1079,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 3.0854430379746836,
1372
+ "grad_norm": 0.6213780641555786,
1373
+ "learning_rate": 7.69035532994924e-05,
1374
+ "loss": 0.1196,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 3.1012658227848102,
1379
+ "grad_norm": 0.8186531066894531,
1380
+ "learning_rate": 7.626903553299492e-05,
1381
+ "loss": 0.1215,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 3.117088607594937,
1386
+ "grad_norm": 0.6212114691734314,
1387
+ "learning_rate": 7.563451776649747e-05,
1388
+ "loss": 0.1222,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 3.132911392405063,
1393
+ "grad_norm": 0.6861391067504883,
1394
+ "learning_rate": 7.500000000000001e-05,
1395
+ "loss": 0.1142,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 3.1487341772151898,
1400
+ "grad_norm": 0.5754695534706116,
1401
+ "learning_rate": 7.436548223350253e-05,
1402
+ "loss": 0.1144,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 3.1645569620253164,
1407
+ "grad_norm": 0.9572857022285461,
1408
+ "learning_rate": 7.373096446700508e-05,
1409
+ "loss": 0.1157,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 3.180379746835443,
1414
+ "grad_norm": 0.6589420437812805,
1415
+ "learning_rate": 7.309644670050762e-05,
1416
+ "loss": 0.1195,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 3.1962025316455698,
1421
+ "grad_norm": 0.7942759990692139,
1422
+ "learning_rate": 7.246192893401015e-05,
1423
+ "loss": 0.1199,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 3.212025316455696,
1428
+ "grad_norm": 0.7023386359214783,
1429
+ "learning_rate": 7.182741116751269e-05,
1430
+ "loss": 0.1198,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 3.2278481012658227,
1435
+ "grad_norm": 0.5077189207077026,
1436
+ "learning_rate": 7.119289340101524e-05,
1437
+ "loss": 0.1193,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 3.2436708860759493,
1442
+ "grad_norm": 1.0440549850463867,
1443
+ "learning_rate": 7.055837563451776e-05,
1444
+ "loss": 0.1141,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 3.259493670886076,
1449
+ "grad_norm": 0.6728818416595459,
1450
+ "learning_rate": 6.99238578680203e-05,
1451
+ "loss": 0.1184,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 3.2753164556962027,
1456
+ "grad_norm": 0.6550622582435608,
1457
+ "learning_rate": 6.928934010152285e-05,
1458
+ "loss": 0.1207,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 3.291139240506329,
1463
+ "grad_norm": 0.9485641121864319,
1464
+ "learning_rate": 6.865482233502538e-05,
1465
+ "loss": 0.1185,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 3.3069620253164556,
1470
+ "grad_norm": 0.7015439867973328,
1471
+ "learning_rate": 6.802030456852793e-05,
1472
+ "loss": 0.1166,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 3.3227848101265822,
1477
+ "grad_norm": 0.7128148674964905,
1478
+ "learning_rate": 6.738578680203046e-05,
1479
+ "loss": 0.1211,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 3.338607594936709,
1484
+ "grad_norm": 0.8616880178451538,
1485
+ "learning_rate": 6.6751269035533e-05,
1486
+ "loss": 0.1224,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 3.3544303797468356,
1491
+ "grad_norm": 1.673384189605713,
1492
+ "learning_rate": 6.611675126903554e-05,
1493
+ "loss": 0.1125,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 3.370253164556962,
1498
+ "grad_norm": 0.7952456474304199,
1499
+ "learning_rate": 6.548223350253807e-05,
1500
+ "loss": 0.1196,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 3.3860759493670884,
1505
+ "grad_norm": 0.7431464791297913,
1506
+ "learning_rate": 6.484771573604061e-05,
1507
+ "loss": 0.1172,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 3.401898734177215,
1512
+ "grad_norm": 0.9536241292953491,
1513
+ "learning_rate": 6.421319796954315e-05,
1514
+ "loss": 0.1227,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 3.4177215189873418,
1519
+ "grad_norm": 0.6027010679244995,
1520
+ "learning_rate": 6.35786802030457e-05,
1521
+ "loss": 0.1183,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 3.4335443037974684,
1526
+ "grad_norm": 0.6765082478523254,
1527
+ "learning_rate": 6.294416243654822e-05,
1528
+ "loss": 0.1222,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 3.449367088607595,
1533
+ "grad_norm": 0.8334203958511353,
1534
+ "learning_rate": 6.230964467005076e-05,
1535
+ "loss": 0.1188,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 3.4651898734177213,
1540
+ "grad_norm": 0.7078428864479065,
1541
+ "learning_rate": 6.167512690355331e-05,
1542
+ "loss": 0.1237,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 3.481012658227848,
1547
+ "grad_norm": 0.5793551206588745,
1548
+ "learning_rate": 6.104060913705584e-05,
1549
+ "loss": 0.1171,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 3.4968354430379747,
1554
+ "grad_norm": 0.816104531288147,
1555
+ "learning_rate": 6.040609137055838e-05,
1556
+ "loss": 0.1216,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 3.5126582278481013,
1561
+ "grad_norm": 0.5165361166000366,
1562
+ "learning_rate": 5.977157360406092e-05,
1563
+ "loss": 0.123,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 3.528481012658228,
1568
+ "grad_norm": 0.7187574505805969,
1569
+ "learning_rate": 5.913705583756346e-05,
1570
+ "loss": 0.1196,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 3.5443037974683547,
1575
+ "grad_norm": 0.8947055339813232,
1576
+ "learning_rate": 5.850253807106599e-05,
1577
+ "loss": 0.121,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 3.560126582278481,
1582
+ "grad_norm": 0.6461635828018188,
1583
+ "learning_rate": 5.786802030456853e-05,
1584
+ "loss": 0.1171,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 3.5759493670886076,
1589
+ "grad_norm": 0.5806897282600403,
1590
+ "learning_rate": 5.723350253807107e-05,
1591
+ "loss": 0.1095,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 3.5917721518987342,
1596
+ "grad_norm": 0.48626071214675903,
1597
+ "learning_rate": 5.65989847715736e-05,
1598
+ "loss": 0.117,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 3.607594936708861,
1603
+ "grad_norm": 0.7649936079978943,
1604
+ "learning_rate": 5.5964467005076145e-05,
1605
+ "loss": 0.1214,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 3.6234177215189876,
1610
+ "grad_norm": 0.8777173757553101,
1611
+ "learning_rate": 5.532994923857868e-05,
1612
+ "loss": 0.126,
1613
+ "step": 1145
1614
+ },
1615
+ {
1616
+ "epoch": 3.6392405063291138,
1617
+ "grad_norm": 0.7628064155578613,
1618
+ "learning_rate": 5.469543147208121e-05,
1619
+ "loss": 0.1194,
1620
+ "step": 1150
1621
+ },
1622
+ {
1623
+ "epoch": 3.6550632911392404,
1624
+ "grad_norm": 0.6170560717582703,
1625
+ "learning_rate": 5.406091370558376e-05,
1626
+ "loss": 0.119,
1627
+ "step": 1155
1628
+ },
1629
+ {
1630
+ "epoch": 3.670886075949367,
1631
+ "grad_norm": 0.6344670057296753,
1632
+ "learning_rate": 5.342639593908629e-05,
1633
+ "loss": 0.1153,
1634
+ "step": 1160
1635
+ },
1636
+ {
1637
+ "epoch": 3.6867088607594938,
1638
+ "grad_norm": 0.6660630702972412,
1639
+ "learning_rate": 5.2791878172588836e-05,
1640
+ "loss": 0.1224,
1641
+ "step": 1165
1642
+ },
1643
+ {
1644
+ "epoch": 3.7025316455696204,
1645
+ "grad_norm": 0.7865625619888306,
1646
+ "learning_rate": 5.215736040609137e-05,
1647
+ "loss": 0.1257,
1648
+ "step": 1170
1649
+ },
1650
+ {
1651
+ "epoch": 3.7183544303797467,
1652
+ "grad_norm": 0.611803412437439,
1653
+ "learning_rate": 5.152284263959392e-05,
1654
+ "loss": 0.1195,
1655
+ "step": 1175
1656
+ },
1657
+ {
1658
+ "epoch": 3.7341772151898733,
1659
+ "grad_norm": 0.9372175931930542,
1660
+ "learning_rate": 5.088832487309645e-05,
1661
+ "loss": 0.1239,
1662
+ "step": 1180
1663
+ },
1664
+ {
1665
+ "epoch": 3.75,
1666
+ "grad_norm": 0.6816895008087158,
1667
+ "learning_rate": 5.0253807106598984e-05,
1668
+ "loss": 0.1228,
1669
+ "step": 1185
1670
+ },
1671
+ {
1672
+ "epoch": 3.7658227848101267,
1673
+ "grad_norm": 0.5107612013816833,
1674
+ "learning_rate": 4.961928934010153e-05,
1675
+ "loss": 0.1171,
1676
+ "step": 1190
1677
+ },
1678
+ {
1679
+ "epoch": 3.7816455696202533,
1680
+ "grad_norm": 0.5778011679649353,
1681
+ "learning_rate": 4.8984771573604064e-05,
1682
+ "loss": 0.1253,
1683
+ "step": 1195
1684
+ },
1685
+ {
1686
+ "epoch": 3.7974683544303796,
1687
+ "grad_norm": 0.7186105251312256,
1688
+ "learning_rate": 4.83502538071066e-05,
1689
+ "loss": 0.1155,
1690
+ "step": 1200
1691
+ },
1692
+ {
1693
+ "epoch": 3.8132911392405062,
1694
+ "grad_norm": 0.7445695996284485,
1695
+ "learning_rate": 4.771573604060914e-05,
1696
+ "loss": 0.1176,
1697
+ "step": 1205
1698
+ },
1699
+ {
1700
+ "epoch": 3.829113924050633,
1701
+ "grad_norm": 0.593574047088623,
1702
+ "learning_rate": 4.7081218274111674e-05,
1703
+ "loss": 0.1158,
1704
+ "step": 1210
1705
+ },
1706
+ {
1707
+ "epoch": 3.8449367088607596,
1708
+ "grad_norm": 0.5334892272949219,
1709
+ "learning_rate": 4.644670050761422e-05,
1710
+ "loss": 0.1172,
1711
+ "step": 1215
1712
+ },
1713
+ {
1714
+ "epoch": 3.8607594936708862,
1715
+ "grad_norm": 0.5709195137023926,
1716
+ "learning_rate": 4.5812182741116755e-05,
1717
+ "loss": 0.1158,
1718
+ "step": 1220
1719
+ },
1720
+ {
1721
+ "epoch": 3.8765822784810124,
1722
+ "grad_norm": 0.6969111561775208,
1723
+ "learning_rate": 4.517766497461929e-05,
1724
+ "loss": 0.1198,
1725
+ "step": 1225
1726
+ },
1727
+ {
1728
+ "epoch": 3.892405063291139,
1729
+ "grad_norm": 0.5967200398445129,
1730
+ "learning_rate": 4.454314720812183e-05,
1731
+ "loss": 0.115,
1732
+ "step": 1230
1733
+ },
1734
+ {
1735
+ "epoch": 3.9082278481012658,
1736
+ "grad_norm": 0.6755451560020447,
1737
+ "learning_rate": 4.3908629441624365e-05,
1738
+ "loss": 0.1171,
1739
+ "step": 1235
1740
+ },
1741
+ {
1742
+ "epoch": 3.9240506329113924,
1743
+ "grad_norm": 0.7690590620040894,
1744
+ "learning_rate": 4.32741116751269e-05,
1745
+ "loss": 0.117,
1746
+ "step": 1240
1747
+ },
1748
+ {
1749
+ "epoch": 3.939873417721519,
1750
+ "grad_norm": 0.7448693513870239,
1751
+ "learning_rate": 4.2639593908629446e-05,
1752
+ "loss": 0.1183,
1753
+ "step": 1245
1754
+ },
1755
+ {
1756
+ "epoch": 3.9556962025316453,
1757
+ "grad_norm": 0.6257800459861755,
1758
+ "learning_rate": 4.200507614213198e-05,
1759
+ "loss": 0.1122,
1760
+ "step": 1250
1761
+ },
1762
+ {
1763
+ "epoch": 3.971518987341772,
1764
+ "grad_norm": 0.7136058807373047,
1765
+ "learning_rate": 4.137055837563452e-05,
1766
+ "loss": 0.1172,
1767
+ "step": 1255
1768
+ },
1769
+ {
1770
+ "epoch": 3.9873417721518987,
1771
+ "grad_norm": 0.8732256293296814,
1772
+ "learning_rate": 4.073604060913706e-05,
1773
+ "loss": 0.1198,
1774
+ "step": 1260
1775
+ },
1776
+ {
1777
+ "epoch": 4.003164556962025,
1778
+ "grad_norm": 0.3908518850803375,
1779
+ "learning_rate": 4.010152284263959e-05,
1780
+ "loss": 0.1182,
1781
+ "step": 1265
1782
+ },
1783
+ {
1784
+ "epoch": 4.018987341772152,
1785
+ "grad_norm": 0.3654375672340393,
1786
+ "learning_rate": 3.946700507614213e-05,
1787
+ "loss": 0.0943,
1788
+ "step": 1270
1789
+ },
1790
+ {
1791
+ "epoch": 4.034810126582278,
1792
+ "grad_norm": 0.44177666306495667,
1793
+ "learning_rate": 3.8832487309644673e-05,
1794
+ "loss": 0.093,
1795
+ "step": 1275
1796
+ },
1797
+ {
1798
+ "epoch": 4.050632911392405,
1799
+ "grad_norm": 0.548538863658905,
1800
+ "learning_rate": 3.819796954314721e-05,
1801
+ "loss": 0.0905,
1802
+ "step": 1280
1803
+ },
1804
+ {
1805
+ "epoch": 4.0664556962025316,
1806
+ "grad_norm": 0.34858939051628113,
1807
+ "learning_rate": 3.756345177664975e-05,
1808
+ "loss": 0.0882,
1809
+ "step": 1285
1810
+ },
1811
+ {
1812
+ "epoch": 4.082278481012658,
1813
+ "grad_norm": 0.44596415758132935,
1814
+ "learning_rate": 3.692893401015229e-05,
1815
+ "loss": 0.091,
1816
+ "step": 1290
1817
+ },
1818
+ {
1819
+ "epoch": 4.098101265822785,
1820
+ "grad_norm": 0.4271854758262634,
1821
+ "learning_rate": 3.629441624365482e-05,
1822
+ "loss": 0.0907,
1823
+ "step": 1295
1824
+ },
1825
+ {
1826
+ "epoch": 4.113924050632911,
1827
+ "grad_norm": 0.7120389938354492,
1828
+ "learning_rate": 3.565989847715736e-05,
1829
+ "loss": 0.0931,
1830
+ "step": 1300
1831
+ },
1832
+ {
1833
+ "epoch": 4.129746835443038,
1834
+ "grad_norm": 0.44612565636634827,
1835
+ "learning_rate": 3.50253807106599e-05,
1836
+ "loss": 0.0887,
1837
+ "step": 1305
1838
+ },
1839
+ {
1840
+ "epoch": 4.1455696202531644,
1841
+ "grad_norm": 0.34034597873687744,
1842
+ "learning_rate": 3.439086294416244e-05,
1843
+ "loss": 0.0903,
1844
+ "step": 1310
1845
+ },
1846
+ {
1847
+ "epoch": 4.1613924050632916,
1848
+ "grad_norm": 0.4155871570110321,
1849
+ "learning_rate": 3.3756345177664975e-05,
1850
+ "loss": 0.092,
1851
+ "step": 1315
1852
+ },
1853
+ {
1854
+ "epoch": 4.177215189873418,
1855
+ "grad_norm": 0.5939737558364868,
1856
+ "learning_rate": 3.312182741116752e-05,
1857
+ "loss": 0.0928,
1858
+ "step": 1320
1859
+ },
1860
+ {
1861
+ "epoch": 4.193037974683544,
1862
+ "grad_norm": 0.611441969871521,
1863
+ "learning_rate": 3.248730964467005e-05,
1864
+ "loss": 0.0897,
1865
+ "step": 1325
1866
+ },
1867
+ {
1868
+ "epoch": 4.208860759493671,
1869
+ "grad_norm": 0.6120615601539612,
1870
+ "learning_rate": 3.185279187817259e-05,
1871
+ "loss": 0.0936,
1872
+ "step": 1330
1873
+ },
1874
+ {
1875
+ "epoch": 4.224683544303797,
1876
+ "grad_norm": 0.4837358593940735,
1877
+ "learning_rate": 3.121827411167513e-05,
1878
+ "loss": 0.0896,
1879
+ "step": 1335
1880
+ },
1881
+ {
1882
+ "epoch": 4.2405063291139244,
1883
+ "grad_norm": 0.40970176458358765,
1884
+ "learning_rate": 3.0583756345177666e-05,
1885
+ "loss": 0.0928,
1886
+ "step": 1340
1887
+ },
1888
+ {
1889
+ "epoch": 4.256329113924051,
1890
+ "grad_norm": 0.4805232286453247,
1891
+ "learning_rate": 2.9949238578680206e-05,
1892
+ "loss": 0.0903,
1893
+ "step": 1345
1894
+ },
1895
+ {
1896
+ "epoch": 4.272151898734177,
1897
+ "grad_norm": 0.4605880379676819,
1898
+ "learning_rate": 2.9314720812182743e-05,
1899
+ "loss": 0.0903,
1900
+ "step": 1350
1901
+ },
1902
+ {
1903
+ "epoch": 4.287974683544304,
1904
+ "grad_norm": 0.4408807158470154,
1905
+ "learning_rate": 2.8680203045685283e-05,
1906
+ "loss": 0.0916,
1907
+ "step": 1355
1908
+ },
1909
+ {
1910
+ "epoch": 4.30379746835443,
1911
+ "grad_norm": 0.4075123071670532,
1912
+ "learning_rate": 2.8045685279187816e-05,
1913
+ "loss": 0.0878,
1914
+ "step": 1360
1915
+ },
1916
+ {
1917
+ "epoch": 4.319620253164557,
1918
+ "grad_norm": 0.5319828987121582,
1919
+ "learning_rate": 2.7411167512690357e-05,
1920
+ "loss": 0.0907,
1921
+ "step": 1365
1922
+ },
1923
+ {
1924
+ "epoch": 4.3354430379746836,
1925
+ "grad_norm": 0.5517973899841309,
1926
+ "learning_rate": 2.6776649746192893e-05,
1927
+ "loss": 0.0895,
1928
+ "step": 1370
1929
+ },
1930
+ {
1931
+ "epoch": 4.35126582278481,
1932
+ "grad_norm": 0.48083606362342834,
1933
+ "learning_rate": 2.6142131979695434e-05,
1934
+ "loss": 0.0921,
1935
+ "step": 1375
1936
+ },
1937
+ {
1938
+ "epoch": 4.367088607594937,
1939
+ "grad_norm": 0.5320701599121094,
1940
+ "learning_rate": 2.5507614213197974e-05,
1941
+ "loss": 0.0917,
1942
+ "step": 1380
1943
+ },
1944
+ {
1945
+ "epoch": 4.382911392405063,
1946
+ "grad_norm": 0.416904479265213,
1947
+ "learning_rate": 2.4873096446700507e-05,
1948
+ "loss": 0.0928,
1949
+ "step": 1385
1950
+ },
1951
+ {
1952
+ "epoch": 4.39873417721519,
1953
+ "grad_norm": 0.49495264887809753,
1954
+ "learning_rate": 2.4238578680203047e-05,
1955
+ "loss": 0.0911,
1956
+ "step": 1390
1957
+ },
1958
+ {
1959
+ "epoch": 4.4145569620253164,
1960
+ "grad_norm": 0.5663470029830933,
1961
+ "learning_rate": 2.3604060913705588e-05,
1962
+ "loss": 0.095,
1963
+ "step": 1395
1964
+ },
1965
+ {
1966
+ "epoch": 4.430379746835443,
1967
+ "grad_norm": 0.49303102493286133,
1968
+ "learning_rate": 2.296954314720812e-05,
1969
+ "loss": 0.0937,
1970
+ "step": 1400
1971
+ },
1972
+ {
1973
+ "epoch": 4.44620253164557,
1974
+ "grad_norm": 0.3795440196990967,
1975
+ "learning_rate": 2.233502538071066e-05,
1976
+ "loss": 0.0899,
1977
+ "step": 1405
1978
+ },
1979
+ {
1980
+ "epoch": 4.462025316455696,
1981
+ "grad_norm": 0.4684379994869232,
1982
+ "learning_rate": 2.17005076142132e-05,
1983
+ "loss": 0.0924,
1984
+ "step": 1410
1985
+ },
1986
+ {
1987
+ "epoch": 4.477848101265823,
1988
+ "grad_norm": 0.3904794156551361,
1989
+ "learning_rate": 2.1065989847715735e-05,
1990
+ "loss": 0.0922,
1991
+ "step": 1415
1992
+ },
1993
+ {
1994
+ "epoch": 4.493670886075949,
1995
+ "grad_norm": 0.6037257313728333,
1996
+ "learning_rate": 2.0431472081218275e-05,
1997
+ "loss": 0.096,
1998
+ "step": 1420
1999
+ },
2000
+ {
2001
+ "epoch": 4.509493670886076,
2002
+ "grad_norm": 0.30922073125839233,
2003
+ "learning_rate": 1.9796954314720815e-05,
2004
+ "loss": 0.091,
2005
+ "step": 1425
2006
+ },
2007
+ {
2008
+ "epoch": 4.525316455696203,
2009
+ "grad_norm": 0.5561403036117554,
2010
+ "learning_rate": 1.916243654822335e-05,
2011
+ "loss": 0.0905,
2012
+ "step": 1430
2013
+ },
2014
+ {
2015
+ "epoch": 4.541139240506329,
2016
+ "grad_norm": 0.389127641916275,
2017
+ "learning_rate": 1.852791878172589e-05,
2018
+ "loss": 0.0906,
2019
+ "step": 1435
2020
+ },
2021
+ {
2022
+ "epoch": 4.556962025316456,
2023
+ "grad_norm": 0.38574787974357605,
2024
+ "learning_rate": 1.789340101522843e-05,
2025
+ "loss": 0.0891,
2026
+ "step": 1440
2027
+ },
2028
+ {
2029
+ "epoch": 4.572784810126582,
2030
+ "grad_norm": 0.42243725061416626,
2031
+ "learning_rate": 1.7258883248730966e-05,
2032
+ "loss": 0.0961,
2033
+ "step": 1445
2034
+ },
2035
+ {
2036
+ "epoch": 4.588607594936709,
2037
+ "grad_norm": 0.522402286529541,
2038
+ "learning_rate": 1.6624365482233503e-05,
2039
+ "loss": 0.0889,
2040
+ "step": 1450
2041
+ },
2042
+ {
2043
+ "epoch": 4.6044303797468356,
2044
+ "grad_norm": 0.3562035858631134,
2045
+ "learning_rate": 1.5989847715736043e-05,
2046
+ "loss": 0.0879,
2047
+ "step": 1455
2048
+ },
2049
+ {
2050
+ "epoch": 4.620253164556962,
2051
+ "grad_norm": 0.7289389967918396,
2052
+ "learning_rate": 1.535532994923858e-05,
2053
+ "loss": 0.0955,
2054
+ "step": 1460
2055
+ },
2056
+ {
2057
+ "epoch": 4.636075949367089,
2058
+ "grad_norm": 0.4322461783885956,
2059
+ "learning_rate": 1.4720812182741117e-05,
2060
+ "loss": 0.0933,
2061
+ "step": 1465
2062
+ },
2063
+ {
2064
+ "epoch": 4.651898734177215,
2065
+ "grad_norm": 0.5375872850418091,
2066
+ "learning_rate": 1.4086294416243657e-05,
2067
+ "loss": 0.0911,
2068
+ "step": 1470
2069
+ },
2070
+ {
2071
+ "epoch": 4.667721518987342,
2072
+ "grad_norm": 0.4194104075431824,
2073
+ "learning_rate": 1.3451776649746192e-05,
2074
+ "loss": 0.0878,
2075
+ "step": 1475
2076
+ },
2077
+ {
2078
+ "epoch": 4.6835443037974684,
2079
+ "grad_norm": 0.4603971242904663,
2080
+ "learning_rate": 1.281725888324873e-05,
2081
+ "loss": 0.0916,
2082
+ "step": 1480
2083
+ },
2084
+ {
2085
+ "epoch": 4.699367088607595,
2086
+ "grad_norm": 0.34578830003738403,
2087
+ "learning_rate": 1.218274111675127e-05,
2088
+ "loss": 0.0905,
2089
+ "step": 1485
2090
+ },
2091
+ {
2092
+ "epoch": 4.715189873417722,
2093
+ "grad_norm": 0.7133288383483887,
2094
+ "learning_rate": 1.1548223350253808e-05,
2095
+ "loss": 0.0889,
2096
+ "step": 1490
2097
+ },
2098
+ {
2099
+ "epoch": 4.731012658227848,
2100
+ "grad_norm": 0.6632990837097168,
2101
+ "learning_rate": 1.0913705583756344e-05,
2102
+ "loss": 0.0912,
2103
+ "step": 1495
2104
+ },
2105
+ {
2106
+ "epoch": 4.746835443037975,
2107
+ "grad_norm": 0.339555561542511,
2108
+ "learning_rate": 1.0279187817258885e-05,
2109
+ "loss": 0.091,
2110
+ "step": 1500
2111
+ },
2112
+ {
2113
+ "epoch": 4.762658227848101,
2114
+ "grad_norm": 0.48535045981407166,
2115
+ "learning_rate": 9.644670050761421e-06,
2116
+ "loss": 0.0957,
2117
+ "step": 1505
2118
+ },
2119
+ {
2120
+ "epoch": 4.7784810126582276,
2121
+ "grad_norm": 0.46517860889434814,
2122
+ "learning_rate": 9.01015228426396e-06,
2123
+ "loss": 0.0919,
2124
+ "step": 1510
2125
+ },
2126
+ {
2127
+ "epoch": 4.794303797468355,
2128
+ "grad_norm": 0.6948912739753723,
2129
+ "learning_rate": 8.375634517766498e-06,
2130
+ "loss": 0.0899,
2131
+ "step": 1515
2132
+ },
2133
+ {
2134
+ "epoch": 4.810126582278481,
2135
+ "grad_norm": 0.4421853721141815,
2136
+ "learning_rate": 7.741116751269035e-06,
2137
+ "loss": 0.092,
2138
+ "step": 1520
2139
+ },
2140
+ {
2141
+ "epoch": 4.825949367088608,
2142
+ "grad_norm": 0.4198189973831177,
2143
+ "learning_rate": 7.106598984771575e-06,
2144
+ "loss": 0.0905,
2145
+ "step": 1525
2146
+ },
2147
+ {
2148
+ "epoch": 4.841772151898734,
2149
+ "grad_norm": 0.47301727533340454,
2150
+ "learning_rate": 6.472081218274112e-06,
2151
+ "loss": 0.0907,
2152
+ "step": 1530
2153
+ },
2154
+ {
2155
+ "epoch": 4.8575949367088604,
2156
+ "grad_norm": 0.36296045780181885,
2157
+ "learning_rate": 5.83756345177665e-06,
2158
+ "loss": 0.0894,
2159
+ "step": 1535
2160
+ },
2161
+ {
2162
+ "epoch": 4.8734177215189876,
2163
+ "grad_norm": 0.4861876666545868,
2164
+ "learning_rate": 5.203045685279188e-06,
2165
+ "loss": 0.091,
2166
+ "step": 1540
2167
+ },
2168
+ {
2169
+ "epoch": 4.889240506329114,
2170
+ "grad_norm": 0.44622302055358887,
2171
+ "learning_rate": 4.568527918781726e-06,
2172
+ "loss": 0.0937,
2173
+ "step": 1545
2174
+ },
2175
+ {
2176
+ "epoch": 4.905063291139241,
2177
+ "grad_norm": 0.45360803604125977,
2178
+ "learning_rate": 3.934010152284264e-06,
2179
+ "loss": 0.0904,
2180
+ "step": 1550
2181
+ },
2182
+ {
2183
+ "epoch": 4.920886075949367,
2184
+ "grad_norm": 0.5564279556274414,
2185
+ "learning_rate": 3.2994923857868023e-06,
2186
+ "loss": 0.0921,
2187
+ "step": 1555
2188
+ },
2189
+ {
2190
+ "epoch": 4.936708860759493,
2191
+ "grad_norm": 0.5952951908111572,
2192
+ "learning_rate": 2.6649746192893404e-06,
2193
+ "loss": 0.0929,
2194
+ "step": 1560
2195
+ },
2196
+ {
2197
+ "epoch": 4.9525316455696204,
2198
+ "grad_norm": 0.6146189570426941,
2199
+ "learning_rate": 2.030456852791878e-06,
2200
+ "loss": 0.0906,
2201
+ "step": 1565
2202
+ },
2203
+ {
2204
+ "epoch": 4.968354430379747,
2205
+ "grad_norm": 0.5644097328186035,
2206
+ "learning_rate": 1.3959390862944163e-06,
2207
+ "loss": 0.0942,
2208
+ "step": 1570
2209
+ },
2210
+ {
2211
+ "epoch": 4.984177215189874,
2212
+ "grad_norm": 0.43627479672431946,
2213
+ "learning_rate": 7.614213197969544e-07,
2214
+ "loss": 0.0935,
2215
+ "step": 1575
2216
+ },
2217
+ {
2218
+ "epoch": 5.0,
2219
+ "grad_norm": 0.864841639995575,
2220
+ "learning_rate": 1.2690355329949238e-07,
2221
+ "loss": 0.0912,
2222
+ "step": 1580
2223
+ }
2224
+ ],
2225
+ "logging_steps": 5,
2226
+ "max_steps": 1580,
2227
+ "num_input_tokens_seen": 0,
2228
+ "num_train_epochs": 5,
2229
+ "save_steps": 500,
2230
+ "stateful_callbacks": {
2231
+ "TrainerControl": {
2232
+ "args": {
2233
+ "should_epoch_stop": false,
2234
+ "should_evaluate": false,
2235
+ "should_log": false,
2236
+ "should_save": true,
2237
+ "should_training_stop": true
2238
+ },
2239
+ "attributes": {}
2240
+ }
2241
+ },
2242
+ "total_flos": 1.3721567654375424e+17,
2243
+ "train_batch_size": 16,
2244
+ "trial_name": null,
2245
+ "trial_params": null
2246
+ }
experiments/de-en-pt-zh/checkpoint-1580/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1f965478a30d642e1d3280129a9cb365127c4096496511633d6b72e8ccf15e
3
+ size 6289
experiments/de-en-pt-zh/checkpoint-500/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.1
experiments/de-en-pt-zh/checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.1,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 8,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "gate_proj",
37
+ "v_proj",
38
+ "o_proj",
39
+ "k_proj",
40
+ "up_proj",
41
+ "down_proj",
42
+ "q_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true
50
+ }
experiments/de-en-pt-zh/checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999c071c224c7037a29d77f5816ccfddb44b8242c7e930711f0a1b0a8aac5552
3
+ size 83945296
experiments/de-en-pt-zh/checkpoint-500/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 %}
experiments/de-en-pt-zh/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48cc06e82e75cf7d4c8d7b0263a4aaf989b60be0a78d9a6c8d7afbf91447dd28
3
+ size 43123429