Lalu-Prakash commited on
Commit
3e778d1
·
verified ·
1 Parent(s): fd62cf5

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 +7 -0
  2. README.md +58 -0
  3. chat_template.jinja +5 -0
  4. checkpoint-141/README.md +209 -0
  5. checkpoint-141/adapter_config.json +39 -0
  6. checkpoint-141/adapter_model.safetensors +3 -0
  7. checkpoint-141/chat_template.jinja +5 -0
  8. checkpoint-141/optimizer.pt +3 -0
  9. checkpoint-141/rng_state.pth +3 -0
  10. checkpoint-141/scheduler.pt +3 -0
  11. checkpoint-141/special_tokens_map.json +16 -0
  12. checkpoint-141/tokenizer.json +3 -0
  13. checkpoint-141/tokenizer_config.json +2062 -0
  14. checkpoint-141/trainer_state.json +1444 -0
  15. checkpoint-141/training_args.bin +3 -0
  16. checkpoint-282/README.md +209 -0
  17. checkpoint-282/adapter_config.json +39 -0
  18. checkpoint-282/adapter_model.safetensors +3 -0
  19. checkpoint-282/chat_template.jinja +5 -0
  20. checkpoint-282/optimizer.pt +3 -0
  21. checkpoint-282/rng_state.pth +3 -0
  22. checkpoint-282/scheduler.pt +3 -0
  23. checkpoint-282/special_tokens_map.json +16 -0
  24. checkpoint-282/tokenizer.json +3 -0
  25. checkpoint-282/tokenizer_config.json +2062 -0
  26. checkpoint-282/trainer_state.json +2854 -0
  27. checkpoint-282/training_args.bin +3 -0
  28. checkpoint-423/README.md +209 -0
  29. checkpoint-423/adapter_config.json +39 -0
  30. checkpoint-423/adapter_model.safetensors +3 -0
  31. checkpoint-423/chat_template.jinja +5 -0
  32. checkpoint-423/optimizer.pt +3 -0
  33. checkpoint-423/rng_state.pth +3 -0
  34. checkpoint-423/scheduler.pt +3 -0
  35. checkpoint-423/special_tokens_map.json +16 -0
  36. checkpoint-423/tokenizer.json +3 -0
  37. checkpoint-423/tokenizer_config.json +2062 -0
  38. checkpoint-423/trainer_state.json +0 -0
  39. checkpoint-423/training_args.bin +3 -0
  40. checkpoint-564/README.md +209 -0
  41. checkpoint-564/adapter_config.json +39 -0
  42. checkpoint-564/adapter_model.safetensors +3 -0
  43. checkpoint-564/chat_template.jinja +5 -0
  44. checkpoint-564/optimizer.pt +3 -0
  45. checkpoint-564/rng_state.pth +3 -0
  46. checkpoint-564/scheduler.pt +3 -0
  47. checkpoint-564/special_tokens_map.json +16 -0
  48. checkpoint-564/tokenizer.json +3 -0
  49. checkpoint-564/tokenizer_config.json +2062 -0
  50. checkpoint-564/trainer_state.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-141/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-282/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-423/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-564/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-705/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-846/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: transformers
4
+ model_name: Llama3-FT-6epochs-Crime_and_gun_right
5
+ tags:
6
+ - generated_from_trainer
7
+ - sft
8
+ - trl
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for Llama3-FT-6epochs-Crime_and_gun_right
13
+
14
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="None", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.23.0
38
+ - Transformers: 4.56.2
39
+ - Pytorch: 2.5.1
40
+ - Datasets: 3.2.0
41
+ - Tokenizers: 0.22.1
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
checkpoint-141/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
checkpoint-141/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj"
32
+ ],
33
+ "target_parameters": null,
34
+ "task_type": "CAUSAL_LM",
35
+ "trainable_token_indices": null,
36
+ "use_dora": false,
37
+ "use_qalora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-141/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f181e388f2dbfd451cc598ab3b51bfc3f7493234ff6e0ae9cc2552efa6286a
3
+ size 54560368
checkpoint-141/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
checkpoint-141/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7f0acca4e8f03195fa986f1c459e93c8bf7ff606c9e7cbb91478834391ccaa
3
+ size 1192
checkpoint-141/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f56f7d91a883de95d47d1d09744f45b58d2515cfcebae517d9162c6bd0ff5c0
3
+ size 14244
checkpoint-141/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8924d6cf083da37e1c25360ba2c8b1cce55f785c1191059df24e52df380b7a0
3
+ size 1064
checkpoint-141/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-141/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
checkpoint-141/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-141/trainer_state.json ADDED
@@ -0,0 +1,1444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 141,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.6387848258018494,
14
+ "epoch": 0.0071301247771836,
15
+ "grad_norm": 0.0,
16
+ "learning_rate": 0.0,
17
+ "loss": 2.6515,
18
+ "mean_token_accuracy": 0.445863775908947,
19
+ "num_tokens": 1051.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 1.6529399156570435,
24
+ "epoch": 0.0142602495543672,
25
+ "grad_norm": 0.0,
26
+ "learning_rate": 4e-05,
27
+ "loss": 2.7153,
28
+ "mean_token_accuracy": 0.4470880478620529,
29
+ "num_tokens": 2187.0,
30
+ "step": 2
31
+ },
32
+ {
33
+ "entropy": 1.5581220388412476,
34
+ "epoch": 0.0213903743315508,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 8e-05,
37
+ "loss": 2.6255,
38
+ "mean_token_accuracy": 0.4684518948197365,
39
+ "num_tokens": 3295.0,
40
+ "step": 3
41
+ },
42
+ {
43
+ "entropy": 1.5885010659694672,
44
+ "epoch": 0.0285204991087344,
45
+ "grad_norm": 0.0,
46
+ "learning_rate": 0.00012,
47
+ "loss": 2.5733,
48
+ "mean_token_accuracy": 0.4601749926805496,
49
+ "num_tokens": 4387.0,
50
+ "step": 4
51
+ },
52
+ {
53
+ "entropy": 1.6543156504631042,
54
+ "epoch": 0.035650623885918005,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.00016,
57
+ "loss": 2.6477,
58
+ "mean_token_accuracy": 0.4556595981121063,
59
+ "num_tokens": 5511.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "entropy": 1.5543809533119202,
64
+ "epoch": 0.0427807486631016,
65
+ "grad_norm": 0.0,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.6579,
68
+ "mean_token_accuracy": 0.46554840356111526,
69
+ "num_tokens": 6598.0,
70
+ "step": 6
71
+ },
72
+ {
73
+ "entropy": 1.5990856289863586,
74
+ "epoch": 0.049910873440285206,
75
+ "grad_norm": 0.0,
76
+ "learning_rate": 0.00019976218787158144,
77
+ "loss": 2.6618,
78
+ "mean_token_accuracy": 0.4601997211575508,
79
+ "num_tokens": 7673.0,
80
+ "step": 7
81
+ },
82
+ {
83
+ "entropy": 1.6176924407482147,
84
+ "epoch": 0.0570409982174688,
85
+ "grad_norm": 0.0,
86
+ "learning_rate": 0.00019952437574316292,
87
+ "loss": 2.7365,
88
+ "mean_token_accuracy": 0.4649490937590599,
89
+ "num_tokens": 8774.0,
90
+ "step": 8
91
+ },
92
+ {
93
+ "entropy": 1.5261479020118713,
94
+ "epoch": 0.06417112299465241,
95
+ "grad_norm": 0.0,
96
+ "learning_rate": 0.00019928656361474436,
97
+ "loss": 2.5824,
98
+ "mean_token_accuracy": 0.47935400158166885,
99
+ "num_tokens": 9886.0,
100
+ "step": 9
101
+ },
102
+ {
103
+ "entropy": 1.6173927783966064,
104
+ "epoch": 0.07130124777183601,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 0.0001990487514863258,
107
+ "loss": 2.53,
108
+ "mean_token_accuracy": 0.47585250437259674,
109
+ "num_tokens": 10983.0,
110
+ "step": 10
111
+ },
112
+ {
113
+ "entropy": 1.5592622458934784,
114
+ "epoch": 0.0784313725490196,
115
+ "grad_norm": 0.0,
116
+ "learning_rate": 0.00019881093935790727,
117
+ "loss": 2.6422,
118
+ "mean_token_accuracy": 0.46385403722524643,
119
+ "num_tokens": 12102.0,
120
+ "step": 11
121
+ },
122
+ {
123
+ "entropy": 1.5775817930698395,
124
+ "epoch": 0.0855614973262032,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 0.0001985731272294887,
127
+ "loss": 2.6095,
128
+ "mean_token_accuracy": 0.49216530472040176,
129
+ "num_tokens": 13219.0,
130
+ "step": 12
131
+ },
132
+ {
133
+ "entropy": 1.6316154599189758,
134
+ "epoch": 0.09269162210338681,
135
+ "grad_norm": 0.0,
136
+ "learning_rate": 0.00019833531510107019,
137
+ "loss": 2.7746,
138
+ "mean_token_accuracy": 0.4526786059141159,
139
+ "num_tokens": 14309.0,
140
+ "step": 13
141
+ },
142
+ {
143
+ "entropy": 1.5752335786819458,
144
+ "epoch": 0.09982174688057041,
145
+ "grad_norm": 0.0,
146
+ "learning_rate": 0.00019809750297265162,
147
+ "loss": 2.6994,
148
+ "mean_token_accuracy": 0.4809372276067734,
149
+ "num_tokens": 15373.0,
150
+ "step": 14
151
+ },
152
+ {
153
+ "entropy": 1.5528400540351868,
154
+ "epoch": 0.10695187165775401,
155
+ "grad_norm": 0.0,
156
+ "learning_rate": 0.00019785969084423305,
157
+ "loss": 2.6607,
158
+ "mean_token_accuracy": 0.4793297126889229,
159
+ "num_tokens": 16485.0,
160
+ "step": 15
161
+ },
162
+ {
163
+ "entropy": 1.6115093529224396,
164
+ "epoch": 0.1140819964349376,
165
+ "grad_norm": 0.0,
166
+ "learning_rate": 0.00019762187871581453,
167
+ "loss": 2.6006,
168
+ "mean_token_accuracy": 0.48629891872406006,
169
+ "num_tokens": 17654.0,
170
+ "step": 16
171
+ },
172
+ {
173
+ "entropy": 1.6650608479976654,
174
+ "epoch": 0.12121212121212122,
175
+ "grad_norm": 0.0,
176
+ "learning_rate": 0.00019738406658739596,
177
+ "loss": 2.8227,
178
+ "mean_token_accuracy": 0.4469343200325966,
179
+ "num_tokens": 18705.0,
180
+ "step": 17
181
+ },
182
+ {
183
+ "entropy": 1.5981396436691284,
184
+ "epoch": 0.12834224598930483,
185
+ "grad_norm": 0.0,
186
+ "learning_rate": 0.00019714625445897742,
187
+ "loss": 2.6602,
188
+ "mean_token_accuracy": 0.48277803510427475,
189
+ "num_tokens": 19799.0,
190
+ "step": 18
191
+ },
192
+ {
193
+ "entropy": 1.6768196523189545,
194
+ "epoch": 0.1354723707664884,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 0.00019690844233055888,
197
+ "loss": 2.7339,
198
+ "mean_token_accuracy": 0.45305337756872177,
199
+ "num_tokens": 20799.0,
200
+ "step": 19
201
+ },
202
+ {
203
+ "entropy": 1.6276516318321228,
204
+ "epoch": 0.14260249554367202,
205
+ "grad_norm": 0.0,
206
+ "learning_rate": 0.0001966706302021403,
207
+ "loss": 2.6103,
208
+ "mean_token_accuracy": 0.45762092620134354,
209
+ "num_tokens": 21918.0,
210
+ "step": 20
211
+ },
212
+ {
213
+ "entropy": 1.5985995829105377,
214
+ "epoch": 0.1497326203208556,
215
+ "grad_norm": 0.0,
216
+ "learning_rate": 0.00019643281807372177,
217
+ "loss": 2.6705,
218
+ "mean_token_accuracy": 0.474429652094841,
219
+ "num_tokens": 23021.0,
220
+ "step": 21
221
+ },
222
+ {
223
+ "entropy": 1.6575533151626587,
224
+ "epoch": 0.1568627450980392,
225
+ "grad_norm": 0.0,
226
+ "learning_rate": 0.00019619500594530322,
227
+ "loss": 2.7187,
228
+ "mean_token_accuracy": 0.4531744047999382,
229
+ "num_tokens": 24138.0,
230
+ "step": 22
231
+ },
232
+ {
233
+ "entropy": 1.6001036167144775,
234
+ "epoch": 0.16399286987522282,
235
+ "grad_norm": 0.0,
236
+ "learning_rate": 0.00019595719381688465,
237
+ "loss": 2.6272,
238
+ "mean_token_accuracy": 0.4594630151987076,
239
+ "num_tokens": 25229.0,
240
+ "step": 23
241
+ },
242
+ {
243
+ "entropy": 1.6082253158092499,
244
+ "epoch": 0.1711229946524064,
245
+ "grad_norm": 0.0,
246
+ "learning_rate": 0.00019571938168846614,
247
+ "loss": 2.5586,
248
+ "mean_token_accuracy": 0.4784083887934685,
249
+ "num_tokens": 26339.0,
250
+ "step": 24
251
+ },
252
+ {
253
+ "entropy": 1.6208438277244568,
254
+ "epoch": 0.17825311942959002,
255
+ "grad_norm": 0.0,
256
+ "learning_rate": 0.00019548156956004757,
257
+ "loss": 2.6095,
258
+ "mean_token_accuracy": 0.4685538485646248,
259
+ "num_tokens": 27389.0,
260
+ "step": 25
261
+ },
262
+ {
263
+ "entropy": 1.6018637418746948,
264
+ "epoch": 0.18538324420677363,
265
+ "grad_norm": 0.0,
266
+ "learning_rate": 0.00019524375743162903,
267
+ "loss": 2.7047,
268
+ "mean_token_accuracy": 0.4501718729734421,
269
+ "num_tokens": 28491.0,
270
+ "step": 26
271
+ },
272
+ {
273
+ "entropy": 1.566238820552826,
274
+ "epoch": 0.1925133689839572,
275
+ "grad_norm": 0.0,
276
+ "learning_rate": 0.00019500594530321049,
277
+ "loss": 2.5167,
278
+ "mean_token_accuracy": 0.4768272563815117,
279
+ "num_tokens": 29617.0,
280
+ "step": 27
281
+ },
282
+ {
283
+ "entropy": 1.5953451693058014,
284
+ "epoch": 0.19964349376114082,
285
+ "grad_norm": 0.0,
286
+ "learning_rate": 0.00019476813317479192,
287
+ "loss": 2.6907,
288
+ "mean_token_accuracy": 0.46527716517448425,
289
+ "num_tokens": 30709.0,
290
+ "step": 28
291
+ },
292
+ {
293
+ "entropy": 1.6036897897720337,
294
+ "epoch": 0.20677361853832443,
295
+ "grad_norm": 0.0,
296
+ "learning_rate": 0.00019453032104637337,
297
+ "loss": 2.621,
298
+ "mean_token_accuracy": 0.47111422568559647,
299
+ "num_tokens": 31780.0,
300
+ "step": 29
301
+ },
302
+ {
303
+ "entropy": 1.6660344302654266,
304
+ "epoch": 0.21390374331550802,
305
+ "grad_norm": 0.0,
306
+ "learning_rate": 0.00019429250891795483,
307
+ "loss": 2.6351,
308
+ "mean_token_accuracy": 0.45088133215904236,
309
+ "num_tokens": 32827.0,
310
+ "step": 30
311
+ },
312
+ {
313
+ "entropy": 1.5515300929546356,
314
+ "epoch": 0.22103386809269163,
315
+ "grad_norm": 0.0,
316
+ "learning_rate": 0.00019405469678953626,
317
+ "loss": 2.5804,
318
+ "mean_token_accuracy": 0.47831422835588455,
319
+ "num_tokens": 33977.0,
320
+ "step": 31
321
+ },
322
+ {
323
+ "entropy": 1.4917864799499512,
324
+ "epoch": 0.2281639928698752,
325
+ "grad_norm": 0.0,
326
+ "learning_rate": 0.00019381688466111775,
327
+ "loss": 2.5906,
328
+ "mean_token_accuracy": 0.4912087470293045,
329
+ "num_tokens": 35070.0,
330
+ "step": 32
331
+ },
332
+ {
333
+ "entropy": 1.591080754995346,
334
+ "epoch": 0.23529411764705882,
335
+ "grad_norm": 0.0,
336
+ "learning_rate": 0.00019357907253269918,
337
+ "loss": 2.7147,
338
+ "mean_token_accuracy": 0.4610803797841072,
339
+ "num_tokens": 36137.0,
340
+ "step": 33
341
+ },
342
+ {
343
+ "entropy": 1.5161702930927277,
344
+ "epoch": 0.24242424242424243,
345
+ "grad_norm": 0.0,
346
+ "learning_rate": 0.00019334126040428064,
347
+ "loss": 2.4586,
348
+ "mean_token_accuracy": 0.5084197968244553,
349
+ "num_tokens": 37239.0,
350
+ "step": 34
351
+ },
352
+ {
353
+ "entropy": 1.5857904851436615,
354
+ "epoch": 0.24955436720142601,
355
+ "grad_norm": 0.0,
356
+ "learning_rate": 0.0001931034482758621,
357
+ "loss": 2.5836,
358
+ "mean_token_accuracy": 0.48300980031490326,
359
+ "num_tokens": 38330.0,
360
+ "step": 35
361
+ },
362
+ {
363
+ "entropy": 1.6427140533924103,
364
+ "epoch": 0.25668449197860965,
365
+ "grad_norm": 0.0,
366
+ "learning_rate": 0.00019286563614744352,
367
+ "loss": 2.6629,
368
+ "mean_token_accuracy": 0.4738333150744438,
369
+ "num_tokens": 39368.0,
370
+ "step": 36
371
+ },
372
+ {
373
+ "entropy": 1.6292171776294708,
374
+ "epoch": 0.2638146167557932,
375
+ "grad_norm": 0.0,
376
+ "learning_rate": 0.00019262782401902498,
377
+ "loss": 2.7382,
378
+ "mean_token_accuracy": 0.46079348772764206,
379
+ "num_tokens": 40474.0,
380
+ "step": 37
381
+ },
382
+ {
383
+ "entropy": 1.5661435425281525,
384
+ "epoch": 0.2709447415329768,
385
+ "grad_norm": 0.0,
386
+ "learning_rate": 0.00019239001189060644,
387
+ "loss": 2.4905,
388
+ "mean_token_accuracy": 0.49719007313251495,
389
+ "num_tokens": 41558.0,
390
+ "step": 38
391
+ },
392
+ {
393
+ "entropy": 1.6255074739456177,
394
+ "epoch": 0.27807486631016043,
395
+ "grad_norm": 0.0,
396
+ "learning_rate": 0.00019215219976218787,
397
+ "loss": 2.6303,
398
+ "mean_token_accuracy": 0.4578748494386673,
399
+ "num_tokens": 42674.0,
400
+ "step": 39
401
+ },
402
+ {
403
+ "entropy": 1.4836209118366241,
404
+ "epoch": 0.28520499108734404,
405
+ "grad_norm": 0.0,
406
+ "learning_rate": 0.00019191438763376933,
407
+ "loss": 2.5324,
408
+ "mean_token_accuracy": 0.4868450313806534,
409
+ "num_tokens": 43815.0,
410
+ "step": 40
411
+ },
412
+ {
413
+ "entropy": 1.5689969956874847,
414
+ "epoch": 0.29233511586452765,
415
+ "grad_norm": 0.0,
416
+ "learning_rate": 0.00019167657550535079,
417
+ "loss": 2.6125,
418
+ "mean_token_accuracy": 0.45523975044488907,
419
+ "num_tokens": 44890.0,
420
+ "step": 41
421
+ },
422
+ {
423
+ "entropy": 1.5794390439987183,
424
+ "epoch": 0.2994652406417112,
425
+ "grad_norm": 0.0,
426
+ "learning_rate": 0.00019143876337693222,
427
+ "loss": 2.6012,
428
+ "mean_token_accuracy": 0.47063395380973816,
429
+ "num_tokens": 45951.0,
430
+ "step": 42
431
+ },
432
+ {
433
+ "entropy": 1.6168677806854248,
434
+ "epoch": 0.3065953654188948,
435
+ "grad_norm": 0.0,
436
+ "learning_rate": 0.0001912009512485137,
437
+ "loss": 2.6358,
438
+ "mean_token_accuracy": 0.46999557316303253,
439
+ "num_tokens": 47083.0,
440
+ "step": 43
441
+ },
442
+ {
443
+ "entropy": 1.6417001783847809,
444
+ "epoch": 0.3137254901960784,
445
+ "grad_norm": 0.0,
446
+ "learning_rate": 0.00019096313912009513,
447
+ "loss": 2.6473,
448
+ "mean_token_accuracy": 0.4624517187476158,
449
+ "num_tokens": 48088.0,
450
+ "step": 44
451
+ },
452
+ {
453
+ "entropy": 1.6053949892520905,
454
+ "epoch": 0.32085561497326204,
455
+ "grad_norm": 0.0,
456
+ "learning_rate": 0.0001907253269916766,
457
+ "loss": 2.6728,
458
+ "mean_token_accuracy": 0.4565429463982582,
459
+ "num_tokens": 49213.0,
460
+ "step": 45
461
+ },
462
+ {
463
+ "entropy": 1.5239336490631104,
464
+ "epoch": 0.32798573975044565,
465
+ "grad_norm": 0.0,
466
+ "learning_rate": 0.00019048751486325805,
467
+ "loss": 2.5886,
468
+ "mean_token_accuracy": 0.47441017627716064,
469
+ "num_tokens": 50287.0,
470
+ "step": 46
471
+ },
472
+ {
473
+ "entropy": 1.5953067243099213,
474
+ "epoch": 0.33511586452762926,
475
+ "grad_norm": 0.0,
476
+ "learning_rate": 0.00019024970273483948,
477
+ "loss": 2.6498,
478
+ "mean_token_accuracy": 0.46358855813741684,
479
+ "num_tokens": 51379.0,
480
+ "step": 47
481
+ },
482
+ {
483
+ "entropy": 1.5651679933071136,
484
+ "epoch": 0.3422459893048128,
485
+ "grad_norm": 0.0,
486
+ "learning_rate": 0.00019001189060642093,
487
+ "loss": 2.6206,
488
+ "mean_token_accuracy": 0.47789186984300613,
489
+ "num_tokens": 52456.0,
490
+ "step": 48
491
+ },
492
+ {
493
+ "entropy": 1.5568871796131134,
494
+ "epoch": 0.3493761140819964,
495
+ "grad_norm": 0.0,
496
+ "learning_rate": 0.0001897740784780024,
497
+ "loss": 2.4854,
498
+ "mean_token_accuracy": 0.46421028673648834,
499
+ "num_tokens": 53606.0,
500
+ "step": 49
501
+ },
502
+ {
503
+ "entropy": 1.5674110054969788,
504
+ "epoch": 0.35650623885918004,
505
+ "grad_norm": 0.0,
506
+ "learning_rate": 0.00018953626634958382,
507
+ "loss": 2.6727,
508
+ "mean_token_accuracy": 0.4703332930803299,
509
+ "num_tokens": 54675.0,
510
+ "step": 50
511
+ },
512
+ {
513
+ "entropy": 1.6391582489013672,
514
+ "epoch": 0.36363636363636365,
515
+ "grad_norm": 0.0,
516
+ "learning_rate": 0.00018929845422116528,
517
+ "loss": 2.737,
518
+ "mean_token_accuracy": 0.4556998685002327,
519
+ "num_tokens": 55814.0,
520
+ "step": 51
521
+ },
522
+ {
523
+ "entropy": 1.6075606942176819,
524
+ "epoch": 0.37076648841354726,
525
+ "grad_norm": 0.0,
526
+ "learning_rate": 0.00018906064209274674,
527
+ "loss": 2.7034,
528
+ "mean_token_accuracy": 0.46947986632585526,
529
+ "num_tokens": 56856.0,
530
+ "step": 52
531
+ },
532
+ {
533
+ "entropy": 1.663224458694458,
534
+ "epoch": 0.3778966131907308,
535
+ "grad_norm": 0.0,
536
+ "learning_rate": 0.0001888228299643282,
537
+ "loss": 2.6482,
538
+ "mean_token_accuracy": 0.46404948085546494,
539
+ "num_tokens": 57913.0,
540
+ "step": 53
541
+ },
542
+ {
543
+ "entropy": 1.5472119748592377,
544
+ "epoch": 0.3850267379679144,
545
+ "grad_norm": 0.0,
546
+ "learning_rate": 0.00018858501783590965,
547
+ "loss": 2.6376,
548
+ "mean_token_accuracy": 0.46229933202266693,
549
+ "num_tokens": 58974.0,
550
+ "step": 54
551
+ },
552
+ {
553
+ "entropy": 1.576840728521347,
554
+ "epoch": 0.39215686274509803,
555
+ "grad_norm": 0.0,
556
+ "learning_rate": 0.00018834720570749108,
557
+ "loss": 2.5702,
558
+ "mean_token_accuracy": 0.4657410681247711,
559
+ "num_tokens": 60045.0,
560
+ "step": 55
561
+ },
562
+ {
563
+ "entropy": 1.5661181211471558,
564
+ "epoch": 0.39928698752228164,
565
+ "grad_norm": 0.0,
566
+ "learning_rate": 0.00018810939357907254,
567
+ "loss": 2.5967,
568
+ "mean_token_accuracy": 0.46670273691415787,
569
+ "num_tokens": 61139.0,
570
+ "step": 56
571
+ },
572
+ {
573
+ "entropy": 1.694770723581314,
574
+ "epoch": 0.40641711229946526,
575
+ "grad_norm": 0.0,
576
+ "learning_rate": 0.000187871581450654,
577
+ "loss": 2.7852,
578
+ "mean_token_accuracy": 0.4311066195368767,
579
+ "num_tokens": 62182.0,
580
+ "step": 57
581
+ },
582
+ {
583
+ "entropy": 1.6365650296211243,
584
+ "epoch": 0.41354723707664887,
585
+ "grad_norm": 0.0,
586
+ "learning_rate": 0.00018763376932223543,
587
+ "loss": 2.6211,
588
+ "mean_token_accuracy": 0.45912958681583405,
589
+ "num_tokens": 63294.0,
590
+ "step": 58
591
+ },
592
+ {
593
+ "entropy": 1.676701843738556,
594
+ "epoch": 0.4206773618538324,
595
+ "grad_norm": 0.0,
596
+ "learning_rate": 0.0001873959571938169,
597
+ "loss": 2.727,
598
+ "mean_token_accuracy": 0.4495629146695137,
599
+ "num_tokens": 64345.0,
600
+ "step": 59
601
+ },
602
+ {
603
+ "entropy": 1.6373060643672943,
604
+ "epoch": 0.42780748663101603,
605
+ "grad_norm": 0.0,
606
+ "learning_rate": 0.00018715814506539835,
607
+ "loss": 2.5274,
608
+ "mean_token_accuracy": 0.49557945132255554,
609
+ "num_tokens": 65514.0,
610
+ "step": 60
611
+ },
612
+ {
613
+ "entropy": 1.60589137673378,
614
+ "epoch": 0.43493761140819964,
615
+ "grad_norm": 0.0,
616
+ "learning_rate": 0.0001869203329369798,
617
+ "loss": 2.5985,
618
+ "mean_token_accuracy": 0.47936083376407623,
619
+ "num_tokens": 66582.0,
620
+ "step": 61
621
+ },
622
+ {
623
+ "entropy": 1.588552087545395,
624
+ "epoch": 0.44206773618538325,
625
+ "grad_norm": 0.0,
626
+ "learning_rate": 0.00018668252080856126,
627
+ "loss": 2.6723,
628
+ "mean_token_accuracy": 0.4559238702058792,
629
+ "num_tokens": 67675.0,
630
+ "step": 62
631
+ },
632
+ {
633
+ "entropy": 1.6571227610111237,
634
+ "epoch": 0.44919786096256686,
635
+ "grad_norm": 0.0,
636
+ "learning_rate": 0.0001864447086801427,
637
+ "loss": 2.6471,
638
+ "mean_token_accuracy": 0.45193884521722794,
639
+ "num_tokens": 68786.0,
640
+ "step": 63
641
+ },
642
+ {
643
+ "entropy": 1.624506950378418,
644
+ "epoch": 0.4563279857397504,
645
+ "grad_norm": 0.0,
646
+ "learning_rate": 0.00018620689655172415,
647
+ "loss": 2.6798,
648
+ "mean_token_accuracy": 0.4612022116780281,
649
+ "num_tokens": 69860.0,
650
+ "step": 64
651
+ },
652
+ {
653
+ "entropy": 1.621217519044876,
654
+ "epoch": 0.46345811051693403,
655
+ "grad_norm": 0.0,
656
+ "learning_rate": 0.0001859690844233056,
657
+ "loss": 2.7073,
658
+ "mean_token_accuracy": 0.4635338932275772,
659
+ "num_tokens": 71015.0,
660
+ "step": 65
661
+ },
662
+ {
663
+ "entropy": 1.613840103149414,
664
+ "epoch": 0.47058823529411764,
665
+ "grad_norm": 0.0,
666
+ "learning_rate": 0.00018573127229488704,
667
+ "loss": 2.5895,
668
+ "mean_token_accuracy": 0.4725746735930443,
669
+ "num_tokens": 72174.0,
670
+ "step": 66
671
+ },
672
+ {
673
+ "entropy": 1.6597147285938263,
674
+ "epoch": 0.47771836007130125,
675
+ "grad_norm": 0.0,
676
+ "learning_rate": 0.0001854934601664685,
677
+ "loss": 2.6713,
678
+ "mean_token_accuracy": 0.453179232776165,
679
+ "num_tokens": 73201.0,
680
+ "step": 67
681
+ },
682
+ {
683
+ "entropy": 1.5728524029254913,
684
+ "epoch": 0.48484848484848486,
685
+ "grad_norm": 0.0,
686
+ "learning_rate": 0.00018525564803804995,
687
+ "loss": 2.5245,
688
+ "mean_token_accuracy": 0.4796541631221771,
689
+ "num_tokens": 74317.0,
690
+ "step": 68
691
+ },
692
+ {
693
+ "entropy": 1.6241073608398438,
694
+ "epoch": 0.4919786096256685,
695
+ "grad_norm": 0.0,
696
+ "learning_rate": 0.0001850178359096314,
697
+ "loss": 2.6027,
698
+ "mean_token_accuracy": 0.45817650109529495,
699
+ "num_tokens": 75379.0,
700
+ "step": 69
701
+ },
702
+ {
703
+ "entropy": 1.6420445144176483,
704
+ "epoch": 0.49910873440285203,
705
+ "grad_norm": 0.0,
706
+ "learning_rate": 0.00018478002378121284,
707
+ "loss": 2.6937,
708
+ "mean_token_accuracy": 0.4578876346349716,
709
+ "num_tokens": 76447.0,
710
+ "step": 70
711
+ },
712
+ {
713
+ "entropy": 1.5464614629745483,
714
+ "epoch": 0.5062388591800356,
715
+ "grad_norm": 0.0,
716
+ "learning_rate": 0.0001845422116527943,
717
+ "loss": 2.6239,
718
+ "mean_token_accuracy": 0.4877299517393112,
719
+ "num_tokens": 77527.0,
720
+ "step": 71
721
+ },
722
+ {
723
+ "entropy": 1.650261253118515,
724
+ "epoch": 0.5133689839572193,
725
+ "grad_norm": 0.0,
726
+ "learning_rate": 0.00018430439952437576,
727
+ "loss": 2.7438,
728
+ "mean_token_accuracy": 0.44178425520658493,
729
+ "num_tokens": 78571.0,
730
+ "step": 72
731
+ },
732
+ {
733
+ "entropy": 1.5863160490989685,
734
+ "epoch": 0.5204991087344029,
735
+ "grad_norm": 0.0,
736
+ "learning_rate": 0.00018406658739595721,
737
+ "loss": 2.6262,
738
+ "mean_token_accuracy": 0.4780261069536209,
739
+ "num_tokens": 79679.0,
740
+ "step": 73
741
+ },
742
+ {
743
+ "entropy": 1.5492512583732605,
744
+ "epoch": 0.5276292335115864,
745
+ "grad_norm": 0.0,
746
+ "learning_rate": 0.00018382877526753865,
747
+ "loss": 2.6273,
748
+ "mean_token_accuracy": 0.4793827310204506,
749
+ "num_tokens": 80814.0,
750
+ "step": 74
751
+ },
752
+ {
753
+ "entropy": 1.641315221786499,
754
+ "epoch": 0.5347593582887701,
755
+ "grad_norm": 0.0,
756
+ "learning_rate": 0.0001835909631391201,
757
+ "loss": 2.7035,
758
+ "mean_token_accuracy": 0.4648021087050438,
759
+ "num_tokens": 81899.0,
760
+ "step": 75
761
+ },
762
+ {
763
+ "entropy": 1.6433144211769104,
764
+ "epoch": 0.5418894830659536,
765
+ "grad_norm": 0.0,
766
+ "learning_rate": 0.00018335315101070156,
767
+ "loss": 2.6694,
768
+ "mean_token_accuracy": 0.46280162036418915,
769
+ "num_tokens": 83027.0,
770
+ "step": 76
771
+ },
772
+ {
773
+ "entropy": 1.5979108810424805,
774
+ "epoch": 0.5490196078431373,
775
+ "grad_norm": 0.0,
776
+ "learning_rate": 0.00018311533888228302,
777
+ "loss": 2.6064,
778
+ "mean_token_accuracy": 0.4912242665886879,
779
+ "num_tokens": 84157.0,
780
+ "step": 77
781
+ },
782
+ {
783
+ "entropy": 1.6251288056373596,
784
+ "epoch": 0.5561497326203209,
785
+ "grad_norm": 0.0,
786
+ "learning_rate": 0.00018287752675386445,
787
+ "loss": 2.7191,
788
+ "mean_token_accuracy": 0.451671302318573,
789
+ "num_tokens": 85250.0,
790
+ "step": 78
791
+ },
792
+ {
793
+ "entropy": 1.5671390295028687,
794
+ "epoch": 0.5632798573975044,
795
+ "grad_norm": 0.0,
796
+ "learning_rate": 0.0001826397146254459,
797
+ "loss": 2.613,
798
+ "mean_token_accuracy": 0.4815371036529541,
799
+ "num_tokens": 86331.0,
800
+ "step": 79
801
+ },
802
+ {
803
+ "entropy": 1.6086040139198303,
804
+ "epoch": 0.5704099821746881,
805
+ "grad_norm": 0.0,
806
+ "learning_rate": 0.00018240190249702736,
807
+ "loss": 2.6629,
808
+ "mean_token_accuracy": 0.4586881175637245,
809
+ "num_tokens": 87430.0,
810
+ "step": 80
811
+ },
812
+ {
813
+ "entropy": 1.643826961517334,
814
+ "epoch": 0.5775401069518716,
815
+ "grad_norm": 0.0,
816
+ "learning_rate": 0.0001821640903686088,
817
+ "loss": 2.5622,
818
+ "mean_token_accuracy": 0.46292658150196075,
819
+ "num_tokens": 88542.0,
820
+ "step": 81
821
+ },
822
+ {
823
+ "entropy": 1.6064577996730804,
824
+ "epoch": 0.5846702317290553,
825
+ "grad_norm": 0.0,
826
+ "learning_rate": 0.00018192627824019025,
827
+ "loss": 2.6491,
828
+ "mean_token_accuracy": 0.47355010360479355,
829
+ "num_tokens": 89674.0,
830
+ "step": 82
831
+ },
832
+ {
833
+ "entropy": 1.628090888261795,
834
+ "epoch": 0.5918003565062389,
835
+ "grad_norm": 0.0,
836
+ "learning_rate": 0.0001816884661117717,
837
+ "loss": 2.5738,
838
+ "mean_token_accuracy": 0.44704899936914444,
839
+ "num_tokens": 90762.0,
840
+ "step": 83
841
+ },
842
+ {
843
+ "entropy": 1.558334767818451,
844
+ "epoch": 0.5989304812834224,
845
+ "grad_norm": 0.0,
846
+ "learning_rate": 0.00018145065398335317,
847
+ "loss": 2.5863,
848
+ "mean_token_accuracy": 0.4635235145688057,
849
+ "num_tokens": 91891.0,
850
+ "step": 84
851
+ },
852
+ {
853
+ "entropy": 1.5913751423358917,
854
+ "epoch": 0.6060606060606061,
855
+ "grad_norm": 0.0,
856
+ "learning_rate": 0.0001812128418549346,
857
+ "loss": 2.5779,
858
+ "mean_token_accuracy": 0.49088721722364426,
859
+ "num_tokens": 92975.0,
860
+ "step": 85
861
+ },
862
+ {
863
+ "entropy": 1.6400005519390106,
864
+ "epoch": 0.6131907308377896,
865
+ "grad_norm": 0.0,
866
+ "learning_rate": 0.00018097502972651606,
867
+ "loss": 2.7314,
868
+ "mean_token_accuracy": 0.4603074938058853,
869
+ "num_tokens": 94049.0,
870
+ "step": 86
871
+ },
872
+ {
873
+ "entropy": 1.6752884984016418,
874
+ "epoch": 0.6203208556149733,
875
+ "grad_norm": 0.0,
876
+ "learning_rate": 0.00018073721759809751,
877
+ "loss": 2.6624,
878
+ "mean_token_accuracy": 0.4621705859899521,
879
+ "num_tokens": 95148.0,
880
+ "step": 87
881
+ },
882
+ {
883
+ "entropy": 1.6517191529273987,
884
+ "epoch": 0.6274509803921569,
885
+ "grad_norm": 0.0,
886
+ "learning_rate": 0.00018049940546967897,
887
+ "loss": 2.6835,
888
+ "mean_token_accuracy": 0.4539112225174904,
889
+ "num_tokens": 96181.0,
890
+ "step": 88
891
+ },
892
+ {
893
+ "entropy": 1.7114574909210205,
894
+ "epoch": 0.6345811051693404,
895
+ "grad_norm": 0.0,
896
+ "learning_rate": 0.0001802615933412604,
897
+ "loss": 2.7193,
898
+ "mean_token_accuracy": 0.4676526263356209,
899
+ "num_tokens": 97301.0,
900
+ "step": 89
901
+ },
902
+ {
903
+ "entropy": 1.5929251611232758,
904
+ "epoch": 0.6417112299465241,
905
+ "grad_norm": 0.0,
906
+ "learning_rate": 0.00018002378121284186,
907
+ "loss": 2.5851,
908
+ "mean_token_accuracy": 0.47982004284858704,
909
+ "num_tokens": 98436.0,
910
+ "step": 90
911
+ },
912
+ {
913
+ "entropy": 1.6745183765888214,
914
+ "epoch": 0.6488413547237076,
915
+ "grad_norm": 0.0,
916
+ "learning_rate": 0.00017978596908442332,
917
+ "loss": 2.7709,
918
+ "mean_token_accuracy": 0.4384681358933449,
919
+ "num_tokens": 99477.0,
920
+ "step": 91
921
+ },
922
+ {
923
+ "entropy": 1.59268319606781,
924
+ "epoch": 0.6559714795008913,
925
+ "grad_norm": 0.0,
926
+ "learning_rate": 0.00017954815695600475,
927
+ "loss": 2.5459,
928
+ "mean_token_accuracy": 0.47278715670108795,
929
+ "num_tokens": 100622.0,
930
+ "step": 92
931
+ },
932
+ {
933
+ "entropy": 1.542839676141739,
934
+ "epoch": 0.6631016042780749,
935
+ "grad_norm": 0.0,
936
+ "learning_rate": 0.0001793103448275862,
937
+ "loss": 2.6196,
938
+ "mean_token_accuracy": 0.48384036868810654,
939
+ "num_tokens": 101710.0,
940
+ "step": 93
941
+ },
942
+ {
943
+ "entropy": 1.675879418849945,
944
+ "epoch": 0.6702317290552585,
945
+ "grad_norm": 0.0,
946
+ "learning_rate": 0.00017907253269916766,
947
+ "loss": 2.7075,
948
+ "mean_token_accuracy": 0.46232420206069946,
949
+ "num_tokens": 102745.0,
950
+ "step": 94
951
+ },
952
+ {
953
+ "entropy": 1.520689070224762,
954
+ "epoch": 0.6773618538324421,
955
+ "grad_norm": 0.0,
956
+ "learning_rate": 0.00017883472057074912,
957
+ "loss": 2.5151,
958
+ "mean_token_accuracy": 0.48868096619844437,
959
+ "num_tokens": 103923.0,
960
+ "step": 95
961
+ },
962
+ {
963
+ "entropy": 1.5939531326293945,
964
+ "epoch": 0.6844919786096256,
965
+ "grad_norm": 0.0,
966
+ "learning_rate": 0.00017859690844233058,
967
+ "loss": 2.5655,
968
+ "mean_token_accuracy": 0.48160815238952637,
969
+ "num_tokens": 105063.0,
970
+ "step": 96
971
+ },
972
+ {
973
+ "entropy": 1.6622373461723328,
974
+ "epoch": 0.6916221033868093,
975
+ "grad_norm": 0.0,
976
+ "learning_rate": 0.000178359096313912,
977
+ "loss": 2.6854,
978
+ "mean_token_accuracy": 0.4513147324323654,
979
+ "num_tokens": 106176.0,
980
+ "step": 97
981
+ },
982
+ {
983
+ "entropy": 1.596898078918457,
984
+ "epoch": 0.6987522281639929,
985
+ "grad_norm": 0.0,
986
+ "learning_rate": 0.00017812128418549347,
987
+ "loss": 2.6575,
988
+ "mean_token_accuracy": 0.46170156449079514,
989
+ "num_tokens": 107276.0,
990
+ "step": 98
991
+ },
992
+ {
993
+ "entropy": 1.6209412813186646,
994
+ "epoch": 0.7058823529411765,
995
+ "grad_norm": 0.0,
996
+ "learning_rate": 0.00017788347205707493,
997
+ "loss": 2.6675,
998
+ "mean_token_accuracy": 0.4495192915201187,
999
+ "num_tokens": 108387.0,
1000
+ "step": 99
1001
+ },
1002
+ {
1003
+ "entropy": 1.5751018524169922,
1004
+ "epoch": 0.7130124777183601,
1005
+ "grad_norm": 0.0,
1006
+ "learning_rate": 0.00017764565992865636,
1007
+ "loss": 2.6782,
1008
+ "mean_token_accuracy": 0.47493766248226166,
1009
+ "num_tokens": 109464.0,
1010
+ "step": 100
1011
+ },
1012
+ {
1013
+ "entropy": 1.5404111742973328,
1014
+ "epoch": 0.7201426024955436,
1015
+ "grad_norm": 0.0,
1016
+ "learning_rate": 0.0001774078478002378,
1017
+ "loss": 2.5644,
1018
+ "mean_token_accuracy": 0.4800315648317337,
1019
+ "num_tokens": 110545.0,
1020
+ "step": 101
1021
+ },
1022
+ {
1023
+ "entropy": 1.5617071688175201,
1024
+ "epoch": 0.7272727272727273,
1025
+ "grad_norm": 0.0,
1026
+ "learning_rate": 0.00017717003567181927,
1027
+ "loss": 2.4542,
1028
+ "mean_token_accuracy": 0.486552469432354,
1029
+ "num_tokens": 111644.0,
1030
+ "step": 102
1031
+ },
1032
+ {
1033
+ "entropy": 1.6221667528152466,
1034
+ "epoch": 0.7344028520499108,
1035
+ "grad_norm": 0.0,
1036
+ "learning_rate": 0.00017693222354340073,
1037
+ "loss": 2.6873,
1038
+ "mean_token_accuracy": 0.4583618715405464,
1039
+ "num_tokens": 112683.0,
1040
+ "step": 103
1041
+ },
1042
+ {
1043
+ "entropy": 1.6229766011238098,
1044
+ "epoch": 0.7415329768270945,
1045
+ "grad_norm": 0.0,
1046
+ "learning_rate": 0.0001766944114149822,
1047
+ "loss": 2.7595,
1048
+ "mean_token_accuracy": 0.4478139355778694,
1049
+ "num_tokens": 113734.0,
1050
+ "step": 104
1051
+ },
1052
+ {
1053
+ "entropy": 1.6290508806705475,
1054
+ "epoch": 0.7486631016042781,
1055
+ "grad_norm": 0.0,
1056
+ "learning_rate": 0.00017645659928656362,
1057
+ "loss": 2.648,
1058
+ "mean_token_accuracy": 0.4640928953886032,
1059
+ "num_tokens": 114840.0,
1060
+ "step": 105
1061
+ },
1062
+ {
1063
+ "entropy": 1.5602010190486908,
1064
+ "epoch": 0.7557932263814616,
1065
+ "grad_norm": 0.0,
1066
+ "learning_rate": 0.00017621878715814507,
1067
+ "loss": 2.6151,
1068
+ "mean_token_accuracy": 0.47945626825094223,
1069
+ "num_tokens": 115918.0,
1070
+ "step": 106
1071
+ },
1072
+ {
1073
+ "entropy": 1.561210036277771,
1074
+ "epoch": 0.7629233511586453,
1075
+ "grad_norm": 0.0,
1076
+ "learning_rate": 0.00017598097502972653,
1077
+ "loss": 2.6753,
1078
+ "mean_token_accuracy": 0.4755818694829941,
1079
+ "num_tokens": 116992.0,
1080
+ "step": 107
1081
+ },
1082
+ {
1083
+ "entropy": 1.5463439524173737,
1084
+ "epoch": 0.7700534759358288,
1085
+ "grad_norm": 0.0,
1086
+ "learning_rate": 0.00017574316290130796,
1087
+ "loss": 2.5312,
1088
+ "mean_token_accuracy": 0.4788963794708252,
1089
+ "num_tokens": 118163.0,
1090
+ "step": 108
1091
+ },
1092
+ {
1093
+ "entropy": 1.545140415430069,
1094
+ "epoch": 0.7771836007130125,
1095
+ "grad_norm": 0.0,
1096
+ "learning_rate": 0.00017550535077288942,
1097
+ "loss": 2.4861,
1098
+ "mean_token_accuracy": 0.48517899960279465,
1099
+ "num_tokens": 119246.0,
1100
+ "step": 109
1101
+ },
1102
+ {
1103
+ "entropy": 1.6490318477153778,
1104
+ "epoch": 0.7843137254901961,
1105
+ "grad_norm": 0.0,
1106
+ "learning_rate": 0.00017526753864447088,
1107
+ "loss": 2.6319,
1108
+ "mean_token_accuracy": 0.4522154629230499,
1109
+ "num_tokens": 120352.0,
1110
+ "step": 110
1111
+ },
1112
+ {
1113
+ "entropy": 1.5705026686191559,
1114
+ "epoch": 0.7914438502673797,
1115
+ "grad_norm": 0.0,
1116
+ "learning_rate": 0.0001750297265160523,
1117
+ "loss": 2.5889,
1118
+ "mean_token_accuracy": 0.4755884185433388,
1119
+ "num_tokens": 121495.0,
1120
+ "step": 111
1121
+ },
1122
+ {
1123
+ "entropy": 1.5974452495574951,
1124
+ "epoch": 0.7985739750445633,
1125
+ "grad_norm": 0.0,
1126
+ "learning_rate": 0.0001747919143876338,
1127
+ "loss": 2.5626,
1128
+ "mean_token_accuracy": 0.4795725420117378,
1129
+ "num_tokens": 122564.0,
1130
+ "step": 112
1131
+ },
1132
+ {
1133
+ "entropy": 1.5680693686008453,
1134
+ "epoch": 0.8057040998217468,
1135
+ "grad_norm": 0.0,
1136
+ "learning_rate": 0.00017455410225921522,
1137
+ "loss": 2.6273,
1138
+ "mean_token_accuracy": 0.4590470939874649,
1139
+ "num_tokens": 123650.0,
1140
+ "step": 113
1141
+ },
1142
+ {
1143
+ "entropy": 1.6800198554992676,
1144
+ "epoch": 0.8128342245989305,
1145
+ "grad_norm": 0.0,
1146
+ "learning_rate": 0.00017431629013079668,
1147
+ "loss": 2.737,
1148
+ "mean_token_accuracy": 0.45866189897060394,
1149
+ "num_tokens": 124779.0,
1150
+ "step": 114
1151
+ },
1152
+ {
1153
+ "entropy": 1.6031546890735626,
1154
+ "epoch": 0.8199643493761141,
1155
+ "grad_norm": 0.0,
1156
+ "learning_rate": 0.00017407847800237814,
1157
+ "loss": 2.5439,
1158
+ "mean_token_accuracy": 0.472602941095829,
1159
+ "num_tokens": 125900.0,
1160
+ "step": 115
1161
+ },
1162
+ {
1163
+ "entropy": 1.6303865611553192,
1164
+ "epoch": 0.8270944741532977,
1165
+ "grad_norm": 0.0,
1166
+ "learning_rate": 0.00017384066587395957,
1167
+ "loss": 2.6487,
1168
+ "mean_token_accuracy": 0.4673057347536087,
1169
+ "num_tokens": 126993.0,
1170
+ "step": 116
1171
+ },
1172
+ {
1173
+ "entropy": 1.6584992706775665,
1174
+ "epoch": 0.8342245989304813,
1175
+ "grad_norm": 0.0,
1176
+ "learning_rate": 0.00017360285374554103,
1177
+ "loss": 2.6956,
1178
+ "mean_token_accuracy": 0.46377309411764145,
1179
+ "num_tokens": 128138.0,
1180
+ "step": 117
1181
+ },
1182
+ {
1183
+ "entropy": 1.591305822134018,
1184
+ "epoch": 0.8413547237076648,
1185
+ "grad_norm": 0.0,
1186
+ "learning_rate": 0.00017336504161712249,
1187
+ "loss": 2.713,
1188
+ "mean_token_accuracy": 0.46212588995695114,
1189
+ "num_tokens": 129222.0,
1190
+ "step": 118
1191
+ },
1192
+ {
1193
+ "entropy": 1.6993348598480225,
1194
+ "epoch": 0.8484848484848485,
1195
+ "grad_norm": 0.0,
1196
+ "learning_rate": 0.00017312722948870392,
1197
+ "loss": 2.7792,
1198
+ "mean_token_accuracy": 0.4319414496421814,
1199
+ "num_tokens": 130249.0,
1200
+ "step": 119
1201
+ },
1202
+ {
1203
+ "entropy": 1.5929858684539795,
1204
+ "epoch": 0.8556149732620321,
1205
+ "grad_norm": 0.0,
1206
+ "learning_rate": 0.0001728894173602854,
1207
+ "loss": 2.6866,
1208
+ "mean_token_accuracy": 0.47090228646993637,
1209
+ "num_tokens": 131310.0,
1210
+ "step": 120
1211
+ },
1212
+ {
1213
+ "entropy": 1.667660892009735,
1214
+ "epoch": 0.8627450980392157,
1215
+ "grad_norm": 0.0,
1216
+ "learning_rate": 0.00017265160523186683,
1217
+ "loss": 2.6699,
1218
+ "mean_token_accuracy": 0.45984991639852524,
1219
+ "num_tokens": 132431.0,
1220
+ "step": 121
1221
+ },
1222
+ {
1223
+ "entropy": 1.548890471458435,
1224
+ "epoch": 0.8698752228163993,
1225
+ "grad_norm": 0.0,
1226
+ "learning_rate": 0.00017241379310344826,
1227
+ "loss": 2.6131,
1228
+ "mean_token_accuracy": 0.4870634377002716,
1229
+ "num_tokens": 133545.0,
1230
+ "step": 122
1231
+ },
1232
+ {
1233
+ "entropy": 1.5599585175514221,
1234
+ "epoch": 0.8770053475935828,
1235
+ "grad_norm": 0.0,
1236
+ "learning_rate": 0.00017217598097502975,
1237
+ "loss": 2.5476,
1238
+ "mean_token_accuracy": 0.4777110442519188,
1239
+ "num_tokens": 134678.0,
1240
+ "step": 123
1241
+ },
1242
+ {
1243
+ "entropy": 1.5160918235778809,
1244
+ "epoch": 0.8841354723707665,
1245
+ "grad_norm": 0.0,
1246
+ "learning_rate": 0.00017193816884661118,
1247
+ "loss": 2.5731,
1248
+ "mean_token_accuracy": 0.478961318731308,
1249
+ "num_tokens": 135821.0,
1250
+ "step": 124
1251
+ },
1252
+ {
1253
+ "entropy": 1.5480628907680511,
1254
+ "epoch": 0.8912655971479501,
1255
+ "grad_norm": 0.0,
1256
+ "learning_rate": 0.00017170035671819264,
1257
+ "loss": 2.5291,
1258
+ "mean_token_accuracy": 0.4755103513598442,
1259
+ "num_tokens": 136971.0,
1260
+ "step": 125
1261
+ },
1262
+ {
1263
+ "entropy": 1.5862606167793274,
1264
+ "epoch": 0.8983957219251337,
1265
+ "grad_norm": 0.0,
1266
+ "learning_rate": 0.0001714625445897741,
1267
+ "loss": 2.6396,
1268
+ "mean_token_accuracy": 0.46081865578889847,
1269
+ "num_tokens": 138007.0,
1270
+ "step": 126
1271
+ },
1272
+ {
1273
+ "entropy": 1.669043391942978,
1274
+ "epoch": 0.9055258467023173,
1275
+ "grad_norm": 0.0,
1276
+ "learning_rate": 0.00017122473246135552,
1277
+ "loss": 2.6321,
1278
+ "mean_token_accuracy": 0.4644095078110695,
1279
+ "num_tokens": 139053.0,
1280
+ "step": 127
1281
+ },
1282
+ {
1283
+ "entropy": 1.5860805809497833,
1284
+ "epoch": 0.9126559714795008,
1285
+ "grad_norm": 0.0,
1286
+ "learning_rate": 0.00017098692033293698,
1287
+ "loss": 2.5403,
1288
+ "mean_token_accuracy": 0.4631856083869934,
1289
+ "num_tokens": 140147.0,
1290
+ "step": 128
1291
+ },
1292
+ {
1293
+ "entropy": 1.6290316879749298,
1294
+ "epoch": 0.9197860962566845,
1295
+ "grad_norm": 0.0,
1296
+ "learning_rate": 0.00017074910820451844,
1297
+ "loss": 2.6503,
1298
+ "mean_token_accuracy": 0.46986210346221924,
1299
+ "num_tokens": 141269.0,
1300
+ "step": 129
1301
+ },
1302
+ {
1303
+ "entropy": 1.5800673365592957,
1304
+ "epoch": 0.9269162210338681,
1305
+ "grad_norm": 0.0,
1306
+ "learning_rate": 0.00017051129607609987,
1307
+ "loss": 2.5817,
1308
+ "mean_token_accuracy": 0.46785174310207367,
1309
+ "num_tokens": 142404.0,
1310
+ "step": 130
1311
+ },
1312
+ {
1313
+ "entropy": 1.5903257727622986,
1314
+ "epoch": 0.9340463458110517,
1315
+ "grad_norm": 0.0,
1316
+ "learning_rate": 0.00017027348394768135,
1317
+ "loss": 2.5134,
1318
+ "mean_token_accuracy": 0.4654293358325958,
1319
+ "num_tokens": 143534.0,
1320
+ "step": 131
1321
+ },
1322
+ {
1323
+ "entropy": 1.5758326351642609,
1324
+ "epoch": 0.9411764705882353,
1325
+ "grad_norm": 0.0,
1326
+ "learning_rate": 0.00017003567181926279,
1327
+ "loss": 2.6744,
1328
+ "mean_token_accuracy": 0.47502800077199936,
1329
+ "num_tokens": 144634.0,
1330
+ "step": 132
1331
+ },
1332
+ {
1333
+ "entropy": 1.555185467004776,
1334
+ "epoch": 0.948306595365419,
1335
+ "grad_norm": 0.0,
1336
+ "learning_rate": 0.00016979785969084424,
1337
+ "loss": 2.5801,
1338
+ "mean_token_accuracy": 0.47467251121997833,
1339
+ "num_tokens": 145695.0,
1340
+ "step": 133
1341
+ },
1342
+ {
1343
+ "entropy": 1.58922079205513,
1344
+ "epoch": 0.9554367201426025,
1345
+ "grad_norm": 0.0,
1346
+ "learning_rate": 0.0001695600475624257,
1347
+ "loss": 2.619,
1348
+ "mean_token_accuracy": 0.4779004603624344,
1349
+ "num_tokens": 146787.0,
1350
+ "step": 134
1351
+ },
1352
+ {
1353
+ "entropy": 1.6058009564876556,
1354
+ "epoch": 0.9625668449197861,
1355
+ "grad_norm": 0.0,
1356
+ "learning_rate": 0.00016932223543400713,
1357
+ "loss": 2.683,
1358
+ "mean_token_accuracy": 0.4785980358719826,
1359
+ "num_tokens": 147817.0,
1360
+ "step": 135
1361
+ },
1362
+ {
1363
+ "entropy": 1.6281861662864685,
1364
+ "epoch": 0.9696969696969697,
1365
+ "grad_norm": 0.0,
1366
+ "learning_rate": 0.0001690844233055886,
1367
+ "loss": 2.7144,
1368
+ "mean_token_accuracy": 0.4627036154270172,
1369
+ "num_tokens": 148907.0,
1370
+ "step": 136
1371
+ },
1372
+ {
1373
+ "entropy": 1.619028925895691,
1374
+ "epoch": 0.9768270944741533,
1375
+ "grad_norm": 0.0,
1376
+ "learning_rate": 0.00016884661117717005,
1377
+ "loss": 2.6079,
1378
+ "mean_token_accuracy": 0.45756662636995316,
1379
+ "num_tokens": 149993.0,
1380
+ "step": 137
1381
+ },
1382
+ {
1383
+ "entropy": 1.5888321995735168,
1384
+ "epoch": 0.983957219251337,
1385
+ "grad_norm": 0.0,
1386
+ "learning_rate": 0.00016860879904875148,
1387
+ "loss": 2.6093,
1388
+ "mean_token_accuracy": 0.4724939614534378,
1389
+ "num_tokens": 151098.0,
1390
+ "step": 138
1391
+ },
1392
+ {
1393
+ "entropy": 1.6436494290828705,
1394
+ "epoch": 0.9910873440285205,
1395
+ "grad_norm": 0.0,
1396
+ "learning_rate": 0.00016837098692033296,
1397
+ "loss": 2.6575,
1398
+ "mean_token_accuracy": 0.4623269736766815,
1399
+ "num_tokens": 152163.0,
1400
+ "step": 139
1401
+ },
1402
+ {
1403
+ "entropy": 1.5655477941036224,
1404
+ "epoch": 0.9982174688057041,
1405
+ "grad_norm": 0.0,
1406
+ "learning_rate": 0.0001681331747919144,
1407
+ "loss": 2.6335,
1408
+ "mean_token_accuracy": 0.47587042301893234,
1409
+ "num_tokens": 153275.0,
1410
+ "step": 140
1411
+ },
1412
+ {
1413
+ "entropy": 1.7136651277542114,
1414
+ "epoch": 1.0,
1415
+ "grad_norm": 0.0,
1416
+ "learning_rate": 0.00016789536266349582,
1417
+ "loss": 2.6691,
1418
+ "mean_token_accuracy": 0.4723247289657593,
1419
+ "num_tokens": 153550.0,
1420
+ "step": 141
1421
+ }
1422
+ ],
1423
+ "logging_steps": 1,
1424
+ "max_steps": 846,
1425
+ "num_input_tokens_seen": 0,
1426
+ "num_train_epochs": 6,
1427
+ "save_steps": 500,
1428
+ "stateful_callbacks": {
1429
+ "TrainerControl": {
1430
+ "args": {
1431
+ "should_epoch_stop": false,
1432
+ "should_evaluate": false,
1433
+ "should_log": false,
1434
+ "should_save": true,
1435
+ "should_training_stop": false
1436
+ },
1437
+ "attributes": {}
1438
+ }
1439
+ },
1440
+ "total_flos": 7251376748298240.0,
1441
+ "train_batch_size": 2,
1442
+ "trial_name": null,
1443
+ "trial_params": null
1444
+ }
checkpoint-141/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2dacdb1830e22d6e3c6a173a3f713ce8117adf1aaa057064b64b600f918e5e1
3
+ size 5816
checkpoint-282/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
checkpoint-282/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj"
32
+ ],
33
+ "target_parameters": null,
34
+ "task_type": "CAUSAL_LM",
35
+ "trainable_token_indices": null,
36
+ "use_dora": false,
37
+ "use_qalora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-282/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f181e388f2dbfd451cc598ab3b51bfc3f7493234ff6e0ae9cc2552efa6286a
3
+ size 54560368
checkpoint-282/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
checkpoint-282/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04f8bd1ff5c7f276a819be97319b10175513ea09ae739bf7471e668e89d574f
3
+ size 1192
checkpoint-282/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1f2b5784498eb52cd259e2bb35bc2d254a7fefc15979757cf1e169c6d7cf83
3
+ size 14244
checkpoint-282/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fd9d09abddb69ba49886efad890d4d9c0662fbbd86d9b3ae1bf0539e6bdb2d
3
+ size 1064
checkpoint-282/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-282/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
checkpoint-282/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-282/trainer_state.json ADDED
@@ -0,0 +1,2854 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 282,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.6387848258018494,
14
+ "epoch": 0.0071301247771836,
15
+ "grad_norm": 0.0,
16
+ "learning_rate": 0.0,
17
+ "loss": 2.6515,
18
+ "mean_token_accuracy": 0.445863775908947,
19
+ "num_tokens": 1051.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 1.6529399156570435,
24
+ "epoch": 0.0142602495543672,
25
+ "grad_norm": 0.0,
26
+ "learning_rate": 4e-05,
27
+ "loss": 2.7153,
28
+ "mean_token_accuracy": 0.4470880478620529,
29
+ "num_tokens": 2187.0,
30
+ "step": 2
31
+ },
32
+ {
33
+ "entropy": 1.5581220388412476,
34
+ "epoch": 0.0213903743315508,
35
+ "grad_norm": 0.0,
36
+ "learning_rate": 8e-05,
37
+ "loss": 2.6255,
38
+ "mean_token_accuracy": 0.4684518948197365,
39
+ "num_tokens": 3295.0,
40
+ "step": 3
41
+ },
42
+ {
43
+ "entropy": 1.5885010659694672,
44
+ "epoch": 0.0285204991087344,
45
+ "grad_norm": 0.0,
46
+ "learning_rate": 0.00012,
47
+ "loss": 2.5733,
48
+ "mean_token_accuracy": 0.4601749926805496,
49
+ "num_tokens": 4387.0,
50
+ "step": 4
51
+ },
52
+ {
53
+ "entropy": 1.6543156504631042,
54
+ "epoch": 0.035650623885918005,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.00016,
57
+ "loss": 2.6477,
58
+ "mean_token_accuracy": 0.4556595981121063,
59
+ "num_tokens": 5511.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "entropy": 1.5543809533119202,
64
+ "epoch": 0.0427807486631016,
65
+ "grad_norm": 0.0,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.6579,
68
+ "mean_token_accuracy": 0.46554840356111526,
69
+ "num_tokens": 6598.0,
70
+ "step": 6
71
+ },
72
+ {
73
+ "entropy": 1.5990856289863586,
74
+ "epoch": 0.049910873440285206,
75
+ "grad_norm": 0.0,
76
+ "learning_rate": 0.00019976218787158144,
77
+ "loss": 2.6618,
78
+ "mean_token_accuracy": 0.4601997211575508,
79
+ "num_tokens": 7673.0,
80
+ "step": 7
81
+ },
82
+ {
83
+ "entropy": 1.6176924407482147,
84
+ "epoch": 0.0570409982174688,
85
+ "grad_norm": 0.0,
86
+ "learning_rate": 0.00019952437574316292,
87
+ "loss": 2.7365,
88
+ "mean_token_accuracy": 0.4649490937590599,
89
+ "num_tokens": 8774.0,
90
+ "step": 8
91
+ },
92
+ {
93
+ "entropy": 1.5261479020118713,
94
+ "epoch": 0.06417112299465241,
95
+ "grad_norm": 0.0,
96
+ "learning_rate": 0.00019928656361474436,
97
+ "loss": 2.5824,
98
+ "mean_token_accuracy": 0.47935400158166885,
99
+ "num_tokens": 9886.0,
100
+ "step": 9
101
+ },
102
+ {
103
+ "entropy": 1.6173927783966064,
104
+ "epoch": 0.07130124777183601,
105
+ "grad_norm": 0.0,
106
+ "learning_rate": 0.0001990487514863258,
107
+ "loss": 2.53,
108
+ "mean_token_accuracy": 0.47585250437259674,
109
+ "num_tokens": 10983.0,
110
+ "step": 10
111
+ },
112
+ {
113
+ "entropy": 1.5592622458934784,
114
+ "epoch": 0.0784313725490196,
115
+ "grad_norm": 0.0,
116
+ "learning_rate": 0.00019881093935790727,
117
+ "loss": 2.6422,
118
+ "mean_token_accuracy": 0.46385403722524643,
119
+ "num_tokens": 12102.0,
120
+ "step": 11
121
+ },
122
+ {
123
+ "entropy": 1.5775817930698395,
124
+ "epoch": 0.0855614973262032,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 0.0001985731272294887,
127
+ "loss": 2.6095,
128
+ "mean_token_accuracy": 0.49216530472040176,
129
+ "num_tokens": 13219.0,
130
+ "step": 12
131
+ },
132
+ {
133
+ "entropy": 1.6316154599189758,
134
+ "epoch": 0.09269162210338681,
135
+ "grad_norm": 0.0,
136
+ "learning_rate": 0.00019833531510107019,
137
+ "loss": 2.7746,
138
+ "mean_token_accuracy": 0.4526786059141159,
139
+ "num_tokens": 14309.0,
140
+ "step": 13
141
+ },
142
+ {
143
+ "entropy": 1.5752335786819458,
144
+ "epoch": 0.09982174688057041,
145
+ "grad_norm": 0.0,
146
+ "learning_rate": 0.00019809750297265162,
147
+ "loss": 2.6994,
148
+ "mean_token_accuracy": 0.4809372276067734,
149
+ "num_tokens": 15373.0,
150
+ "step": 14
151
+ },
152
+ {
153
+ "entropy": 1.5528400540351868,
154
+ "epoch": 0.10695187165775401,
155
+ "grad_norm": 0.0,
156
+ "learning_rate": 0.00019785969084423305,
157
+ "loss": 2.6607,
158
+ "mean_token_accuracy": 0.4793297126889229,
159
+ "num_tokens": 16485.0,
160
+ "step": 15
161
+ },
162
+ {
163
+ "entropy": 1.6115093529224396,
164
+ "epoch": 0.1140819964349376,
165
+ "grad_norm": 0.0,
166
+ "learning_rate": 0.00019762187871581453,
167
+ "loss": 2.6006,
168
+ "mean_token_accuracy": 0.48629891872406006,
169
+ "num_tokens": 17654.0,
170
+ "step": 16
171
+ },
172
+ {
173
+ "entropy": 1.6650608479976654,
174
+ "epoch": 0.12121212121212122,
175
+ "grad_norm": 0.0,
176
+ "learning_rate": 0.00019738406658739596,
177
+ "loss": 2.8227,
178
+ "mean_token_accuracy": 0.4469343200325966,
179
+ "num_tokens": 18705.0,
180
+ "step": 17
181
+ },
182
+ {
183
+ "entropy": 1.5981396436691284,
184
+ "epoch": 0.12834224598930483,
185
+ "grad_norm": 0.0,
186
+ "learning_rate": 0.00019714625445897742,
187
+ "loss": 2.6602,
188
+ "mean_token_accuracy": 0.48277803510427475,
189
+ "num_tokens": 19799.0,
190
+ "step": 18
191
+ },
192
+ {
193
+ "entropy": 1.6768196523189545,
194
+ "epoch": 0.1354723707664884,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 0.00019690844233055888,
197
+ "loss": 2.7339,
198
+ "mean_token_accuracy": 0.45305337756872177,
199
+ "num_tokens": 20799.0,
200
+ "step": 19
201
+ },
202
+ {
203
+ "entropy": 1.6276516318321228,
204
+ "epoch": 0.14260249554367202,
205
+ "grad_norm": 0.0,
206
+ "learning_rate": 0.0001966706302021403,
207
+ "loss": 2.6103,
208
+ "mean_token_accuracy": 0.45762092620134354,
209
+ "num_tokens": 21918.0,
210
+ "step": 20
211
+ },
212
+ {
213
+ "entropy": 1.5985995829105377,
214
+ "epoch": 0.1497326203208556,
215
+ "grad_norm": 0.0,
216
+ "learning_rate": 0.00019643281807372177,
217
+ "loss": 2.6705,
218
+ "mean_token_accuracy": 0.474429652094841,
219
+ "num_tokens": 23021.0,
220
+ "step": 21
221
+ },
222
+ {
223
+ "entropy": 1.6575533151626587,
224
+ "epoch": 0.1568627450980392,
225
+ "grad_norm": 0.0,
226
+ "learning_rate": 0.00019619500594530322,
227
+ "loss": 2.7187,
228
+ "mean_token_accuracy": 0.4531744047999382,
229
+ "num_tokens": 24138.0,
230
+ "step": 22
231
+ },
232
+ {
233
+ "entropy": 1.6001036167144775,
234
+ "epoch": 0.16399286987522282,
235
+ "grad_norm": 0.0,
236
+ "learning_rate": 0.00019595719381688465,
237
+ "loss": 2.6272,
238
+ "mean_token_accuracy": 0.4594630151987076,
239
+ "num_tokens": 25229.0,
240
+ "step": 23
241
+ },
242
+ {
243
+ "entropy": 1.6082253158092499,
244
+ "epoch": 0.1711229946524064,
245
+ "grad_norm": 0.0,
246
+ "learning_rate": 0.00019571938168846614,
247
+ "loss": 2.5586,
248
+ "mean_token_accuracy": 0.4784083887934685,
249
+ "num_tokens": 26339.0,
250
+ "step": 24
251
+ },
252
+ {
253
+ "entropy": 1.6208438277244568,
254
+ "epoch": 0.17825311942959002,
255
+ "grad_norm": 0.0,
256
+ "learning_rate": 0.00019548156956004757,
257
+ "loss": 2.6095,
258
+ "mean_token_accuracy": 0.4685538485646248,
259
+ "num_tokens": 27389.0,
260
+ "step": 25
261
+ },
262
+ {
263
+ "entropy": 1.6018637418746948,
264
+ "epoch": 0.18538324420677363,
265
+ "grad_norm": 0.0,
266
+ "learning_rate": 0.00019524375743162903,
267
+ "loss": 2.7047,
268
+ "mean_token_accuracy": 0.4501718729734421,
269
+ "num_tokens": 28491.0,
270
+ "step": 26
271
+ },
272
+ {
273
+ "entropy": 1.566238820552826,
274
+ "epoch": 0.1925133689839572,
275
+ "grad_norm": 0.0,
276
+ "learning_rate": 0.00019500594530321049,
277
+ "loss": 2.5167,
278
+ "mean_token_accuracy": 0.4768272563815117,
279
+ "num_tokens": 29617.0,
280
+ "step": 27
281
+ },
282
+ {
283
+ "entropy": 1.5953451693058014,
284
+ "epoch": 0.19964349376114082,
285
+ "grad_norm": 0.0,
286
+ "learning_rate": 0.00019476813317479192,
287
+ "loss": 2.6907,
288
+ "mean_token_accuracy": 0.46527716517448425,
289
+ "num_tokens": 30709.0,
290
+ "step": 28
291
+ },
292
+ {
293
+ "entropy": 1.6036897897720337,
294
+ "epoch": 0.20677361853832443,
295
+ "grad_norm": 0.0,
296
+ "learning_rate": 0.00019453032104637337,
297
+ "loss": 2.621,
298
+ "mean_token_accuracy": 0.47111422568559647,
299
+ "num_tokens": 31780.0,
300
+ "step": 29
301
+ },
302
+ {
303
+ "entropy": 1.6660344302654266,
304
+ "epoch": 0.21390374331550802,
305
+ "grad_norm": 0.0,
306
+ "learning_rate": 0.00019429250891795483,
307
+ "loss": 2.6351,
308
+ "mean_token_accuracy": 0.45088133215904236,
309
+ "num_tokens": 32827.0,
310
+ "step": 30
311
+ },
312
+ {
313
+ "entropy": 1.5515300929546356,
314
+ "epoch": 0.22103386809269163,
315
+ "grad_norm": 0.0,
316
+ "learning_rate": 0.00019405469678953626,
317
+ "loss": 2.5804,
318
+ "mean_token_accuracy": 0.47831422835588455,
319
+ "num_tokens": 33977.0,
320
+ "step": 31
321
+ },
322
+ {
323
+ "entropy": 1.4917864799499512,
324
+ "epoch": 0.2281639928698752,
325
+ "grad_norm": 0.0,
326
+ "learning_rate": 0.00019381688466111775,
327
+ "loss": 2.5906,
328
+ "mean_token_accuracy": 0.4912087470293045,
329
+ "num_tokens": 35070.0,
330
+ "step": 32
331
+ },
332
+ {
333
+ "entropy": 1.591080754995346,
334
+ "epoch": 0.23529411764705882,
335
+ "grad_norm": 0.0,
336
+ "learning_rate": 0.00019357907253269918,
337
+ "loss": 2.7147,
338
+ "mean_token_accuracy": 0.4610803797841072,
339
+ "num_tokens": 36137.0,
340
+ "step": 33
341
+ },
342
+ {
343
+ "entropy": 1.5161702930927277,
344
+ "epoch": 0.24242424242424243,
345
+ "grad_norm": 0.0,
346
+ "learning_rate": 0.00019334126040428064,
347
+ "loss": 2.4586,
348
+ "mean_token_accuracy": 0.5084197968244553,
349
+ "num_tokens": 37239.0,
350
+ "step": 34
351
+ },
352
+ {
353
+ "entropy": 1.5857904851436615,
354
+ "epoch": 0.24955436720142601,
355
+ "grad_norm": 0.0,
356
+ "learning_rate": 0.0001931034482758621,
357
+ "loss": 2.5836,
358
+ "mean_token_accuracy": 0.48300980031490326,
359
+ "num_tokens": 38330.0,
360
+ "step": 35
361
+ },
362
+ {
363
+ "entropy": 1.6427140533924103,
364
+ "epoch": 0.25668449197860965,
365
+ "grad_norm": 0.0,
366
+ "learning_rate": 0.00019286563614744352,
367
+ "loss": 2.6629,
368
+ "mean_token_accuracy": 0.4738333150744438,
369
+ "num_tokens": 39368.0,
370
+ "step": 36
371
+ },
372
+ {
373
+ "entropy": 1.6292171776294708,
374
+ "epoch": 0.2638146167557932,
375
+ "grad_norm": 0.0,
376
+ "learning_rate": 0.00019262782401902498,
377
+ "loss": 2.7382,
378
+ "mean_token_accuracy": 0.46079348772764206,
379
+ "num_tokens": 40474.0,
380
+ "step": 37
381
+ },
382
+ {
383
+ "entropy": 1.5661435425281525,
384
+ "epoch": 0.2709447415329768,
385
+ "grad_norm": 0.0,
386
+ "learning_rate": 0.00019239001189060644,
387
+ "loss": 2.4905,
388
+ "mean_token_accuracy": 0.49719007313251495,
389
+ "num_tokens": 41558.0,
390
+ "step": 38
391
+ },
392
+ {
393
+ "entropy": 1.6255074739456177,
394
+ "epoch": 0.27807486631016043,
395
+ "grad_norm": 0.0,
396
+ "learning_rate": 0.00019215219976218787,
397
+ "loss": 2.6303,
398
+ "mean_token_accuracy": 0.4578748494386673,
399
+ "num_tokens": 42674.0,
400
+ "step": 39
401
+ },
402
+ {
403
+ "entropy": 1.4836209118366241,
404
+ "epoch": 0.28520499108734404,
405
+ "grad_norm": 0.0,
406
+ "learning_rate": 0.00019191438763376933,
407
+ "loss": 2.5324,
408
+ "mean_token_accuracy": 0.4868450313806534,
409
+ "num_tokens": 43815.0,
410
+ "step": 40
411
+ },
412
+ {
413
+ "entropy": 1.5689969956874847,
414
+ "epoch": 0.29233511586452765,
415
+ "grad_norm": 0.0,
416
+ "learning_rate": 0.00019167657550535079,
417
+ "loss": 2.6125,
418
+ "mean_token_accuracy": 0.45523975044488907,
419
+ "num_tokens": 44890.0,
420
+ "step": 41
421
+ },
422
+ {
423
+ "entropy": 1.5794390439987183,
424
+ "epoch": 0.2994652406417112,
425
+ "grad_norm": 0.0,
426
+ "learning_rate": 0.00019143876337693222,
427
+ "loss": 2.6012,
428
+ "mean_token_accuracy": 0.47063395380973816,
429
+ "num_tokens": 45951.0,
430
+ "step": 42
431
+ },
432
+ {
433
+ "entropy": 1.6168677806854248,
434
+ "epoch": 0.3065953654188948,
435
+ "grad_norm": 0.0,
436
+ "learning_rate": 0.0001912009512485137,
437
+ "loss": 2.6358,
438
+ "mean_token_accuracy": 0.46999557316303253,
439
+ "num_tokens": 47083.0,
440
+ "step": 43
441
+ },
442
+ {
443
+ "entropy": 1.6417001783847809,
444
+ "epoch": 0.3137254901960784,
445
+ "grad_norm": 0.0,
446
+ "learning_rate": 0.00019096313912009513,
447
+ "loss": 2.6473,
448
+ "mean_token_accuracy": 0.4624517187476158,
449
+ "num_tokens": 48088.0,
450
+ "step": 44
451
+ },
452
+ {
453
+ "entropy": 1.6053949892520905,
454
+ "epoch": 0.32085561497326204,
455
+ "grad_norm": 0.0,
456
+ "learning_rate": 0.0001907253269916766,
457
+ "loss": 2.6728,
458
+ "mean_token_accuracy": 0.4565429463982582,
459
+ "num_tokens": 49213.0,
460
+ "step": 45
461
+ },
462
+ {
463
+ "entropy": 1.5239336490631104,
464
+ "epoch": 0.32798573975044565,
465
+ "grad_norm": 0.0,
466
+ "learning_rate": 0.00019048751486325805,
467
+ "loss": 2.5886,
468
+ "mean_token_accuracy": 0.47441017627716064,
469
+ "num_tokens": 50287.0,
470
+ "step": 46
471
+ },
472
+ {
473
+ "entropy": 1.5953067243099213,
474
+ "epoch": 0.33511586452762926,
475
+ "grad_norm": 0.0,
476
+ "learning_rate": 0.00019024970273483948,
477
+ "loss": 2.6498,
478
+ "mean_token_accuracy": 0.46358855813741684,
479
+ "num_tokens": 51379.0,
480
+ "step": 47
481
+ },
482
+ {
483
+ "entropy": 1.5651679933071136,
484
+ "epoch": 0.3422459893048128,
485
+ "grad_norm": 0.0,
486
+ "learning_rate": 0.00019001189060642093,
487
+ "loss": 2.6206,
488
+ "mean_token_accuracy": 0.47789186984300613,
489
+ "num_tokens": 52456.0,
490
+ "step": 48
491
+ },
492
+ {
493
+ "entropy": 1.5568871796131134,
494
+ "epoch": 0.3493761140819964,
495
+ "grad_norm": 0.0,
496
+ "learning_rate": 0.0001897740784780024,
497
+ "loss": 2.4854,
498
+ "mean_token_accuracy": 0.46421028673648834,
499
+ "num_tokens": 53606.0,
500
+ "step": 49
501
+ },
502
+ {
503
+ "entropy": 1.5674110054969788,
504
+ "epoch": 0.35650623885918004,
505
+ "grad_norm": 0.0,
506
+ "learning_rate": 0.00018953626634958382,
507
+ "loss": 2.6727,
508
+ "mean_token_accuracy": 0.4703332930803299,
509
+ "num_tokens": 54675.0,
510
+ "step": 50
511
+ },
512
+ {
513
+ "entropy": 1.6391582489013672,
514
+ "epoch": 0.36363636363636365,
515
+ "grad_norm": 0.0,
516
+ "learning_rate": 0.00018929845422116528,
517
+ "loss": 2.737,
518
+ "mean_token_accuracy": 0.4556998685002327,
519
+ "num_tokens": 55814.0,
520
+ "step": 51
521
+ },
522
+ {
523
+ "entropy": 1.6075606942176819,
524
+ "epoch": 0.37076648841354726,
525
+ "grad_norm": 0.0,
526
+ "learning_rate": 0.00018906064209274674,
527
+ "loss": 2.7034,
528
+ "mean_token_accuracy": 0.46947986632585526,
529
+ "num_tokens": 56856.0,
530
+ "step": 52
531
+ },
532
+ {
533
+ "entropy": 1.663224458694458,
534
+ "epoch": 0.3778966131907308,
535
+ "grad_norm": 0.0,
536
+ "learning_rate": 0.0001888228299643282,
537
+ "loss": 2.6482,
538
+ "mean_token_accuracy": 0.46404948085546494,
539
+ "num_tokens": 57913.0,
540
+ "step": 53
541
+ },
542
+ {
543
+ "entropy": 1.5472119748592377,
544
+ "epoch": 0.3850267379679144,
545
+ "grad_norm": 0.0,
546
+ "learning_rate": 0.00018858501783590965,
547
+ "loss": 2.6376,
548
+ "mean_token_accuracy": 0.46229933202266693,
549
+ "num_tokens": 58974.0,
550
+ "step": 54
551
+ },
552
+ {
553
+ "entropy": 1.576840728521347,
554
+ "epoch": 0.39215686274509803,
555
+ "grad_norm": 0.0,
556
+ "learning_rate": 0.00018834720570749108,
557
+ "loss": 2.5702,
558
+ "mean_token_accuracy": 0.4657410681247711,
559
+ "num_tokens": 60045.0,
560
+ "step": 55
561
+ },
562
+ {
563
+ "entropy": 1.5661181211471558,
564
+ "epoch": 0.39928698752228164,
565
+ "grad_norm": 0.0,
566
+ "learning_rate": 0.00018810939357907254,
567
+ "loss": 2.5967,
568
+ "mean_token_accuracy": 0.46670273691415787,
569
+ "num_tokens": 61139.0,
570
+ "step": 56
571
+ },
572
+ {
573
+ "entropy": 1.694770723581314,
574
+ "epoch": 0.40641711229946526,
575
+ "grad_norm": 0.0,
576
+ "learning_rate": 0.000187871581450654,
577
+ "loss": 2.7852,
578
+ "mean_token_accuracy": 0.4311066195368767,
579
+ "num_tokens": 62182.0,
580
+ "step": 57
581
+ },
582
+ {
583
+ "entropy": 1.6365650296211243,
584
+ "epoch": 0.41354723707664887,
585
+ "grad_norm": 0.0,
586
+ "learning_rate": 0.00018763376932223543,
587
+ "loss": 2.6211,
588
+ "mean_token_accuracy": 0.45912958681583405,
589
+ "num_tokens": 63294.0,
590
+ "step": 58
591
+ },
592
+ {
593
+ "entropy": 1.676701843738556,
594
+ "epoch": 0.4206773618538324,
595
+ "grad_norm": 0.0,
596
+ "learning_rate": 0.0001873959571938169,
597
+ "loss": 2.727,
598
+ "mean_token_accuracy": 0.4495629146695137,
599
+ "num_tokens": 64345.0,
600
+ "step": 59
601
+ },
602
+ {
603
+ "entropy": 1.6373060643672943,
604
+ "epoch": 0.42780748663101603,
605
+ "grad_norm": 0.0,
606
+ "learning_rate": 0.00018715814506539835,
607
+ "loss": 2.5274,
608
+ "mean_token_accuracy": 0.49557945132255554,
609
+ "num_tokens": 65514.0,
610
+ "step": 60
611
+ },
612
+ {
613
+ "entropy": 1.60589137673378,
614
+ "epoch": 0.43493761140819964,
615
+ "grad_norm": 0.0,
616
+ "learning_rate": 0.0001869203329369798,
617
+ "loss": 2.5985,
618
+ "mean_token_accuracy": 0.47936083376407623,
619
+ "num_tokens": 66582.0,
620
+ "step": 61
621
+ },
622
+ {
623
+ "entropy": 1.588552087545395,
624
+ "epoch": 0.44206773618538325,
625
+ "grad_norm": 0.0,
626
+ "learning_rate": 0.00018668252080856126,
627
+ "loss": 2.6723,
628
+ "mean_token_accuracy": 0.4559238702058792,
629
+ "num_tokens": 67675.0,
630
+ "step": 62
631
+ },
632
+ {
633
+ "entropy": 1.6571227610111237,
634
+ "epoch": 0.44919786096256686,
635
+ "grad_norm": 0.0,
636
+ "learning_rate": 0.0001864447086801427,
637
+ "loss": 2.6471,
638
+ "mean_token_accuracy": 0.45193884521722794,
639
+ "num_tokens": 68786.0,
640
+ "step": 63
641
+ },
642
+ {
643
+ "entropy": 1.624506950378418,
644
+ "epoch": 0.4563279857397504,
645
+ "grad_norm": 0.0,
646
+ "learning_rate": 0.00018620689655172415,
647
+ "loss": 2.6798,
648
+ "mean_token_accuracy": 0.4612022116780281,
649
+ "num_tokens": 69860.0,
650
+ "step": 64
651
+ },
652
+ {
653
+ "entropy": 1.621217519044876,
654
+ "epoch": 0.46345811051693403,
655
+ "grad_norm": 0.0,
656
+ "learning_rate": 0.0001859690844233056,
657
+ "loss": 2.7073,
658
+ "mean_token_accuracy": 0.4635338932275772,
659
+ "num_tokens": 71015.0,
660
+ "step": 65
661
+ },
662
+ {
663
+ "entropy": 1.613840103149414,
664
+ "epoch": 0.47058823529411764,
665
+ "grad_norm": 0.0,
666
+ "learning_rate": 0.00018573127229488704,
667
+ "loss": 2.5895,
668
+ "mean_token_accuracy": 0.4725746735930443,
669
+ "num_tokens": 72174.0,
670
+ "step": 66
671
+ },
672
+ {
673
+ "entropy": 1.6597147285938263,
674
+ "epoch": 0.47771836007130125,
675
+ "grad_norm": 0.0,
676
+ "learning_rate": 0.0001854934601664685,
677
+ "loss": 2.6713,
678
+ "mean_token_accuracy": 0.453179232776165,
679
+ "num_tokens": 73201.0,
680
+ "step": 67
681
+ },
682
+ {
683
+ "entropy": 1.5728524029254913,
684
+ "epoch": 0.48484848484848486,
685
+ "grad_norm": 0.0,
686
+ "learning_rate": 0.00018525564803804995,
687
+ "loss": 2.5245,
688
+ "mean_token_accuracy": 0.4796541631221771,
689
+ "num_tokens": 74317.0,
690
+ "step": 68
691
+ },
692
+ {
693
+ "entropy": 1.6241073608398438,
694
+ "epoch": 0.4919786096256685,
695
+ "grad_norm": 0.0,
696
+ "learning_rate": 0.0001850178359096314,
697
+ "loss": 2.6027,
698
+ "mean_token_accuracy": 0.45817650109529495,
699
+ "num_tokens": 75379.0,
700
+ "step": 69
701
+ },
702
+ {
703
+ "entropy": 1.6420445144176483,
704
+ "epoch": 0.49910873440285203,
705
+ "grad_norm": 0.0,
706
+ "learning_rate": 0.00018478002378121284,
707
+ "loss": 2.6937,
708
+ "mean_token_accuracy": 0.4578876346349716,
709
+ "num_tokens": 76447.0,
710
+ "step": 70
711
+ },
712
+ {
713
+ "entropy": 1.5464614629745483,
714
+ "epoch": 0.5062388591800356,
715
+ "grad_norm": 0.0,
716
+ "learning_rate": 0.0001845422116527943,
717
+ "loss": 2.6239,
718
+ "mean_token_accuracy": 0.4877299517393112,
719
+ "num_tokens": 77527.0,
720
+ "step": 71
721
+ },
722
+ {
723
+ "entropy": 1.650261253118515,
724
+ "epoch": 0.5133689839572193,
725
+ "grad_norm": 0.0,
726
+ "learning_rate": 0.00018430439952437576,
727
+ "loss": 2.7438,
728
+ "mean_token_accuracy": 0.44178425520658493,
729
+ "num_tokens": 78571.0,
730
+ "step": 72
731
+ },
732
+ {
733
+ "entropy": 1.5863160490989685,
734
+ "epoch": 0.5204991087344029,
735
+ "grad_norm": 0.0,
736
+ "learning_rate": 0.00018406658739595721,
737
+ "loss": 2.6262,
738
+ "mean_token_accuracy": 0.4780261069536209,
739
+ "num_tokens": 79679.0,
740
+ "step": 73
741
+ },
742
+ {
743
+ "entropy": 1.5492512583732605,
744
+ "epoch": 0.5276292335115864,
745
+ "grad_norm": 0.0,
746
+ "learning_rate": 0.00018382877526753865,
747
+ "loss": 2.6273,
748
+ "mean_token_accuracy": 0.4793827310204506,
749
+ "num_tokens": 80814.0,
750
+ "step": 74
751
+ },
752
+ {
753
+ "entropy": 1.641315221786499,
754
+ "epoch": 0.5347593582887701,
755
+ "grad_norm": 0.0,
756
+ "learning_rate": 0.0001835909631391201,
757
+ "loss": 2.7035,
758
+ "mean_token_accuracy": 0.4648021087050438,
759
+ "num_tokens": 81899.0,
760
+ "step": 75
761
+ },
762
+ {
763
+ "entropy": 1.6433144211769104,
764
+ "epoch": 0.5418894830659536,
765
+ "grad_norm": 0.0,
766
+ "learning_rate": 0.00018335315101070156,
767
+ "loss": 2.6694,
768
+ "mean_token_accuracy": 0.46280162036418915,
769
+ "num_tokens": 83027.0,
770
+ "step": 76
771
+ },
772
+ {
773
+ "entropy": 1.5979108810424805,
774
+ "epoch": 0.5490196078431373,
775
+ "grad_norm": 0.0,
776
+ "learning_rate": 0.00018311533888228302,
777
+ "loss": 2.6064,
778
+ "mean_token_accuracy": 0.4912242665886879,
779
+ "num_tokens": 84157.0,
780
+ "step": 77
781
+ },
782
+ {
783
+ "entropy": 1.6251288056373596,
784
+ "epoch": 0.5561497326203209,
785
+ "grad_norm": 0.0,
786
+ "learning_rate": 0.00018287752675386445,
787
+ "loss": 2.7191,
788
+ "mean_token_accuracy": 0.451671302318573,
789
+ "num_tokens": 85250.0,
790
+ "step": 78
791
+ },
792
+ {
793
+ "entropy": 1.5671390295028687,
794
+ "epoch": 0.5632798573975044,
795
+ "grad_norm": 0.0,
796
+ "learning_rate": 0.0001826397146254459,
797
+ "loss": 2.613,
798
+ "mean_token_accuracy": 0.4815371036529541,
799
+ "num_tokens": 86331.0,
800
+ "step": 79
801
+ },
802
+ {
803
+ "entropy": 1.6086040139198303,
804
+ "epoch": 0.5704099821746881,
805
+ "grad_norm": 0.0,
806
+ "learning_rate": 0.00018240190249702736,
807
+ "loss": 2.6629,
808
+ "mean_token_accuracy": 0.4586881175637245,
809
+ "num_tokens": 87430.0,
810
+ "step": 80
811
+ },
812
+ {
813
+ "entropy": 1.643826961517334,
814
+ "epoch": 0.5775401069518716,
815
+ "grad_norm": 0.0,
816
+ "learning_rate": 0.0001821640903686088,
817
+ "loss": 2.5622,
818
+ "mean_token_accuracy": 0.46292658150196075,
819
+ "num_tokens": 88542.0,
820
+ "step": 81
821
+ },
822
+ {
823
+ "entropy": 1.6064577996730804,
824
+ "epoch": 0.5846702317290553,
825
+ "grad_norm": 0.0,
826
+ "learning_rate": 0.00018192627824019025,
827
+ "loss": 2.6491,
828
+ "mean_token_accuracy": 0.47355010360479355,
829
+ "num_tokens": 89674.0,
830
+ "step": 82
831
+ },
832
+ {
833
+ "entropy": 1.628090888261795,
834
+ "epoch": 0.5918003565062389,
835
+ "grad_norm": 0.0,
836
+ "learning_rate": 0.0001816884661117717,
837
+ "loss": 2.5738,
838
+ "mean_token_accuracy": 0.44704899936914444,
839
+ "num_tokens": 90762.0,
840
+ "step": 83
841
+ },
842
+ {
843
+ "entropy": 1.558334767818451,
844
+ "epoch": 0.5989304812834224,
845
+ "grad_norm": 0.0,
846
+ "learning_rate": 0.00018145065398335317,
847
+ "loss": 2.5863,
848
+ "mean_token_accuracy": 0.4635235145688057,
849
+ "num_tokens": 91891.0,
850
+ "step": 84
851
+ },
852
+ {
853
+ "entropy": 1.5913751423358917,
854
+ "epoch": 0.6060606060606061,
855
+ "grad_norm": 0.0,
856
+ "learning_rate": 0.0001812128418549346,
857
+ "loss": 2.5779,
858
+ "mean_token_accuracy": 0.49088721722364426,
859
+ "num_tokens": 92975.0,
860
+ "step": 85
861
+ },
862
+ {
863
+ "entropy": 1.6400005519390106,
864
+ "epoch": 0.6131907308377896,
865
+ "grad_norm": 0.0,
866
+ "learning_rate": 0.00018097502972651606,
867
+ "loss": 2.7314,
868
+ "mean_token_accuracy": 0.4603074938058853,
869
+ "num_tokens": 94049.0,
870
+ "step": 86
871
+ },
872
+ {
873
+ "entropy": 1.6752884984016418,
874
+ "epoch": 0.6203208556149733,
875
+ "grad_norm": 0.0,
876
+ "learning_rate": 0.00018073721759809751,
877
+ "loss": 2.6624,
878
+ "mean_token_accuracy": 0.4621705859899521,
879
+ "num_tokens": 95148.0,
880
+ "step": 87
881
+ },
882
+ {
883
+ "entropy": 1.6517191529273987,
884
+ "epoch": 0.6274509803921569,
885
+ "grad_norm": 0.0,
886
+ "learning_rate": 0.00018049940546967897,
887
+ "loss": 2.6835,
888
+ "mean_token_accuracy": 0.4539112225174904,
889
+ "num_tokens": 96181.0,
890
+ "step": 88
891
+ },
892
+ {
893
+ "entropy": 1.7114574909210205,
894
+ "epoch": 0.6345811051693404,
895
+ "grad_norm": 0.0,
896
+ "learning_rate": 0.0001802615933412604,
897
+ "loss": 2.7193,
898
+ "mean_token_accuracy": 0.4676526263356209,
899
+ "num_tokens": 97301.0,
900
+ "step": 89
901
+ },
902
+ {
903
+ "entropy": 1.5929251611232758,
904
+ "epoch": 0.6417112299465241,
905
+ "grad_norm": 0.0,
906
+ "learning_rate": 0.00018002378121284186,
907
+ "loss": 2.5851,
908
+ "mean_token_accuracy": 0.47982004284858704,
909
+ "num_tokens": 98436.0,
910
+ "step": 90
911
+ },
912
+ {
913
+ "entropy": 1.6745183765888214,
914
+ "epoch": 0.6488413547237076,
915
+ "grad_norm": 0.0,
916
+ "learning_rate": 0.00017978596908442332,
917
+ "loss": 2.7709,
918
+ "mean_token_accuracy": 0.4384681358933449,
919
+ "num_tokens": 99477.0,
920
+ "step": 91
921
+ },
922
+ {
923
+ "entropy": 1.59268319606781,
924
+ "epoch": 0.6559714795008913,
925
+ "grad_norm": 0.0,
926
+ "learning_rate": 0.00017954815695600475,
927
+ "loss": 2.5459,
928
+ "mean_token_accuracy": 0.47278715670108795,
929
+ "num_tokens": 100622.0,
930
+ "step": 92
931
+ },
932
+ {
933
+ "entropy": 1.542839676141739,
934
+ "epoch": 0.6631016042780749,
935
+ "grad_norm": 0.0,
936
+ "learning_rate": 0.0001793103448275862,
937
+ "loss": 2.6196,
938
+ "mean_token_accuracy": 0.48384036868810654,
939
+ "num_tokens": 101710.0,
940
+ "step": 93
941
+ },
942
+ {
943
+ "entropy": 1.675879418849945,
944
+ "epoch": 0.6702317290552585,
945
+ "grad_norm": 0.0,
946
+ "learning_rate": 0.00017907253269916766,
947
+ "loss": 2.7075,
948
+ "mean_token_accuracy": 0.46232420206069946,
949
+ "num_tokens": 102745.0,
950
+ "step": 94
951
+ },
952
+ {
953
+ "entropy": 1.520689070224762,
954
+ "epoch": 0.6773618538324421,
955
+ "grad_norm": 0.0,
956
+ "learning_rate": 0.00017883472057074912,
957
+ "loss": 2.5151,
958
+ "mean_token_accuracy": 0.48868096619844437,
959
+ "num_tokens": 103923.0,
960
+ "step": 95
961
+ },
962
+ {
963
+ "entropy": 1.5939531326293945,
964
+ "epoch": 0.6844919786096256,
965
+ "grad_norm": 0.0,
966
+ "learning_rate": 0.00017859690844233058,
967
+ "loss": 2.5655,
968
+ "mean_token_accuracy": 0.48160815238952637,
969
+ "num_tokens": 105063.0,
970
+ "step": 96
971
+ },
972
+ {
973
+ "entropy": 1.6622373461723328,
974
+ "epoch": 0.6916221033868093,
975
+ "grad_norm": 0.0,
976
+ "learning_rate": 0.000178359096313912,
977
+ "loss": 2.6854,
978
+ "mean_token_accuracy": 0.4513147324323654,
979
+ "num_tokens": 106176.0,
980
+ "step": 97
981
+ },
982
+ {
983
+ "entropy": 1.596898078918457,
984
+ "epoch": 0.6987522281639929,
985
+ "grad_norm": 0.0,
986
+ "learning_rate": 0.00017812128418549347,
987
+ "loss": 2.6575,
988
+ "mean_token_accuracy": 0.46170156449079514,
989
+ "num_tokens": 107276.0,
990
+ "step": 98
991
+ },
992
+ {
993
+ "entropy": 1.6209412813186646,
994
+ "epoch": 0.7058823529411765,
995
+ "grad_norm": 0.0,
996
+ "learning_rate": 0.00017788347205707493,
997
+ "loss": 2.6675,
998
+ "mean_token_accuracy": 0.4495192915201187,
999
+ "num_tokens": 108387.0,
1000
+ "step": 99
1001
+ },
1002
+ {
1003
+ "entropy": 1.5751018524169922,
1004
+ "epoch": 0.7130124777183601,
1005
+ "grad_norm": 0.0,
1006
+ "learning_rate": 0.00017764565992865636,
1007
+ "loss": 2.6782,
1008
+ "mean_token_accuracy": 0.47493766248226166,
1009
+ "num_tokens": 109464.0,
1010
+ "step": 100
1011
+ },
1012
+ {
1013
+ "entropy": 1.5404111742973328,
1014
+ "epoch": 0.7201426024955436,
1015
+ "grad_norm": 0.0,
1016
+ "learning_rate": 0.0001774078478002378,
1017
+ "loss": 2.5644,
1018
+ "mean_token_accuracy": 0.4800315648317337,
1019
+ "num_tokens": 110545.0,
1020
+ "step": 101
1021
+ },
1022
+ {
1023
+ "entropy": 1.5617071688175201,
1024
+ "epoch": 0.7272727272727273,
1025
+ "grad_norm": 0.0,
1026
+ "learning_rate": 0.00017717003567181927,
1027
+ "loss": 2.4542,
1028
+ "mean_token_accuracy": 0.486552469432354,
1029
+ "num_tokens": 111644.0,
1030
+ "step": 102
1031
+ },
1032
+ {
1033
+ "entropy": 1.6221667528152466,
1034
+ "epoch": 0.7344028520499108,
1035
+ "grad_norm": 0.0,
1036
+ "learning_rate": 0.00017693222354340073,
1037
+ "loss": 2.6873,
1038
+ "mean_token_accuracy": 0.4583618715405464,
1039
+ "num_tokens": 112683.0,
1040
+ "step": 103
1041
+ },
1042
+ {
1043
+ "entropy": 1.6229766011238098,
1044
+ "epoch": 0.7415329768270945,
1045
+ "grad_norm": 0.0,
1046
+ "learning_rate": 0.0001766944114149822,
1047
+ "loss": 2.7595,
1048
+ "mean_token_accuracy": 0.4478139355778694,
1049
+ "num_tokens": 113734.0,
1050
+ "step": 104
1051
+ },
1052
+ {
1053
+ "entropy": 1.6290508806705475,
1054
+ "epoch": 0.7486631016042781,
1055
+ "grad_norm": 0.0,
1056
+ "learning_rate": 0.00017645659928656362,
1057
+ "loss": 2.648,
1058
+ "mean_token_accuracy": 0.4640928953886032,
1059
+ "num_tokens": 114840.0,
1060
+ "step": 105
1061
+ },
1062
+ {
1063
+ "entropy": 1.5602010190486908,
1064
+ "epoch": 0.7557932263814616,
1065
+ "grad_norm": 0.0,
1066
+ "learning_rate": 0.00017621878715814507,
1067
+ "loss": 2.6151,
1068
+ "mean_token_accuracy": 0.47945626825094223,
1069
+ "num_tokens": 115918.0,
1070
+ "step": 106
1071
+ },
1072
+ {
1073
+ "entropy": 1.561210036277771,
1074
+ "epoch": 0.7629233511586453,
1075
+ "grad_norm": 0.0,
1076
+ "learning_rate": 0.00017598097502972653,
1077
+ "loss": 2.6753,
1078
+ "mean_token_accuracy": 0.4755818694829941,
1079
+ "num_tokens": 116992.0,
1080
+ "step": 107
1081
+ },
1082
+ {
1083
+ "entropy": 1.5463439524173737,
1084
+ "epoch": 0.7700534759358288,
1085
+ "grad_norm": 0.0,
1086
+ "learning_rate": 0.00017574316290130796,
1087
+ "loss": 2.5312,
1088
+ "mean_token_accuracy": 0.4788963794708252,
1089
+ "num_tokens": 118163.0,
1090
+ "step": 108
1091
+ },
1092
+ {
1093
+ "entropy": 1.545140415430069,
1094
+ "epoch": 0.7771836007130125,
1095
+ "grad_norm": 0.0,
1096
+ "learning_rate": 0.00017550535077288942,
1097
+ "loss": 2.4861,
1098
+ "mean_token_accuracy": 0.48517899960279465,
1099
+ "num_tokens": 119246.0,
1100
+ "step": 109
1101
+ },
1102
+ {
1103
+ "entropy": 1.6490318477153778,
1104
+ "epoch": 0.7843137254901961,
1105
+ "grad_norm": 0.0,
1106
+ "learning_rate": 0.00017526753864447088,
1107
+ "loss": 2.6319,
1108
+ "mean_token_accuracy": 0.4522154629230499,
1109
+ "num_tokens": 120352.0,
1110
+ "step": 110
1111
+ },
1112
+ {
1113
+ "entropy": 1.5705026686191559,
1114
+ "epoch": 0.7914438502673797,
1115
+ "grad_norm": 0.0,
1116
+ "learning_rate": 0.0001750297265160523,
1117
+ "loss": 2.5889,
1118
+ "mean_token_accuracy": 0.4755884185433388,
1119
+ "num_tokens": 121495.0,
1120
+ "step": 111
1121
+ },
1122
+ {
1123
+ "entropy": 1.5974452495574951,
1124
+ "epoch": 0.7985739750445633,
1125
+ "grad_norm": 0.0,
1126
+ "learning_rate": 0.0001747919143876338,
1127
+ "loss": 2.5626,
1128
+ "mean_token_accuracy": 0.4795725420117378,
1129
+ "num_tokens": 122564.0,
1130
+ "step": 112
1131
+ },
1132
+ {
1133
+ "entropy": 1.5680693686008453,
1134
+ "epoch": 0.8057040998217468,
1135
+ "grad_norm": 0.0,
1136
+ "learning_rate": 0.00017455410225921522,
1137
+ "loss": 2.6273,
1138
+ "mean_token_accuracy": 0.4590470939874649,
1139
+ "num_tokens": 123650.0,
1140
+ "step": 113
1141
+ },
1142
+ {
1143
+ "entropy": 1.6800198554992676,
1144
+ "epoch": 0.8128342245989305,
1145
+ "grad_norm": 0.0,
1146
+ "learning_rate": 0.00017431629013079668,
1147
+ "loss": 2.737,
1148
+ "mean_token_accuracy": 0.45866189897060394,
1149
+ "num_tokens": 124779.0,
1150
+ "step": 114
1151
+ },
1152
+ {
1153
+ "entropy": 1.6031546890735626,
1154
+ "epoch": 0.8199643493761141,
1155
+ "grad_norm": 0.0,
1156
+ "learning_rate": 0.00017407847800237814,
1157
+ "loss": 2.5439,
1158
+ "mean_token_accuracy": 0.472602941095829,
1159
+ "num_tokens": 125900.0,
1160
+ "step": 115
1161
+ },
1162
+ {
1163
+ "entropy": 1.6303865611553192,
1164
+ "epoch": 0.8270944741532977,
1165
+ "grad_norm": 0.0,
1166
+ "learning_rate": 0.00017384066587395957,
1167
+ "loss": 2.6487,
1168
+ "mean_token_accuracy": 0.4673057347536087,
1169
+ "num_tokens": 126993.0,
1170
+ "step": 116
1171
+ },
1172
+ {
1173
+ "entropy": 1.6584992706775665,
1174
+ "epoch": 0.8342245989304813,
1175
+ "grad_norm": 0.0,
1176
+ "learning_rate": 0.00017360285374554103,
1177
+ "loss": 2.6956,
1178
+ "mean_token_accuracy": 0.46377309411764145,
1179
+ "num_tokens": 128138.0,
1180
+ "step": 117
1181
+ },
1182
+ {
1183
+ "entropy": 1.591305822134018,
1184
+ "epoch": 0.8413547237076648,
1185
+ "grad_norm": 0.0,
1186
+ "learning_rate": 0.00017336504161712249,
1187
+ "loss": 2.713,
1188
+ "mean_token_accuracy": 0.46212588995695114,
1189
+ "num_tokens": 129222.0,
1190
+ "step": 118
1191
+ },
1192
+ {
1193
+ "entropy": 1.6993348598480225,
1194
+ "epoch": 0.8484848484848485,
1195
+ "grad_norm": 0.0,
1196
+ "learning_rate": 0.00017312722948870392,
1197
+ "loss": 2.7792,
1198
+ "mean_token_accuracy": 0.4319414496421814,
1199
+ "num_tokens": 130249.0,
1200
+ "step": 119
1201
+ },
1202
+ {
1203
+ "entropy": 1.5929858684539795,
1204
+ "epoch": 0.8556149732620321,
1205
+ "grad_norm": 0.0,
1206
+ "learning_rate": 0.0001728894173602854,
1207
+ "loss": 2.6866,
1208
+ "mean_token_accuracy": 0.47090228646993637,
1209
+ "num_tokens": 131310.0,
1210
+ "step": 120
1211
+ },
1212
+ {
1213
+ "entropy": 1.667660892009735,
1214
+ "epoch": 0.8627450980392157,
1215
+ "grad_norm": 0.0,
1216
+ "learning_rate": 0.00017265160523186683,
1217
+ "loss": 2.6699,
1218
+ "mean_token_accuracy": 0.45984991639852524,
1219
+ "num_tokens": 132431.0,
1220
+ "step": 121
1221
+ },
1222
+ {
1223
+ "entropy": 1.548890471458435,
1224
+ "epoch": 0.8698752228163993,
1225
+ "grad_norm": 0.0,
1226
+ "learning_rate": 0.00017241379310344826,
1227
+ "loss": 2.6131,
1228
+ "mean_token_accuracy": 0.4870634377002716,
1229
+ "num_tokens": 133545.0,
1230
+ "step": 122
1231
+ },
1232
+ {
1233
+ "entropy": 1.5599585175514221,
1234
+ "epoch": 0.8770053475935828,
1235
+ "grad_norm": 0.0,
1236
+ "learning_rate": 0.00017217598097502975,
1237
+ "loss": 2.5476,
1238
+ "mean_token_accuracy": 0.4777110442519188,
1239
+ "num_tokens": 134678.0,
1240
+ "step": 123
1241
+ },
1242
+ {
1243
+ "entropy": 1.5160918235778809,
1244
+ "epoch": 0.8841354723707665,
1245
+ "grad_norm": 0.0,
1246
+ "learning_rate": 0.00017193816884661118,
1247
+ "loss": 2.5731,
1248
+ "mean_token_accuracy": 0.478961318731308,
1249
+ "num_tokens": 135821.0,
1250
+ "step": 124
1251
+ },
1252
+ {
1253
+ "entropy": 1.5480628907680511,
1254
+ "epoch": 0.8912655971479501,
1255
+ "grad_norm": 0.0,
1256
+ "learning_rate": 0.00017170035671819264,
1257
+ "loss": 2.5291,
1258
+ "mean_token_accuracy": 0.4755103513598442,
1259
+ "num_tokens": 136971.0,
1260
+ "step": 125
1261
+ },
1262
+ {
1263
+ "entropy": 1.5862606167793274,
1264
+ "epoch": 0.8983957219251337,
1265
+ "grad_norm": 0.0,
1266
+ "learning_rate": 0.0001714625445897741,
1267
+ "loss": 2.6396,
1268
+ "mean_token_accuracy": 0.46081865578889847,
1269
+ "num_tokens": 138007.0,
1270
+ "step": 126
1271
+ },
1272
+ {
1273
+ "entropy": 1.669043391942978,
1274
+ "epoch": 0.9055258467023173,
1275
+ "grad_norm": 0.0,
1276
+ "learning_rate": 0.00017122473246135552,
1277
+ "loss": 2.6321,
1278
+ "mean_token_accuracy": 0.4644095078110695,
1279
+ "num_tokens": 139053.0,
1280
+ "step": 127
1281
+ },
1282
+ {
1283
+ "entropy": 1.5860805809497833,
1284
+ "epoch": 0.9126559714795008,
1285
+ "grad_norm": 0.0,
1286
+ "learning_rate": 0.00017098692033293698,
1287
+ "loss": 2.5403,
1288
+ "mean_token_accuracy": 0.4631856083869934,
1289
+ "num_tokens": 140147.0,
1290
+ "step": 128
1291
+ },
1292
+ {
1293
+ "entropy": 1.6290316879749298,
1294
+ "epoch": 0.9197860962566845,
1295
+ "grad_norm": 0.0,
1296
+ "learning_rate": 0.00017074910820451844,
1297
+ "loss": 2.6503,
1298
+ "mean_token_accuracy": 0.46986210346221924,
1299
+ "num_tokens": 141269.0,
1300
+ "step": 129
1301
+ },
1302
+ {
1303
+ "entropy": 1.5800673365592957,
1304
+ "epoch": 0.9269162210338681,
1305
+ "grad_norm": 0.0,
1306
+ "learning_rate": 0.00017051129607609987,
1307
+ "loss": 2.5817,
1308
+ "mean_token_accuracy": 0.46785174310207367,
1309
+ "num_tokens": 142404.0,
1310
+ "step": 130
1311
+ },
1312
+ {
1313
+ "entropy": 1.5903257727622986,
1314
+ "epoch": 0.9340463458110517,
1315
+ "grad_norm": 0.0,
1316
+ "learning_rate": 0.00017027348394768135,
1317
+ "loss": 2.5134,
1318
+ "mean_token_accuracy": 0.4654293358325958,
1319
+ "num_tokens": 143534.0,
1320
+ "step": 131
1321
+ },
1322
+ {
1323
+ "entropy": 1.5758326351642609,
1324
+ "epoch": 0.9411764705882353,
1325
+ "grad_norm": 0.0,
1326
+ "learning_rate": 0.00017003567181926279,
1327
+ "loss": 2.6744,
1328
+ "mean_token_accuracy": 0.47502800077199936,
1329
+ "num_tokens": 144634.0,
1330
+ "step": 132
1331
+ },
1332
+ {
1333
+ "entropy": 1.555185467004776,
1334
+ "epoch": 0.948306595365419,
1335
+ "grad_norm": 0.0,
1336
+ "learning_rate": 0.00016979785969084424,
1337
+ "loss": 2.5801,
1338
+ "mean_token_accuracy": 0.47467251121997833,
1339
+ "num_tokens": 145695.0,
1340
+ "step": 133
1341
+ },
1342
+ {
1343
+ "entropy": 1.58922079205513,
1344
+ "epoch": 0.9554367201426025,
1345
+ "grad_norm": 0.0,
1346
+ "learning_rate": 0.0001695600475624257,
1347
+ "loss": 2.619,
1348
+ "mean_token_accuracy": 0.4779004603624344,
1349
+ "num_tokens": 146787.0,
1350
+ "step": 134
1351
+ },
1352
+ {
1353
+ "entropy": 1.6058009564876556,
1354
+ "epoch": 0.9625668449197861,
1355
+ "grad_norm": 0.0,
1356
+ "learning_rate": 0.00016932223543400713,
1357
+ "loss": 2.683,
1358
+ "mean_token_accuracy": 0.4785980358719826,
1359
+ "num_tokens": 147817.0,
1360
+ "step": 135
1361
+ },
1362
+ {
1363
+ "entropy": 1.6281861662864685,
1364
+ "epoch": 0.9696969696969697,
1365
+ "grad_norm": 0.0,
1366
+ "learning_rate": 0.0001690844233055886,
1367
+ "loss": 2.7144,
1368
+ "mean_token_accuracy": 0.4627036154270172,
1369
+ "num_tokens": 148907.0,
1370
+ "step": 136
1371
+ },
1372
+ {
1373
+ "entropy": 1.619028925895691,
1374
+ "epoch": 0.9768270944741533,
1375
+ "grad_norm": 0.0,
1376
+ "learning_rate": 0.00016884661117717005,
1377
+ "loss": 2.6079,
1378
+ "mean_token_accuracy": 0.45756662636995316,
1379
+ "num_tokens": 149993.0,
1380
+ "step": 137
1381
+ },
1382
+ {
1383
+ "entropy": 1.5888321995735168,
1384
+ "epoch": 0.983957219251337,
1385
+ "grad_norm": 0.0,
1386
+ "learning_rate": 0.00016860879904875148,
1387
+ "loss": 2.6093,
1388
+ "mean_token_accuracy": 0.4724939614534378,
1389
+ "num_tokens": 151098.0,
1390
+ "step": 138
1391
+ },
1392
+ {
1393
+ "entropy": 1.6436494290828705,
1394
+ "epoch": 0.9910873440285205,
1395
+ "grad_norm": 0.0,
1396
+ "learning_rate": 0.00016837098692033296,
1397
+ "loss": 2.6575,
1398
+ "mean_token_accuracy": 0.4623269736766815,
1399
+ "num_tokens": 152163.0,
1400
+ "step": 139
1401
+ },
1402
+ {
1403
+ "entropy": 1.5655477941036224,
1404
+ "epoch": 0.9982174688057041,
1405
+ "grad_norm": 0.0,
1406
+ "learning_rate": 0.0001681331747919144,
1407
+ "loss": 2.6335,
1408
+ "mean_token_accuracy": 0.47587042301893234,
1409
+ "num_tokens": 153275.0,
1410
+ "step": 140
1411
+ },
1412
+ {
1413
+ "entropy": 1.7136651277542114,
1414
+ "epoch": 1.0,
1415
+ "grad_norm": 0.0,
1416
+ "learning_rate": 0.00016789536266349582,
1417
+ "loss": 2.6691,
1418
+ "mean_token_accuracy": 0.4723247289657593,
1419
+ "num_tokens": 153550.0,
1420
+ "step": 141
1421
+ },
1422
+ {
1423
+ "entropy": 1.6066825091838837,
1424
+ "epoch": 1.0071301247771836,
1425
+ "grad_norm": 0.0,
1426
+ "learning_rate": 0.0001676575505350773,
1427
+ "loss": 2.5409,
1428
+ "mean_token_accuracy": 0.48296716809272766,
1429
+ "num_tokens": 154641.0,
1430
+ "step": 142
1431
+ },
1432
+ {
1433
+ "entropy": 1.5699058771133423,
1434
+ "epoch": 1.014260249554367,
1435
+ "grad_norm": 0.0,
1436
+ "learning_rate": 0.00016741973840665874,
1437
+ "loss": 2.5472,
1438
+ "mean_token_accuracy": 0.47184478491544724,
1439
+ "num_tokens": 155762.0,
1440
+ "step": 143
1441
+ },
1442
+ {
1443
+ "entropy": 1.5619142949581146,
1444
+ "epoch": 1.0213903743315509,
1445
+ "grad_norm": 0.0,
1446
+ "learning_rate": 0.0001671819262782402,
1447
+ "loss": 2.6692,
1448
+ "mean_token_accuracy": 0.4779776930809021,
1449
+ "num_tokens": 156859.0,
1450
+ "step": 144
1451
+ },
1452
+ {
1453
+ "entropy": 1.5965659022331238,
1454
+ "epoch": 1.0285204991087344,
1455
+ "grad_norm": 0.0,
1456
+ "learning_rate": 0.00016694411414982165,
1457
+ "loss": 2.621,
1458
+ "mean_token_accuracy": 0.4778958112001419,
1459
+ "num_tokens": 157991.0,
1460
+ "step": 145
1461
+ },
1462
+ {
1463
+ "entropy": 1.6152032911777496,
1464
+ "epoch": 1.035650623885918,
1465
+ "grad_norm": 0.0,
1466
+ "learning_rate": 0.00016670630202140308,
1467
+ "loss": 2.5771,
1468
+ "mean_token_accuracy": 0.4681878834962845,
1469
+ "num_tokens": 159092.0,
1470
+ "step": 146
1471
+ },
1472
+ {
1473
+ "entropy": 1.5952391922473907,
1474
+ "epoch": 1.0427807486631016,
1475
+ "grad_norm": 0.0,
1476
+ "learning_rate": 0.00016646848989298457,
1477
+ "loss": 2.6372,
1478
+ "mean_token_accuracy": 0.48037248849868774,
1479
+ "num_tokens": 160160.0,
1480
+ "step": 147
1481
+ },
1482
+ {
1483
+ "entropy": 1.565784215927124,
1484
+ "epoch": 1.049910873440285,
1485
+ "grad_norm": 0.0,
1486
+ "learning_rate": 0.000166230677764566,
1487
+ "loss": 2.6739,
1488
+ "mean_token_accuracy": 0.4823187068104744,
1489
+ "num_tokens": 161263.0,
1490
+ "step": 148
1491
+ },
1492
+ {
1493
+ "entropy": 1.5616013407707214,
1494
+ "epoch": 1.0570409982174689,
1495
+ "grad_norm": 0.0,
1496
+ "learning_rate": 0.00016599286563614743,
1497
+ "loss": 2.538,
1498
+ "mean_token_accuracy": 0.4936261996626854,
1499
+ "num_tokens": 162366.0,
1500
+ "step": 149
1501
+ },
1502
+ {
1503
+ "entropy": 1.550614982843399,
1504
+ "epoch": 1.0641711229946524,
1505
+ "grad_norm": 0.0,
1506
+ "learning_rate": 0.00016575505350772892,
1507
+ "loss": 2.5405,
1508
+ "mean_token_accuracy": 0.4571392834186554,
1509
+ "num_tokens": 163510.0,
1510
+ "step": 150
1511
+ },
1512
+ {
1513
+ "entropy": 1.6245464980602264,
1514
+ "epoch": 1.071301247771836,
1515
+ "grad_norm": 0.0,
1516
+ "learning_rate": 0.00016551724137931035,
1517
+ "loss": 2.6446,
1518
+ "mean_token_accuracy": 0.46846461296081543,
1519
+ "num_tokens": 164565.0,
1520
+ "step": 151
1521
+ },
1522
+ {
1523
+ "entropy": 1.4947470128536224,
1524
+ "epoch": 1.0784313725490196,
1525
+ "grad_norm": 0.0,
1526
+ "learning_rate": 0.0001652794292508918,
1527
+ "loss": 2.5193,
1528
+ "mean_token_accuracy": 0.4816185459494591,
1529
+ "num_tokens": 165718.0,
1530
+ "step": 152
1531
+ },
1532
+ {
1533
+ "entropy": 1.5682013034820557,
1534
+ "epoch": 1.085561497326203,
1535
+ "grad_norm": 0.0,
1536
+ "learning_rate": 0.00016504161712247326,
1537
+ "loss": 2.5916,
1538
+ "mean_token_accuracy": 0.46111301332712173,
1539
+ "num_tokens": 166812.0,
1540
+ "step": 153
1541
+ },
1542
+ {
1543
+ "entropy": 1.6156157553195953,
1544
+ "epoch": 1.0926916221033869,
1545
+ "grad_norm": 0.0,
1546
+ "learning_rate": 0.0001648038049940547,
1547
+ "loss": 2.6128,
1548
+ "mean_token_accuracy": 0.4597594439983368,
1549
+ "num_tokens": 167926.0,
1550
+ "step": 154
1551
+ },
1552
+ {
1553
+ "entropy": 1.59586563706398,
1554
+ "epoch": 1.0998217468805704,
1555
+ "grad_norm": 0.0,
1556
+ "learning_rate": 0.00016456599286563618,
1557
+ "loss": 2.6021,
1558
+ "mean_token_accuracy": 0.4618517607450485,
1559
+ "num_tokens": 168982.0,
1560
+ "step": 155
1561
+ },
1562
+ {
1563
+ "entropy": 1.6061933636665344,
1564
+ "epoch": 1.106951871657754,
1565
+ "grad_norm": 0.0,
1566
+ "learning_rate": 0.0001643281807372176,
1567
+ "loss": 2.6854,
1568
+ "mean_token_accuracy": 0.43533751368522644,
1569
+ "num_tokens": 170010.0,
1570
+ "step": 156
1571
+ },
1572
+ {
1573
+ "entropy": 1.6085174083709717,
1574
+ "epoch": 1.1140819964349375,
1575
+ "grad_norm": 0.0,
1576
+ "learning_rate": 0.00016409036860879904,
1577
+ "loss": 2.6981,
1578
+ "mean_token_accuracy": 0.4599795266985893,
1579
+ "num_tokens": 171113.0,
1580
+ "step": 157
1581
+ },
1582
+ {
1583
+ "entropy": 1.5913650691509247,
1584
+ "epoch": 1.121212121212121,
1585
+ "grad_norm": 0.0,
1586
+ "learning_rate": 0.00016385255648038052,
1587
+ "loss": 2.5902,
1588
+ "mean_token_accuracy": 0.4770422652363777,
1589
+ "num_tokens": 172251.0,
1590
+ "step": 158
1591
+ },
1592
+ {
1593
+ "entropy": 1.5887981355190277,
1594
+ "epoch": 1.1283422459893049,
1595
+ "grad_norm": 0.0,
1596
+ "learning_rate": 0.00016361474435196195,
1597
+ "loss": 2.6519,
1598
+ "mean_token_accuracy": 0.46707142144441605,
1599
+ "num_tokens": 173342.0,
1600
+ "step": 159
1601
+ },
1602
+ {
1603
+ "entropy": 1.574705809354782,
1604
+ "epoch": 1.1354723707664884,
1605
+ "grad_norm": 0.0,
1606
+ "learning_rate": 0.0001633769322235434,
1607
+ "loss": 2.6085,
1608
+ "mean_token_accuracy": 0.478085033595562,
1609
+ "num_tokens": 174460.0,
1610
+ "step": 160
1611
+ },
1612
+ {
1613
+ "entropy": 1.5885936915874481,
1614
+ "epoch": 1.142602495543672,
1615
+ "grad_norm": 0.0,
1616
+ "learning_rate": 0.00016313912009512487,
1617
+ "loss": 2.7184,
1618
+ "mean_token_accuracy": 0.45598648488521576,
1619
+ "num_tokens": 175576.0,
1620
+ "step": 161
1621
+ },
1622
+ {
1623
+ "entropy": 1.5892296731472015,
1624
+ "epoch": 1.1497326203208555,
1625
+ "grad_norm": 0.0,
1626
+ "learning_rate": 0.0001629013079667063,
1627
+ "loss": 2.7047,
1628
+ "mean_token_accuracy": 0.46477679163217545,
1629
+ "num_tokens": 176675.0,
1630
+ "step": 162
1631
+ },
1632
+ {
1633
+ "entropy": 1.6486813724040985,
1634
+ "epoch": 1.156862745098039,
1635
+ "grad_norm": 0.0,
1636
+ "learning_rate": 0.00016266349583828776,
1637
+ "loss": 2.7061,
1638
+ "mean_token_accuracy": 0.46870480477809906,
1639
+ "num_tokens": 177740.0,
1640
+ "step": 163
1641
+ },
1642
+ {
1643
+ "entropy": 1.5759459435939789,
1644
+ "epoch": 1.1639928698752229,
1645
+ "grad_norm": 0.0,
1646
+ "learning_rate": 0.00016242568370986922,
1647
+ "loss": 2.5503,
1648
+ "mean_token_accuracy": 0.46419017761945724,
1649
+ "num_tokens": 178796.0,
1650
+ "step": 164
1651
+ },
1652
+ {
1653
+ "entropy": 1.6036653220653534,
1654
+ "epoch": 1.1711229946524064,
1655
+ "grad_norm": 0.0,
1656
+ "learning_rate": 0.00016218787158145065,
1657
+ "loss": 2.6642,
1658
+ "mean_token_accuracy": 0.47088219970464706,
1659
+ "num_tokens": 179879.0,
1660
+ "step": 165
1661
+ },
1662
+ {
1663
+ "entropy": 1.5834835767745972,
1664
+ "epoch": 1.17825311942959,
1665
+ "grad_norm": 0.0,
1666
+ "learning_rate": 0.00016195005945303213,
1667
+ "loss": 2.6007,
1668
+ "mean_token_accuracy": 0.4636633098125458,
1669
+ "num_tokens": 181061.0,
1670
+ "step": 166
1671
+ },
1672
+ {
1673
+ "entropy": 1.7047175765037537,
1674
+ "epoch": 1.1853832442067735,
1675
+ "grad_norm": 0.0,
1676
+ "learning_rate": 0.00016171224732461356,
1677
+ "loss": 2.6283,
1678
+ "mean_token_accuracy": 0.46398939192295074,
1679
+ "num_tokens": 182160.0,
1680
+ "step": 167
1681
+ },
1682
+ {
1683
+ "entropy": 1.649744689464569,
1684
+ "epoch": 1.192513368983957,
1685
+ "grad_norm": 0.0,
1686
+ "learning_rate": 0.00016147443519619502,
1687
+ "loss": 2.7414,
1688
+ "mean_token_accuracy": 0.44918210059404373,
1689
+ "num_tokens": 183238.0,
1690
+ "step": 168
1691
+ },
1692
+ {
1693
+ "entropy": 1.4582054913043976,
1694
+ "epoch": 1.1996434937611409,
1695
+ "grad_norm": 0.0,
1696
+ "learning_rate": 0.00016123662306777648,
1697
+ "loss": 2.4485,
1698
+ "mean_token_accuracy": 0.5028558596968651,
1699
+ "num_tokens": 184343.0,
1700
+ "step": 169
1701
+ },
1702
+ {
1703
+ "entropy": 1.5874928832054138,
1704
+ "epoch": 1.2067736185383244,
1705
+ "grad_norm": 0.0,
1706
+ "learning_rate": 0.0001609988109393579,
1707
+ "loss": 2.6477,
1708
+ "mean_token_accuracy": 0.47324957698583603,
1709
+ "num_tokens": 185432.0,
1710
+ "step": 170
1711
+ },
1712
+ {
1713
+ "entropy": 1.5870967209339142,
1714
+ "epoch": 1.213903743315508,
1715
+ "grad_norm": 0.0,
1716
+ "learning_rate": 0.00016076099881093936,
1717
+ "loss": 2.6929,
1718
+ "mean_token_accuracy": 0.459871307015419,
1719
+ "num_tokens": 186527.0,
1720
+ "step": 171
1721
+ },
1722
+ {
1723
+ "entropy": 1.6552450358867645,
1724
+ "epoch": 1.2210338680926915,
1725
+ "grad_norm": 0.0,
1726
+ "learning_rate": 0.00016052318668252082,
1727
+ "loss": 2.6735,
1728
+ "mean_token_accuracy": 0.45555536448955536,
1729
+ "num_tokens": 187577.0,
1730
+ "step": 172
1731
+ },
1732
+ {
1733
+ "entropy": 1.6631282269954681,
1734
+ "epoch": 1.228163992869875,
1735
+ "grad_norm": 0.0,
1736
+ "learning_rate": 0.00016028537455410225,
1737
+ "loss": 2.6354,
1738
+ "mean_token_accuracy": 0.47852643579244614,
1739
+ "num_tokens": 188730.0,
1740
+ "step": 173
1741
+ },
1742
+ {
1743
+ "entropy": 1.6064516603946686,
1744
+ "epoch": 1.2352941176470589,
1745
+ "grad_norm": 0.0,
1746
+ "learning_rate": 0.00016004756242568374,
1747
+ "loss": 2.6498,
1748
+ "mean_token_accuracy": 0.4627776965498924,
1749
+ "num_tokens": 189851.0,
1750
+ "step": 174
1751
+ },
1752
+ {
1753
+ "entropy": 1.6195379793643951,
1754
+ "epoch": 1.2424242424242424,
1755
+ "grad_norm": 0.0,
1756
+ "learning_rate": 0.00015980975029726517,
1757
+ "loss": 2.5955,
1758
+ "mean_token_accuracy": 0.4755994454026222,
1759
+ "num_tokens": 190954.0,
1760
+ "step": 175
1761
+ },
1762
+ {
1763
+ "entropy": 1.583428680896759,
1764
+ "epoch": 1.249554367201426,
1765
+ "grad_norm": 0.0,
1766
+ "learning_rate": 0.00015957193816884663,
1767
+ "loss": 2.5734,
1768
+ "mean_token_accuracy": 0.486144557595253,
1769
+ "num_tokens": 192084.0,
1770
+ "step": 176
1771
+ },
1772
+ {
1773
+ "entropy": 1.61075758934021,
1774
+ "epoch": 1.2566844919786098,
1775
+ "grad_norm": 0.0,
1776
+ "learning_rate": 0.00015933412604042808,
1777
+ "loss": 2.699,
1778
+ "mean_token_accuracy": 0.4629248157143593,
1779
+ "num_tokens": 193111.0,
1780
+ "step": 177
1781
+ },
1782
+ {
1783
+ "entropy": 1.5986732840538025,
1784
+ "epoch": 1.263814616755793,
1785
+ "grad_norm": 0.0,
1786
+ "learning_rate": 0.00015909631391200951,
1787
+ "loss": 2.6723,
1788
+ "mean_token_accuracy": 0.4575885683298111,
1789
+ "num_tokens": 194260.0,
1790
+ "step": 178
1791
+ },
1792
+ {
1793
+ "entropy": 1.5930440127849579,
1794
+ "epoch": 1.2709447415329769,
1795
+ "grad_norm": 0.0,
1796
+ "learning_rate": 0.00015885850178359097,
1797
+ "loss": 2.7138,
1798
+ "mean_token_accuracy": 0.4715413674712181,
1799
+ "num_tokens": 195316.0,
1800
+ "step": 179
1801
+ },
1802
+ {
1803
+ "entropy": 1.605830729007721,
1804
+ "epoch": 1.2780748663101604,
1805
+ "grad_norm": 0.0,
1806
+ "learning_rate": 0.00015862068965517243,
1807
+ "loss": 2.6979,
1808
+ "mean_token_accuracy": 0.4691004157066345,
1809
+ "num_tokens": 196406.0,
1810
+ "step": 180
1811
+ },
1812
+ {
1813
+ "entropy": 1.6044515669345856,
1814
+ "epoch": 1.285204991087344,
1815
+ "grad_norm": 0.0,
1816
+ "learning_rate": 0.00015838287752675386,
1817
+ "loss": 2.6274,
1818
+ "mean_token_accuracy": 0.4783453792333603,
1819
+ "num_tokens": 197500.0,
1820
+ "step": 181
1821
+ },
1822
+ {
1823
+ "entropy": 1.5863282978534698,
1824
+ "epoch": 1.2923351158645278,
1825
+ "grad_norm": 0.0,
1826
+ "learning_rate": 0.00015814506539833532,
1827
+ "loss": 2.5774,
1828
+ "mean_token_accuracy": 0.48002146929502487,
1829
+ "num_tokens": 198661.0,
1830
+ "step": 182
1831
+ },
1832
+ {
1833
+ "entropy": 1.673670768737793,
1834
+ "epoch": 1.299465240641711,
1835
+ "grad_norm": 0.0,
1836
+ "learning_rate": 0.00015790725326991678,
1837
+ "loss": 2.6731,
1838
+ "mean_token_accuracy": 0.46556977182626724,
1839
+ "num_tokens": 199760.0,
1840
+ "step": 183
1841
+ },
1842
+ {
1843
+ "entropy": 1.5792707800865173,
1844
+ "epoch": 1.3065953654188949,
1845
+ "grad_norm": 0.0,
1846
+ "learning_rate": 0.0001576694411414982,
1847
+ "loss": 2.598,
1848
+ "mean_token_accuracy": 0.4617435112595558,
1849
+ "num_tokens": 200837.0,
1850
+ "step": 184
1851
+ },
1852
+ {
1853
+ "entropy": 1.6057993471622467,
1854
+ "epoch": 1.3137254901960784,
1855
+ "grad_norm": 0.0,
1856
+ "learning_rate": 0.0001574316290130797,
1857
+ "loss": 2.5975,
1858
+ "mean_token_accuracy": 0.469496913254261,
1859
+ "num_tokens": 201963.0,
1860
+ "step": 185
1861
+ },
1862
+ {
1863
+ "entropy": 1.6113585829734802,
1864
+ "epoch": 1.320855614973262,
1865
+ "grad_norm": 0.0,
1866
+ "learning_rate": 0.00015719381688466112,
1867
+ "loss": 2.7397,
1868
+ "mean_token_accuracy": 0.46607375144958496,
1869
+ "num_tokens": 203043.0,
1870
+ "step": 186
1871
+ },
1872
+ {
1873
+ "entropy": 1.6389738619327545,
1874
+ "epoch": 1.3279857397504458,
1875
+ "grad_norm": 0.0,
1876
+ "learning_rate": 0.00015695600475624258,
1877
+ "loss": 2.6493,
1878
+ "mean_token_accuracy": 0.4742783457040787,
1879
+ "num_tokens": 204118.0,
1880
+ "step": 187
1881
+ },
1882
+ {
1883
+ "entropy": 1.6438090801239014,
1884
+ "epoch": 1.3351158645276293,
1885
+ "grad_norm": 0.0,
1886
+ "learning_rate": 0.00015671819262782404,
1887
+ "loss": 2.7208,
1888
+ "mean_token_accuracy": 0.4482914060354233,
1889
+ "num_tokens": 205174.0,
1890
+ "step": 188
1891
+ },
1892
+ {
1893
+ "entropy": 1.5948124527931213,
1894
+ "epoch": 1.3422459893048129,
1895
+ "grad_norm": 0.0,
1896
+ "learning_rate": 0.00015648038049940547,
1897
+ "loss": 2.6397,
1898
+ "mean_token_accuracy": 0.4829149469733238,
1899
+ "num_tokens": 206322.0,
1900
+ "step": 189
1901
+ },
1902
+ {
1903
+ "entropy": 1.5886778235435486,
1904
+ "epoch": 1.3493761140819964,
1905
+ "grad_norm": 0.0,
1906
+ "learning_rate": 0.00015624256837098693,
1907
+ "loss": 2.4934,
1908
+ "mean_token_accuracy": 0.4762219786643982,
1909
+ "num_tokens": 207430.0,
1910
+ "step": 190
1911
+ },
1912
+ {
1913
+ "entropy": 1.5851022601127625,
1914
+ "epoch": 1.35650623885918,
1915
+ "grad_norm": 0.0,
1916
+ "learning_rate": 0.00015600475624256838,
1917
+ "loss": 2.5747,
1918
+ "mean_token_accuracy": 0.44965071976184845,
1919
+ "num_tokens": 208572.0,
1920
+ "step": 191
1921
+ },
1922
+ {
1923
+ "entropy": 1.6201273202896118,
1924
+ "epoch": 1.3636363636363638,
1925
+ "grad_norm": 0.0,
1926
+ "learning_rate": 0.00015576694411414981,
1927
+ "loss": 2.6311,
1928
+ "mean_token_accuracy": 0.462075375020504,
1929
+ "num_tokens": 209649.0,
1930
+ "step": 192
1931
+ },
1932
+ {
1933
+ "entropy": 1.5876831114292145,
1934
+ "epoch": 1.3707664884135473,
1935
+ "grad_norm": 0.0,
1936
+ "learning_rate": 0.00015552913198573127,
1937
+ "loss": 2.6102,
1938
+ "mean_token_accuracy": 0.48762883245944977,
1939
+ "num_tokens": 210713.0,
1940
+ "step": 193
1941
+ },
1942
+ {
1943
+ "entropy": 1.5845709443092346,
1944
+ "epoch": 1.3778966131907309,
1945
+ "grad_norm": 0.0,
1946
+ "learning_rate": 0.00015529131985731273,
1947
+ "loss": 2.6816,
1948
+ "mean_token_accuracy": 0.48001401126384735,
1949
+ "num_tokens": 211837.0,
1950
+ "step": 194
1951
+ },
1952
+ {
1953
+ "entropy": 1.6651998162269592,
1954
+ "epoch": 1.3850267379679144,
1955
+ "grad_norm": 0.0,
1956
+ "learning_rate": 0.0001550535077288942,
1957
+ "loss": 2.6997,
1958
+ "mean_token_accuracy": 0.4684208855032921,
1959
+ "num_tokens": 212932.0,
1960
+ "step": 195
1961
+ },
1962
+ {
1963
+ "entropy": 1.6087098717689514,
1964
+ "epoch": 1.392156862745098,
1965
+ "grad_norm": 0.0,
1966
+ "learning_rate": 0.00015481569560047564,
1967
+ "loss": 2.6176,
1968
+ "mean_token_accuracy": 0.46499625593423843,
1969
+ "num_tokens": 214054.0,
1970
+ "step": 196
1971
+ },
1972
+ {
1973
+ "entropy": 1.6280483305454254,
1974
+ "epoch": 1.3992869875222818,
1975
+ "grad_norm": 0.0,
1976
+ "learning_rate": 0.00015457788347205708,
1977
+ "loss": 2.7304,
1978
+ "mean_token_accuracy": 0.4452286586165428,
1979
+ "num_tokens": 215200.0,
1980
+ "step": 197
1981
+ },
1982
+ {
1983
+ "entropy": 1.5492911636829376,
1984
+ "epoch": 1.4064171122994653,
1985
+ "grad_norm": 0.0,
1986
+ "learning_rate": 0.00015434007134363853,
1987
+ "loss": 2.5217,
1988
+ "mean_token_accuracy": 0.49339231103658676,
1989
+ "num_tokens": 216317.0,
1990
+ "step": 198
1991
+ },
1992
+ {
1993
+ "entropy": 1.5941800773143768,
1994
+ "epoch": 1.4135472370766489,
1995
+ "grad_norm": 0.0,
1996
+ "learning_rate": 0.00015410225921522,
1997
+ "loss": 2.4819,
1998
+ "mean_token_accuracy": 0.4754658564925194,
1999
+ "num_tokens": 217405.0,
2000
+ "step": 199
2001
+ },
2002
+ {
2003
+ "entropy": 1.5978778004646301,
2004
+ "epoch": 1.4206773618538324,
2005
+ "grad_norm": 0.0,
2006
+ "learning_rate": 0.00015386444708680142,
2007
+ "loss": 2.7044,
2008
+ "mean_token_accuracy": 0.45556849241256714,
2009
+ "num_tokens": 218504.0,
2010
+ "step": 200
2011
+ },
2012
+ {
2013
+ "entropy": 1.5847291052341461,
2014
+ "epoch": 1.427807486631016,
2015
+ "grad_norm": 0.0,
2016
+ "learning_rate": 0.00015362663495838288,
2017
+ "loss": 2.6487,
2018
+ "mean_token_accuracy": 0.46325846016407013,
2019
+ "num_tokens": 219640.0,
2020
+ "step": 201
2021
+ },
2022
+ {
2023
+ "entropy": 1.5988908410072327,
2024
+ "epoch": 1.4349376114081998,
2025
+ "grad_norm": 0.0,
2026
+ "learning_rate": 0.00015338882282996434,
2027
+ "loss": 2.664,
2028
+ "mean_token_accuracy": 0.46224743872880936,
2029
+ "num_tokens": 220642.0,
2030
+ "step": 202
2031
+ },
2032
+ {
2033
+ "entropy": 1.5120367109775543,
2034
+ "epoch": 1.4420677361853833,
2035
+ "grad_norm": 0.0,
2036
+ "learning_rate": 0.0001531510107015458,
2037
+ "loss": 2.5895,
2038
+ "mean_token_accuracy": 0.48113133013248444,
2039
+ "num_tokens": 221735.0,
2040
+ "step": 203
2041
+ },
2042
+ {
2043
+ "entropy": 1.5507851243019104,
2044
+ "epoch": 1.4491978609625669,
2045
+ "grad_norm": 0.0,
2046
+ "learning_rate": 0.00015291319857312725,
2047
+ "loss": 2.5664,
2048
+ "mean_token_accuracy": 0.48080600798130035,
2049
+ "num_tokens": 222814.0,
2050
+ "step": 204
2051
+ },
2052
+ {
2053
+ "entropy": 1.6826366484165192,
2054
+ "epoch": 1.4563279857397504,
2055
+ "grad_norm": 0.0,
2056
+ "learning_rate": 0.00015267538644470868,
2057
+ "loss": 2.7612,
2058
+ "mean_token_accuracy": 0.4607429876923561,
2059
+ "num_tokens": 223905.0,
2060
+ "step": 205
2061
+ },
2062
+ {
2063
+ "entropy": 1.6085248589515686,
2064
+ "epoch": 1.463458110516934,
2065
+ "grad_norm": 0.0,
2066
+ "learning_rate": 0.00015243757431629014,
2067
+ "loss": 2.6815,
2068
+ "mean_token_accuracy": 0.45429935306310654,
2069
+ "num_tokens": 224999.0,
2070
+ "step": 206
2071
+ },
2072
+ {
2073
+ "entropy": 1.6905607879161835,
2074
+ "epoch": 1.4705882352941178,
2075
+ "grad_norm": 0.0,
2076
+ "learning_rate": 0.0001521997621878716,
2077
+ "loss": 2.7331,
2078
+ "mean_token_accuracy": 0.4660051390528679,
2079
+ "num_tokens": 226068.0,
2080
+ "step": 207
2081
+ },
2082
+ {
2083
+ "entropy": 1.6017423570156097,
2084
+ "epoch": 1.4777183600713013,
2085
+ "grad_norm": 0.0,
2086
+ "learning_rate": 0.00015196195005945303,
2087
+ "loss": 2.6021,
2088
+ "mean_token_accuracy": 0.46242382377386093,
2089
+ "num_tokens": 227126.0,
2090
+ "step": 208
2091
+ },
2092
+ {
2093
+ "entropy": 1.493167519569397,
2094
+ "epoch": 1.4848484848484849,
2095
+ "grad_norm": 0.0,
2096
+ "learning_rate": 0.00015172413793103449,
2097
+ "loss": 2.5246,
2098
+ "mean_token_accuracy": 0.48408984392881393,
2099
+ "num_tokens": 228245.0,
2100
+ "step": 209
2101
+ },
2102
+ {
2103
+ "entropy": 1.5619983673095703,
2104
+ "epoch": 1.4919786096256684,
2105
+ "grad_norm": 0.0,
2106
+ "learning_rate": 0.00015148632580261594,
2107
+ "loss": 2.6306,
2108
+ "mean_token_accuracy": 0.4775094836950302,
2109
+ "num_tokens": 229336.0,
2110
+ "step": 210
2111
+ },
2112
+ {
2113
+ "entropy": 1.587768405675888,
2114
+ "epoch": 1.499108734402852,
2115
+ "grad_norm": 0.0,
2116
+ "learning_rate": 0.0001512485136741974,
2117
+ "loss": 2.6375,
2118
+ "mean_token_accuracy": 0.47264014929533005,
2119
+ "num_tokens": 230431.0,
2120
+ "step": 211
2121
+ },
2122
+ {
2123
+ "entropy": 1.6371296346187592,
2124
+ "epoch": 1.5062388591800357,
2125
+ "grad_norm": 0.0,
2126
+ "learning_rate": 0.00015101070154577883,
2127
+ "loss": 2.6987,
2128
+ "mean_token_accuracy": 0.45142069458961487,
2129
+ "num_tokens": 231538.0,
2130
+ "step": 212
2131
+ },
2132
+ {
2133
+ "entropy": 1.615380883216858,
2134
+ "epoch": 1.5133689839572193,
2135
+ "grad_norm": 0.0,
2136
+ "learning_rate": 0.0001507728894173603,
2137
+ "loss": 2.5931,
2138
+ "mean_token_accuracy": 0.46151647716760635,
2139
+ "num_tokens": 232692.0,
2140
+ "step": 213
2141
+ },
2142
+ {
2143
+ "entropy": 1.6657347679138184,
2144
+ "epoch": 1.5204991087344029,
2145
+ "grad_norm": 0.0,
2146
+ "learning_rate": 0.00015053507728894175,
2147
+ "loss": 2.767,
2148
+ "mean_token_accuracy": 0.45710520446300507,
2149
+ "num_tokens": 233752.0,
2150
+ "step": 214
2151
+ },
2152
+ {
2153
+ "entropy": 1.5707046389579773,
2154
+ "epoch": 1.5276292335115864,
2155
+ "grad_norm": 0.0,
2156
+ "learning_rate": 0.0001502972651605232,
2157
+ "loss": 2.575,
2158
+ "mean_token_accuracy": 0.47789450734853745,
2159
+ "num_tokens": 234860.0,
2160
+ "step": 215
2161
+ },
2162
+ {
2163
+ "entropy": 1.6575550436973572,
2164
+ "epoch": 1.53475935828877,
2165
+ "grad_norm": 0.0,
2166
+ "learning_rate": 0.00015005945303210464,
2167
+ "loss": 2.6208,
2168
+ "mean_token_accuracy": 0.46910084784030914,
2169
+ "num_tokens": 235953.0,
2170
+ "step": 216
2171
+ },
2172
+ {
2173
+ "entropy": 1.5557922422885895,
2174
+ "epoch": 1.5418894830659537,
2175
+ "grad_norm": 0.0,
2176
+ "learning_rate": 0.0001498216409036861,
2177
+ "loss": 2.6316,
2178
+ "mean_token_accuracy": 0.47147487103939056,
2179
+ "num_tokens": 237113.0,
2180
+ "step": 217
2181
+ },
2182
+ {
2183
+ "entropy": 1.5967816710472107,
2184
+ "epoch": 1.5490196078431373,
2185
+ "grad_norm": 0.0,
2186
+ "learning_rate": 0.00014958382877526755,
2187
+ "loss": 2.6435,
2188
+ "mean_token_accuracy": 0.4659326821565628,
2189
+ "num_tokens": 238183.0,
2190
+ "step": 218
2191
+ },
2192
+ {
2193
+ "entropy": 1.5619607269763947,
2194
+ "epoch": 1.5561497326203209,
2195
+ "grad_norm": 0.0,
2196
+ "learning_rate": 0.000149346016646849,
2197
+ "loss": 2.6573,
2198
+ "mean_token_accuracy": 0.4648478552699089,
2199
+ "num_tokens": 239250.0,
2200
+ "step": 219
2201
+ },
2202
+ {
2203
+ "entropy": 1.5970399975776672,
2204
+ "epoch": 1.5632798573975044,
2205
+ "grad_norm": 0.0,
2206
+ "learning_rate": 0.00014910820451843044,
2207
+ "loss": 2.5817,
2208
+ "mean_token_accuracy": 0.47652987390756607,
2209
+ "num_tokens": 240379.0,
2210
+ "step": 220
2211
+ },
2212
+ {
2213
+ "entropy": 1.6112593710422516,
2214
+ "epoch": 1.570409982174688,
2215
+ "grad_norm": 0.0,
2216
+ "learning_rate": 0.0001488703923900119,
2217
+ "loss": 2.6912,
2218
+ "mean_token_accuracy": 0.46139268577098846,
2219
+ "num_tokens": 241489.0,
2220
+ "step": 221
2221
+ },
2222
+ {
2223
+ "entropy": 1.6720410883426666,
2224
+ "epoch": 1.5775401069518717,
2225
+ "grad_norm": 0.0,
2226
+ "learning_rate": 0.00014863258026159336,
2227
+ "loss": 2.6818,
2228
+ "mean_token_accuracy": 0.438846156001091,
2229
+ "num_tokens": 242546.0,
2230
+ "step": 222
2231
+ },
2232
+ {
2233
+ "entropy": 1.6308137476444244,
2234
+ "epoch": 1.5846702317290553,
2235
+ "grad_norm": 0.0,
2236
+ "learning_rate": 0.00014839476813317479,
2237
+ "loss": 2.7512,
2238
+ "mean_token_accuracy": 0.4592900201678276,
2239
+ "num_tokens": 243638.0,
2240
+ "step": 223
2241
+ },
2242
+ {
2243
+ "entropy": 1.5938476026058197,
2244
+ "epoch": 1.5918003565062389,
2245
+ "grad_norm": 0.0,
2246
+ "learning_rate": 0.00014815695600475624,
2247
+ "loss": 2.5778,
2248
+ "mean_token_accuracy": 0.47352661937475204,
2249
+ "num_tokens": 244751.0,
2250
+ "step": 224
2251
+ },
2252
+ {
2253
+ "entropy": 1.5609805583953857,
2254
+ "epoch": 1.5989304812834224,
2255
+ "grad_norm": 0.0,
2256
+ "learning_rate": 0.0001479191438763377,
2257
+ "loss": 2.6435,
2258
+ "mean_token_accuracy": 0.4681161344051361,
2259
+ "num_tokens": 245826.0,
2260
+ "step": 225
2261
+ },
2262
+ {
2263
+ "entropy": 1.6306316256523132,
2264
+ "epoch": 1.606060606060606,
2265
+ "grad_norm": 0.0,
2266
+ "learning_rate": 0.00014768133174791916,
2267
+ "loss": 2.6791,
2268
+ "mean_token_accuracy": 0.4553253725171089,
2269
+ "num_tokens": 246871.0,
2270
+ "step": 226
2271
+ },
2272
+ {
2273
+ "entropy": 1.5593467950820923,
2274
+ "epoch": 1.6131907308377897,
2275
+ "grad_norm": 0.0,
2276
+ "learning_rate": 0.00014744351961950062,
2277
+ "loss": 2.5499,
2278
+ "mean_token_accuracy": 0.47761671245098114,
2279
+ "num_tokens": 247955.0,
2280
+ "step": 227
2281
+ },
2282
+ {
2283
+ "entropy": 1.55764502286911,
2284
+ "epoch": 1.6203208556149733,
2285
+ "grad_norm": 0.0,
2286
+ "learning_rate": 0.00014720570749108205,
2287
+ "loss": 2.5377,
2288
+ "mean_token_accuracy": 0.49300002306699753,
2289
+ "num_tokens": 249061.0,
2290
+ "step": 228
2291
+ },
2292
+ {
2293
+ "entropy": 1.5418426096439362,
2294
+ "epoch": 1.6274509803921569,
2295
+ "grad_norm": 0.0,
2296
+ "learning_rate": 0.0001469678953626635,
2297
+ "loss": 2.6276,
2298
+ "mean_token_accuracy": 0.4840138778090477,
2299
+ "num_tokens": 250157.0,
2300
+ "step": 229
2301
+ },
2302
+ {
2303
+ "entropy": 1.6196385324001312,
2304
+ "epoch": 1.6345811051693404,
2305
+ "grad_norm": 0.0,
2306
+ "learning_rate": 0.00014673008323424496,
2307
+ "loss": 2.5876,
2308
+ "mean_token_accuracy": 0.440780833363533,
2309
+ "num_tokens": 251267.0,
2310
+ "step": 230
2311
+ },
2312
+ {
2313
+ "entropy": 1.4990095794200897,
2314
+ "epoch": 1.641711229946524,
2315
+ "grad_norm": 0.0,
2316
+ "learning_rate": 0.0001464922711058264,
2317
+ "loss": 2.528,
2318
+ "mean_token_accuracy": 0.49401114135980606,
2319
+ "num_tokens": 252371.0,
2320
+ "step": 231
2321
+ },
2322
+ {
2323
+ "entropy": 1.5892696976661682,
2324
+ "epoch": 1.6488413547237077,
2325
+ "grad_norm": 0.0,
2326
+ "learning_rate": 0.00014625445897740785,
2327
+ "loss": 2.5374,
2328
+ "mean_token_accuracy": 0.4945196509361267,
2329
+ "num_tokens": 253491.0,
2330
+ "step": 232
2331
+ },
2332
+ {
2333
+ "entropy": 1.6785107553005219,
2334
+ "epoch": 1.6559714795008913,
2335
+ "grad_norm": 0.0,
2336
+ "learning_rate": 0.0001460166468489893,
2337
+ "loss": 2.6625,
2338
+ "mean_token_accuracy": 0.4550144597887993,
2339
+ "num_tokens": 254598.0,
2340
+ "step": 233
2341
+ },
2342
+ {
2343
+ "entropy": 1.5320258140563965,
2344
+ "epoch": 1.6631016042780749,
2345
+ "grad_norm": 0.0,
2346
+ "learning_rate": 0.00014577883472057077,
2347
+ "loss": 2.6136,
2348
+ "mean_token_accuracy": 0.48827097564935684,
2349
+ "num_tokens": 255724.0,
2350
+ "step": 234
2351
+ },
2352
+ {
2353
+ "entropy": 1.5822700262069702,
2354
+ "epoch": 1.6702317290552586,
2355
+ "grad_norm": 0.0,
2356
+ "learning_rate": 0.0001455410225921522,
2357
+ "loss": 2.5751,
2358
+ "mean_token_accuracy": 0.4698340594768524,
2359
+ "num_tokens": 256830.0,
2360
+ "step": 235
2361
+ },
2362
+ {
2363
+ "entropy": 1.6102330684661865,
2364
+ "epoch": 1.677361853832442,
2365
+ "grad_norm": 0.0,
2366
+ "learning_rate": 0.00014530321046373365,
2367
+ "loss": 2.6332,
2368
+ "mean_token_accuracy": 0.47240811586380005,
2369
+ "num_tokens": 257916.0,
2370
+ "step": 236
2371
+ },
2372
+ {
2373
+ "entropy": 1.5286598205566406,
2374
+ "epoch": 1.6844919786096257,
2375
+ "grad_norm": 0.0,
2376
+ "learning_rate": 0.0001450653983353151,
2377
+ "loss": 2.5149,
2378
+ "mean_token_accuracy": 0.48652924597263336,
2379
+ "num_tokens": 259019.0,
2380
+ "step": 237
2381
+ },
2382
+ {
2383
+ "entropy": 1.535717934370041,
2384
+ "epoch": 1.6916221033868093,
2385
+ "grad_norm": 0.0,
2386
+ "learning_rate": 0.00014482758620689657,
2387
+ "loss": 2.5691,
2388
+ "mean_token_accuracy": 0.4858531951904297,
2389
+ "num_tokens": 260128.0,
2390
+ "step": 238
2391
+ },
2392
+ {
2393
+ "entropy": 1.6363422572612762,
2394
+ "epoch": 1.6987522281639929,
2395
+ "grad_norm": 0.0,
2396
+ "learning_rate": 0.000144589774078478,
2397
+ "loss": 2.6366,
2398
+ "mean_token_accuracy": 0.4610147476196289,
2399
+ "num_tokens": 261228.0,
2400
+ "step": 239
2401
+ },
2402
+ {
2403
+ "entropy": 1.6290847063064575,
2404
+ "epoch": 1.7058823529411766,
2405
+ "grad_norm": 0.0,
2406
+ "learning_rate": 0.00014435196195005946,
2407
+ "loss": 2.7225,
2408
+ "mean_token_accuracy": 0.47234660387039185,
2409
+ "num_tokens": 262270.0,
2410
+ "step": 240
2411
+ },
2412
+ {
2413
+ "entropy": 1.6157021522521973,
2414
+ "epoch": 1.71301247771836,
2415
+ "grad_norm": 0.0,
2416
+ "learning_rate": 0.00014411414982164092,
2417
+ "loss": 2.6575,
2418
+ "mean_token_accuracy": 0.45069990307092667,
2419
+ "num_tokens": 263361.0,
2420
+ "step": 241
2421
+ },
2422
+ {
2423
+ "entropy": 1.6559931337833405,
2424
+ "epoch": 1.7201426024955437,
2425
+ "grad_norm": 0.0,
2426
+ "learning_rate": 0.00014387633769322235,
2427
+ "loss": 2.5864,
2428
+ "mean_token_accuracy": 0.4479330778121948,
2429
+ "num_tokens": 264391.0,
2430
+ "step": 242
2431
+ },
2432
+ {
2433
+ "entropy": 1.6161220967769623,
2434
+ "epoch": 1.7272727272727273,
2435
+ "grad_norm": 0.0,
2436
+ "learning_rate": 0.0001436385255648038,
2437
+ "loss": 2.6456,
2438
+ "mean_token_accuracy": 0.47140543162822723,
2439
+ "num_tokens": 265517.0,
2440
+ "step": 243
2441
+ },
2442
+ {
2443
+ "entropy": 1.6491332352161407,
2444
+ "epoch": 1.7344028520499108,
2445
+ "grad_norm": 0.0,
2446
+ "learning_rate": 0.00014340071343638526,
2447
+ "loss": 2.7443,
2448
+ "mean_token_accuracy": 0.4643326923251152,
2449
+ "num_tokens": 266569.0,
2450
+ "step": 244
2451
+ },
2452
+ {
2453
+ "entropy": 1.6256919205188751,
2454
+ "epoch": 1.7415329768270946,
2455
+ "grad_norm": 0.0,
2456
+ "learning_rate": 0.00014316290130796672,
2457
+ "loss": 2.6762,
2458
+ "mean_token_accuracy": 0.4532029777765274,
2459
+ "num_tokens": 267611.0,
2460
+ "step": 245
2461
+ },
2462
+ {
2463
+ "entropy": 1.619517207145691,
2464
+ "epoch": 1.748663101604278,
2465
+ "grad_norm": 0.0,
2466
+ "learning_rate": 0.00014292508917954818,
2467
+ "loss": 2.7279,
2468
+ "mean_token_accuracy": 0.45651988685131073,
2469
+ "num_tokens": 268692.0,
2470
+ "step": 246
2471
+ },
2472
+ {
2473
+ "entropy": 1.5403787195682526,
2474
+ "epoch": 1.7557932263814617,
2475
+ "grad_norm": 0.0,
2476
+ "learning_rate": 0.0001426872770511296,
2477
+ "loss": 2.5525,
2478
+ "mean_token_accuracy": 0.4840865433216095,
2479
+ "num_tokens": 269788.0,
2480
+ "step": 247
2481
+ },
2482
+ {
2483
+ "entropy": 1.6027557253837585,
2484
+ "epoch": 1.7629233511586453,
2485
+ "grad_norm": 0.0,
2486
+ "learning_rate": 0.00014244946492271107,
2487
+ "loss": 2.574,
2488
+ "mean_token_accuracy": 0.48409949243068695,
2489
+ "num_tokens": 270843.0,
2490
+ "step": 248
2491
+ },
2492
+ {
2493
+ "entropy": 1.5946480631828308,
2494
+ "epoch": 1.7700534759358288,
2495
+ "grad_norm": 0.0,
2496
+ "learning_rate": 0.00014221165279429252,
2497
+ "loss": 2.5633,
2498
+ "mean_token_accuracy": 0.4869764968752861,
2499
+ "num_tokens": 271964.0,
2500
+ "step": 249
2501
+ },
2502
+ {
2503
+ "entropy": 1.6484409868717194,
2504
+ "epoch": 1.7771836007130126,
2505
+ "grad_norm": 0.0,
2506
+ "learning_rate": 0.00014197384066587395,
2507
+ "loss": 2.6964,
2508
+ "mean_token_accuracy": 0.4450046420097351,
2509
+ "num_tokens": 273054.0,
2510
+ "step": 250
2511
+ },
2512
+ {
2513
+ "entropy": 1.6375533640384674,
2514
+ "epoch": 1.784313725490196,
2515
+ "grad_norm": 0.0,
2516
+ "learning_rate": 0.0001417360285374554,
2517
+ "loss": 2.6718,
2518
+ "mean_token_accuracy": 0.4587417542934418,
2519
+ "num_tokens": 274133.0,
2520
+ "step": 251
2521
+ },
2522
+ {
2523
+ "entropy": 1.5944361984729767,
2524
+ "epoch": 1.7914438502673797,
2525
+ "grad_norm": 0.0,
2526
+ "learning_rate": 0.00014149821640903687,
2527
+ "loss": 2.5917,
2528
+ "mean_token_accuracy": 0.4714890420436859,
2529
+ "num_tokens": 275243.0,
2530
+ "step": 252
2531
+ },
2532
+ {
2533
+ "entropy": 1.6059032678604126,
2534
+ "epoch": 1.7985739750445633,
2535
+ "grad_norm": 0.0,
2536
+ "learning_rate": 0.0001412604042806183,
2537
+ "loss": 2.6893,
2538
+ "mean_token_accuracy": 0.45041677355766296,
2539
+ "num_tokens": 276280.0,
2540
+ "step": 253
2541
+ },
2542
+ {
2543
+ "entropy": 1.6716269254684448,
2544
+ "epoch": 1.8057040998217468,
2545
+ "grad_norm": 0.0,
2546
+ "learning_rate": 0.00014102259215219978,
2547
+ "loss": 2.7229,
2548
+ "mean_token_accuracy": 0.45646892488002777,
2549
+ "num_tokens": 277383.0,
2550
+ "step": 254
2551
+ },
2552
+ {
2553
+ "entropy": 1.6591968834400177,
2554
+ "epoch": 1.8128342245989306,
2555
+ "grad_norm": 0.0,
2556
+ "learning_rate": 0.00014078478002378122,
2557
+ "loss": 2.6642,
2558
+ "mean_token_accuracy": 0.457190565764904,
2559
+ "num_tokens": 278468.0,
2560
+ "step": 255
2561
+ },
2562
+ {
2563
+ "entropy": 1.6405368149280548,
2564
+ "epoch": 1.819964349376114,
2565
+ "grad_norm": 0.0,
2566
+ "learning_rate": 0.00014054696789536267,
2567
+ "loss": 2.6468,
2568
+ "mean_token_accuracy": 0.4580274894833565,
2569
+ "num_tokens": 279544.0,
2570
+ "step": 256
2571
+ },
2572
+ {
2573
+ "entropy": 1.6274996399879456,
2574
+ "epoch": 1.8270944741532977,
2575
+ "grad_norm": 0.0,
2576
+ "learning_rate": 0.00014030915576694413,
2577
+ "loss": 2.6112,
2578
+ "mean_token_accuracy": 0.4569789469242096,
2579
+ "num_tokens": 280607.0,
2580
+ "step": 257
2581
+ },
2582
+ {
2583
+ "entropy": 1.5651440620422363,
2584
+ "epoch": 1.8342245989304813,
2585
+ "grad_norm": 0.0,
2586
+ "learning_rate": 0.00014007134363852556,
2587
+ "loss": 2.6034,
2588
+ "mean_token_accuracy": 0.4507257267832756,
2589
+ "num_tokens": 281691.0,
2590
+ "step": 258
2591
+ },
2592
+ {
2593
+ "entropy": 1.5355416238307953,
2594
+ "epoch": 1.8413547237076648,
2595
+ "grad_norm": 0.0,
2596
+ "learning_rate": 0.00013983353151010702,
2597
+ "loss": 2.5293,
2598
+ "mean_token_accuracy": 0.4817895218729973,
2599
+ "num_tokens": 282815.0,
2600
+ "step": 259
2601
+ },
2602
+ {
2603
+ "entropy": 1.592032641172409,
2604
+ "epoch": 1.8484848484848486,
2605
+ "grad_norm": 0.0,
2606
+ "learning_rate": 0.00013959571938168848,
2607
+ "loss": 2.6128,
2608
+ "mean_token_accuracy": 0.4846939668059349,
2609
+ "num_tokens": 283931.0,
2610
+ "step": 260
2611
+ },
2612
+ {
2613
+ "entropy": 1.6933747231960297,
2614
+ "epoch": 1.855614973262032,
2615
+ "grad_norm": 0.0,
2616
+ "learning_rate": 0.0001393579072532699,
2617
+ "loss": 2.8414,
2618
+ "mean_token_accuracy": 0.42922718822956085,
2619
+ "num_tokens": 284997.0,
2620
+ "step": 261
2621
+ },
2622
+ {
2623
+ "entropy": 1.549606055021286,
2624
+ "epoch": 1.8627450980392157,
2625
+ "grad_norm": 0.0,
2626
+ "learning_rate": 0.0001391200951248514,
2627
+ "loss": 2.6134,
2628
+ "mean_token_accuracy": 0.47253087162971497,
2629
+ "num_tokens": 286090.0,
2630
+ "step": 262
2631
+ },
2632
+ {
2633
+ "entropy": 1.6243177652359009,
2634
+ "epoch": 1.8698752228163993,
2635
+ "grad_norm": 0.0,
2636
+ "learning_rate": 0.00013888228299643282,
2637
+ "loss": 2.7223,
2638
+ "mean_token_accuracy": 0.45962000638246536,
2639
+ "num_tokens": 287183.0,
2640
+ "step": 263
2641
+ },
2642
+ {
2643
+ "entropy": 1.5972241163253784,
2644
+ "epoch": 1.8770053475935828,
2645
+ "grad_norm": 0.0,
2646
+ "learning_rate": 0.00013864447086801425,
2647
+ "loss": 2.6094,
2648
+ "mean_token_accuracy": 0.47941046208143234,
2649
+ "num_tokens": 288231.0,
2650
+ "step": 264
2651
+ },
2652
+ {
2653
+ "entropy": 1.6008118391036987,
2654
+ "epoch": 1.8841354723707666,
2655
+ "grad_norm": 0.0,
2656
+ "learning_rate": 0.00013840665873959574,
2657
+ "loss": 2.6731,
2658
+ "mean_token_accuracy": 0.4635191634297371,
2659
+ "num_tokens": 289284.0,
2660
+ "step": 265
2661
+ },
2662
+ {
2663
+ "entropy": 1.5784848630428314,
2664
+ "epoch": 1.89126559714795,
2665
+ "grad_norm": 0.0,
2666
+ "learning_rate": 0.00013816884661117717,
2667
+ "loss": 2.6694,
2668
+ "mean_token_accuracy": 0.47262611985206604,
2669
+ "num_tokens": 290386.0,
2670
+ "step": 266
2671
+ },
2672
+ {
2673
+ "entropy": 1.6606462597846985,
2674
+ "epoch": 1.8983957219251337,
2675
+ "grad_norm": 0.0,
2676
+ "learning_rate": 0.00013793103448275863,
2677
+ "loss": 2.7134,
2678
+ "mean_token_accuracy": 0.44980067759752274,
2679
+ "num_tokens": 291460.0,
2680
+ "step": 267
2681
+ },
2682
+ {
2683
+ "entropy": 1.6004058420658112,
2684
+ "epoch": 1.9055258467023173,
2685
+ "grad_norm": 0.0,
2686
+ "learning_rate": 0.00013769322235434008,
2687
+ "loss": 2.5894,
2688
+ "mean_token_accuracy": 0.4649396017193794,
2689
+ "num_tokens": 292530.0,
2690
+ "step": 268
2691
+ },
2692
+ {
2693
+ "entropy": 1.6282309591770172,
2694
+ "epoch": 1.9126559714795008,
2695
+ "grad_norm": 0.0,
2696
+ "learning_rate": 0.00013745541022592151,
2697
+ "loss": 2.6314,
2698
+ "mean_token_accuracy": 0.4572133645415306,
2699
+ "num_tokens": 293655.0,
2700
+ "step": 269
2701
+ },
2702
+ {
2703
+ "entropy": 1.5889360904693604,
2704
+ "epoch": 1.9197860962566846,
2705
+ "grad_norm": 0.0,
2706
+ "learning_rate": 0.000137217598097503,
2707
+ "loss": 2.6898,
2708
+ "mean_token_accuracy": 0.4732029587030411,
2709
+ "num_tokens": 294730.0,
2710
+ "step": 270
2711
+ },
2712
+ {
2713
+ "entropy": 1.6428880095481873,
2714
+ "epoch": 1.926916221033868,
2715
+ "grad_norm": 0.0,
2716
+ "learning_rate": 0.00013697978596908443,
2717
+ "loss": 2.6273,
2718
+ "mean_token_accuracy": 0.4647170379757881,
2719
+ "num_tokens": 295818.0,
2720
+ "step": 271
2721
+ },
2722
+ {
2723
+ "entropy": 1.5940674245357513,
2724
+ "epoch": 1.9340463458110517,
2725
+ "grad_norm": 0.0,
2726
+ "learning_rate": 0.00013674197384066586,
2727
+ "loss": 2.5628,
2728
+ "mean_token_accuracy": 0.47556307166814804,
2729
+ "num_tokens": 296920.0,
2730
+ "step": 272
2731
+ },
2732
+ {
2733
+ "entropy": 1.5898773968219757,
2734
+ "epoch": 1.9411764705882353,
2735
+ "grad_norm": 0.0,
2736
+ "learning_rate": 0.00013650416171224735,
2737
+ "loss": 2.6949,
2738
+ "mean_token_accuracy": 0.47456144541502,
2739
+ "num_tokens": 298028.0,
2740
+ "step": 273
2741
+ },
2742
+ {
2743
+ "entropy": 1.651709407567978,
2744
+ "epoch": 1.9483065953654188,
2745
+ "grad_norm": 0.0,
2746
+ "learning_rate": 0.00013626634958382878,
2747
+ "loss": 2.6833,
2748
+ "mean_token_accuracy": 0.45697759836912155,
2749
+ "num_tokens": 299111.0,
2750
+ "step": 274
2751
+ },
2752
+ {
2753
+ "entropy": 1.6460674107074738,
2754
+ "epoch": 1.9554367201426026,
2755
+ "grad_norm": 0.0,
2756
+ "learning_rate": 0.00013602853745541023,
2757
+ "loss": 2.7098,
2758
+ "mean_token_accuracy": 0.45604951679706573,
2759
+ "num_tokens": 300236.0,
2760
+ "step": 275
2761
+ },
2762
+ {
2763
+ "entropy": 1.645053118467331,
2764
+ "epoch": 1.962566844919786,
2765
+ "grad_norm": 0.0,
2766
+ "learning_rate": 0.0001357907253269917,
2767
+ "loss": 2.5929,
2768
+ "mean_token_accuracy": 0.467997670173645,
2769
+ "num_tokens": 301315.0,
2770
+ "step": 276
2771
+ },
2772
+ {
2773
+ "entropy": 1.6668168604373932,
2774
+ "epoch": 1.9696969696969697,
2775
+ "grad_norm": 0.0,
2776
+ "learning_rate": 0.00013555291319857312,
2777
+ "loss": 2.711,
2778
+ "mean_token_accuracy": 0.4511336088180542,
2779
+ "num_tokens": 302441.0,
2780
+ "step": 277
2781
+ },
2782
+ {
2783
+ "entropy": 1.6053387224674225,
2784
+ "epoch": 1.9768270944741533,
2785
+ "grad_norm": 0.0,
2786
+ "learning_rate": 0.00013531510107015458,
2787
+ "loss": 2.5949,
2788
+ "mean_token_accuracy": 0.4798056557774544,
2789
+ "num_tokens": 303551.0,
2790
+ "step": 278
2791
+ },
2792
+ {
2793
+ "entropy": 1.6160295009613037,
2794
+ "epoch": 1.9839572192513368,
2795
+ "grad_norm": 0.0,
2796
+ "learning_rate": 0.00013507728894173604,
2797
+ "loss": 2.7294,
2798
+ "mean_token_accuracy": 0.45531073212623596,
2799
+ "num_tokens": 304641.0,
2800
+ "step": 279
2801
+ },
2802
+ {
2803
+ "entropy": 1.6171720921993256,
2804
+ "epoch": 1.9910873440285206,
2805
+ "grad_norm": 0.0,
2806
+ "learning_rate": 0.00013483947681331747,
2807
+ "loss": 2.5741,
2808
+ "mean_token_accuracy": 0.4656490460038185,
2809
+ "num_tokens": 305726.0,
2810
+ "step": 280
2811
+ },
2812
+ {
2813
+ "entropy": 1.6310756206512451,
2814
+ "epoch": 1.998217468805704,
2815
+ "grad_norm": 0.0,
2816
+ "learning_rate": 0.00013460166468489895,
2817
+ "loss": 2.59,
2818
+ "mean_token_accuracy": 0.45554178953170776,
2819
+ "num_tokens": 306833.0,
2820
+ "step": 281
2821
+ },
2822
+ {
2823
+ "entropy": 1.6477800607681274,
2824
+ "epoch": 2.0,
2825
+ "grad_norm": 0.0,
2826
+ "learning_rate": 0.00013436385255648038,
2827
+ "loss": 2.7133,
2828
+ "mean_token_accuracy": 0.4486691951751709,
2829
+ "num_tokens": 307100.0,
2830
+ "step": 282
2831
+ }
2832
+ ],
2833
+ "logging_steps": 1,
2834
+ "max_steps": 846,
2835
+ "num_input_tokens_seen": 0,
2836
+ "num_train_epochs": 6,
2837
+ "save_steps": 500,
2838
+ "stateful_callbacks": {
2839
+ "TrainerControl": {
2840
+ "args": {
2841
+ "should_epoch_stop": false,
2842
+ "should_evaluate": false,
2843
+ "should_log": false,
2844
+ "should_save": true,
2845
+ "should_training_stop": false
2846
+ },
2847
+ "attributes": {}
2848
+ }
2849
+ },
2850
+ "total_flos": 1.450573084483584e+16,
2851
+ "train_batch_size": 2,
2852
+ "trial_name": null,
2853
+ "trial_params": null
2854
+ }
checkpoint-282/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2dacdb1830e22d6e3c6a173a3f713ce8117adf1aaa057064b64b600f918e5e1
3
+ size 5816
checkpoint-423/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
checkpoint-423/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj"
32
+ ],
33
+ "target_parameters": null,
34
+ "task_type": "CAUSAL_LM",
35
+ "trainable_token_indices": null,
36
+ "use_dora": false,
37
+ "use_qalora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-423/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f181e388f2dbfd451cc598ab3b51bfc3f7493234ff6e0ae9cc2552efa6286a
3
+ size 54560368
checkpoint-423/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
checkpoint-423/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4194b812ca1086a47ebcf54d2b55b27f7ff23fbf91462d66863b4938bc122837
3
+ size 1192
checkpoint-423/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9797583c1051c6833afce8a64b51e1b34149ed71340d99085baf1e80f684bb1b
3
+ size 14244
checkpoint-423/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6352f4ee63fae94cba5cb0f299de71608ee7f7cc7b64dbec7a35f90d6e7590
3
+ size 1064
checkpoint-423/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-423/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
checkpoint-423/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-423/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-423/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2dacdb1830e22d6e3c6a173a3f713ce8117adf1aaa057064b64b600f918e5e1
3
+ size 5816
checkpoint-564/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.17.1
checkpoint-564/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj"
32
+ ],
33
+ "target_parameters": null,
34
+ "task_type": "CAUSAL_LM",
35
+ "trainable_token_indices": null,
36
+ "use_dora": false,
37
+ "use_qalora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-564/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f181e388f2dbfd451cc598ab3b51bfc3f7493234ff6e0ae9cc2552efa6286a
3
+ size 54560368
checkpoint-564/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
checkpoint-564/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a759942a59f92507674de7a6e51ec9f1fb5cdbc124fed02614eb33dde2195fa2
3
+ size 1192
checkpoint-564/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991807b2b5249aaf15a4705e5a32dc46f4ebd2bdab85ccf81149616402b4ff29
3
+ size 14244
checkpoint-564/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03fc0f985c825f77fe46e1a871585ee59a34dcff89de8891a4cf1ed034b3cbfd
3
+ size 1064
checkpoint-564/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
checkpoint-564/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
checkpoint-564/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-564/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff