jameselmore commited on
Commit
4aeed98
·
verified ·
1 Parent(s): 3d7cbc3

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. checkpoint-1000/README.md +202 -0
  2. checkpoint-1000/adapter_config.json +32 -0
  3. checkpoint-1000/adapter_model.safetensors +3 -0
  4. checkpoint-1000/optimizer.pt +3 -0
  5. checkpoint-1000/rng_state.pth +3 -0
  6. checkpoint-1000/scheduler.pt +3 -0
  7. checkpoint-1000/special_tokens_map.json +23 -0
  8. checkpoint-1000/tokenizer.json +0 -0
  9. checkpoint-1000/tokenizer_config.json +2079 -0
  10. checkpoint-1000/trainer_state.json +0 -0
  11. checkpoint-1000/training_args.bin +3 -0
  12. checkpoint-1431/README.md +202 -0
  13. checkpoint-1431/adapter_config.json +32 -0
  14. checkpoint-1431/adapter_model.safetensors +3 -0
  15. checkpoint-1431/optimizer.pt +3 -0
  16. checkpoint-1431/rng_state.pth +3 -0
  17. checkpoint-1431/scheduler.pt +3 -0
  18. checkpoint-1431/special_tokens_map.json +23 -0
  19. checkpoint-1431/tokenizer.json +0 -0
  20. checkpoint-1431/tokenizer_config.json +2079 -0
  21. checkpoint-1431/trainer_state.json +0 -0
  22. checkpoint-1431/training_args.bin +3 -0
  23. checkpoint-500/README.md +202 -0
  24. checkpoint-500/adapter_config.json +32 -0
  25. checkpoint-500/adapter_model.safetensors +3 -0
  26. checkpoint-500/optimizer.pt +3 -0
  27. checkpoint-500/rng_state.pth +3 -0
  28. checkpoint-500/scheduler.pt +3 -0
  29. checkpoint-500/special_tokens_map.json +23 -0
  30. checkpoint-500/tokenizer.json +0 -0
  31. checkpoint-500/tokenizer_config.json +2079 -0
  32. checkpoint-500/trainer_state.json +3541 -0
  33. checkpoint-500/training_args.bin +3 -0
  34. final_model/README.md +202 -0
  35. final_model/adapter_config.json +32 -0
  36. final_model/adapter_model.safetensors +3 -0
  37. merged_model/config.json +29 -0
  38. merged_model/generation_config.json +7 -0
  39. merged_model/model-00001-of-00007.safetensors +3 -0
  40. merged_model/model-00002-of-00007.safetensors +3 -0
  41. merged_model/model-00003-of-00007.safetensors +3 -0
  42. merged_model/model-00004-of-00007.safetensors +3 -0
  43. merged_model/model-00005-of-00007.safetensors +3 -0
  44. merged_model/model-00006-of-00007.safetensors +3 -0
  45. merged_model/model-00007-of-00007.safetensors +3 -0
  46. merged_model/model.safetensors.index.json +298 -0
checkpoint-1000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.8.2
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "up_proj",
24
+ "v_proj",
25
+ "gate_proj",
26
+ "q_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": true
32
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0c161bcc22b5e09a3e484ac99a6e0cbe64ae95446db8a449c4f7b60ba2374d
3
+ size 1342238560
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1502e059c4e645f2908e3200143c63552eb69a22ce615eaf655054005aa02e4
3
+ size 2684732882
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a931f8c85c543e82d5cb9716e05134fda2f3f77efa92a25391bc5dac7d2ecbef
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2a185d5f27b57d468155b02ee10767364742eb964d929f89d72508d1efc378
3
+ size 1064
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,2079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": false
2066
+ }
2067
+ },
2068
+ "bos_token": "<|begin_of_text|>",
2069
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2070
+ "clean_up_tokenization_spaces": true,
2071
+ "eos_token": "<|im_end|>",
2072
+ "model_input_names": [
2073
+ "input_ids",
2074
+ "attention_mask"
2075
+ ],
2076
+ "model_max_length": 1000000000000000019884624838656,
2077
+ "pad_token": "<|end_of_text|>",
2078
+ "tokenizer_class": "PreTrainedTokenizerFast"
2079
+ }
checkpoint-1000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86f5bab8dd2b00d5dcc124ddb4bdfc8546468f0fde48d81a745ed29055777d6
3
+ size 5176
checkpoint-1431/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.8.2
checkpoint-1431/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "up_proj",
24
+ "v_proj",
25
+ "gate_proj",
26
+ "q_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": true
32
+ }
checkpoint-1431/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f7f81c15b686111aa534bae8d8d8525b4c34ff835d5211981bc01605d94c66
3
+ size 1342238560
checkpoint-1431/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca25e2d4293d35f68652a44fe691ba377dc92f95ed4308d2023ff64fdf7cd9f0
3
+ size 2684732882
checkpoint-1431/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15230cd66b4eb42f896e2dfa117941c396dee239bcd41f01c9ad55af058b9b9
3
+ size 14244
checkpoint-1431/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fec6fdcc78d17d15c842bbd08b3cd9a21d03110fef28cfd58aaf6959c95c4a8
3
+ size 1064
checkpoint-1431/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-1431/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1431/tokenizer_config.json ADDED
@@ -0,0 +1,2079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": false
2066
+ }
2067
+ },
2068
+ "bos_token": "<|begin_of_text|>",
2069
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2070
+ "clean_up_tokenization_spaces": true,
2071
+ "eos_token": "<|im_end|>",
2072
+ "model_input_names": [
2073
+ "input_ids",
2074
+ "attention_mask"
2075
+ ],
2076
+ "model_max_length": 1000000000000000019884624838656,
2077
+ "pad_token": "<|end_of_text|>",
2078
+ "tokenizer_class": "PreTrainedTokenizerFast"
2079
+ }
checkpoint-1431/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1431/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86f5bab8dd2b00d5dcc124ddb4bdfc8546468f0fde48d81a745ed29055777d6
3
+ size 5176
checkpoint-500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.8.2
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "up_proj",
24
+ "v_proj",
25
+ "gate_proj",
26
+ "q_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": true
32
+ }
checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9e251178403547ac5c0896a60a302a79962a1840fdb4128dfd7f2d1a89d8b1
3
+ size 1342238560
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432aa55f60661c784bde87e19bc901ac8453069c2996443de16eb65acfcbfb23
3
+ size 2684732882
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985e13d55fcc68f45a8be32dab68e2d873b4c1f04cebd2b49019016f79fd675c
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31fefaf6abcefce20ac44f93bfc4e3ee012406a59b9d980371b2eb1d461a950
3
+ size 1064
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,2079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<|im_end|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_start|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": false
2066
+ }
2067
+ },
2068
+ "bos_token": "<|begin_of_text|>",
2069
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2070
+ "clean_up_tokenization_spaces": true,
2071
+ "eos_token": "<|im_end|>",
2072
+ "model_input_names": [
2073
+ "input_ids",
2074
+ "attention_mask"
2075
+ ],
2076
+ "model_max_length": 1000000000000000019884624838656,
2077
+ "pad_token": "<|end_of_text|>",
2078
+ "tokenizer_class": "PreTrainedTokenizerFast"
2079
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,3541 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3494060097833683,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0006988120195667365,
13
+ "grad_norm": 29.745662689208984,
14
+ "learning_rate": 3.472222222222222e-08,
15
+ "loss": 0.4892,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.001397624039133473,
20
+ "grad_norm": 27.119117736816406,
21
+ "learning_rate": 6.944444444444444e-08,
22
+ "loss": 0.5036,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0020964360587002098,
27
+ "grad_norm": 26.687828063964844,
28
+ "learning_rate": 1.0416666666666667e-07,
29
+ "loss": 0.4122,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.002795248078266946,
34
+ "grad_norm": 34.61165237426758,
35
+ "learning_rate": 1.3888888888888888e-07,
36
+ "loss": 0.364,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.0034940600978336828,
41
+ "grad_norm": 45.05033874511719,
42
+ "learning_rate": 1.7361111111111115e-07,
43
+ "loss": 1.0297,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0041928721174004195,
48
+ "grad_norm": 26.53506851196289,
49
+ "learning_rate": 2.0833333333333333e-07,
50
+ "loss": 0.2974,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.004891684136967156,
55
+ "grad_norm": 26.738407135009766,
56
+ "learning_rate": 2.430555555555556e-07,
57
+ "loss": 0.3303,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.005590496156533892,
62
+ "grad_norm": 14.776915550231934,
63
+ "learning_rate": 2.7777777777777776e-07,
64
+ "loss": 0.1818,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.006289308176100629,
69
+ "grad_norm": 23.260135650634766,
70
+ "learning_rate": 3.125e-07,
71
+ "loss": 0.2969,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0069881201956673656,
76
+ "grad_norm": 15.725804328918457,
77
+ "learning_rate": 3.472222222222223e-07,
78
+ "loss": 0.2365,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.007686932215234102,
83
+ "grad_norm": 76.81114196777344,
84
+ "learning_rate": 3.819444444444445e-07,
85
+ "loss": 1.1389,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.008385744234800839,
90
+ "grad_norm": 18.762008666992188,
91
+ "learning_rate": 4.1666666666666667e-07,
92
+ "loss": 0.2786,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.009084556254367574,
97
+ "grad_norm": 19.521512985229492,
98
+ "learning_rate": 4.5138888888888893e-07,
99
+ "loss": 0.2404,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.009783368273934312,
104
+ "grad_norm": 53.75028610229492,
105
+ "learning_rate": 4.861111111111112e-07,
106
+ "loss": 1.0421,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.010482180293501049,
111
+ "grad_norm": 23.264202117919922,
112
+ "learning_rate": 5.208333333333334e-07,
113
+ "loss": 0.3734,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.011180992313067784,
118
+ "grad_norm": 24.78360366821289,
119
+ "learning_rate": 5.555555555555555e-07,
120
+ "loss": 0.3425,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.011879804332634521,
125
+ "grad_norm": 8.888618469238281,
126
+ "learning_rate": 5.902777777777778e-07,
127
+ "loss": 0.1022,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.012578616352201259,
132
+ "grad_norm": 47.52095413208008,
133
+ "learning_rate": 6.25e-07,
134
+ "loss": 0.7342,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.013277428371767994,
139
+ "grad_norm": 22.385765075683594,
140
+ "learning_rate": 6.597222222222223e-07,
141
+ "loss": 0.3538,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.013976240391334731,
146
+ "grad_norm": 10.82557201385498,
147
+ "learning_rate": 6.944444444444446e-07,
148
+ "loss": 0.092,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.014675052410901468,
153
+ "grad_norm": 22.204137802124023,
154
+ "learning_rate": 7.291666666666667e-07,
155
+ "loss": 0.3104,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.015373864430468204,
160
+ "grad_norm": 19.167959213256836,
161
+ "learning_rate": 7.63888888888889e-07,
162
+ "loss": 0.3576,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.01607267645003494,
167
+ "grad_norm": 17.112138748168945,
168
+ "learning_rate": 7.986111111111111e-07,
169
+ "loss": 0.3013,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.016771488469601678,
174
+ "grad_norm": 10.015545845031738,
175
+ "learning_rate": 8.333333333333333e-07,
176
+ "loss": 0.1068,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.017470300489168415,
181
+ "grad_norm": 10.68148136138916,
182
+ "learning_rate": 8.680555555555556e-07,
183
+ "loss": 0.1036,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.01816911250873515,
188
+ "grad_norm": 25.902118682861328,
189
+ "learning_rate": 9.027777777777779e-07,
190
+ "loss": 0.2941,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.018867924528301886,
195
+ "grad_norm": 14.709237098693848,
196
+ "learning_rate": 9.375000000000001e-07,
197
+ "loss": 0.1508,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.019566736547868623,
202
+ "grad_norm": 11.095511436462402,
203
+ "learning_rate": 9.722222222222224e-07,
204
+ "loss": 0.0734,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.02026554856743536,
209
+ "grad_norm": 6.820224761962891,
210
+ "learning_rate": 1.0069444444444447e-06,
211
+ "loss": 0.0676,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.020964360587002098,
216
+ "grad_norm": 35.560279846191406,
217
+ "learning_rate": 1.0416666666666667e-06,
218
+ "loss": 0.5665,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.02166317260656883,
223
+ "grad_norm": 18.7200984954834,
224
+ "learning_rate": 1.076388888888889e-06,
225
+ "loss": 0.2377,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.02236198462613557,
230
+ "grad_norm": 24.008363723754883,
231
+ "learning_rate": 1.111111111111111e-06,
232
+ "loss": 0.3863,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.023060796645702306,
237
+ "grad_norm": 42.345916748046875,
238
+ "learning_rate": 1.1458333333333333e-06,
239
+ "loss": 0.6234,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.023759608665269043,
244
+ "grad_norm": 14.686384201049805,
245
+ "learning_rate": 1.1805555555555556e-06,
246
+ "loss": 0.1656,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.02445842068483578,
251
+ "grad_norm": 15.544900894165039,
252
+ "learning_rate": 1.2152777777777778e-06,
253
+ "loss": 0.0781,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.025157232704402517,
258
+ "grad_norm": 20.373491287231445,
259
+ "learning_rate": 1.25e-06,
260
+ "loss": 0.3014,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.02585604472396925,
265
+ "grad_norm": 19.440364837646484,
266
+ "learning_rate": 1.2847222222222222e-06,
267
+ "loss": 0.2605,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.026554856743535988,
272
+ "grad_norm": 14.13811206817627,
273
+ "learning_rate": 1.3194444444444446e-06,
274
+ "loss": 0.0976,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.027253668763102725,
279
+ "grad_norm": 16.72405433654785,
280
+ "learning_rate": 1.3541666666666667e-06,
281
+ "loss": 0.189,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.027952480782669462,
286
+ "grad_norm": 26.501976013183594,
287
+ "learning_rate": 1.3888888888888892e-06,
288
+ "loss": 0.5341,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.0286512928022362,
293
+ "grad_norm": 16.74985122680664,
294
+ "learning_rate": 1.4236111111111112e-06,
295
+ "loss": 0.1534,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.029350104821802937,
300
+ "grad_norm": 37.214256286621094,
301
+ "learning_rate": 1.4583333333333335e-06,
302
+ "loss": 0.5655,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.03004891684136967,
307
+ "grad_norm": 7.750210285186768,
308
+ "learning_rate": 1.4930555555555555e-06,
309
+ "loss": 0.052,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.030747728860936407,
314
+ "grad_norm": 18.785743713378906,
315
+ "learning_rate": 1.527777777777778e-06,
316
+ "loss": 0.3389,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.031446540880503145,
321
+ "grad_norm": 31.0648250579834,
322
+ "learning_rate": 1.5625e-06,
323
+ "loss": 0.3845,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.03214535290006988,
328
+ "grad_norm": 52.98978805541992,
329
+ "learning_rate": 1.5972222222222221e-06,
330
+ "loss": 0.8845,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.03284416491963662,
335
+ "grad_norm": 26.285877227783203,
336
+ "learning_rate": 1.6319444444444446e-06,
337
+ "loss": 0.3638,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.033542976939203356,
342
+ "grad_norm": 30.1326904296875,
343
+ "learning_rate": 1.6666666666666667e-06,
344
+ "loss": 0.3756,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.03424178895877009,
349
+ "grad_norm": 19.73238754272461,
350
+ "learning_rate": 1.7013888888888891e-06,
351
+ "loss": 0.3055,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.03494060097833683,
356
+ "grad_norm": 21.93083381652832,
357
+ "learning_rate": 1.7361111111111112e-06,
358
+ "loss": 0.2084,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.03563941299790356,
363
+ "grad_norm": 44.288185119628906,
364
+ "learning_rate": 1.7708333333333337e-06,
365
+ "loss": 0.6509,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.0363382250174703,
370
+ "grad_norm": 10.11754035949707,
371
+ "learning_rate": 1.8055555555555557e-06,
372
+ "loss": 0.1512,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.037037037037037035,
377
+ "grad_norm": 16.429866790771484,
378
+ "learning_rate": 1.840277777777778e-06,
379
+ "loss": 0.2423,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.03773584905660377,
384
+ "grad_norm": 53.626380920410156,
385
+ "learning_rate": 1.8750000000000003e-06,
386
+ "loss": 0.8959,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.03843466107617051,
391
+ "grad_norm": 18.586044311523438,
392
+ "learning_rate": 1.909722222222222e-06,
393
+ "loss": 0.4167,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.039133473095737246,
398
+ "grad_norm": 22.02561378479004,
399
+ "learning_rate": 1.944444444444445e-06,
400
+ "loss": 0.3638,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.039832285115303984,
405
+ "grad_norm": 12.25664234161377,
406
+ "learning_rate": 1.9791666666666666e-06,
407
+ "loss": 0.1458,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.04053109713487072,
412
+ "grad_norm": 26.37610626220703,
413
+ "learning_rate": 2.0138888888888893e-06,
414
+ "loss": 0.4709,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.04122990915443746,
419
+ "grad_norm": 23.607717514038086,
420
+ "learning_rate": 2.048611111111111e-06,
421
+ "loss": 0.3147,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.041928721174004195,
426
+ "grad_norm": 12.090802192687988,
427
+ "learning_rate": 2.0833333333333334e-06,
428
+ "loss": 0.1457,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.04262753319357093,
433
+ "grad_norm": 9.616584777832031,
434
+ "learning_rate": 2.1180555555555557e-06,
435
+ "loss": 0.1364,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.04332634521313766,
440
+ "grad_norm": 22.472373962402344,
441
+ "learning_rate": 2.152777777777778e-06,
442
+ "loss": 0.4109,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.0440251572327044,
447
+ "grad_norm": 15.625946044921875,
448
+ "learning_rate": 2.1875000000000002e-06,
449
+ "loss": 0.1571,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.04472396925227114,
454
+ "grad_norm": 15.733026504516602,
455
+ "learning_rate": 2.222222222222222e-06,
456
+ "loss": 0.2123,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.045422781271837874,
461
+ "grad_norm": 17.976316452026367,
462
+ "learning_rate": 2.2569444444444448e-06,
463
+ "loss": 0.211,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.04612159329140461,
468
+ "grad_norm": 33.2844123840332,
469
+ "learning_rate": 2.2916666666666666e-06,
470
+ "loss": 0.633,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.04682040531097135,
475
+ "grad_norm": 46.91634750366211,
476
+ "learning_rate": 2.3263888888888893e-06,
477
+ "loss": 0.5234,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.047519217330538085,
482
+ "grad_norm": 37.31273651123047,
483
+ "learning_rate": 2.361111111111111e-06,
484
+ "loss": 0.603,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.04821802935010482,
489
+ "grad_norm": 37.39180374145508,
490
+ "learning_rate": 2.395833333333334e-06,
491
+ "loss": 0.6505,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.04891684136967156,
496
+ "grad_norm": 23.082998275756836,
497
+ "learning_rate": 2.4305555555555557e-06,
498
+ "loss": 0.3517,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.0496156533892383,
503
+ "grad_norm": 6.721218109130859,
504
+ "learning_rate": 2.465277777777778e-06,
505
+ "loss": 0.0438,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.050314465408805034,
510
+ "grad_norm": 17.105623245239258,
511
+ "learning_rate": 2.5e-06,
512
+ "loss": 0.2446,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.05101327742837177,
517
+ "grad_norm": 21.732906341552734,
518
+ "learning_rate": 2.5347222222222225e-06,
519
+ "loss": 0.2211,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.0517120894479385,
524
+ "grad_norm": 11.384443283081055,
525
+ "learning_rate": 2.5694444444444443e-06,
526
+ "loss": 0.1657,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.05241090146750524,
531
+ "grad_norm": 4.708110809326172,
532
+ "learning_rate": 2.604166666666667e-06,
533
+ "loss": 0.0341,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.053109713487071976,
538
+ "grad_norm": 14.210625648498535,
539
+ "learning_rate": 2.6388888888888893e-06,
540
+ "loss": 0.1754,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.05380852550663871,
545
+ "grad_norm": 13.893073081970215,
546
+ "learning_rate": 2.673611111111111e-06,
547
+ "loss": 0.1682,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.05450733752620545,
552
+ "grad_norm": 18.905048370361328,
553
+ "learning_rate": 2.7083333333333334e-06,
554
+ "loss": 0.2632,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.05520614954577219,
559
+ "grad_norm": 12.439525604248047,
560
+ "learning_rate": 2.743055555555556e-06,
561
+ "loss": 0.1458,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.055904961565338925,
566
+ "grad_norm": 24.605615615844727,
567
+ "learning_rate": 2.7777777777777783e-06,
568
+ "loss": 0.3817,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.05660377358490566,
573
+ "grad_norm": 27.12447738647461,
574
+ "learning_rate": 2.8125e-06,
575
+ "loss": 0.5378,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.0573025856044724,
580
+ "grad_norm": 21.627233505249023,
581
+ "learning_rate": 2.8472222222222224e-06,
582
+ "loss": 0.3125,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.058001397624039136,
587
+ "grad_norm": 2.656435966491699,
588
+ "learning_rate": 2.8819444444444443e-06,
589
+ "loss": 0.0084,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.05870020964360587,
594
+ "grad_norm": 20.46363067626953,
595
+ "learning_rate": 2.916666666666667e-06,
596
+ "loss": 0.279,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.0593990216631726,
601
+ "grad_norm": 17.098342895507812,
602
+ "learning_rate": 2.9513888888888892e-06,
603
+ "loss": 0.2007,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.06009783368273934,
608
+ "grad_norm": 22.730363845825195,
609
+ "learning_rate": 2.986111111111111e-06,
610
+ "loss": 0.3265,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.06079664570230608,
615
+ "grad_norm": 13.15532112121582,
616
+ "learning_rate": 3.0208333333333334e-06,
617
+ "loss": 0.1778,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.061495457721872815,
622
+ "grad_norm": 12.832003593444824,
623
+ "learning_rate": 3.055555555555556e-06,
624
+ "loss": 0.1664,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.06219426974143955,
629
+ "grad_norm": 4.212726593017578,
630
+ "learning_rate": 3.0902777777777783e-06,
631
+ "loss": 0.0126,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.06289308176100629,
636
+ "grad_norm": 9.53214168548584,
637
+ "learning_rate": 3.125e-06,
638
+ "loss": 0.0876,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.06359189378057302,
643
+ "grad_norm": 53.41883087158203,
644
+ "learning_rate": 3.1597222222222224e-06,
645
+ "loss": 0.9937,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.06429070580013976,
650
+ "grad_norm": 16.07880973815918,
651
+ "learning_rate": 3.1944444444444443e-06,
652
+ "loss": 0.1187,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.0649895178197065,
657
+ "grad_norm": 4.490603446960449,
658
+ "learning_rate": 3.229166666666667e-06,
659
+ "loss": 0.015,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.06568832983927324,
664
+ "grad_norm": 32.008087158203125,
665
+ "learning_rate": 3.2638888888888892e-06,
666
+ "loss": 0.5616,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.06638714185883997,
671
+ "grad_norm": 30.389848709106445,
672
+ "learning_rate": 3.2986111111111115e-06,
673
+ "loss": 0.4378,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.06708595387840671,
678
+ "grad_norm": 20.06416130065918,
679
+ "learning_rate": 3.3333333333333333e-06,
680
+ "loss": 0.2875,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.06778476589797344,
685
+ "grad_norm": 8.978775978088379,
686
+ "learning_rate": 3.368055555555556e-06,
687
+ "loss": 0.1084,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.06848357791754019,
692
+ "grad_norm": 59.80595779418945,
693
+ "learning_rate": 3.4027777777777783e-06,
694
+ "loss": 0.9074,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.06918238993710692,
699
+ "grad_norm": 18.711381912231445,
700
+ "learning_rate": 3.4375e-06,
701
+ "loss": 0.2926,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.06988120195667366,
706
+ "grad_norm": 9.171241760253906,
707
+ "learning_rate": 3.4722222222222224e-06,
708
+ "loss": 0.1213,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.07058001397624039,
713
+ "grad_norm": 12.976991653442383,
714
+ "learning_rate": 3.5069444444444447e-06,
715
+ "loss": 0.2017,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.07127882599580712,
720
+ "grad_norm": 2.725184917449951,
721
+ "learning_rate": 3.5416666666666673e-06,
722
+ "loss": 0.0167,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.07197763801537387,
727
+ "grad_norm": 12.85250473022461,
728
+ "learning_rate": 3.576388888888889e-06,
729
+ "loss": 0.1463,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.0726764500349406,
734
+ "grad_norm": 23.173830032348633,
735
+ "learning_rate": 3.6111111111111115e-06,
736
+ "loss": 0.3149,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.07337526205450734,
741
+ "grad_norm": 32.99692153930664,
742
+ "learning_rate": 3.6458333333333333e-06,
743
+ "loss": 0.6735,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.07407407407407407,
748
+ "grad_norm": 15.19417667388916,
749
+ "learning_rate": 3.680555555555556e-06,
750
+ "loss": 0.2826,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.07477288609364081,
755
+ "grad_norm": 13.61240291595459,
756
+ "learning_rate": 3.7152777777777783e-06,
757
+ "loss": 0.1674,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.07547169811320754,
762
+ "grad_norm": 10.538482666015625,
763
+ "learning_rate": 3.7500000000000005e-06,
764
+ "loss": 0.1172,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.07617051013277429,
769
+ "grad_norm": 9.325597763061523,
770
+ "learning_rate": 3.7847222222222224e-06,
771
+ "loss": 0.0898,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.07686932215234102,
776
+ "grad_norm": 29.34699821472168,
777
+ "learning_rate": 3.819444444444444e-06,
778
+ "loss": 0.4043,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.07756813417190776,
783
+ "grad_norm": 10.5206937789917,
784
+ "learning_rate": 3.854166666666667e-06,
785
+ "loss": 0.1151,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.07826694619147449,
790
+ "grad_norm": 16.31255531311035,
791
+ "learning_rate": 3.88888888888889e-06,
792
+ "loss": 0.1857,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.07896575821104122,
797
+ "grad_norm": 10.712072372436523,
798
+ "learning_rate": 3.9236111111111114e-06,
799
+ "loss": 0.0467,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.07966457023060797,
804
+ "grad_norm": 49.4650764465332,
805
+ "learning_rate": 3.958333333333333e-06,
806
+ "loss": 0.8661,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.0803633822501747,
811
+ "grad_norm": 10.439119338989258,
812
+ "learning_rate": 3.993055555555556e-06,
813
+ "loss": 0.1552,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.08106219426974144,
818
+ "grad_norm": 8.641897201538086,
819
+ "learning_rate": 4.027777777777779e-06,
820
+ "loss": 0.0724,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.08176100628930817,
825
+ "grad_norm": 21.5423641204834,
826
+ "learning_rate": 4.0625000000000005e-06,
827
+ "loss": 0.3887,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.08245981830887492,
832
+ "grad_norm": 10.582996368408203,
833
+ "learning_rate": 4.097222222222222e-06,
834
+ "loss": 0.1831,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.08315863032844165,
839
+ "grad_norm": 4.447153568267822,
840
+ "learning_rate": 4.131944444444444e-06,
841
+ "loss": 0.0429,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.08385744234800839,
846
+ "grad_norm": 4.488365173339844,
847
+ "learning_rate": 4.166666666666667e-06,
848
+ "loss": 0.0286,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.08455625436757512,
853
+ "grad_norm": 27.888690948486328,
854
+ "learning_rate": 4.2013888888888896e-06,
855
+ "loss": 0.5963,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.08525506638714186,
860
+ "grad_norm": 22.506404876708984,
861
+ "learning_rate": 4.236111111111111e-06,
862
+ "loss": 0.4488,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.0859538784067086,
867
+ "grad_norm": 12.767803192138672,
868
+ "learning_rate": 4.270833333333333e-06,
869
+ "loss": 0.0468,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.08665269042627533,
874
+ "grad_norm": 21.219179153442383,
875
+ "learning_rate": 4.305555555555556e-06,
876
+ "loss": 0.396,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.08735150244584207,
881
+ "grad_norm": 19.373239517211914,
882
+ "learning_rate": 4.340277777777779e-06,
883
+ "loss": 0.2474,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.0880503144654088,
888
+ "grad_norm": 1.8469300270080566,
889
+ "learning_rate": 4.3750000000000005e-06,
890
+ "loss": 0.0126,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.08874912648497554,
895
+ "grad_norm": 2.2161784172058105,
896
+ "learning_rate": 4.409722222222222e-06,
897
+ "loss": 0.0194,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.08944793850454227,
902
+ "grad_norm": 10.892654418945312,
903
+ "learning_rate": 4.444444444444444e-06,
904
+ "loss": 0.1174,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.09014675052410902,
909
+ "grad_norm": 21.090118408203125,
910
+ "learning_rate": 4.479166666666667e-06,
911
+ "loss": 0.2698,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.09084556254367575,
916
+ "grad_norm": 15.25643539428711,
917
+ "learning_rate": 4.5138888888888895e-06,
918
+ "loss": 0.1317,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.09154437456324249,
923
+ "grad_norm": 31.168315887451172,
924
+ "learning_rate": 4.548611111111111e-06,
925
+ "loss": 0.4776,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.09224318658280922,
930
+ "grad_norm": 33.08750534057617,
931
+ "learning_rate": 4.583333333333333e-06,
932
+ "loss": 0.4328,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.09294199860237597,
937
+ "grad_norm": 52.183746337890625,
938
+ "learning_rate": 4.618055555555556e-06,
939
+ "loss": 0.564,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.0936408106219427,
944
+ "grad_norm": 40.50120162963867,
945
+ "learning_rate": 4.652777777777779e-06,
946
+ "loss": 0.5272,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.09433962264150944,
951
+ "grad_norm": 20.32408905029297,
952
+ "learning_rate": 4.6875000000000004e-06,
953
+ "loss": 0.2767,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.09503843466107617,
958
+ "grad_norm": 2.8684241771698,
959
+ "learning_rate": 4.722222222222222e-06,
960
+ "loss": 0.0144,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.0957372466806429,
965
+ "grad_norm": 7.477058410644531,
966
+ "learning_rate": 4.756944444444445e-06,
967
+ "loss": 0.0493,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.09643605870020965,
972
+ "grad_norm": 23.22918128967285,
973
+ "learning_rate": 4.791666666666668e-06,
974
+ "loss": 0.3952,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.09713487071977638,
979
+ "grad_norm": 9.2420654296875,
980
+ "learning_rate": 4.8263888888888895e-06,
981
+ "loss": 0.0882,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.09783368273934312,
986
+ "grad_norm": 27.750822067260742,
987
+ "learning_rate": 4.861111111111111e-06,
988
+ "loss": 0.3521,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.09853249475890985,
993
+ "grad_norm": 12.380672454833984,
994
+ "learning_rate": 4.895833333333333e-06,
995
+ "loss": 0.1333,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.0992313067784766,
1000
+ "grad_norm": 25.04052734375,
1001
+ "learning_rate": 4.930555555555556e-06,
1002
+ "loss": 0.3795,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.09993011879804332,
1007
+ "grad_norm": 11.43722915649414,
1008
+ "learning_rate": 4.9652777777777786e-06,
1009
+ "loss": 0.1927,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.10062893081761007,
1014
+ "grad_norm": 55.4820442199707,
1015
+ "learning_rate": 5e-06,
1016
+ "loss": 0.9907,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.1013277428371768,
1021
+ "grad_norm": 20.55660057067871,
1022
+ "learning_rate": 4.999992551780808e-06,
1023
+ "loss": 0.2302,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.10202655485674354,
1028
+ "grad_norm": 13.871188163757324,
1029
+ "learning_rate": 4.999970207167611e-06,
1030
+ "loss": 0.1635,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.10272536687631027,
1035
+ "grad_norm": 17.654191970825195,
1036
+ "learning_rate": 4.999932966293553e-06,
1037
+ "loss": 0.2374,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.103424178895877,
1042
+ "grad_norm": 13.314811706542969,
1043
+ "learning_rate": 4.9998808293805355e-06,
1044
+ "loss": 0.1912,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.10412299091544375,
1049
+ "grad_norm": 12.17277717590332,
1050
+ "learning_rate": 4.9998137967392205e-06,
1051
+ "loss": 0.1267,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.10482180293501048,
1056
+ "grad_norm": 1.8680511713027954,
1057
+ "learning_rate": 4.999731868769027e-06,
1058
+ "loss": 0.0062,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.10552061495457722,
1063
+ "grad_norm": 3.3582608699798584,
1064
+ "learning_rate": 4.999635045958129e-06,
1065
+ "loss": 0.0244,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.10621942697414395,
1070
+ "grad_norm": 15.267073631286621,
1071
+ "learning_rate": 4.999523328883451e-06,
1072
+ "loss": 0.226,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.1069182389937107,
1077
+ "grad_norm": 13.432097434997559,
1078
+ "learning_rate": 4.999396718210671e-06,
1079
+ "loss": 0.1862,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.10761705101327743,
1084
+ "grad_norm": 34.178123474121094,
1085
+ "learning_rate": 4.9992552146942054e-06,
1086
+ "loss": 0.4717,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.10831586303284417,
1091
+ "grad_norm": 10.88023853302002,
1092
+ "learning_rate": 4.999098819177214e-06,
1093
+ "loss": 0.0827,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.1090146750524109,
1098
+ "grad_norm": 12.706320762634277,
1099
+ "learning_rate": 4.998927532591592e-06,
1100
+ "loss": 0.24,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.10971348707197764,
1105
+ "grad_norm": 33.3758544921875,
1106
+ "learning_rate": 4.998741355957963e-06,
1107
+ "loss": 0.3967,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.11041229909154437,
1112
+ "grad_norm": 9.823050498962402,
1113
+ "learning_rate": 4.998540290385675e-06,
1114
+ "loss": 0.1052,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.1111111111111111,
1119
+ "grad_norm": 21.20310401916504,
1120
+ "learning_rate": 4.998324337072792e-06,
1121
+ "loss": 0.3256,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.11180992313067785,
1126
+ "grad_norm": 3.378161668777466,
1127
+ "learning_rate": 4.998093497306088e-06,
1128
+ "loss": 0.0348,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.11250873515024458,
1133
+ "grad_norm": 16.39934539794922,
1134
+ "learning_rate": 4.997847772461038e-06,
1135
+ "loss": 0.2811,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.11320754716981132,
1140
+ "grad_norm": 11.997238159179688,
1141
+ "learning_rate": 4.997587164001815e-06,
1142
+ "loss": 0.1928,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.11390635918937805,
1147
+ "grad_norm": 11.762815475463867,
1148
+ "learning_rate": 4.997311673481272e-06,
1149
+ "loss": 0.1047,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.1146051712089448,
1154
+ "grad_norm": 41.98662185668945,
1155
+ "learning_rate": 4.99702130254094e-06,
1156
+ "loss": 0.8216,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.11530398322851153,
1161
+ "grad_norm": 0.8907880783081055,
1162
+ "learning_rate": 4.996716052911017e-06,
1163
+ "loss": 0.0136,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.11600279524807827,
1168
+ "grad_norm": 6.044946193695068,
1169
+ "learning_rate": 4.996395926410354e-06,
1170
+ "loss": 0.0574,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.116701607267645,
1175
+ "grad_norm": 7.652251243591309,
1176
+ "learning_rate": 4.996060924946452e-06,
1177
+ "loss": 0.1021,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.11740041928721175,
1182
+ "grad_norm": 16.434112548828125,
1183
+ "learning_rate": 4.99571105051544e-06,
1184
+ "loss": 0.3096,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.11809923130677848,
1189
+ "grad_norm": 8.08709716796875,
1190
+ "learning_rate": 4.995346305202073e-06,
1191
+ "loss": 0.0687,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.1187980433263452,
1196
+ "grad_norm": 16.4686222076416,
1197
+ "learning_rate": 4.994966691179712e-06,
1198
+ "loss": 0.3045,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.11949685534591195,
1203
+ "grad_norm": 28.794492721557617,
1204
+ "learning_rate": 4.994572210710315e-06,
1205
+ "loss": 0.3226,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.12019566736547868,
1210
+ "grad_norm": 1.1931850910186768,
1211
+ "learning_rate": 4.994162866144425e-06,
1212
+ "loss": 0.0193,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.12089447938504543,
1217
+ "grad_norm": 13.104757308959961,
1218
+ "learning_rate": 4.993738659921153e-06,
1219
+ "loss": 0.1906,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.12159329140461216,
1224
+ "grad_norm": 20.407514572143555,
1225
+ "learning_rate": 4.993299594568163e-06,
1226
+ "loss": 0.3464,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.1222921034241789,
1231
+ "grad_norm": 18.145898818969727,
1232
+ "learning_rate": 4.992845672701658e-06,
1233
+ "loss": 0.3235,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.12299091544374563,
1238
+ "grad_norm": 11.253594398498535,
1239
+ "learning_rate": 4.9923768970263675e-06,
1240
+ "loss": 0.1361,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.12368972746331237,
1245
+ "grad_norm": 13.6408109664917,
1246
+ "learning_rate": 4.991893270335526e-06,
1247
+ "loss": 0.2828,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.1243885394828791,
1252
+ "grad_norm": 38.79020309448242,
1253
+ "learning_rate": 4.9913947955108575e-06,
1254
+ "loss": 0.604,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.12508735150244585,
1259
+ "grad_norm": 11.21642017364502,
1260
+ "learning_rate": 4.990881475522566e-06,
1261
+ "loss": 0.0548,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.12578616352201258,
1266
+ "grad_norm": 19.890596389770508,
1267
+ "learning_rate": 4.9903533134293035e-06,
1268
+ "loss": 0.3927,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.1264849755415793,
1273
+ "grad_norm": 13.620441436767578,
1274
+ "learning_rate": 4.989810312378165e-06,
1275
+ "loss": 0.1395,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.12718378756114604,
1280
+ "grad_norm": 7.4906134605407715,
1281
+ "learning_rate": 4.989252475604664e-06,
1282
+ "loss": 0.0814,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.1278825995807128,
1287
+ "grad_norm": 9.755054473876953,
1288
+ "learning_rate": 4.988679806432712e-06,
1289
+ "loss": 0.1458,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.12858141160027953,
1294
+ "grad_norm": 14.173589706420898,
1295
+ "learning_rate": 4.9880923082746015e-06,
1296
+ "loss": 0.1895,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.12928022361984626,
1301
+ "grad_norm": 10.801349639892578,
1302
+ "learning_rate": 4.987489984630985e-06,
1303
+ "loss": 0.1126,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.129979035639413,
1308
+ "grad_norm": 21.870594024658203,
1309
+ "learning_rate": 4.986872839090853e-06,
1310
+ "loss": 0.3324,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.13067784765897975,
1315
+ "grad_norm": 32.091796875,
1316
+ "learning_rate": 4.986240875331513e-06,
1317
+ "loss": 0.7947,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.13137665967854648,
1322
+ "grad_norm": 12.568334579467773,
1323
+ "learning_rate": 4.9855940971185705e-06,
1324
+ "loss": 0.2354,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.1320754716981132,
1329
+ "grad_norm": 37.35740280151367,
1330
+ "learning_rate": 4.9849325083059e-06,
1331
+ "loss": 0.6075,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.13277428371767994,
1336
+ "grad_norm": 24.105323791503906,
1337
+ "learning_rate": 4.98425611283563e-06,
1338
+ "loss": 0.3857,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.1334730957372467,
1343
+ "grad_norm": 3.437150239944458,
1344
+ "learning_rate": 4.983564914738113e-06,
1345
+ "loss": 0.0299,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.13417190775681342,
1350
+ "grad_norm": 19.739456176757812,
1351
+ "learning_rate": 4.982858918131906e-06,
1352
+ "loss": 0.2763,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.13487071977638015,
1357
+ "grad_norm": 20.301265716552734,
1358
+ "learning_rate": 4.982138127223742e-06,
1359
+ "loss": 0.3133,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.13556953179594688,
1364
+ "grad_norm": 26.877233505249023,
1365
+ "learning_rate": 4.981402546308508e-06,
1366
+ "loss": 0.4081,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.13626834381551362,
1371
+ "grad_norm": 26.43645477294922,
1372
+ "learning_rate": 4.9806521797692184e-06,
1373
+ "loss": 0.2629,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.13696715583508037,
1378
+ "grad_norm": 23.70842933654785,
1379
+ "learning_rate": 4.9798870320769884e-06,
1380
+ "loss": 0.364,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.1376659678546471,
1385
+ "grad_norm": 17.802026748657227,
1386
+ "learning_rate": 4.979107107791009e-06,
1387
+ "loss": 0.2183,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.13836477987421383,
1392
+ "grad_norm": 24.834115982055664,
1393
+ "learning_rate": 4.978312411558518e-06,
1394
+ "loss": 0.2716,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.13906359189378056,
1399
+ "grad_norm": 22.922401428222656,
1400
+ "learning_rate": 4.977502948114772e-06,
1401
+ "loss": 0.2933,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.13976240391334732,
1406
+ "grad_norm": 34.77713394165039,
1407
+ "learning_rate": 4.976678722283019e-06,
1408
+ "loss": 0.7012,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.14046121593291405,
1413
+ "grad_norm": 12.13795280456543,
1414
+ "learning_rate": 4.975839738974473e-06,
1415
+ "loss": 0.1903,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.14116002795248078,
1420
+ "grad_norm": 16.988998413085938,
1421
+ "learning_rate": 4.974986003188278e-06,
1422
+ "loss": 0.2054,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.1418588399720475,
1427
+ "grad_norm": 19.275632858276367,
1428
+ "learning_rate": 4.974117520011484e-06,
1429
+ "loss": 0.2453,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.14255765199161424,
1434
+ "grad_norm": 35.913509368896484,
1435
+ "learning_rate": 4.973234294619011e-06,
1436
+ "loss": 0.5632,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.143256464011181,
1441
+ "grad_norm": 28.961172103881836,
1442
+ "learning_rate": 4.972336332273626e-06,
1443
+ "loss": 0.6512,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.14395527603074773,
1448
+ "grad_norm": 33.84477233886719,
1449
+ "learning_rate": 4.971423638325906e-06,
1450
+ "loss": 0.8773,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.14465408805031446,
1455
+ "grad_norm": 15.914165496826172,
1456
+ "learning_rate": 4.970496218214205e-06,
1457
+ "loss": 0.1928,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.1453529000698812,
1462
+ "grad_norm": 12.857492446899414,
1463
+ "learning_rate": 4.969554077464626e-06,
1464
+ "loss": 0.2481,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.14605171208944795,
1469
+ "grad_norm": 18.26762580871582,
1470
+ "learning_rate": 4.968597221690986e-06,
1471
+ "loss": 0.3223,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.14675052410901468,
1476
+ "grad_norm": 3.23185396194458,
1477
+ "learning_rate": 4.967625656594782e-06,
1478
+ "loss": 0.0309,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.1474493361285814,
1483
+ "grad_norm": 39.02360534667969,
1484
+ "learning_rate": 4.966639387965158e-06,
1485
+ "loss": 0.4517,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.14814814814814814,
1490
+ "grad_norm": 4.6353840827941895,
1491
+ "learning_rate": 4.965638421678871e-06,
1492
+ "loss": 0.0509,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.1488469601677149,
1497
+ "grad_norm": 4.9387993812561035,
1498
+ "learning_rate": 4.964622763700252e-06,
1499
+ "loss": 0.05,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.14954577218728163,
1504
+ "grad_norm": 3.62610125541687,
1505
+ "learning_rate": 4.963592420081177e-06,
1506
+ "loss": 0.0318,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.15024458420684836,
1511
+ "grad_norm": 39.914981842041016,
1512
+ "learning_rate": 4.962547396961026e-06,
1513
+ "loss": 0.6649,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.1509433962264151,
1518
+ "grad_norm": 29.543420791625977,
1519
+ "learning_rate": 4.961487700566646e-06,
1520
+ "loss": 0.4618,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.15164220824598182,
1525
+ "grad_norm": 15.438580513000488,
1526
+ "learning_rate": 4.960413337212321e-06,
1527
+ "loss": 0.0964,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.15234102026554858,
1532
+ "grad_norm": 12.203367233276367,
1533
+ "learning_rate": 4.959324313299724e-06,
1534
+ "loss": 0.1419,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.1530398322851153,
1539
+ "grad_norm": 36.472225189208984,
1540
+ "learning_rate": 4.958220635317886e-06,
1541
+ "loss": 0.7075,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.15373864430468204,
1546
+ "grad_norm": 15.606555938720703,
1547
+ "learning_rate": 4.957102309843157e-06,
1548
+ "loss": 0.1814,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.15443745632424877,
1553
+ "grad_norm": 34.66213607788086,
1554
+ "learning_rate": 4.955969343539162e-06,
1555
+ "loss": 0.4877,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.15513626834381553,
1560
+ "grad_norm": 2.426269292831421,
1561
+ "learning_rate": 4.9548217431567665e-06,
1562
+ "loss": 0.015,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.15583508036338226,
1567
+ "grad_norm": 7.730508804321289,
1568
+ "learning_rate": 4.953659515534035e-06,
1569
+ "loss": 0.1582,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.15653389238294899,
1574
+ "grad_norm": 34.605899810791016,
1575
+ "learning_rate": 4.952482667596187e-06,
1576
+ "loss": 0.3362,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.15723270440251572,
1581
+ "grad_norm": 48.30050277709961,
1582
+ "learning_rate": 4.95129120635556e-06,
1583
+ "loss": 0.9097,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.15793151642208245,
1588
+ "grad_norm": 5.044818878173828,
1589
+ "learning_rate": 4.9500851389115645e-06,
1590
+ "loss": 0.0458,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.1586303284416492,
1595
+ "grad_norm": 13.12427043914795,
1596
+ "learning_rate": 4.948864472450646e-06,
1597
+ "loss": 0.1505,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.15932914046121593,
1602
+ "grad_norm": 8.89181900024414,
1603
+ "learning_rate": 4.947629214246238e-06,
1604
+ "loss": 0.1343,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.16002795248078266,
1609
+ "grad_norm": 8.44274616241455,
1610
+ "learning_rate": 4.946379371658717e-06,
1611
+ "loss": 0.0818,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.1607267645003494,
1616
+ "grad_norm": 9.806259155273438,
1617
+ "learning_rate": 4.9451149521353655e-06,
1618
+ "loss": 0.1254,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.16142557651991615,
1623
+ "grad_norm": 4.928332328796387,
1624
+ "learning_rate": 4.943835963210324e-06,
1625
+ "loss": 0.0608,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.16212438853948288,
1630
+ "grad_norm": 17.608247756958008,
1631
+ "learning_rate": 4.942542412504543e-06,
1632
+ "loss": 0.2809,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.1628232005590496,
1637
+ "grad_norm": 13.168478012084961,
1638
+ "learning_rate": 4.9412343077257415e-06,
1639
+ "loss": 0.1497,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.16352201257861634,
1644
+ "grad_norm": 3.6533076763153076,
1645
+ "learning_rate": 4.939911656668361e-06,
1646
+ "loss": 0.0362,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.1642208245981831,
1651
+ "grad_norm": 26.288984298706055,
1652
+ "learning_rate": 4.938574467213519e-06,
1653
+ "loss": 0.46,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.16491963661774983,
1658
+ "grad_norm": 18.746585845947266,
1659
+ "learning_rate": 4.937222747328956e-06,
1660
+ "loss": 0.2843,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.16561844863731656,
1665
+ "grad_norm": 13.078903198242188,
1666
+ "learning_rate": 4.935856505068999e-06,
1667
+ "loss": 0.1926,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.1663172606568833,
1672
+ "grad_norm": 11.8361177444458,
1673
+ "learning_rate": 4.934475748574506e-06,
1674
+ "loss": 0.1823,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.16701607267645002,
1679
+ "grad_norm": 40.54023361206055,
1680
+ "learning_rate": 4.933080486072817e-06,
1681
+ "loss": 0.8266,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.16771488469601678,
1686
+ "grad_norm": 14.78891372680664,
1687
+ "learning_rate": 4.93167072587771e-06,
1688
+ "loss": 0.2339,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.1684136967155835,
1693
+ "grad_norm": 8.922636032104492,
1694
+ "learning_rate": 4.9302464763893474e-06,
1695
+ "loss": 0.1516,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.16911250873515024,
1700
+ "grad_norm": 28.712753295898438,
1701
+ "learning_rate": 4.9288077460942266e-06,
1702
+ "loss": 0.3758,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.16981132075471697,
1707
+ "grad_norm": 20.33342170715332,
1708
+ "learning_rate": 4.927354543565131e-06,
1709
+ "loss": 0.2495,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.17051013277428373,
1714
+ "grad_norm": 6.673890590667725,
1715
+ "learning_rate": 4.925886877461076e-06,
1716
+ "loss": 0.0951,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.17120894479385046,
1721
+ "grad_norm": 17.336618423461914,
1722
+ "learning_rate": 4.924404756527262e-06,
1723
+ "loss": 0.2111,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.1719077568134172,
1728
+ "grad_norm": 10.82662296295166,
1729
+ "learning_rate": 4.9229081895950185e-06,
1730
+ "loss": 0.1613,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.17260656883298392,
1735
+ "grad_norm": 54.12034606933594,
1736
+ "learning_rate": 4.92139718558175e-06,
1737
+ "loss": 0.9248,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.17330538085255065,
1742
+ "grad_norm": 14.005218505859375,
1743
+ "learning_rate": 4.919871753490892e-06,
1744
+ "loss": 0.2436,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.1740041928721174,
1749
+ "grad_norm": 34.445777893066406,
1750
+ "learning_rate": 4.918331902411842e-06,
1751
+ "loss": 0.5176,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.17470300489168414,
1756
+ "grad_norm": 10.388051986694336,
1757
+ "learning_rate": 4.916777641519921e-06,
1758
+ "loss": 0.1205,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.17540181691125087,
1763
+ "grad_norm": 2.350389242172241,
1764
+ "learning_rate": 4.91520898007631e-06,
1765
+ "loss": 0.0318,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.1761006289308176,
1770
+ "grad_norm": 8.809117317199707,
1771
+ "learning_rate": 4.913625927427996e-06,
1772
+ "loss": 0.0922,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.17679944095038436,
1777
+ "grad_norm": 11.93591594696045,
1778
+ "learning_rate": 4.912028493007717e-06,
1779
+ "loss": 0.1614,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.1774982529699511,
1784
+ "grad_norm": 19.281707763671875,
1785
+ "learning_rate": 4.9104166863339065e-06,
1786
+ "loss": 0.2842,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.17819706498951782,
1791
+ "grad_norm": 17.486173629760742,
1792
+ "learning_rate": 4.908790517010637e-06,
1793
+ "loss": 0.2744,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.17889587700908455,
1798
+ "grad_norm": 8.761900901794434,
1799
+ "learning_rate": 4.907149994727559e-06,
1800
+ "loss": 0.0757,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.1795946890286513,
1805
+ "grad_norm": 8.123963356018066,
1806
+ "learning_rate": 4.90549512925985e-06,
1807
+ "loss": 0.1441,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.18029350104821804,
1812
+ "grad_norm": 13.555806159973145,
1813
+ "learning_rate": 4.903825930468149e-06,
1814
+ "loss": 0.171,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.18099231306778477,
1819
+ "grad_norm": 20.24187469482422,
1820
+ "learning_rate": 4.902142408298504e-06,
1821
+ "loss": 0.3552,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.1816911250873515,
1826
+ "grad_norm": 16.279403686523438,
1827
+ "learning_rate": 4.9004445727823095e-06,
1828
+ "loss": 0.2269,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.18238993710691823,
1833
+ "grad_norm": 35.07636260986328,
1834
+ "learning_rate": 4.8987324340362445e-06,
1835
+ "loss": 0.6414,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.18308874912648498,
1840
+ "grad_norm": 7.011019706726074,
1841
+ "learning_rate": 4.897006002262217e-06,
1842
+ "loss": 0.0676,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.18378756114605171,
1847
+ "grad_norm": 25.15359115600586,
1848
+ "learning_rate": 4.895265287747302e-06,
1849
+ "loss": 0.3347,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.18448637316561844,
1854
+ "grad_norm": 1.544360637664795,
1855
+ "learning_rate": 4.893510300863677e-06,
1856
+ "loss": 0.0242,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.18518518518518517,
1861
+ "grad_norm": 28.481163024902344,
1862
+ "learning_rate": 4.8917410520685635e-06,
1863
+ "loss": 0.6507,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.18588399720475193,
1868
+ "grad_norm": 10.587766647338867,
1869
+ "learning_rate": 4.889957551904164e-06,
1870
+ "loss": 0.172,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.18658280922431866,
1875
+ "grad_norm": 4.213011264801025,
1876
+ "learning_rate": 4.8881598109976e-06,
1877
+ "loss": 0.0372,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.1872816212438854,
1882
+ "grad_norm": 4.916326999664307,
1883
+ "learning_rate": 4.886347840060845e-06,
1884
+ "loss": 0.0578,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.18798043326345212,
1889
+ "grad_norm": 17.933826446533203,
1890
+ "learning_rate": 4.884521649890664e-06,
1891
+ "loss": 0.344,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.18867924528301888,
1896
+ "grad_norm": 35.10563278198242,
1897
+ "learning_rate": 4.882681251368549e-06,
1898
+ "loss": 0.5693,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.1893780573025856,
1903
+ "grad_norm": 16.641815185546875,
1904
+ "learning_rate": 4.8808266554606535e-06,
1905
+ "loss": 0.313,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.19007686932215234,
1910
+ "grad_norm": 18.587114334106445,
1911
+ "learning_rate": 4.878957873217727e-06,
1912
+ "loss": 0.3172,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.19077568134171907,
1917
+ "grad_norm": 26.699010848999023,
1918
+ "learning_rate": 4.877074915775049e-06,
1919
+ "loss": 0.4658,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.1914744933612858,
1924
+ "grad_norm": 19.77286720275879,
1925
+ "learning_rate": 4.875177794352364e-06,
1926
+ "loss": 0.2559,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.19217330538085256,
1931
+ "grad_norm": 35.742652893066406,
1932
+ "learning_rate": 4.873266520253812e-06,
1933
+ "loss": 0.4641,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.1928721174004193,
1938
+ "grad_norm": 23.883516311645508,
1939
+ "learning_rate": 4.8713411048678635e-06,
1940
+ "loss": 0.3472,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.19357092941998602,
1945
+ "grad_norm": 7.226071357727051,
1946
+ "learning_rate": 4.869401559667253e-06,
1947
+ "loss": 0.0887,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.19426974143955275,
1952
+ "grad_norm": 1.5649971961975098,
1953
+ "learning_rate": 4.867447896208906e-06,
1954
+ "loss": 0.0164,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.1949685534591195,
1959
+ "grad_norm": 5.674210548400879,
1960
+ "learning_rate": 4.865480126133872e-06,
1961
+ "loss": 0.0697,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.19566736547868624,
1966
+ "grad_norm": 27.634450912475586,
1967
+ "learning_rate": 4.863498261167258e-06,
1968
+ "loss": 0.2649,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.19636617749825297,
1973
+ "grad_norm": 13.977226257324219,
1974
+ "learning_rate": 4.861502313118157e-06,
1975
+ "loss": 0.1844,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.1970649895178197,
1980
+ "grad_norm": 2.140982151031494,
1981
+ "learning_rate": 4.859492293879574e-06,
1982
+ "loss": 0.008,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.19776380153738643,
1987
+ "grad_norm": 8.574052810668945,
1988
+ "learning_rate": 4.857468215428362e-06,
1989
+ "loss": 0.158,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.1984626135569532,
1994
+ "grad_norm": 2.9333882331848145,
1995
+ "learning_rate": 4.855430089825143e-06,
1996
+ "loss": 0.0322,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.19916142557651992,
2001
+ "grad_norm": 31.97005271911621,
2002
+ "learning_rate": 4.853377929214243e-06,
2003
+ "loss": 0.8695,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.19986023759608665,
2008
+ "grad_norm": 18.904457092285156,
2009
+ "learning_rate": 4.851311745823616e-06,
2010
+ "loss": 0.2074,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.20055904961565338,
2015
+ "grad_norm": 7.113580226898193,
2016
+ "learning_rate": 4.849231551964771e-06,
2017
+ "loss": 0.0478,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.20125786163522014,
2022
+ "grad_norm": 14.682963371276855,
2023
+ "learning_rate": 4.8471373600327e-06,
2024
+ "loss": 0.2164,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.20195667365478687,
2029
+ "grad_norm": 17.470304489135742,
2030
+ "learning_rate": 4.8450291825058036e-06,
2031
+ "loss": 0.4563,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.2026554856743536,
2036
+ "grad_norm": 10.486756324768066,
2037
+ "learning_rate": 4.842907031945815e-06,
2038
+ "loss": 0.1696,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.20335429769392033,
2043
+ "grad_norm": 15.90971851348877,
2044
+ "learning_rate": 4.84077092099773e-06,
2045
+ "loss": 0.3015,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.20405310971348709,
2050
+ "grad_norm": 15.302689552307129,
2051
+ "learning_rate": 4.838620862389727e-06,
2052
+ "loss": 0.2725,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.20475192173305382,
2057
+ "grad_norm": 10.254291534423828,
2058
+ "learning_rate": 4.83645686893309e-06,
2059
+ "loss": 0.2092,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.20545073375262055,
2064
+ "grad_norm": 10.138662338256836,
2065
+ "learning_rate": 4.834278953522139e-06,
2066
+ "loss": 0.0555,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.20614954577218728,
2071
+ "grad_norm": 34.5139274597168,
2072
+ "learning_rate": 4.8320871291341455e-06,
2073
+ "loss": 0.4119,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.206848357791754,
2078
+ "grad_norm": 11.110896110534668,
2079
+ "learning_rate": 4.829881408829262e-06,
2080
+ "loss": 0.2111,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.20754716981132076,
2085
+ "grad_norm": 3.394921064376831,
2086
+ "learning_rate": 4.827661805750438e-06,
2087
+ "loss": 0.0446,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.2082459818308875,
2092
+ "grad_norm": 19.610963821411133,
2093
+ "learning_rate": 4.825428333123346e-06,
2094
+ "loss": 0.3897,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.20894479385045422,
2099
+ "grad_norm": 20.56781005859375,
2100
+ "learning_rate": 4.823181004256301e-06,
2101
+ "loss": 0.3383,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.20964360587002095,
2106
+ "grad_norm": 4.803562164306641,
2107
+ "learning_rate": 4.8209198325401815e-06,
2108
+ "loss": 0.0608,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.2103424178895877,
2113
+ "grad_norm": 52.001216888427734,
2114
+ "learning_rate": 4.81864483144835e-06,
2115
+ "loss": 0.8058,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.21104122990915444,
2120
+ "grad_norm": 36.58800506591797,
2121
+ "learning_rate": 4.816356014536571e-06,
2122
+ "loss": 0.6983,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.21174004192872117,
2127
+ "grad_norm": 7.013560771942139,
2128
+ "learning_rate": 4.814053395442933e-06,
2129
+ "loss": 0.1034,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.2124388539482879,
2134
+ "grad_norm": 5.222038269042969,
2135
+ "learning_rate": 4.811736987887765e-06,
2136
+ "loss": 0.0527,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.21313766596785463,
2141
+ "grad_norm": 48.45743179321289,
2142
+ "learning_rate": 4.8094068056735564e-06,
2143
+ "loss": 0.9699,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.2138364779874214,
2148
+ "grad_norm": 27.32036018371582,
2149
+ "learning_rate": 4.807062862684874e-06,
2150
+ "loss": 0.4697,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.21453529000698812,
2155
+ "grad_norm": 12.215785026550293,
2156
+ "learning_rate": 4.804705172888277e-06,
2157
+ "loss": 0.1393,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.21523410202655485,
2162
+ "grad_norm": 17.731470108032227,
2163
+ "learning_rate": 4.80233375033224e-06,
2164
+ "loss": 0.1351,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.21593291404612158,
2169
+ "grad_norm": 28.933956146240234,
2170
+ "learning_rate": 4.799948609147061e-06,
2171
+ "loss": 0.5294,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.21663172606568834,
2176
+ "grad_norm": 13.886995315551758,
2177
+ "learning_rate": 4.797549763544784e-06,
2178
+ "loss": 0.2022,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.21733053808525507,
2183
+ "grad_norm": 9.811971664428711,
2184
+ "learning_rate": 4.795137227819113e-06,
2185
+ "loss": 0.1662,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.2180293501048218,
2190
+ "grad_norm": 8.048477172851562,
2191
+ "learning_rate": 4.792711016345322e-06,
2192
+ "loss": 0.101,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.21872816212438853,
2197
+ "grad_norm": 6.266959190368652,
2198
+ "learning_rate": 4.790271143580174e-06,
2199
+ "loss": 0.1021,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.2194269741439553,
2204
+ "grad_norm": 39.531700134277344,
2205
+ "learning_rate": 4.787817624061838e-06,
2206
+ "loss": 0.8468,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.22012578616352202,
2211
+ "grad_norm": 5.592189311981201,
2212
+ "learning_rate": 4.785350472409792e-06,
2213
+ "loss": 0.0619,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.22082459818308875,
2218
+ "grad_norm": 17.003190994262695,
2219
+ "learning_rate": 4.782869703324746e-06,
2220
+ "loss": 0.2143,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.22152341020265548,
2225
+ "grad_norm": 9.305402755737305,
2226
+ "learning_rate": 4.78037533158855e-06,
2227
+ "loss": 0.0783,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.2222222222222222,
2232
+ "grad_norm": 15.373815536499023,
2233
+ "learning_rate": 4.777867372064105e-06,
2234
+ "loss": 0.2495,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.22292103424178897,
2239
+ "grad_norm": 10.769071578979492,
2240
+ "learning_rate": 4.775345839695279e-06,
2241
+ "loss": 0.2074,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.2236198462613557,
2246
+ "grad_norm": 0.8323988318443298,
2247
+ "learning_rate": 4.77281074950681e-06,
2248
+ "loss": 0.0114,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.22431865828092243,
2253
+ "grad_norm": 16.682310104370117,
2254
+ "learning_rate": 4.770262116604224e-06,
2255
+ "loss": 0.1843,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.22501747030048916,
2260
+ "grad_norm": 12.464035987854004,
2261
+ "learning_rate": 4.767699956173745e-06,
2262
+ "loss": 0.1565,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.22571628232005592,
2267
+ "grad_norm": 10.665525436401367,
2268
+ "learning_rate": 4.765124283482195e-06,
2269
+ "loss": 0.1886,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.22641509433962265,
2274
+ "grad_norm": 8.285576820373535,
2275
+ "learning_rate": 4.7625351138769175e-06,
2276
+ "loss": 0.1113,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.22711390635918938,
2281
+ "grad_norm": 13.075751304626465,
2282
+ "learning_rate": 4.759932462785672e-06,
2283
+ "loss": 0.1893,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.2278127183787561,
2288
+ "grad_norm": 18.610963821411133,
2289
+ "learning_rate": 4.757316345716554e-06,
2290
+ "loss": 0.2235,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.22851153039832284,
2295
+ "grad_norm": 35.326637268066406,
2296
+ "learning_rate": 4.754686778257891e-06,
2297
+ "loss": 0.8035,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.2292103424178896,
2302
+ "grad_norm": 18.4339542388916,
2303
+ "learning_rate": 4.75204377607816e-06,
2304
+ "loss": 0.4119,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.22990915443745633,
2309
+ "grad_norm": 34.74818420410156,
2310
+ "learning_rate": 4.74938735492589e-06,
2311
+ "loss": 0.6765,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.23060796645702306,
2316
+ "grad_norm": 1.2656896114349365,
2317
+ "learning_rate": 4.746717530629565e-06,
2318
+ "loss": 0.0165,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.23130677847658979,
2323
+ "grad_norm": 33.5367546081543,
2324
+ "learning_rate": 4.744034319097536e-06,
2325
+ "loss": 0.6406,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.23200559049615654,
2330
+ "grad_norm": 4.118407726287842,
2331
+ "learning_rate": 4.741337736317919e-06,
2332
+ "loss": 0.0494,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.23270440251572327,
2337
+ "grad_norm": 35.5570068359375,
2338
+ "learning_rate": 4.738627798358506e-06,
2339
+ "loss": 0.6405,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.23340321453529,
2344
+ "grad_norm": 13.001288414001465,
2345
+ "learning_rate": 4.7359045213666675e-06,
2346
+ "loss": 0.285,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.23410202655485673,
2351
+ "grad_norm": 10.730605125427246,
2352
+ "learning_rate": 4.733167921569255e-06,
2353
+ "loss": 0.1991,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.2348008385744235,
2358
+ "grad_norm": 0.6715048551559448,
2359
+ "learning_rate": 4.7304180152725035e-06,
2360
+ "loss": 0.0091,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.23549965059399022,
2365
+ "grad_norm": 10.875028610229492,
2366
+ "learning_rate": 4.727654818861937e-06,
2367
+ "loss": 0.2589,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.23619846261355695,
2372
+ "grad_norm": 2.7218732833862305,
2373
+ "learning_rate": 4.724878348802271e-06,
2374
+ "loss": 0.0154,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.23689727463312368,
2379
+ "grad_norm": 7.1363935470581055,
2380
+ "learning_rate": 4.7220886216373095e-06,
2381
+ "loss": 0.1054,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.2375960866526904,
2386
+ "grad_norm": 8.102635383605957,
2387
+ "learning_rate": 4.719285653989852e-06,
2388
+ "loss": 0.1246,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.23829489867225717,
2393
+ "grad_norm": 32.68269729614258,
2394
+ "learning_rate": 4.716469462561595e-06,
2395
+ "loss": 0.6109,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.2389937106918239,
2400
+ "grad_norm": 14.749852180480957,
2401
+ "learning_rate": 4.7136400641330245e-06,
2402
+ "loss": 0.236,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.23969252271139063,
2407
+ "grad_norm": 18.897247314453125,
2408
+ "learning_rate": 4.710797475563327e-06,
2409
+ "loss": 0.3625,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.24039133473095736,
2414
+ "grad_norm": 11.592190742492676,
2415
+ "learning_rate": 4.707941713790279e-06,
2416
+ "loss": 0.1785,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.24109014675052412,
2421
+ "grad_norm": 32.90082931518555,
2422
+ "learning_rate": 4.7050727958301505e-06,
2423
+ "loss": 0.548,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.24178895877009085,
2428
+ "grad_norm": 4.296587944030762,
2429
+ "learning_rate": 4.702190738777608e-06,
2430
+ "loss": 0.0411,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.24248777078965758,
2435
+ "grad_norm": 5.985422611236572,
2436
+ "learning_rate": 4.699295559805606e-06,
2437
+ "loss": 0.093,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.2431865828092243,
2442
+ "grad_norm": 11.231877326965332,
2443
+ "learning_rate": 4.696387276165284e-06,
2444
+ "loss": 0.1743,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.24388539482879107,
2449
+ "grad_norm": 10.44618034362793,
2450
+ "learning_rate": 4.693465905185871e-06,
2451
+ "loss": 0.0967,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.2445842068483578,
2456
+ "grad_norm": 11.621986389160156,
2457
+ "learning_rate": 4.690531464274577e-06,
2458
+ "loss": 0.2119,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.24528301886792453,
2463
+ "grad_norm": 9.701064109802246,
2464
+ "learning_rate": 4.687583970916487e-06,
2465
+ "loss": 0.1547,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.24598183088749126,
2470
+ "grad_norm": 0.47121426463127136,
2471
+ "learning_rate": 4.684623442674463e-06,
2472
+ "loss": 0.0093,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.246680642907058,
2477
+ "grad_norm": 12.1204195022583,
2478
+ "learning_rate": 4.681649897189036e-06,
2479
+ "loss": 0.2302,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.24737945492662475,
2484
+ "grad_norm": 18.194692611694336,
2485
+ "learning_rate": 4.678663352178301e-06,
2486
+ "loss": 0.2065,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.24807826694619148,
2491
+ "grad_norm": 20.830915451049805,
2492
+ "learning_rate": 4.675663825437811e-06,
2493
+ "loss": 0.3612,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.2487770789657582,
2498
+ "grad_norm": 10.530333518981934,
2499
+ "learning_rate": 4.6726513348404736e-06,
2500
+ "loss": 0.1429,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.24947589098532494,
2505
+ "grad_norm": 5.4854326248168945,
2506
+ "learning_rate": 4.669625898336439e-06,
2507
+ "loss": 0.0727,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.2501747030048917,
2512
+ "grad_norm": 30.590425491333008,
2513
+ "learning_rate": 4.666587533952998e-06,
2514
+ "loss": 0.6164,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.2508735150244584,
2519
+ "grad_norm": 40.59944534301758,
2520
+ "learning_rate": 4.663536259794477e-06,
2521
+ "loss": 0.844,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.25157232704402516,
2526
+ "grad_norm": 11.132962226867676,
2527
+ "learning_rate": 4.660472094042121e-06,
2528
+ "loss": 0.1291,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.2522711390635919,
2533
+ "grad_norm": 6.713598728179932,
2534
+ "learning_rate": 4.657395054953992e-06,
2535
+ "loss": 0.1139,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.2529699510831586,
2540
+ "grad_norm": 16.51830291748047,
2541
+ "learning_rate": 4.65430516086486e-06,
2542
+ "loss": 0.3327,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.25366876310272535,
2547
+ "grad_norm": 12.358148574829102,
2548
+ "learning_rate": 4.6512024301860925e-06,
2549
+ "loss": 0.2048,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.2543675751222921,
2554
+ "grad_norm": 29.781177520751953,
2555
+ "learning_rate": 4.648086881405542e-06,
2556
+ "loss": 0.5272,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.25506638714185886,
2561
+ "grad_norm": 20.371816635131836,
2562
+ "learning_rate": 4.644958533087443e-06,
2563
+ "loss": 0.301,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.2557651991614256,
2568
+ "grad_norm": 20.111852645874023,
2569
+ "learning_rate": 4.641817403872293e-06,
2570
+ "loss": 0.5609,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.2564640111809923,
2575
+ "grad_norm": 11.709222793579102,
2576
+ "learning_rate": 4.638663512476748e-06,
2577
+ "loss": 0.1922,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.25716282320055905,
2582
+ "grad_norm": 13.188800811767578,
2583
+ "learning_rate": 4.635496877693507e-06,
2584
+ "loss": 0.1669,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.2578616352201258,
2589
+ "grad_norm": 32.15465545654297,
2590
+ "learning_rate": 4.632317518391203e-06,
2591
+ "loss": 0.6982,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.2585604472396925,
2596
+ "grad_norm": 26.257347106933594,
2597
+ "learning_rate": 4.629125453514286e-06,
2598
+ "loss": 0.3907,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.25925925925925924,
2603
+ "grad_norm": 25.885942459106445,
2604
+ "learning_rate": 4.625920702082918e-06,
2605
+ "loss": 0.4158,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.259958071278826,
2610
+ "grad_norm": 15.703845024108887,
2611
+ "learning_rate": 4.622703283192849e-06,
2612
+ "loss": 0.1871,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.2606568832983927,
2617
+ "grad_norm": 11.522906303405762,
2618
+ "learning_rate": 4.619473216015313e-06,
2619
+ "loss": 0.168,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.2613556953179595,
2624
+ "grad_norm": 32.49365997314453,
2625
+ "learning_rate": 4.616230519796909e-06,
2626
+ "loss": 0.6912,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.2620545073375262,
2631
+ "grad_norm": 0.8261187672615051,
2632
+ "learning_rate": 4.612975213859487e-06,
2633
+ "loss": 0.0107,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.26275331935709295,
2638
+ "grad_norm": 25.673416137695312,
2639
+ "learning_rate": 4.6097073176000325e-06,
2640
+ "loss": 0.5722,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.2634521313766597,
2645
+ "grad_norm": 35.15298080444336,
2646
+ "learning_rate": 4.606426850490551e-06,
2647
+ "loss": 0.5508,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.2641509433962264,
2652
+ "grad_norm": 6.139308929443359,
2653
+ "learning_rate": 4.603133832077953e-06,
2654
+ "loss": 0.0962,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.26484975541579314,
2659
+ "grad_norm": 18.431100845336914,
2660
+ "learning_rate": 4.599828281983938e-06,
2661
+ "loss": 0.3406,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.2655485674353599,
2666
+ "grad_norm": 14.415935516357422,
2667
+ "learning_rate": 4.596510219904874e-06,
2668
+ "loss": 0.2035,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.2662473794549266,
2673
+ "grad_norm": 6.168896198272705,
2674
+ "learning_rate": 4.593179665611685e-06,
2675
+ "loss": 0.0701,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.2669461914744934,
2680
+ "grad_norm": 19.408126831054688,
2681
+ "learning_rate": 4.589836638949729e-06,
2682
+ "loss": 0.2329,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.2676450034940601,
2687
+ "grad_norm": 10.20333480834961,
2688
+ "learning_rate": 4.586481159838682e-06,
2689
+ "loss": 0.1782,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.26834381551362685,
2694
+ "grad_norm": 1.0518056154251099,
2695
+ "learning_rate": 4.58311324827242e-06,
2696
+ "loss": 0.0157,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.2690426275331936,
2701
+ "grad_norm": 37.60113525390625,
2702
+ "learning_rate": 4.579732924318898e-06,
2703
+ "loss": 0.7857,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.2697414395527603,
2708
+ "grad_norm": 24.878284454345703,
2709
+ "learning_rate": 4.5763402081200295e-06,
2710
+ "loss": 0.5532,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.27044025157232704,
2715
+ "grad_norm": 13.037965774536133,
2716
+ "learning_rate": 4.5729351198915715e-06,
2717
+ "loss": 0.1916,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.27113906359189377,
2722
+ "grad_norm": 0.6771875619888306,
2723
+ "learning_rate": 4.569517679922997e-06,
2724
+ "loss": 0.0056,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.2718378756114605,
2729
+ "grad_norm": 14.487314224243164,
2730
+ "learning_rate": 4.566087908577382e-06,
2731
+ "loss": 0.2975,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.27253668763102723,
2736
+ "grad_norm": 18.10540199279785,
2737
+ "learning_rate": 4.5626458262912745e-06,
2738
+ "loss": 0.2606,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.273235499650594,
2743
+ "grad_norm": 9.74409008026123,
2744
+ "learning_rate": 4.559191453574582e-06,
2745
+ "loss": 0.1439,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.27393431167016075,
2750
+ "grad_norm": 11.126801490783691,
2751
+ "learning_rate": 4.555724811010447e-06,
2752
+ "loss": 0.1839,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.2746331236897275,
2757
+ "grad_norm": 14.446985244750977,
2758
+ "learning_rate": 4.5522459192551175e-06,
2759
+ "loss": 0.312,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.2753319357092942,
2764
+ "grad_norm": 7.447902202606201,
2765
+ "learning_rate": 4.548754799037834e-06,
2766
+ "loss": 0.1061,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.27603074772886094,
2771
+ "grad_norm": 28.85816192626953,
2772
+ "learning_rate": 4.545251471160698e-06,
2773
+ "loss": 0.6249,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.27672955974842767,
2778
+ "grad_norm": 33.03690719604492,
2779
+ "learning_rate": 4.541735956498555e-06,
2780
+ "loss": 0.508,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.2774283717679944,
2785
+ "grad_norm": 20.449827194213867,
2786
+ "learning_rate": 4.538208275998861e-06,
2787
+ "loss": 0.2899,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.2781271837875611,
2792
+ "grad_norm": 16.259653091430664,
2793
+ "learning_rate": 4.534668450681569e-06,
2794
+ "loss": 0.292,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.27882599580712786,
2799
+ "grad_norm": 26.654836654663086,
2800
+ "learning_rate": 4.531116501638992e-06,
2801
+ "loss": 0.3557,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.27952480782669464,
2806
+ "grad_norm": 1.7782492637634277,
2807
+ "learning_rate": 4.527552450035689e-06,
2808
+ "loss": 0.0237,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.2802236198462614,
2813
+ "grad_norm": 20.36215591430664,
2814
+ "learning_rate": 4.523976317108326e-06,
2815
+ "loss": 0.3595,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.2809224318658281,
2820
+ "grad_norm": 4.038337707519531,
2821
+ "learning_rate": 4.520388124165564e-06,
2822
+ "loss": 0.0438,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.28162124388539483,
2827
+ "grad_norm": 17.7996768951416,
2828
+ "learning_rate": 4.516787892587921e-06,
2829
+ "loss": 0.3754,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.28232005590496156,
2834
+ "grad_norm": 33.77705764770508,
2835
+ "learning_rate": 4.513175643827647e-06,
2836
+ "loss": 0.5027,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.2830188679245283,
2841
+ "grad_norm": 1.2933781147003174,
2842
+ "learning_rate": 4.509551399408598e-06,
2843
+ "loss": 0.0147,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.283717679944095,
2848
+ "grad_norm": 37.71927261352539,
2849
+ "learning_rate": 4.5059151809261085e-06,
2850
+ "loss": 0.5584,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.28441649196366176,
2855
+ "grad_norm": 45.29424285888672,
2856
+ "learning_rate": 4.50226701004686e-06,
2857
+ "loss": 0.8957,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.2851153039832285,
2862
+ "grad_norm": 16.94281578063965,
2863
+ "learning_rate": 4.498606908508754e-06,
2864
+ "loss": 0.3971,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.28581411600279527,
2869
+ "grad_norm": 54.23704528808594,
2870
+ "learning_rate": 4.494934898120779e-06,
2871
+ "loss": 0.9391,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.286512928022362,
2876
+ "grad_norm": 13.617294311523438,
2877
+ "learning_rate": 4.491251000762889e-06,
2878
+ "loss": 0.1867,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.28721174004192873,
2883
+ "grad_norm": 4.1379923820495605,
2884
+ "learning_rate": 4.487555238385862e-06,
2885
+ "loss": 0.0204,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.28791055206149546,
2890
+ "grad_norm": 18.19028663635254,
2891
+ "learning_rate": 4.483847633011177e-06,
2892
+ "loss": 0.3196,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.2886093640810622,
2897
+ "grad_norm": 7.146092891693115,
2898
+ "learning_rate": 4.480128206730881e-06,
2899
+ "loss": 0.1091,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.2893081761006289,
2904
+ "grad_norm": 14.049055099487305,
2905
+ "learning_rate": 4.476396981707454e-06,
2906
+ "loss": 0.2865,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.29000698812019565,
2911
+ "grad_norm": 6.086685657501221,
2912
+ "learning_rate": 4.4726539801736815e-06,
2913
+ "loss": 0.0453,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.2907058001397624,
2918
+ "grad_norm": 7.355288982391357,
2919
+ "learning_rate": 4.4688992244325215e-06,
2920
+ "loss": 0.0962,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.2914046121593291,
2925
+ "grad_norm": 27.951030731201172,
2926
+ "learning_rate": 4.4651327368569695e-06,
2927
+ "loss": 0.4766,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.2921034241788959,
2932
+ "grad_norm": 10.94737720489502,
2933
+ "learning_rate": 4.461354539889923e-06,
2934
+ "loss": 0.1603,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.29280223619846263,
2939
+ "grad_norm": 5.964730262756348,
2940
+ "learning_rate": 4.457564656044056e-06,
2941
+ "loss": 0.0751,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.29350104821802936,
2946
+ "grad_norm": 18.6251277923584,
2947
+ "learning_rate": 4.453763107901676e-06,
2948
+ "loss": 0.4091,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.2941998602375961,
2953
+ "grad_norm": 36.76710891723633,
2954
+ "learning_rate": 4.449949918114593e-06,
2955
+ "loss": 0.8475,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.2948986722571628,
2960
+ "grad_norm": 16.30900764465332,
2961
+ "learning_rate": 4.446125109403987e-06,
2962
+ "loss": 0.229,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.29559748427672955,
2967
+ "grad_norm": 0.9128844738006592,
2968
+ "learning_rate": 4.442288704560268e-06,
2969
+ "loss": 0.0206,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.2962962962962963,
2974
+ "grad_norm": 5.981807231903076,
2975
+ "learning_rate": 4.438440726442944e-06,
2976
+ "loss": 0.0885,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.296995108315863,
2981
+ "grad_norm": 27.69352912902832,
2982
+ "learning_rate": 4.434581197980483e-06,
2983
+ "loss": 0.608,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.2976939203354298,
2988
+ "grad_norm": 17.880767822265625,
2989
+ "learning_rate": 4.430710142170176e-06,
2990
+ "loss": 0.252,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.2983927323549965,
2995
+ "grad_norm": 5.650568962097168,
2996
+ "learning_rate": 4.426827582077999e-06,
2997
+ "loss": 0.0755,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.29909154437456326,
3002
+ "grad_norm": 13.807109832763672,
3003
+ "learning_rate": 4.422933540838481e-06,
3004
+ "loss": 0.1333,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.29979035639413,
3009
+ "grad_norm": 22.934085845947266,
3010
+ "learning_rate": 4.419028041654559e-06,
3011
+ "loss": 0.4995,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.3004891684136967,
3016
+ "grad_norm": 21.154132843017578,
3017
+ "learning_rate": 4.415111107797445e-06,
3018
+ "loss": 0.2275,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.30118798043326345,
3023
+ "grad_norm": 45.836483001708984,
3024
+ "learning_rate": 4.411182762606484e-06,
3025
+ "loss": 0.6165,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.3018867924528302,
3030
+ "grad_norm": 18.20020866394043,
3031
+ "learning_rate": 4.407243029489018e-06,
3032
+ "loss": 0.3395,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.3025856044723969,
3037
+ "grad_norm": 6.130852699279785,
3038
+ "learning_rate": 4.4032919319202415e-06,
3039
+ "loss": 0.0991,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.30328441649196364,
3044
+ "grad_norm": 12.936942100524902,
3045
+ "learning_rate": 4.399329493443067e-06,
3046
+ "loss": 0.1179,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.3039832285115304,
3051
+ "grad_norm": 12.123394966125488,
3052
+ "learning_rate": 4.3953557376679856e-06,
3053
+ "loss": 0.1573,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.30468204053109715,
3058
+ "grad_norm": 14.226133346557617,
3059
+ "learning_rate": 4.391370688272919e-06,
3060
+ "loss": 0.1557,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.3053808525506639,
3065
+ "grad_norm": 27.995567321777344,
3066
+ "learning_rate": 4.387374369003083e-06,
3067
+ "loss": 0.5142,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.3060796645702306,
3072
+ "grad_norm": 12.208261489868164,
3073
+ "learning_rate": 4.383366803670849e-06,
3074
+ "loss": 0.201,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.30677847658979734,
3079
+ "grad_norm": 27.00516128540039,
3080
+ "learning_rate": 4.379348016155596e-06,
3081
+ "loss": 0.4225,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.3074772886093641,
3086
+ "grad_norm": 7.272449493408203,
3087
+ "learning_rate": 4.375318030403573e-06,
3088
+ "loss": 0.0786,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.3081761006289308,
3093
+ "grad_norm": 0.5066769123077393,
3094
+ "learning_rate": 4.3712768704277535e-06,
3095
+ "loss": 0.0102,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.30887491264849753,
3100
+ "grad_norm": 9.54050350189209,
3101
+ "learning_rate": 4.367224560307693e-06,
3102
+ "loss": 0.1596,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.30957372466806427,
3107
+ "grad_norm": 15.01711654663086,
3108
+ "learning_rate": 4.363161124189387e-06,
3109
+ "loss": 0.3198,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.31027253668763105,
3114
+ "grad_norm": 16.74932861328125,
3115
+ "learning_rate": 4.359086586285127e-06,
3116
+ "loss": 0.3108,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.3109713487071978,
3121
+ "grad_norm": 40.40657424926758,
3122
+ "learning_rate": 4.355000970873352e-06,
3123
+ "loss": 0.8194,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.3116701607267645,
3128
+ "grad_norm": 4.776082992553711,
3129
+ "learning_rate": 4.350904302298511e-06,
3130
+ "loss": 0.0333,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.31236897274633124,
3135
+ "grad_norm": 11.798108100891113,
3136
+ "learning_rate": 4.346796604970913e-06,
3137
+ "loss": 0.2779,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.31306778476589797,
3142
+ "grad_norm": 27.99241828918457,
3143
+ "learning_rate": 4.34267790336658e-06,
3144
+ "loss": 0.5368,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.3137665967854647,
3149
+ "grad_norm": 16.165719985961914,
3150
+ "learning_rate": 4.338548222027107e-06,
3151
+ "loss": 0.3069,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.31446540880503143,
3156
+ "grad_norm": 5.398584842681885,
3157
+ "learning_rate": 4.33440758555951e-06,
3158
+ "loss": 0.0882,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.31516422082459816,
3163
+ "grad_norm": 17.657291412353516,
3164
+ "learning_rate": 4.330256018636086e-06,
3165
+ "loss": 0.2464,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.3158630328441649,
3170
+ "grad_norm": 13.588639259338379,
3171
+ "learning_rate": 4.326093545994258e-06,
3172
+ "loss": 0.1828,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.3165618448637317,
3177
+ "grad_norm": 5.476947784423828,
3178
+ "learning_rate": 4.3219201924364325e-06,
3179
+ "loss": 0.0618,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.3172606568832984,
3184
+ "grad_norm": 50.05097198486328,
3185
+ "learning_rate": 4.317735982829852e-06,
3186
+ "loss": 0.9741,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.31795946890286514,
3191
+ "grad_norm": 3.6453871726989746,
3192
+ "learning_rate": 4.313540942106445e-06,
3193
+ "loss": 0.0466,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.31865828092243187,
3198
+ "grad_norm": 5.7373785972595215,
3199
+ "learning_rate": 4.309335095262675e-06,
3200
+ "loss": 0.0701,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.3193570929419986,
3205
+ "grad_norm": 32.402801513671875,
3206
+ "learning_rate": 4.305118467359402e-06,
3207
+ "loss": 0.6547,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.32005590496156533,
3212
+ "grad_norm": 9.464690208435059,
3213
+ "learning_rate": 4.300891083521717e-06,
3214
+ "loss": 0.0971,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.32075471698113206,
3219
+ "grad_norm": 33.40875244140625,
3220
+ "learning_rate": 4.296652968938807e-06,
3221
+ "loss": 0.6254,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.3214535290006988,
3226
+ "grad_norm": 8.698691368103027,
3227
+ "learning_rate": 4.2924041488637966e-06,
3228
+ "loss": 0.1062,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.3221523410202656,
3233
+ "grad_norm": 35.50666427612305,
3234
+ "learning_rate": 4.288144648613601e-06,
3235
+ "loss": 0.8304,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.3228511530398323,
3240
+ "grad_norm": 5.5079169273376465,
3241
+ "learning_rate": 4.283874493568772e-06,
3242
+ "loss": 0.0682,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.32354996505939904,
3247
+ "grad_norm": 29.080564498901367,
3248
+ "learning_rate": 4.279593709173352e-06,
3249
+ "loss": 0.4879,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.32424877707896577,
3254
+ "grad_norm": 0.8691240549087524,
3255
+ "learning_rate": 4.2753023209347164e-06,
3256
+ "loss": 0.0137,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.3249475890985325,
3261
+ "grad_norm": 18.309951782226562,
3262
+ "learning_rate": 4.2710003544234255e-06,
3263
+ "loss": 0.3709,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.3256464011180992,
3268
+ "grad_norm": 25.955778121948242,
3269
+ "learning_rate": 4.266687835273071e-06,
3270
+ "loss": 0.4848,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.32634521313766596,
3275
+ "grad_norm": 2.9740233421325684,
3276
+ "learning_rate": 4.262364789180123e-06,
3277
+ "loss": 0.0299,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.3270440251572327,
3282
+ "grad_norm": 24.613683700561523,
3283
+ "learning_rate": 4.258031241903778e-06,
3284
+ "loss": 0.4708,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.3277428371767994,
3289
+ "grad_norm": 32.723487854003906,
3290
+ "learning_rate": 4.253687219265803e-06,
3291
+ "loss": 0.6666,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.3284416491963662,
3296
+ "grad_norm": 9.264688491821289,
3297
+ "learning_rate": 4.249332747150386e-06,
3298
+ "loss": 0.1299,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.32914046121593293,
3303
+ "grad_norm": 16.0210018157959,
3304
+ "learning_rate": 4.244967851503975e-06,
3305
+ "loss": 0.2999,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.32983927323549966,
3310
+ "grad_norm": 14.11863899230957,
3311
+ "learning_rate": 4.240592558335131e-06,
3312
+ "loss": 0.1809,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.3305380852550664,
3317
+ "grad_norm": 5.871946811676025,
3318
+ "learning_rate": 4.236206893714369e-06,
3319
+ "loss": 0.0786,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.3312368972746331,
3324
+ "grad_norm": 24.123607635498047,
3325
+ "learning_rate": 4.231810883773999e-06,
3326
+ "loss": 0.4737,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.33193570929419985,
3331
+ "grad_norm": 36.70653533935547,
3332
+ "learning_rate": 4.22740455470798e-06,
3333
+ "loss": 0.8122,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.3326345213137666,
3338
+ "grad_norm": 8.99547290802002,
3339
+ "learning_rate": 4.2229879327717545e-06,
3340
+ "loss": 0.0938,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.3333333333333333,
3345
+ "grad_norm": 10.947245597839355,
3346
+ "learning_rate": 4.218561044282099e-06,
3347
+ "loss": 0.1411,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.33403214535290005,
3352
+ "grad_norm": 9.174323081970215,
3353
+ "learning_rate": 4.21412391561696e-06,
3354
+ "loss": 0.1841,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.33473095737246683,
3359
+ "grad_norm": 5.052950859069824,
3360
+ "learning_rate": 4.209676573215304e-06,
3361
+ "loss": 0.0873,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.33542976939203356,
3366
+ "grad_norm": 3.0600333213806152,
3367
+ "learning_rate": 4.205219043576955e-06,
3368
+ "loss": 0.0213,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.3361285814116003,
3373
+ "grad_norm": 10.695812225341797,
3374
+ "learning_rate": 4.200751353262442e-06,
3375
+ "loss": 0.1853,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.336827393431167,
3380
+ "grad_norm": 24.313112258911133,
3381
+ "learning_rate": 4.196273528892831e-06,
3382
+ "loss": 0.3228,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.33752620545073375,
3387
+ "grad_norm": 3.9740796089172363,
3388
+ "learning_rate": 4.191785597149577e-06,
3389
+ "loss": 0.0468,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.3382250174703005,
3394
+ "grad_norm": 24.344791412353516,
3395
+ "learning_rate": 4.1872875847743605e-06,
3396
+ "loss": 0.3732,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.3389238294898672,
3401
+ "grad_norm": 32.8441276550293,
3402
+ "learning_rate": 4.182779518568925e-06,
3403
+ "loss": 0.7411,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.33962264150943394,
3408
+ "grad_norm": 12.237163543701172,
3409
+ "learning_rate": 4.178261425394926e-06,
3410
+ "loss": 0.2246,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.3403214535290007,
3415
+ "grad_norm": 17.052074432373047,
3416
+ "learning_rate": 4.173733332173759e-06,
3417
+ "loss": 0.3097,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.34102026554856746,
3422
+ "grad_norm": 0.5796659588813782,
3423
+ "learning_rate": 4.1691952658864106e-06,
3424
+ "loss": 0.013,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.3417190775681342,
3429
+ "grad_norm": 20.193439483642578,
3430
+ "learning_rate": 4.16464725357329e-06,
3431
+ "loss": 0.2634,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.3424178895877009,
3436
+ "grad_norm": 13.251941680908203,
3437
+ "learning_rate": 4.160089322334071e-06,
3438
+ "loss": 0.2221,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.34311670160726765,
3443
+ "grad_norm": 44.23042678833008,
3444
+ "learning_rate": 4.15552149932753e-06,
3445
+ "loss": 0.9051,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.3438155136268344,
3450
+ "grad_norm": 10.936775207519531,
3451
+ "learning_rate": 4.150943811771387e-06,
3452
+ "loss": 0.2734,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.3445143256464011,
3457
+ "grad_norm": 11.693808555603027,
3458
+ "learning_rate": 4.146356286942136e-06,
3459
+ "loss": 0.1532,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.34521313766596784,
3464
+ "grad_norm": 0.5446651577949524,
3465
+ "learning_rate": 4.1417589521748895e-06,
3466
+ "loss": 0.0103,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.34591194968553457,
3471
+ "grad_norm": 19.49287986755371,
3472
+ "learning_rate": 4.137151834863213e-06,
3473
+ "loss": 0.5919,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.3466107617051013,
3478
+ "grad_norm": 20.148540496826172,
3479
+ "learning_rate": 4.1325349624589625e-06,
3480
+ "loss": 0.3516,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.3473095737246681,
3485
+ "grad_norm": 7.5778398513793945,
3486
+ "learning_rate": 4.127908362472121e-06,
3487
+ "loss": 0.0888,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.3480083857442348,
3492
+ "grad_norm": 16.51567840576172,
3493
+ "learning_rate": 4.123272062470633e-06,
3494
+ "loss": 0.3252,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.34870719776380155,
3499
+ "grad_norm": 10.965740203857422,
3500
+ "learning_rate": 4.1186260900802405e-06,
3501
+ "loss": 0.1349,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.3494060097833683,
3506
+ "grad_norm": 21.047245025634766,
3507
+ "learning_rate": 4.11397047298432e-06,
3508
+ "loss": 0.3691,
3509
+ "step": 500
3510
+ },
3511
+ {
3512
+ "epoch": 0.3494060097833683,
3513
+ "eval_loss": 0.2600938379764557,
3514
+ "eval_runtime": 305.1384,
3515
+ "eval_samples_per_second": 2.084,
3516
+ "eval_steps_per_second": 0.521,
3517
+ "step": 500
3518
+ }
3519
+ ],
3520
+ "logging_steps": 1,
3521
+ "max_steps": 1431,
3522
+ "num_input_tokens_seen": 0,
3523
+ "num_train_epochs": 1,
3524
+ "save_steps": 500,
3525
+ "stateful_callbacks": {
3526
+ "TrainerControl": {
3527
+ "args": {
3528
+ "should_epoch_stop": false,
3529
+ "should_evaluate": false,
3530
+ "should_log": false,
3531
+ "should_save": true,
3532
+ "should_training_stop": false
3533
+ },
3534
+ "attributes": {}
3535
+ }
3536
+ },
3537
+ "total_flos": 4.916543708725248e+16,
3538
+ "train_batch_size": 4,
3539
+ "trial_name": null,
3540
+ "trial_params": null
3541
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86f5bab8dd2b00d5dcc124ddb4bdfc8546468f0fde48d81a745ed29055777d6
3
+ size 5176
final_model/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.8.2
final_model/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "up_proj",
24
+ "v_proj",
25
+ "gate_proj",
26
+ "q_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": true
32
+ }
final_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f7f81c15b686111aa534bae8d8d8525b4c34ff835d5211981bc01605d94c66
3
+ size 1342238560
merged_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-8b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128256,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.44.2",
27
+ "use_cache": false,
28
+ "vocab_size": 128258
29
+ }
merged_model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "transformers_version": "4.44.2"
7
+ }
merged_model/model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd009889fc71bf04d81973171b570ae7d1fce8ecf49eeb6fc68a7bc2e7264d5
3
+ size 4886498936
merged_model/model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a36a7f9dfd7c2841d805e3c438b0d7ef6a579228d7080054169a7408d43893
3
+ size 4832007448
merged_model/model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cafe66c53cb2fe09b7e74ae7a074d2cb529681c7c9ca4038b4f4df7fb094b09
3
+ size 4999813112
merged_model/model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d135c7bec6e25c4ed07232a8765baa70e002a3180b91dd1f752c6ff2614079
3
+ size 4999813128
merged_model/model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4b5d5198fe1f9ebb66549b916375c1b3dbd0f6c336179bc63f50598e2048fa
3
+ size 4832007496
merged_model/model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2de67d21bf844bc82adb556e746c1137788086a60819eb54f5c46b00e1bb416
3
+ size 4999813120
merged_model/model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd4486dd536d4e7f1b9a4b1d82b96114bc8c5d60be19e5734d5e23ac1691edd
3
+ size 2571190952
merged_model/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32121110528
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00007-of-00007.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
296
+ "model.norm.weight": "model-00007-of-00007.safetensors"
297
+ }
298
+ }